Sensors

16 pages, 7429 KiB

Open AccessEditor’s ChoiceArticle

Hyperspectral Imaging for the Detection of Glioblastoma Tumor Cells in H&E Slides Using Convolutional Neural Networks

by Samuel Ortega, Martin Halicek, Himar Fabelo, Rafael Camacho, María de la Luz Plaza, Fred Godtliebsen, Gustavo M. Callicó and Baowei Fei

Sensors 2020, 20(7), 1911; https://doi.org/10.3390/s20071911 - 30 Mar 2020

Cited by 59 | Viewed by 6742

Abstract

Hyperspectral imaging (HSI) technology has demonstrated potential to provide useful information about the chemical composition of tissue and its morphological features in a single image modality. Deep learning (DL) techniques have demonstrated the ability of automatic feature extraction from data for a successful [...] Read more.

Hyperspectral imaging (HSI) technology has demonstrated potential to provide useful information about the chemical composition of tissue and its morphological features in a single image modality. Deep learning (DL) techniques have demonstrated the ability of automatic feature extraction from data for a successful classification. In this study, we exploit HSI and DL for the automatic differentiation of glioblastoma (GB) and non-tumor tissue on hematoxylin and eosin (H&E) stained histological slides of human brain tissue. GB detection is a challenging application, showing high heterogeneity in the cellular morphology across different patients. We employed an HSI microscope, with a spectral range from 400 to 1000 nm, to collect 517 HS cubes from 13 GB patients using 20× magnification. Using a convolutional neural network (CNN), we were able to automatically detect GB within the pathological slides, achieving average sensitivity and specificity values of 88% and 77%, respectively, representing an improvement of 7% and 8% respectively, as compared to the results obtained using RGB (red, green, and blue) images. This study demonstrates that the combination of hyperspectral microscopic imaging and deep learning is a promising tool for future computational pathologies. Full article

(This article belongs to the Special Issue Sensors, Signal and Image Processing in Biomedicine and Assisted Living)

► Show Figures

Figure 1

23 pages, 5564 KiB

Open AccessEditor’s ChoiceArticle

Path Loss Prediction Based on Machine Learning Techniques: Principal Component Analysis, Artificial Neural Network, and Gaussian Process

by Han-Shin Jo, Chanshin Park, Eunhyoung Lee, Haing Kun Choi and Jaedon Park

Sensors 2020, 20(7), 1927; https://doi.org/10.3390/s20071927 - 30 Mar 2020

Cited by 87 | Viewed by 6184

Abstract

Although various linear log-distance path loss models have been developed for wireless sensor networks, advanced models are required to more accurately and flexibly represent the path loss for complex environments. This paper proposes a machine learning framework for modeling path loss using a [...] Read more.

Although various linear log-distance path loss models have been developed for wireless sensor networks, advanced models are required to more accurately and flexibly represent the path loss for complex environments. This paper proposes a machine learning framework for modeling path loss using a combination of three key techniques: artificial neural network (ANN)-based multi-dimensional regression, Gaussian process-based variance analysis, and principle component analysis (PCA)-aided feature selection. In general, the measured path loss dataset comprises multiple features such as distance, antenna height, etc. First, PCA is adopted to reduce the number of features of the dataset and simplify the learning model accordingly. ANN then learns the path loss structure from the dataset with reduced dimension, and Gaussian process learns the shadowing effect. Path loss data measured in a suburban area in Korea are employed. We observe that the proposed combined path loss and shadowing model is more accurate and flexible compared to the conventional linear path loss plus log-normal shadowing model. Full article

(This article belongs to the Special Issue Machine Learning Models for Wireless Network Monitoring and Data Analysis)

► Show Figures

Figure 1

23 pages, 4894 KiB

Open AccessEditor’s ChoiceArticle

Deep Joint Spatiotemporal Network (DJSTN) for Efficient Facial Expression Recognition

by Dami Jeong, Byung-Gyu Kim and Suh-Yeon Dong

Sensors 2020, 20(7), 1936; https://doi.org/10.3390/s20071936 - 30 Mar 2020

Cited by 78 | Viewed by 5634

Abstract

Understanding a person’s feelings is a very important process for the affective computing. People express their emotions in various ways. Among them, facial expression is the most effective way to present human emotional status. We propose efficient deep joint spatiotemporal features for facial [...] Read more.

Understanding a person’s feelings is a very important process for the affective computing. People express their emotions in various ways. Among them, facial expression is the most effective way to present human emotional status. We propose efficient deep joint spatiotemporal features for facial expression recognition based on the deep appearance and geometric neural networks. We apply three-dimensional (3D) convolution to extract spatial and temporal features at the same time. For the geometric network, 23 dominant facial landmarks are selected to express the movement of facial muscle through the analysis of energy distribution of whole facial landmarks.We combine these features by the designed joint fusion classifier to complement each other. From the experimental results, we verify the recognition accuracy of 99.21%, 87.88%, and 91.83% for CK+, MMI, and FERA datasets, respectively. Through the comparative analysis, we show that the proposed scheme is able to improve the recognition accuracy by 4% at least. Full article

(This article belongs to the Special Issue Deep Learning Methods for Human Activity Recognition and Emotion Detection)

► Show Figures

Figure 1

20 pages, 3986 KiB

Open AccessEditor’s ChoiceArticle

Wearable Hand Module and Real-Time Tracking Algorithms for Measuring Finger Joint Angles of Different Hand Sizes with High Accuracy Using FBG Strain Sensor

by Jun Sik Kim, Byung Kook Kim, Minsu Jang, Kyumin Kang, Dae Eun Kim, Byeong-Kwon Ju and Jinseok Kim

Sensors 2020, 20(7), 1921; https://doi.org/10.3390/s20071921 - 30 Mar 2020

Cited by 33 | Viewed by 6990

Abstract

This paper presents a wearable hand module which was made of five fiber Bragg grating (FBG) strain sensor and algorithms to achieve high accuracy even when worn on different hand sizes of users. For real-time calculation with high accuracy, FBG strain sensors move [...] Read more.

This paper presents a wearable hand module which was made of five fiber Bragg grating (FBG) strain sensor and algorithms to achieve high accuracy even when worn on different hand sizes of users. For real-time calculation with high accuracy, FBG strain sensors move continuously according to the size of the hand and the bending of the joint. Representatively, four algorithms were proposed; point strain (PTS), area summation (AREA), proportional summation (PS), and PS/interference (PS/I or PS/I_

α

). For more accurate and efficient assessments, 3D printed hand replica with different finger sizes was adopted and quantitative evaluations were performed for index~little fingers (77 to 117 mm) and thumb (68~78 mm). For index~little fingers, the optimized algorithms were PS and PS/I_

α

. For thumb, the optimized algorithms were PS/I_

α

and AREA. The average error angle of the wearable hand module was observed to be 0.47 ± 2.51° and mean absolute error (MAE) was achieved at 1.63 ± 1.97°. These results showed that more accurate hand modules than other glove modules applied to different hand sizes can be manufactured using FBG strain sensors which move continuously and algorithms for tracking this movable FBG sensors. Full article

(This article belongs to the Special Issue Fiber Bragg Grating Based Sensors and Systems)

► Show Figures

Figure 1

17 pages, 3381 KiB

Open AccessEditor’s ChoiceArticle

Pattern Recognition and Anomaly Detection by Self-Organizing Maps in a Multi Month E-nose Survey at an Industrial Site

by Sabina Licen, Alessia Di Gilio, Jolanda Palmisani, Stefania Petraccone, Gianluigi de Gennaro and Pierluigi Barbieri

Sensors 2020, 20(7), 1887; https://doi.org/10.3390/s20071887 - 29 Mar 2020

Cited by 20 | Viewed by 4589

Abstract

Currently people are aware of the risk related to pollution exposure. Thus odor annoyances are considered a warning about the possible presence of toxic volatile compounds. Malodor often generates immediate alarm among citizens, and electronic noses are convenient instruments to detect mixture of [...] Read more.

Currently people are aware of the risk related to pollution exposure. Thus odor annoyances are considered a warning about the possible presence of toxic volatile compounds. Malodor often generates immediate alarm among citizens, and electronic noses are convenient instruments to detect mixture of odorant compounds with high monitoring frequency. In this paper we present a study on pattern recognition on ambient air composition in proximity of a gas and oil pretreatment plant by elaboration of data from an electronic nose implementing 10 metal-oxide-semiconductor (MOS) sensors and positioned outdoor continuously during three months. A total of 80,017 e-nose vectors have been elaborated applying the self-organizing map (SOM) algorithm and then k-means clustering on SOM outputs on the whole data set evidencing an anomalous data cluster. Retaining data characterized by dynamic responses of the multisensory system, a SOM with 264 recurrent sensor responses to air mixture sampled at the site and four main air type profiles (clusters) have been identified. One of this sensor profiles has been related to the odor fugitive emissions of the plant, by using ancillary data from a total volatile organic compound (VOC) detector and wind speed and direction data. The overall and daily cluster frequencies have been evaluated, allowing us to identify the daily duration of presence at the monitoring site of air related to industrial emissions. The refined model allowed us to confirm the anomaly detection of the sensor responses. Full article

(This article belongs to the Special Issue Electronic Noses and Tongues for Environmental Monitoring)

► Show Figures

Figure 1

18 pages, 2572 KiB

Open AccessEditor’s ChoiceReview

PEDOT:PSS-Based Conductive Textiles and Their Applications

by Granch Berhe Tseghai, Desalegn Alemu Mengistie, Benny Malengier, Kinde Anlay Fante and Lieva Van Langenhove

Sensors 2020, 20(7), 1881; https://doi.org/10.3390/s20071881 - 28 Mar 2020

Cited by 129 | Viewed by 17017

Abstract

The conductive polymer complex poly (3,4-ethylene dioxythiophene):polystyrene sulfonate (PEDOT:PSS) is the most explored conductive polymer for conductive textiles applications. Since PEDOT:PSS is readily available in water dispersion form, it is convenient for roll-to-roll processing which is compatible with the current textile processing applications. [...] Read more.

The conductive polymer complex poly (3,4-ethylene dioxythiophene):polystyrene sulfonate (PEDOT:PSS) is the most explored conductive polymer for conductive textiles applications. Since PEDOT:PSS is readily available in water dispersion form, it is convenient for roll-to-roll processing which is compatible with the current textile processing applications. In this work, we have made a comprehensive review on the PEDOT:PSS-based conductive textiles, methods of application onto textiles and their applications. The conductivity of PEDOT:PSS can be enhanced by several orders of magnitude using processing agents. However, neat PEDOT:PSS lacks flexibility and strechability for wearable electronics applications. One way to improve the mechanical flexibility of conductive polymers is making a composite with commodity polymers such as polyurethane which have high flexibility and stretchability. The conductive polymer composites also increase attachment of the conductive polymer to the textile, thereby increasing durability to washing and mechanical actions. Pure PEDOT:PSS conductive fibers have been produced by solution spinning or electrospinning methods. Application of PEDOT:PSS can be carried out by polymerization of the monomer on the fabric, coating/dyeing and printing methods. PEDOT:PSS-based conductive textiles have been used for the development of sensors, actuators, antenna, interconnections, energy harvesting, and storage devices. In this review, the application methods of PEDOT:SS-based conductive polymers in/on to a textile substrate structure and their application thereof are discussed. Full article

(This article belongs to the Special Issue Smart Structures and Materials for Sensor Applications)

► Show Figures

Figure 1

19 pages, 3749 KiB

Open AccessEditor’s ChoiceArticle

Bearing Fault Diagnosis of Induction Motors Using a Genetic Algorithm and Machine Learning Classifiers

by Rafia Nishat Toma, Alexander E. Prosvirin and Jong-Myon Kim

Sensors 2020, 20(7), 1884; https://doi.org/10.3390/s20071884 - 28 Mar 2020

Cited by 156 | Viewed by 11173

Abstract

Efficient fault diagnosis of electrical and mechanical anomalies in induction motors (IMs) is challenging but necessary to ensure safety and economical operation in industries. Research has shown that bearing faults are the most frequently occurring faults in IMs. The vibration signals carry rich [...] Read more.

Efficient fault diagnosis of electrical and mechanical anomalies in induction motors (IMs) is challenging but necessary to ensure safety and economical operation in industries. Research has shown that bearing faults are the most frequently occurring faults in IMs. The vibration signals carry rich information about bearing health conditions and are commonly utilized for fault diagnosis in bearings. However, collecting these signals is expensive and sometimes impractical because it requires the use of external sensors. The external sensors demand enough space and are difficult to install in inaccessible sites. To overcome these disadvantages, motor current signal-based bearing fault diagnosis methods offer an attractive solution. As such, this paper proposes a hybrid motor-current data-driven approach that utilizes statistical features, genetic algorithm (GA) and machine learning models for bearing fault diagnosis. First, the statistical features are extracted from the motor current signals. Second, the GA is utilized to reduce the number of features and select the most important ones from the feature database. Finally, three different classification algorithms namely KNN, decision tree, and random forest, are trained and tested using these features in order to evaluate the bearing faults. This combination of techniques increases the accuracy and reduces the computational complexity. The experimental results show that the three classifiers achieve an accuracy of more than 97%. In addition, the evaluation parameters such as precision, F1-score, sensitivity, and specificity show better performance. Finally, to validate the efficiency of the proposed model, it is compared with some recently adopted techniques. The comparison results demonstrate that the suggested technique is promising for diagnosis of IM bearing faults. Full article

(This article belongs to the Special Issue Sensor Applications in Fault Diagnosis and Monitoring of Electrical Machines)

► Show Figures

Figure 1

17 pages, 15903 KiB

Open AccessEditor’s ChoiceArticle

Leveraging LoRaWAN Technology for Precision Agriculture in Greenhouses

by Ritesh Kumar Singh, Michiel Aernouts, Mats De Meyer, Maarten Weyn and Rafael Berkvens

Sensors 2020, 20(7), 1827; https://doi.org/10.3390/s20071827 - 25 Mar 2020

Cited by 67 | Viewed by 8302

Abstract

The technology development in wireless sensor network (WSN) offers a sustainable solution towards precision agriculture (PA) in greenhouses. It helps to effectively use the agricultural resources and management tools and monitors different parameters to attain better quality yield and production. WSN makes use [...] Read more.

The technology development in wireless sensor network (WSN) offers a sustainable solution towards precision agriculture (PA) in greenhouses. It helps to effectively use the agricultural resources and management tools and monitors different parameters to attain better quality yield and production. WSN makes use of Low-Power Wide-Area Networks (LPWANs), a wireless technology to transmit data over long distances with minimal power consumption. LoRaWAN is one of the most successful LPWAN technologies despite its low data rate and because of its low deployment and management costs. Greenhouses are susceptible to different types of interference and diversification, demanding an improved WSN design scheme. In this paper, we contemplate the viable challenges for PA in greenhouses and propose the successive steps essential for effectual WSN deployment and facilitation. We performed a real-time, end-to-end deployment of a LoRaWAN-based sensor network in a greenhouse of the ’Proefcentrum Hoogstraten’ research center in Belgium. We have designed a dashboard for better visualization and analysis of the data, analyzed the power consumption for the LoRaWAN communication, and tried three different enclosure types (commercial, simple box and airflow box, respectively). We validated the implications of real-word challenges on the end-to-end deployment and air circulation for the correct sensor readings. We found that temperature and humidity have a larger impact on the sensor readings inside the greenhouse than we initially thought, which we successfully solved through the airflow box design. Full article

(This article belongs to the Special Issue Smart Agricultural Applications with Internet of Things)

► Show Figures

Figure 1

23 pages, 4257 KiB

Open AccessEditor’s ChoiceArticle

Ultrasound Image-Based Diagnosis of Malignant Thyroid Nodule Using Artificial Intelligence

by Dat Tien Nguyen, Jin Kyu Kang, Tuyen Danh Pham, Ganbayar Batchuluun and Kang Ryoung Park

Sensors 2020, 20(7), 1822; https://doi.org/10.3390/s20071822 - 25 Mar 2020

Cited by 83 | Viewed by 10744

Abstract

Computer-aided diagnosis systems have been developed to assist doctors in diagnosing thyroid nodules to reduce errors made by traditional diagnosis methods, which are mainly based on the experiences of doctors. Therefore, the performance of such systems plays an important role in enhancing the [...] Read more.

Computer-aided diagnosis systems have been developed to assist doctors in diagnosing thyroid nodules to reduce errors made by traditional diagnosis methods, which are mainly based on the experiences of doctors. Therefore, the performance of such systems plays an important role in enhancing the quality of a diagnosing task. Although there have been the state-of-the art studies regarding this problem, which are based on handcrafted features, deep features, or the combination of the two, their performances are still limited. To overcome these problems, we propose an ultrasound image-based diagnosis of the malignant thyroid nodule method using artificial intelligence based on the analysis in both spatial and frequency domains. Additionally, we propose the use of weighted binary cross-entropy loss function for the training of deep convolutional neural networks to reduce the effects of unbalanced training samples of the target classes in the training data. Through our experiments with a popular open dataset, namely the thyroid digital image database (TDID), we confirm the superiority of our method compared to the state-of-the-art methods. Full article

(This article belongs to the Special Issue Image and Video Processing and Recognition Based on Artificial Intelligence)

► Show Figures

Figure 1

20 pages, 2037 KiB

Open AccessEditor’s ChoiceArticle

Exploiting Smart Contracts for Capability-Based Access Control in the Internet of Things

by Yuta Nakamura, Yuanyu Zhang, Masahiro Sasabe and Shoji Kasahara

Sensors 2020, 20(6), 1793; https://doi.org/10.3390/s20061793 - 24 Mar 2020

Cited by 52 | Viewed by 6444

Abstract

Due to the rapid penetration of the Internet of Things (IoT) into human life, illegal access to IoT resources (e.g., data and actuators) has greatly threatened our safety. Access control, which specifies who (i.e., subjects) can access what resources (i.e., objects) under what [...] Read more.

Due to the rapid penetration of the Internet of Things (IoT) into human life, illegal access to IoT resources (e.g., data and actuators) has greatly threatened our safety. Access control, which specifies who (i.e., subjects) can access what resources (i.e., objects) under what conditions, has been recognized as an effective solution to address this issue. To cope with the distributed and trust-less nature of IoT systems, we propose a decentralized and trustworthy Capability-Based Access Control (CapBAC) scheme by using the Ethereum smart contract technology. In this scheme, a smart contract is created for each object to store and manage the capability tokens (i.e., data structures recording granted access rights) assigned to the related subjects, and also to verify the ownership and validity of the tokens for access control. Different from previous schemes which manage the tokens in units of subjects, i.e., one token per subject, our scheme manages the tokens in units of access rights or actions, i.e., one token per action. Such novel management achieves more fine-grained and flexible capability delegation and also ensures the consistency between the delegation information and the information stored in the tokens. We implemented the proposed CapBAC scheme in a locally constructed Ethereum blockchain network to demonstrate its feasibility. In addition, we measured the monetary cost of our scheme in terms of gas consumption to compare our scheme with the existing Blockchain-Enabled Decentralized Capability-Based Access Control (BlendCAC) scheme proposed by other researchers. The experimental results show that the proposed scheme outperforms the BlendCAC scheme in terms of the flexibility, granularity, and consistency of capability delegation at almost the same monetary cost. Full article

(This article belongs to the Special Issue Blockchain Security and Privacy for the Internet of Things)

► Show Figures

Figure 1

21 pages, 2277 KiB

Open AccessEditor’s ChoiceReview

The Hierarchic Treatment of Marine Ecological Information from Spatial Networks of Benthic Platforms

by Jacopo Aguzzi, Damianos Chatzievangelou, Marco Francescangeli, Simone Marini, Federico Bonofiglio, Joaquin del Rio and Roberto Danovaro

Sensors 2020, 20(6), 1751; https://doi.org/10.3390/s20061751 - 21 Mar 2020

Cited by 32 | Viewed by 5338

Abstract

Measuring biodiversity simultaneously in different locations, at different temporal scales, and over wide spatial scales is of strategic importance for the improvement of our understanding of the functioning of marine ecosystems and for the conservation of their biodiversity. Monitoring networks of cabled observatories, [...] Read more.

Measuring biodiversity simultaneously in different locations, at different temporal scales, and over wide spatial scales is of strategic importance for the improvement of our understanding of the functioning of marine ecosystems and for the conservation of their biodiversity. Monitoring networks of cabled observatories, along with other docked autonomous systems (e.g., Remotely Operated Vehicles [ROVs], Autonomous Underwater Vehicles [AUVs], and crawlers), are being conceived and established at a spatial scale capable of tracking energy fluxes across benthic and pelagic compartments, as well as across geographic ecotones. At the same time, optoacoustic imaging is sustaining an unprecedented expansion in marine ecological monitoring, enabling the acquisition of new biological and environmental data at an appropriate spatiotemporal scale. At this stage, one of the main problems for an effective application of these technologies is the processing, storage, and treatment of the acquired complex ecological information. Here, we provide a conceptual overview on the technological developments in the multiparametric generation, storage, and automated hierarchic treatment of biological and environmental information required to capture the spatiotemporal complexity of a marine ecosystem. In doing so, we present a pipeline of ecological data acquisition and processing in different steps and prone to automation. We also give an example of population biomass, community richness and biodiversity data computation (as indicators for ecosystem functionality) with an Internet Operated Vehicle (a mobile crawler). Finally, we discuss the software requirements for that automated data processing at the level of cyber-infrastructures with sensor calibration and control, data banking, and ingestion into large data portals. Full article

(This article belongs to the Special Issue Underwater Sensor Networks)

► Show Figures

Figure 1

21 pages, 11730 KiB

Open AccessEditor’s ChoiceArticle

A Novel Fabry-Pérot Optical Sensor for Guided Wave Signal Acquisition

by Cheng Xu and Zahra Sharif Khodaei

Sensors 2020, 20(6), 1728; https://doi.org/10.3390/s20061728 - 19 Mar 2020

Cited by 15 | Viewed by 3593

Abstract

In this paper, a novel hybrid damage detection system is proposed, which utilizes piezoelectric actuators for guided wave excitation and a new fibre optic (FO) sensor based on Fabry-Perot (FP) and Fiber Bragg Grating (FBG). By replacing the FBG sensors with FBG-based FP [...] Read more.

In this paper, a novel hybrid damage detection system is proposed, which utilizes piezoelectric actuators for guided wave excitation and a new fibre optic (FO) sensor based on Fabry-Perot (FP) and Fiber Bragg Grating (FBG). By replacing the FBG sensors with FBG-based FP sensors in the hybrid damage detection system, a higher strain resolution is achieved, which results in higher damage sensitivity and higher reliability in diagnosis. To develop the novel sensor, optimum parameters such as reflectivity, a wavelength spectrum, and a sensor length were chosen carefully through an analytical model of the sensor, which has been validated with experiments. The sensitivity of the new FBG-based FP sensors was compared to FBG sensors to emphasize the superiority of the new sensors in measuring micro-strains. Lastly, the new FBG-based FP sensor was utilized for recording guided waves in a hybrid setup and compared to the conventional FBG hybrid sensor network to demonstrate their improved performance for a structural health monitoring (SHM) application. Full article

(This article belongs to the Section Optical Sensors)

► Show Figures

Figure 1

25 pages, 7743 KiB

Open AccessEditor’s ChoiceArticle

A Wristwatch-Based Wireless Sensor Platform for IoT Health Monitoring Applications

by Sanjeev Kumar, John L. Buckley, John Barton, Melusine Pigeon, Robert Newberry, Matthew Rodencal, Adhurim Hajzeraj, Tim Hannon, Ken Rogers, Declan Casey, Donal O’Sullivan and Brendan O’Flynn

Sensors 2020, 20(6), 1675; https://doi.org/10.3390/s20061675 - 17 Mar 2020

Cited by 42 | Viewed by 15619

Abstract

A wristwatch-based wireless sensor platform for IoT wearable health monitoring applications is presented. The paper describes the platform in detail, with a particular focus given to the design of a novel and compact wireless sub-system for 868 MHz wristwatch applications. An example application [...] Read more.

A wristwatch-based wireless sensor platform for IoT wearable health monitoring applications is presented. The paper describes the platform in detail, with a particular focus given to the design of a novel and compact wireless sub-system for 868 MHz wristwatch applications. An example application using the developed platform is discussed for arterial oxygen saturation (SpO₂) and heart rate measurement using optical photoplethysmography (PPG). A comparison of the wireless performance in the 868 MHz and the 2.45 GHz bands is performed. Another contribution of this work is the development of a highly integrated 868 MHz antenna. The antenna structure is printed on the surface of a wristwatch enclosure using laser direct structuring (LDS) technology. At 868 MHz, a low specific absorption rate (SAR) of less than 0.1% of the maximum permissible limit in the simulation is demonstrated. The measured on-body prototype antenna exhibits a −10 dB impedance bandwidth of 36 MHz, a peak realized gain of −4.86 dBi and a radiation efficiency of 14.53% at 868 MHz. To evaluate the performance of the developed 868 MHz sensor platform, the wireless communication range measurements are performed in an indoor environment and compared with a commercial Bluetooth wristwatch device. Full article

(This article belongs to the Special Issue Wearable Sensors and Systems in the IOT)

► Show Figures

Figure 1

26 pages, 578 KiB

Open AccessEditor’s ChoiceReview

Biofeedback Systems for Gait Rehabilitation of Individuals with Lower-Limb Amputation: A Systematic Review

by Rafael Escamilla-Nunez, Alexandria Michelini and Jan Andrysek

Sensors 2020, 20(6), 1628; https://doi.org/10.3390/s20061628 - 14 Mar 2020

Cited by 33 | Viewed by 9339

Abstract

Individuals with lower-limb amputation often have gait deficits and diminished mobility function. Biofeedback systems have the potential to improve gait rehabilitation outcomes. Research on biofeedback has steadily increased in recent decades, representing the growing interest toward this topic. This systematic review highlights the [...] Read more.

Individuals with lower-limb amputation often have gait deficits and diminished mobility function. Biofeedback systems have the potential to improve gait rehabilitation outcomes. Research on biofeedback has steadily increased in recent decades, representing the growing interest toward this topic. This systematic review highlights the methodological designs, main technical and clinical challenges, and evidence relating to the effectiveness of biofeedback systems for gait rehabilitation. This review provides insights for developing an effective, robust, and user-friendly wearable biofeedback system. The literature search was conducted on six databases and 31 full-text articles were included in this review. Most studies found biofeedback to be effective in improving gait. Biofeedback was most commonly concurrently provided and related to limb loading and symmetry ratios for stance or step time. Visual feedback was the most used modality, followed by auditory and haptic. Biofeedback must not be obtrusive and ideally provide a level of enjoyment to the user. Biofeedback appears to be most effective during the early stages of rehabilitation but presents some usability challenges when applied to the elderly. More research is needed on younger populations and higher amputation levels, understanding retention as well as the relationship between training intensity and performance. Full article

(This article belongs to the Collection Sensors for Gait, Human Movement Analysis, and Health Monitoring)

► Show Figures

Figure 1

15 pages, 2237 KiB

Open AccessEditor’s ChoiceArticle

Analysis of Machine Learning-Based Assessment for Elbow Spasticity Using Inertial Sensors

by Jung-Yeon Kim, Geunsu Park, Seong-A Lee and Yunyoung Nam

Sensors 2020, 20(6), 1622; https://doi.org/10.3390/s20061622 - 14 Mar 2020

Cited by 40 | Viewed by 4809

Abstract

Spasticity is a frequently observed symptom in patients with neurological impairments. Spastic movements of their upper and lower limbs are periodically measured to evaluate functional outcomes of physical rehabilitation, and they are quantified by clinical outcome measures such as the modified Ashworth scale [...] Read more.

Spasticity is a frequently observed symptom in patients with neurological impairments. Spastic movements of their upper and lower limbs are periodically measured to evaluate functional outcomes of physical rehabilitation, and they are quantified by clinical outcome measures such as the modified Ashworth scale (MAS). This study proposes a method to determine the severity of elbow spasticity, by analyzing the acceleration and rotation attributes collected from the elbow of the affected side of patients and machine-learning algorithms to classify the degree of spastic movement; this approach is comparable to assigning an MAS score. We collected inertial data from participants using a wearable device incorporating inertial measurement units during a passive stretch test. Machine-learning algorithms—including decision tree, random forests (RFs), support vector machine, linear discriminant analysis, and multilayer perceptrons—were evaluated in combinations of two segmentation techniques and feature sets. A RF performed well, achieving up to 95.4% accuracy. This work not only successfully demonstrates how wearable technology and machine learning can be used to generate a clinically meaningful index but also offers rehabilitation patients an opportunity to monitor the degree of spasticity, even in nonhealthcare institutions where the help of clinical professionals is unavailable. Full article

(This article belongs to the Special Issue Wearable Sensors and Systems for Rehabilitation)

► Show Figures

Figure 1

11 pages, 1521 KiB

Open AccessEditor’s ChoiceArticle

Surface Plasmon Resonance-Based Sensing Utilizing Spatial Phase Modulation in an Imaging Interferometer

by Roman Kaňok, Dalibor Ciprian and Petr Hlubina

Sensors 2020, 20(6), 1616; https://doi.org/10.3390/s20061616 - 13 Mar 2020

Cited by 9 | Viewed by 3566

Abstract

Spatial phase modulation in an imaging interferometer is utilized in surface plasmon resonance (SPR) based sensing of liquid analytes. In the interferometer, a collimated light beam from a laser diode irradiating at 637.1 nm is passing through a polarizer and is reflected from [...] Read more.

Spatial phase modulation in an imaging interferometer is utilized in surface plasmon resonance (SPR) based sensing of liquid analytes. In the interferometer, a collimated light beam from a laser diode irradiating at 637.1 nm is passing through a polarizer and is reflected from a plasmonic structure of SF10/Cr/Au attached to a prism in the Kretschmann configuration. The beam passes through a combination of a Wollaston prism, a polarizer and a lens, and forms an interference pattern on a CCD sensor of a color camera. Interference patterns obtained for different liquid analytes are acquired and transferred to the computer for data processing. The sensing concept is based on the detection of a refractive index change, which is transformed via the SPR phenomenon into an interference fringe phase shift. By calculating the phase shift for the plasmonic structure of SF10/Cr/Au of known parameters we demonstrate that this technique can detect different weight concentrations of ethanol diluted in water, or equivalently, different changes in the refractive index. The sensitivity to the refractive index and the detection limit obtained are −278 rad/refractive-index-unit (RIU) and 3.6

\times 10^{- 6}

RIU, respectively. The technique is demonstrated in experiments with the same liquid analytes as in the theory. Applying an original approach in retrieving the fringe phase shift, we revealed good agreement between experiment and theory, and the measured sensitivity to the refractive index and the detection limit reached −226 rad/RIU and 4.4

\times 10^{- 6}

RIU, respectively. These results suggest that the SPR interferometer with the detection of a fringe phase shift is particularly useful in applications that require measuring refractive index changes with high sensitivity. Full article

(This article belongs to the Section Optical Sensors)

► Show Figures

Figure 1

15 pages, 5286 KiB

Open AccessEditor’s ChoiceArticle

Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network

by Xiaoming Lv, Fajie Duan, Jia-jia Jiang, Xiao Fu and Lin Gan

Sensors 2020, 20(6), 1562; https://doi.org/10.3390/s20061562 - 11 Mar 2020

Cited by 175 | Viewed by 13286

Abstract

Metallic surface defect detection is an essential and necessary process to control the qualities of industrial products. However, due to the limited data scale and defect categories, existing defect datasets are generally unavailable for the deployment of the detection model. To address this [...] Read more.

Metallic surface defect detection is an essential and necessary process to control the qualities of industrial products. However, due to the limited data scale and defect categories, existing defect datasets are generally unavailable for the deployment of the detection model. To address this problem, we contribute a new dataset called GC10-DET for large-scale metallic surface defect detection. The GC10-DET dataset has great challenges on defect categories, image number, and data scale. Besides, traditional detection approaches are poor in both efficiency and accuracy for the complex real-world environment. Thus, we also propose a novel end-to-end defect detection network (EDDN) based on the Single Shot MultiBox Detector. The EDDN model can deal with defects with different scales. Furthermore, a hard negative mining method is designed to alleviate the problem of data imbalance, while some data augmentation methods are adopted to enrich the training data for the expensive data collection problem. Finally, the extensive experiments on two datasets demonstrate that the proposed method is robust and can meet accuracy requirements for metallic defect detection. Full article

(This article belongs to the Collection Signal Processing, Control, and Estimation for Intelligent Sensor Systems)

► Show Figures

Figure 1

21 pages, 3548 KiB

Open AccessEditor’s ChoiceArticle

Doubling the Accuracy of Indoor Positioning: Frequency Diversity

by Berthold K.P. Horn

Sensors 2020, 20(5), 1489; https://doi.org/10.3390/s20051489 - 9 Mar 2020

Cited by 39 | Viewed by 4966

Abstract

Determination of indoor position based on fine time measurement (FTM) of the round trip time (RTT) of a signal between an initiator (smartphone) and a responder (Wi-Fi access point) enables a number of applications. However, the accuracy currently attainable—standard deviations of 1–2 m [...] Read more.

Determination of indoor position based on fine time measurement (FTM) of the round trip time (RTT) of a signal between an initiator (smartphone) and a responder (Wi-Fi access point) enables a number of applications. However, the accuracy currently attainable—standard deviations of 1–2 m in distance measurement under favorable circumstances—limits the range of possible applications. An emergency worker, for example, may not be able to unequivocally determine on which floor someone in need of help is in a multi-story building. The error in position depends on several factors, including the bandwidth of the RF signal, delay of the signal due to the high relative permittivity of construction materials, and the geometry-dependent “noise gain” of position determination. Errors in distance measurements have unusal properties that are exposed here. Improvements in accuracy depend on understanding all of these error sources. This paper introduces “frequency diversity,” a method for doubling the accuracy of indoor position determination using weighted averages of measurements with uncorrelated errors obtained in different channels. The properties of this method are verified experimentally with a range of responders. Finally, different ways of using the distance measurements to determine indoor position are discussed and the Bayesian grid update method shown to be more useful than others, given the non-Gaussian nature of the measurement errors. Full article

(This article belongs to the Special Issue Sensors and Sensing Technologies for Indoor Positioning and Indoor Navigation)

► Show Figures

Figure 1

14 pages, 4032 KiB

Open AccessEditor’s ChoiceArticle

Motion Artifact Reduction in Wearable Photoplethysmography Based on Multi-Channel Sensors with Multiple Wavelengths

by Jongshill Lee, Minseong Kim, Hoon-Ki Park and In Young Kim

Sensors 2020, 20(5), 1493; https://doi.org/10.3390/s20051493 - 9 Mar 2020

Cited by 74 | Viewed by 9960

Abstract

Photoplethysmography (PPG) is an easy and convenient method by which to measure heart rate (HR). However, PPG signals that optically measure volumetric changes in blood are not robust to motion artifacts. In this paper, we develop a PPG measuring system based on multi-channel [...] Read more.

Photoplethysmography (PPG) is an easy and convenient method by which to measure heart rate (HR). However, PPG signals that optically measure volumetric changes in blood are not robust to motion artifacts. In this paper, we develop a PPG measuring system based on multi-channel sensors with multiple wavelengths and propose a motion artifact reduction algorithm using independent component analysis (ICA). We also propose a truncated singular value decomposition for 12-channel PPG signals, which contain direction and depth information measured using the developed multi-channel PPG measurement system. The performance of the proposed method is evaluated against the R-peaks of an electrocardiogram in terms of sensitivity (Se), positive predictive value (PPV), and failed detection rate (FDR). The experimental results show that Se, PPV, and FDR were 99%, 99.55%, and 0.45% for walking, 96.28%, 99.24%, and 0.77% for fast walking, and 82.49%, 99.83%, and 0.17% for running, respectively. The evaluation shows that the proposed method is effective in reducing errors in HR estimation from PPG signals with motion artifacts in intensive motion situations such as fast walking and running. Full article

(This article belongs to the Special Issue Advanced Signal Processing in Wearable Sensors for Health Monitoring)

► Show Figures

Figure 1

17 pages, 6667 KiB

Open AccessEditor’s ChoiceArticle

Image-Based Phenotyping of Flowering Intensity in Cool-Season Crops

by Chongyuan Zhang, Wilson A. Craine, Rebecca J. McGee, George J. Vandemark, James B. Davis, Jack Brown, Scot H. Hulbert and Sindhuja Sankaran

Sensors 2020, 20(5), 1450; https://doi.org/10.3390/s20051450 - 6 Mar 2020

Cited by 22 | Viewed by 4283

Abstract

The timing and duration of flowering are key agronomic traits that are often associated with the ability of a variety to escape abiotic stress such as heat and drought. Flowering information is valuable in both plant breeding and agricultural production management. Visual assessment, [...] Read more.

The timing and duration of flowering are key agronomic traits that are often associated with the ability of a variety to escape abiotic stress such as heat and drought. Flowering information is valuable in both plant breeding and agricultural production management. Visual assessment, the standard protocol used for phenotyping flowering, is a low-throughput and subjective method. In this study, we evaluated multiple imaging sensors (RGB and multiple multispectral cameras), image resolution (proximal/remote sensing at 1.6 to 30 m above ground level/AGL), and image processing (standard and unsupervised learning) techniques in monitoring flowering intensity of four cool-season crops (canola, camelina, chickpea, and pea) to enhance the accuracy and efficiency in quantifying flowering traits. The features (flower area, percentage of flower area with respect to canopy area) extracted from proximal (1.6–2.2 m AGL) RGB and multispectral (with near infrared, green and blue band) image data were strongly correlated (r up to 0.89) with visual rating scores, especially in pea and canola. The features extracted from unmanned aerial vehicle integrated RGB image data (15–30 m AGL) could also accurately detect and quantify large flowers of winter canola (r up to 0.84), spring canola (r up to 0.72), and pea (r up to 0.72), but not camelina or chickpea flowers. When standard image processing using thresholds and unsupervised machine learning such as k-means clustering were utilized for flower detection and feature extraction, the results were comparable. In general, for applicability of imaging for flower detection, it is recommended that the image data resolution (i.e., ground sampling distance) is at least 2–3 times smaller than that of the flower size. Overall, this study demonstrates the feasibility of utilizing imaging for monitoring flowering intensity in multiple varieties of evaluated crops. Full article

(This article belongs to the Special Issue Advanced Sensor Technologies for Crop Phenotyping Application)

► Show Figures

Figure 1

16 pages, 4119 KiB

Open AccessEditor’s ChoiceArticle

Towards Efficient Electricity Forecasting in Residential and Commercial Buildings: A Novel Hybrid CNN with a LSTM-AE based Framework

by Zulfiqar Ahmad Khan, Tanveer Hussain, Amin Ullah, Seungmin Rho, Miyoung Lee and Sung Wook Baik

Sensors 2020, 20(5), 1399; https://doi.org/10.3390/s20051399 - 4 Mar 2020

Cited by 126 | Viewed by 9617

Abstract

Due to industrialization and the rising demand for energy, global energy consumption has been rapidly increasing. Recent studies show that the biggest portion of energy is consumed in residential buildings, i.e., in European Union countries up to 40% of the total energy is [...] Read more.

Due to industrialization and the rising demand for energy, global energy consumption has been rapidly increasing. Recent studies show that the biggest portion of energy is consumed in residential buildings, i.e., in European Union countries up to 40% of the total energy is consumed by households. Most residential buildings and industrial zones are equipped with smart sensors such as metering electric sensors, that are inadequately utilized for better energy management. In this paper, we develop a hybrid convolutional neural network (CNN) with an long short-term memory autoencoder (LSTM-AE) model for future energy prediction in residential and commercial buildings. The central focus of this research work is to utilize the smart meters’ data for energy forecasting in order to enable appropriate energy management in buildings. We performed extensive research using several deep learning-based forecasting models and proposed an optimal hybrid CNN with the LSTM-AE model. To the best of our knowledge, we are the first to incorporate the aforementioned models under the umbrella of a unified framework with some utility preprocessing. Initially, the CNN model extracts features from the input data, which are then fed to the LSTM-encoder to generate encoded sequences. The encoded sequences are decoded by another following LSTM-decoder to advance it to the final dense layer for energy prediction. The experimental results using different evaluation metrics show that the proposed hybrid model works well. Also, it records the smallest value for mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE) when compared to other state-of-the-art forecasting methods over the UCI residential building dataset. Furthermore, we conducted experiments on Korean commercial building data and the results indicate that our proposed hybrid model is a worthy contribution to energy forecasting. Full article

(This article belongs to the Special Issue Smart IoT System for Renewable Energy Resource)

► Show Figures

Figure 1

14 pages, 15615 KiB

Open AccessEditor’s ChoiceArticle

Water Management for Sustainable Irrigation Systems Using Internet-of-Things

by André Glória, Carolina Dionisio, Gonçalo Simões, João Cardoso and Pedro Sebastião

Sensors 2020, 20(5), 1402; https://doi.org/10.3390/s20051402 - 4 Mar 2020

Cited by 39 | Viewed by 7488

Abstract

This paper introduces a new way of managing water in irrigation systems, which can be applied to gardens or agricultural fields, replacing human intervention with Wireless Sensor Networks. A typical irrigation system wastes on average 30% of the water used, due to poor [...] Read more.

This paper introduces a new way of managing water in irrigation systems, which can be applied to gardens or agricultural fields, replacing human intervention with Wireless Sensor Networks. A typical irrigation system wastes on average 30% of the water used, due to poor management and configuration. This sustainable irrigation system allows a better efficiency in the process of irrigation that can lead to savings for the end user, not only monetary but also in natural resources, such as water and energy, leading to a more sustainable environment. The system can retrieve real time data and use them to determinate the correct amount of water to be used in a garden. With this solution, it is possible to save up to 34% of water when using sensor data from temperature, humidity and soil moisture, or up to 26% when using only temperature inputs. Besides a detailed system architecture, this paper includes a real case scenario implementation and results discussion. Full article

(This article belongs to the Special Issue Sensing and Instrumentation in IoT Era)

► Show Figures

Figure 1

26 pages, 1631 KiB

Open AccessEditor’s ChoiceReview

Recent Advances in Indoor Localization via Visible Lights: A Survey

by A B M Mohaimenur Rahman, Ting Li and Yu Wang

Sensors 2020, 20(5), 1382; https://doi.org/10.3390/s20051382 - 3 Mar 2020

Cited by 85 | Viewed by 8261

Abstract

Because of the limitations of the Global Positioning System (GPS) in indoor scenarios, various types of indoor positioning or localization technologies have been proposed and deployed. Wireless radio signals have been widely used for both communication and localization purposes due to their popular [...] Read more.

Because of the limitations of the Global Positioning System (GPS) in indoor scenarios, various types of indoor positioning or localization technologies have been proposed and deployed. Wireless radio signals have been widely used for both communication and localization purposes due to their popular availability in indoor spaces. However, the accuracy of indoor localization based purely on radio signals is still not perfect. Recently, visible light communication (VLC) has made use of electromagnetic radiation from light sources for transmitting data. The potential for deploying visible light communication for indoor localization has been investigated in recent years. Visible-light-based localization enjoys low deployment cost, high throughput, and high security. In this article, the most recent advances in visible-light-based indoor localization systems have been reviewed. We strongly believe that visible-light-based localization will become a low-cost and feasible complementary solution for indoor localization and other smart building applications. Full article

(This article belongs to the Section Internet of Things)

► Show Figures

Figure 1

19 pages, 2726 KiB

Open AccessEditor’s ChoiceReview

Sensor-Integrated Microfluidic Approaches for Liquid Biopsies Applications in Early Detection of Cancer

by Jessica Sierra, José Marrugo-Ramírez, Romen Rodriguez-Trujillo, Mònica Mir and Josep Samitier

Sensors 2020, 20(5), 1317; https://doi.org/10.3390/s20051317 - 28 Feb 2020

Cited by 40 | Viewed by 7483

Abstract

Cancer represents one of the conditions with the most causes of death worldwide. Common methods for its diagnosis are based on tissue biopsies—the extraction of tissue from the primary tumor, which is used for its histological analysis. However, this technique represents a risk [...] Read more.

Cancer represents one of the conditions with the most causes of death worldwide. Common methods for its diagnosis are based on tissue biopsies—the extraction of tissue from the primary tumor, which is used for its histological analysis. However, this technique represents a risk for the patient, along with being expensive and time-consuming and so it cannot be frequently used to follow the progress of the disease. Liquid biopsy is a new cancer diagnostic alternative, which allows the analysis of the molecular information of the solid tumors via a body fluid draw. This fluid-based diagnostic method displays relevant advantages, including its minimal invasiveness, lower risk, use as often as required, it can be analyzed with the use of microfluidic-based platforms with low consumption of reagent, and it does not require specialized personnel and expensive equipment for the diagnosis. In recent years, the integration of sensors in microfluidics lab-on-a-chip devices was performed for liquid biopsies applications, granting significant advantages in the separation and detection of circulating tumor nucleic acids (ctNAs), circulating tumor cells (CTCs) and exosomes. The improvements in isolation and detection technologies offer increasingly sensitive and selective equipment’s, and the integration in microfluidic devices provides a better characterization and analysis of these biomarkers. These fully integrated systems will facilitate the generation of fully automatized platforms at low-cost for compact cancer diagnosis systems at an early stage and for the prediction and prognosis of cancer treatment through the biomarkers for personalized tumor analysis. Full article

(This article belongs to the Special Issue Sensors Integration in Organ-on-chip & Microfluidic Systems)

► Show Figures

Figure 1

31 pages, 10669 KiB

Open AccessEditor’s ChoiceArticle

The Field Monitoring Experiment of the Roof Strata Movement in Coal Mining Based on DFOS

by Tao Hu, Gongyu Hou and Zixiang Li

Sensors 2020, 20(5), 1318; https://doi.org/10.3390/s20051318 - 28 Feb 2020

Cited by 39 | Viewed by 4242

Abstract

Mining deformation of roof strata is the main cause of methane explosion, water inrush, and roof collapse accidents amid underground coal mining. To ensure the safety of coal mining, the distributed optical fiber sensor (DFOS) technology has been applied in the 150,313 working [...] Read more.

Mining deformation of roof strata is the main cause of methane explosion, water inrush, and roof collapse accidents amid underground coal mining. To ensure the safety of coal mining, the distributed optical fiber sensor (DFOS) technology has been applied in the 150,313 working face by Yinying Coal Mine in Shanxi Province, north China to monitor the roof strata movement, so as to grasp the movement law of roof strata and make it serve for production. The optical fibers are laid out in the holes drilled through the overlying strata on the roadway roof and BOTDR technique is utilized to carry out the on-site monitoring. Prior to the on-site test, the coupling test of the fiber strain in the concrete anchorage, the calibration test of the fiber strain coefficient of the 5-mm steel strand (SS) fiber, and the test of the strain transfer performance of the SS fiber were carried out in the laboratory. The approaches for fiber laying-out in the holes and fiber’s spatial positioning underground the coal mine have been optimized in the field. The indoor test results show that the high-strength SS optical fiber has a high strain transfer performance, which can be coupled with the concrete anchor with uniform deformation. This demonstrated the feasibility of SS fiber for monitoring strata movement theoretically and experimentally; and the law of roof strata fracturing and collapse is obtained from the field test results. This paper is a trial to study the whole process of dynamic movement of the deformation of roof strata. Eventually the study results will help Yinying Coal Mine to optimize mining design, prevent coal mine accidents, and provide detailed test basis for DFOS monitoring technique of roof strata movement. Full article

(This article belongs to the Special Issue Optical Fiber Sensors and Photonic Devices)

► Show Figures

Figure 1

48 pages, 3863 KiB

Open AccessEditor’s ChoiceReview

Review of Non-Invasive Glucose Sensing Techniques: Optical, Electrical and Breath Acetone

by Maryamsadat Shokrekhodaei and Stella Quinones

Sensors 2020, 20(5), 1251; https://doi.org/10.3390/s20051251 - 25 Feb 2020

Cited by 138 | Viewed by 21833

Abstract

Annual deaths in the U.S. attributed to diabetes are expected to increase from 280,210 in 2015 to 385,840 in 2030. The increase in the number of people affected by diabetes has made it one of the major public health challenges around the world. [...] Read more.

Annual deaths in the U.S. attributed to diabetes are expected to increase from 280,210 in 2015 to 385,840 in 2030. The increase in the number of people affected by diabetes has made it one of the major public health challenges around the world. Better management of diabetes has the potential to decrease yearly medical costs and deaths associated with the disease. Non-invasive methods are in high demand to take the place of the traditional finger prick method as they can facilitate continuous glucose monitoring. Research groups have been trying for decades to develop functional commercial non-invasive glucose measurement devices. The challenges associated with non-invasive glucose monitoring are the many factors that contribute to inaccurate readings. We identify and address the experimental and physiological challenges and provide recommendations to pave the way for a systematic pathway to a solution. We have reviewed and categorized non-invasive glucose measurement methods based on: (1) the intrinsic properties of glucose, (2) blood/tissue properties and (3) breath acetone analysis. This approach highlights potential critical commonalities among the challenges that act as barriers to future progress. The focus here is on the pertinent physiological aspects, remaining challenges, recent advancements and the sensors that have reached acceptable clinical accuracy. Full article

(This article belongs to the Special Issue Bioimaging and Biosensing in Telemedicine)

► Show Figures

Figure 1

18 pages, 7367 KiB

Open AccessEditor’s ChoiceArticle

Miniaturized 0.13-μm CMOS Front-End Analog for AlN PMUT Arrays

by Iván Zamora, Eyglis Ledesma, Arantxa Uranga and Núria Barniol

Sensors 2020, 20(4), 1205; https://doi.org/10.3390/s20041205 - 22 Feb 2020

Cited by 30 | Viewed by 6887

Abstract

This paper presents an analog front-end transceiver for an ultrasound imaging system based on a high-voltage (HV) transmitter, a low-noise front-end amplifier (RX), and a complementary-metal-oxide-semiconductor, aluminum nitride, piezoelectric micromachined ultrasonic transducer (CMOS-AlN-PMUT). The system was designed using the 0.13-μm Silterra CMOS process [...] Read more.

This paper presents an analog front-end transceiver for an ultrasound imaging system based on a high-voltage (HV) transmitter, a low-noise front-end amplifier (RX), and a complementary-metal-oxide-semiconductor, aluminum nitride, piezoelectric micromachined ultrasonic transducer (CMOS-AlN-PMUT). The system was designed using the 0.13-μm Silterra CMOS process and the MEMS-on-CMOS platform, which allowed for the implementation of an AlN PMUT on top of the CMOS-integrated circuit. The HV transmitter drives a column of six 80-μm-square PMUTs excited with 32 V in order to generate enough acoustic pressure at a 2.1-mm axial distance. On the reception side, another six 80-μm-square PMUT columns convert the received echo into an electric charge that is amplified by the receiver front-end amplifier. A comparative analysis between a voltage front-end amplifier (VA) based on capacitive integration and a charge-sensitive front-end amplifier (CSA) is presented. Electrical and acoustic experiments successfully demonstrated the functionality of the designed low-power analog front-end circuitry, which outperformed a state-of-the art front-end application-specific integrated circuit (ASIC) in terms of power consumption, noise performance, and area. Full article

(This article belongs to the Special Issue Electronics for Sensors)

► Show Figures

Figure 1

16 pages, 2130 KiB

Open AccessEditor’s ChoiceArticle

Detecting Respiratory Pathologies Using Convolutional Neural Networks and Variational Autoencoders for Unbalancing Data

by María Teresa García-Ordás, José Alberto Benítez-Andrades, Isaías García-Rodríguez, Carmen Benavides and Héctor Alaiz-Moretón

Sensors 2020, 20(4), 1214; https://doi.org/10.3390/s20041214 - 22 Feb 2020

Cited by 72 | Viewed by 6723

Abstract

The aim of this paper was the detection of pathologies through respiratory sounds. The ICBHI (International Conference on Biomedical and Health Informatics) Benchmark was used. This dataset is composed of 920 sounds of which 810 are of chronic diseases, 75 of non-chronic diseases [...] Read more.

The aim of this paper was the detection of pathologies through respiratory sounds. The ICBHI (International Conference on Biomedical and Health Informatics) Benchmark was used. This dataset is composed of 920 sounds of which 810 are of chronic diseases, 75 of non-chronic diseases and only 35 of healthy individuals. As more than 88% of the samples of the dataset are from the same class (Chronic), the use of a Variational Convolutional Autoencoder was proposed to generate new labeled data and other well known oversampling techniques after determining that the dataset classes are unbalanced. Once the preprocessing step was carried out, a Convolutional Neural Network (CNN) was used to classify the respiratory sounds into healthy, chronic, and non-chronic disease. In addition, we carried out a more challenging classification trying to distinguish between the different types of pathologies or healthy: URTI, COPD, Bronchiectasis, Pneumonia, and Bronchiolitis. We achieved results up to 0.993 F-Score in the three-label classification and 0.990 F-Score in the more challenging six-class classification. Full article

(This article belongs to the Special Issue Sensor and Systems Evaluation for Telemedicine and eHealth)

► Show Figures

Figure 1

16 pages, 6867 KiB

Open AccessEditor’s ChoiceArticle

A Self-Powered Wireless Water Quality Sensing Network Enabling Smart Monitoring of Biological and Chemical Stability in Supply Systems

by Marco Carminati, Andrea Turolla, Lorenzo Mezzera, Michele Di Mauro, Marco Tizzoni, Gaia Pani, Francesco Zanetto, Jacopo Foschi and Manuela Antonelli

Sensors 2020, 20(4), 1125; https://doi.org/10.3390/s20041125 - 19 Feb 2020

Cited by 48 | Viewed by 8543

Abstract

A smart, safe, and efficient management of water is fundamental for both developed and developing countries. Several wireless sensor networks have been proposed for real-time monitoring of drinking water quantity and quality, both in the environment and in pipelines. However, surface fouling significantly [...] Read more.

A smart, safe, and efficient management of water is fundamental for both developed and developing countries. Several wireless sensor networks have been proposed for real-time monitoring of drinking water quantity and quality, both in the environment and in pipelines. However, surface fouling significantly affects the long-term reliability of pipes and sensors installed in-line. To address this relevant issue, we presented a multi-parameter sensing node embedding a miniaturized slime monitor able to estimate the micrometric thickness and type of slime. The measurement of thin deposits in pipes is descriptive of water biological and chemical stability and enables early warning functions, predictive maintenance, and more efficient management processes. After the description of the sensing node, the related electronics, and the data processing strategies, we presented the results of a two-month validation in the field of a three-node pilot network. Furthermore, self-powering by means of direct energy harvesting from the water flowing through the sensing node was also demonstrated. The robustness and low cost of this solution enable its upscaling to larger monitoring networks, paving the way to water monitoring with unprecedented spatio-temporal resolution. Full article

(This article belongs to the Special Issue Sensor Systems in Smart Environments)

► Show Figures

Figure 1

11 pages, 2175 KiB

Open AccessEditor’s ChoiceArticle

Embedded Fiber Sensors to Monitor Temperature and Strain of Polymeric Parts Fabricated by Additive Manufacturing and Reinforced with NiTi Wires

by Micael Nascimento, Patrick Inácio, Tiago Paixão, Edgar Camacho, Susana Novais, Telmo G. Santos, Francisco Manuel Braz Fernandes and João L. Pinto

Sensors 2020, 20(4), 1122; https://doi.org/10.3390/s20041122 - 19 Feb 2020

Cited by 18 | Viewed by 3808

Abstract

This paper focuses on three main issues regarding Material Extrusion (MEX) Additive Manufacturing (AM) of thermoplastic composites reinforced by pre-functionalized continuous Nickel–Titanium (NiTi) wires: (i) Evaluation of the effect of the MEX process on the properties of the pre-functionalized NiTi, (ii) evaluation of [...] Read more.

This paper focuses on three main issues regarding Material Extrusion (MEX) Additive Manufacturing (AM) of thermoplastic composites reinforced by pre-functionalized continuous Nickel–Titanium (NiTi) wires: (i) Evaluation of the effect of the MEX process on the properties of the pre-functionalized NiTi, (ii) evaluation of the mechanical and thermal behavior of the composite material during usage, (iii) the inspection of the parts by Non-Destructive Testing (NDT). For this purpose, an optical fiber sensing network, based on fiber Bragg grating and a cascaded optical fiber sensor, was successfully embedded during the 3D printing of a polylactic acid (PLA) matrix reinforced by NiTi wires. Thermal and mechanical perturbations were successfully registered as a consequence of thermal and mechanical stimuli. During a heating/cooling cycle, a maximum contraction of ≈100 µm was detected by the cascaded sensor in the PLA material at the end of the heating step (induced by Joule effect) of NiTi wires and a thermal perturbation associated with the structural transformation of austenite to R-phase was observed during the natural cooling step, near 33.0 °C. Regarding tensile cycling tests, higher increases in temperature arose when the applied force ranged between 0.7 and 1.1 kN, reaching a maximum temperature variation of 9.5 ± 0.1 °C. During the unload step, a slope change in the temperature behavior was detected, which is associated with the material transformation of the NiTi wire (martensite to austenite). The embedded optical sensing methodology presented here proved to be an effective and precise tool to identify structural transformations regarding the specific application as a Non-Destructive Testing for AM. Full article

(This article belongs to the Special Issue Optical Sensors for Structural Health Monitoring)

► Show Figures

Figure 1

16 pages, 7493 KiB

Open AccessEditor’s ChoiceArticle

Prediction of Limb Joint Angles Based on Multi-Source Signals by GS-GRNN for Exoskeleton Wearer

by Hualong Xie, Guanchao Li, Xiaofei Zhao and Fei Li

Sensors 2020, 20(4), 1104; https://doi.org/10.3390/s20041104 - 18 Feb 2020

Cited by 33 | Viewed by 3650

Abstract

To enable exoskeleton wearers to walk on level ground, estimation of lower limb movement is particularly indispensable. In fact, it allows the exoskeleton to follow the human movement in real time. In this paper, the general regression neural network optimized by golden section [...] Read more.

To enable exoskeleton wearers to walk on level ground, estimation of lower limb movement is particularly indispensable. In fact, it allows the exoskeleton to follow the human movement in real time. In this paper, the general regression neural network optimized by golden section algorithm (GS-GRNN) is used to realize prediction of the human lower limb joint angle. The human body hip joint angle and the surface electromyographic (sEMG) signals of the thigh muscles are taken as the inputs of a neural network to predict joint angles of lower limbs. To improve the prediction accuracy in different gait phases, the plantar pressure signals are also added into the input. After that, the error between the prediction result and the actual data decreases significantly. Finally, compared with the prediction result of the BP neural network, GRNN shows splendid prediction performance for its less processing time and higher prediction accuracy. Full article

(This article belongs to the Section Electronic Sensors)

► Show Figures

Figure 1

71 pages, 15226 KiB

Open AccessEditor’s ChoiceReview

Applications of Graphene Quantum Dots in Biomedical Sensors

by Bhargav D. Mansuriya and Zeynep Altintas

Sensors 2020, 20(4), 1072; https://doi.org/10.3390/s20041072 - 16 Feb 2020

Cited by 154 | Viewed by 15735

Abstract

Due to the proliferative cancer rates, cardiovascular diseases, neurodegenerative disorders, autoimmune diseases and a plethora of infections across the globe, it is essential to introduce strategies that can rapidly and specifically detect the ultralow concentrations of relevant biomarkers, pathogens, toxins and pharmaceuticals in [...] Read more.

Due to the proliferative cancer rates, cardiovascular diseases, neurodegenerative disorders, autoimmune diseases and a plethora of infections across the globe, it is essential to introduce strategies that can rapidly and specifically detect the ultralow concentrations of relevant biomarkers, pathogens, toxins and pharmaceuticals in biological matrices. Considering these pathophysiologies, various research works have become necessary to fabricate biosensors for their early diagnosis and treatment, using nanomaterials like quantum dots (QDs). These nanomaterials effectively ameliorate the sensor performance with respect to their reproducibility, selectivity as well as sensitivity. In particular, graphene quantum dots (GQDs), which are ideally graphene fragments of nanometer size, constitute discrete features such as acting as attractive fluorophores and excellent electro-catalysts owing to their photo-stability, water-solubility, biocompatibility, non-toxicity and lucrativeness that make them favorable candidates for a wide range of novel biomedical applications. Herein, we reviewed about 300 biomedical studies reported over the last five years which entail the state of art as well as some pioneering ideas with respect to the prominent role of GQDs, especially in the development of optical, electrochemical and photoelectrochemical biosensors. Additionally, we outline the ideal properties of GQDs, their eclectic methods of synthesis, and the general principle behind several biosensing techniques. Full article

(This article belongs to the Special Issue Nanoimmunosensor)

► Show Figures

Graphical abstract

21 pages, 2853 KiB

Open AccessEditor’s ChoiceArticle

Assessment of the Potential of Wrist-Worn Wearable Sensors for Driver Drowsiness Detection

by Thomas Kundinger, Nikoletta Sofra and Andreas Riener

Sensors 2020, 20(4), 1029; https://doi.org/10.3390/s20041029 - 14 Feb 2020

Cited by 57 | Viewed by 8733

Abstract

Drowsy driving imposes a high safety risk. Current systems often use driving behavior parameters for driver drowsiness detection. The continuous driving automation reduces the availability of these parameters, therefore reducing the scope of such methods. Especially, techniques that include physiological measurements seem to [...] Read more.

Drowsy driving imposes a high safety risk. Current systems often use driving behavior parameters for driver drowsiness detection. The continuous driving automation reduces the availability of these parameters, therefore reducing the scope of such methods. Especially, techniques that include physiological measurements seem to be a promising alternative. However, in a dynamic environment such as driving, only non- or minimal intrusive methods are accepted, and vibrations from the roadbed could lead to degraded sensor technology. This work contributes to driver drowsiness detection with a machine learning approach applied solely to physiological data collected from a non-intrusive retrofittable system in the form of a wrist-worn wearable sensor. To check accuracy and feasibility, results are compared with reference data from a medical-grade ECG device. A user study with 30 participants in a high-fidelity driving simulator was conducted. Several machine learning algorithms for binary classification were applied in user-dependent and independent tests. Results provide evidence that the non-intrusive setting achieves a similar accuracy as compared to the medical-grade device, and high accuracies (>92%) could be achieved, especially in a user-dependent scenario. The proposed approach offers new possibilities for human–machine interaction in a car and especially for driver state monitoring in the field of automated driving. Full article

(This article belongs to the Special Issue Human-Machine Interaction and Sensors)

► Show Figures

Graphical abstract

48 pages, 7736 KiB

Open AccessEditor’s ChoiceReview

IoT-Based Smart Irrigation Systems: An Overview on the Recent Trends on Sensors and IoT Systems for Irrigation in Precision Agriculture

by Laura García, Lorena Parra, Jose M. Jimenez, Jaime Lloret and Pascal Lorenz

Sensors 2020, 20(4), 1042; https://doi.org/10.3390/s20041042 - 14 Feb 2020

Cited by 367 | Viewed by 51931

Abstract

Water management is paramount in countries with water scarcity. This also affects agriculture, as a large amount of water is dedicated to that use. The possible consequences of global warming lead to the consideration of creating water adaptation measures to ensure the availability [...] Read more.

Water management is paramount in countries with water scarcity. This also affects agriculture, as a large amount of water is dedicated to that use. The possible consequences of global warming lead to the consideration of creating water adaptation measures to ensure the availability of water for food production and consumption. Thus, studies aimed at saving water usage in the irrigation process have increased over the years. Typical commercial sensors for agriculture irrigation systems are very expensive, making it impossible for smaller farmers to implement this type of system. However, manufacturers are currently offering low-cost sensors that can be connected to nodes to implement affordable systems for irrigation management and agriculture monitoring. Due to the recent advances in IoT and WSN technologies that can be applied in the development of these systems, we present a survey aimed at summarizing the current state of the art regarding smart irrigation systems. We determine the parameters that are monitored in irrigation systems regarding water quantity and quality, soil characteristics and weather conditions. We provide an overview of the most utilized nodes and wireless technologies. Lastly, we will discuss the challenges and the best practices for the implementation of sensor-based irrigation systems. Full article

(This article belongs to the Special Issue Surveys of Sensor Networks and Sensor Systems Deployments)

► Show Figures

Figure 1

24 pages, 9732 KiB

Open AccessEditor’s ChoiceArticle

Evaluation of HoloLens Tracking and Depth Sensing for Indoor Mapping Applications

by Patrick Hübner, Kate Clintworth, Qingyi Liu, Martin Weinmann and Sven Wursthorn

Sensors 2020, 20(4), 1021; https://doi.org/10.3390/s20041021 - 14 Feb 2020

Cited by 93 | Viewed by 13542

Abstract

The Microsoft HoloLens is a head-worn mobile augmented reality device that is capable of mapping its direct environment in real-time as triangle meshes and localize itself within these three-dimensional meshes simultaneously. The device is equipped with a variety of sensors including four tracking [...] Read more.

The Microsoft HoloLens is a head-worn mobile augmented reality device that is capable of mapping its direct environment in real-time as triangle meshes and localize itself within these three-dimensional meshes simultaneously. The device is equipped with a variety of sensors including four tracking cameras and a time-of-flight (ToF) range camera. Sensor images and their poses estimated by the built-in tracking system can be accessed by the user. This makes the HoloLens potentially interesting as an indoor mapping device. In this paper, we introduce the different sensors of the device and evaluate the complete system in respect of the task of mapping indoor environments. The overall quality of such a system depends mainly on the quality of the depth sensor together with its associated pose derived from the tracking system. For this purpose, we first evaluate the performance of the HoloLens depth sensor and its tracking system separately. Finally, we evaluate the overall system regarding its capability for mapping multi-room environments. Full article

(This article belongs to the Special Issue Sensors for Construction Automation and Management)

► Show Figures

Figure 1

19 pages, 2612 KiB

Open AccessEditor’s ChoiceReview

Noble Metal-Assisted Surface Plasmon Resonance Immunosensors

by Jin-Ha Choi, Jin-Ho Lee, Joohyung Son and Jeong-Woo Choi

Sensors 2020, 20(4), 1003; https://doi.org/10.3390/s20041003 - 13 Feb 2020

Cited by 37 | Viewed by 6946

Abstract

For the early diagnosis of several diseases, various biomarkers have been discovered and utilized through the measurement of concentrations in body fluids such as blood, urine, and saliva. The most representative analytical method for biomarker detection is an immunosensor, which exploits the specific [...] Read more.

For the early diagnosis of several diseases, various biomarkers have been discovered and utilized through the measurement of concentrations in body fluids such as blood, urine, and saliva. The most representative analytical method for biomarker detection is an immunosensor, which exploits the specific antigen-antibody immunoreaction. Among diverse analytical methods, surface plasmon resonance (SPR)-based immunosensors are emerging as a potential detection platform due to high sensitivity, selectivity, and intuitive features. Particularly, SPR-based immunosensors could detect biomarkers without labeling of a specific detection probe, as typical immunosensors such as enzyme-linked immunosorbent assay (ELISA) use enzymes like horseradish peroxidase (HRP). In this review, SPR-based immunosensors utilizing noble metals such as Au and Ag as SPR-inducing factors for the measurement of different types of protein biomarkers, including viruses, microbes, and extracellular vesicles (EV), are briefly introduced. Full article

(This article belongs to the Special Issue Optical Immunosensors)

► Show Figures

Figure 1

21 pages, 11078 KiB

Open AccessEditor’s ChoiceArticle

Detection of Early Signs of Diabetic Retinopathy Based on Textural and Morphological Information in Fundus Images

by Adrián Colomer, Jorge Igual and Valery Naranjo

Sensors 2020, 20(4), 1005; https://doi.org/10.3390/s20041005 - 13 Feb 2020

Cited by 63 | Viewed by 6172

Abstract

Estimated blind people in the world will exceed 40 million by 2025. To develop novel algorithms based on fundus image descriptors that allow the automatic classification of retinal tissue into healthy and pathological in early stages is necessary. In this paper, we focus [...] Read more.

Estimated blind people in the world will exceed 40 million by 2025. To develop novel algorithms based on fundus image descriptors that allow the automatic classification of retinal tissue into healthy and pathological in early stages is necessary. In this paper, we focus on one of the most common pathologies in the current society: diabetic retinopathy. The proposed method avoids the necessity of lesion segmentation or candidate map generation before the classification stage. Local binary patterns and granulometric profiles are locally computed to extract texture and morphological information from retinal images. Different combinations of this information feed classification algorithms to optimally discriminate bright and dark lesions from healthy tissues. Through several experiments, the ability of the proposed system to identify diabetic retinopathy signs is validated using different public databases with a large degree of variability and without image exclusion. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medical Sensors)

► Show Figures

Figure 1

16 pages, 3288 KiB

Open AccessEditor’s ChoiceArticle

Processing of Near Real Time Land Surface Temperature and Its Application in Forecasting Forest Fire Danger Conditions

by M. Razu Ahmed, Quazi K. Hassan, Masoud Abdollahi and Anil Gupta

Sensors 2020, 20(4), 984; https://doi.org/10.3390/s20040984 - 12 Feb 2020

Cited by 14 | Viewed by 3336

Abstract

Near real time (NRT) remote sensing derived land surface temperature (Ts) data has an utmost importance in various applications of natural hazards and disasters. Space-based instrument MODIS (moderate resolution imaging spectroradiometer) acquired NRT data products of Ts are made available for the users [...] Read more.

Near real time (NRT) remote sensing derived land surface temperature (Ts) data has an utmost importance in various applications of natural hazards and disasters. Space-based instrument MODIS (moderate resolution imaging spectroradiometer) acquired NRT data products of Ts are made available for the users by LANCE (Land, Atmosphere Near real-time Capability) for Earth Observing System (EOS) of NASA (National Aeronautics and Space Administration) free of cost. Such Ts products are swath data with 5 min temporal increments of satellite acquisition, and the average latency is 60-125 min to be available in public domain. The swath data of Ts requires a specialized tool, i.e., HEG (HDF-EOS to GeoTIFF conversion tool) to process and make the data useful for further analysis. However, the file naming convention of the available swath data files in LANCE is not appropriate to download for an area of interest (AOI) to be processed by HEG. In this study, we developed a method/algorithm to overcome such issues in identifying the appropriate swath data files for an AOI that would be able to further processes supported by the HEG. In this case, we used Terra MODIS acquired NRT swath data of Ts, and further applied it to an existing framework of forecasting forest fires (as a case study) for the performance evaluation of our processed Ts. We were successful in selecting appropriate swath data files of Ts for our study area that was further processed by HEG, and finally were able to generate fire danger map in the existing forecasting model. Our proposed method/algorithm could be applied on any swath data product available in LANCE for any location in the world. Full article

(This article belongs to the Special Issue Remote Sensing and Geoinformatics in Wildfire Management)

► Show Figures

Figure 1

15 pages, 2277 KiB

Open AccessEditor’s ChoiceReview

Electrochemical Paper-Based Biosensor Devices for Rapid Detection of Biomarkers

by Manuel Gutiérrez-Capitán, Antonio Baldi and César Fernández-Sánchez

Sensors 2020, 20(4), 967; https://doi.org/10.3390/s20040967 - 11 Feb 2020

Cited by 56 | Viewed by 7555

Abstract

In healthcare, new diagnostic tools that help in the diagnosis, prognosis, and monitoring of diseases rapidly and accurately are in high demand. For in-situ measurement of disease or infection biomarkers, point-of-care devices provide a dramatic speed advantage over conventional techniques, thus aiding clinicians [...] Read more.

In healthcare, new diagnostic tools that help in the diagnosis, prognosis, and monitoring of diseases rapidly and accurately are in high demand. For in-situ measurement of disease or infection biomarkers, point-of-care devices provide a dramatic speed advantage over conventional techniques, thus aiding clinicians in decision-making. During the last decade, paper-based analytical devices, combining paper substrates and electrochemical detection components, have emerged as important point-of-need diagnostic tools. This review highlights significant works on this topic over the last five years, from 2015 to 2019. The most relevant articles published in 2018 and 2019 are examined in detail, focusing on device fabrication techniques and materials applied to the production of paper fluidic and electrochemical cell architectures as well as on the final device assembly. Two main approaches were identified, that are, on one hand, those ones where the fabrication of the electrochemical cell is done on the paper substrate, where the fluidic structures are also defined, and, on the other hand, the fabrication of those ones where the electrochemical cell and liquid-driving paper component are defined on different substrates and then heterogeneously assembled. The main limitations of the current technologies are outlined and an outlook on the current technology status and future prospects is given. Full article

(This article belongs to the Special Issue Electrochemical Nanobiosensors)

► Show Figures

Figure 1

22 pages, 2916 KiB

Open AccessEditor’s ChoiceArticle

IoT-Stream: A Lightweight Ontology for Internet of Things Data Streams and Its Use with Data Analytics and Event Detection Services

by Tarek Elsaleh, Shirin Enshaeifar, Roonak Rezvani, Sahr Thomas Acton, Valentinas Janeiko and Maria Bermudez-Edo

Sensors 2020, 20(4), 953; https://doi.org/10.3390/s20040953 - 11 Feb 2020

Cited by 61 | Viewed by 8577

Abstract

With the proliferation of sensors and IoT technologies, stream data are increasingly stored and analysed, but rarely combined, due to the heterogeneity of sources and technologies. Semantics are increasingly used to share sensory data, but not so much for annotating stream data. Semantic [...] Read more.

With the proliferation of sensors and IoT technologies, stream data are increasingly stored and analysed, but rarely combined, due to the heterogeneity of sources and technologies. Semantics are increasingly used to share sensory data, but not so much for annotating stream data. Semantic models for stream annotation are scarce, as generally, semantics are heavy to process and not ideal for Internet of Things (IoT) environments, where the data are frequently updated. We present a light model to semantically annotate streams, IoT-Stream. It takes advantage of common knowledge sharing of the semantics, but keeping the inferences and queries simple. Furthermore, we present a system architecture to demonstrate the adoption the semantic model, and provide examples of instantiation of the system for different use cases. The system architecture is based on commonly used architectures in the field of IoT, such as web services, microservices and middleware. Our system approach includes the semantic annotations that take place in the pipeline of IoT services and sensory data analytics. It includes modules needed to annotate, consume, and query data annotated with IoT-Stream. In addition to this, we present tools that could be used in conjunction to the IoT-Stream model and facilitate the use of semantics in IoT. Full article

(This article belongs to the Special Issue Selected Papers from the 3rd Global IoT Summit)

► Show Figures

Figure 1

39 pages, 3192 KiB

Open AccessEditor’s ChoiceReview

Deep Learning in Physiological Signal Data: A Survey

by Beanbonyka Rim, Nak-Jun Sung, Sedong Min and Min Hong

Sensors 2020, 20(4), 969; https://doi.org/10.3390/s20040969 - 11 Feb 2020

Cited by 129 | Viewed by 14829

Abstract

Deep Learning (DL), a successful promising approach for discriminative and generative tasks, has recently proved its high potential in 2D medical imaging analysis; however, physiological data in the form of 1D signals have yet to be beneficially exploited from this novel approach to [...] Read more.

Deep Learning (DL), a successful promising approach for discriminative and generative tasks, has recently proved its high potential in 2D medical imaging analysis; however, physiological data in the form of 1D signals have yet to be beneficially exploited from this novel approach to fulfil the desired medical tasks. Therefore, in this paper we survey the latest scientific research on deep learning in physiological signal data such as electromyogram (EMG), electrocardiogram (ECG), electroencephalogram (EEG), and electrooculogram (EOG). We found 147 papers published between January 2018 and October 2019 inclusive from various journals and publishers. The objective of this paper is to conduct a detailed study to comprehend, categorize, and compare the key parameters of the deep-learning approaches that have been used in physiological signal analysis for various medical applications. The key parameters of deep-learning approach that we review are the input data type, deep-learning task, deep-learning model, training architecture, and dataset sources. Those are the main key parameters that affect system performance. We taxonomize the research works using deep-learning method in physiological signal analysis based on: (1) physiological signal data perspective, such as data modality and medical application; and (2) deep-learning concept perspective such as training architecture and dataset sources. Full article

(This article belongs to the Special Issue Internet of Medical Things in Healthcare Applications)

► Show Figures

Figure 1

19 pages, 1741 KiB

Open AccessEditor’s ChoiceArticle

Secure Authentication and Credential Establishment in Narrowband IoT and 5G

by Jesus Sanchez-Gomez, Dan Garcia-Carrillo, Rafael Marin-Perez and Antonio F. Skarmeta

Sensors 2020, 20(3), 882; https://doi.org/10.3390/s20030882 - 7 Feb 2020

Cited by 25 | Viewed by 5081

Abstract

Security is critical in the deployment and maintenance of novel IoT and 5G networks. The process of bootstrapping is required to establish a secure data exchange between IoT devices and data-driven platforms. It entails, among other steps, authentication, authorization, and credential management. Nevertheless, [...] Read more.

Security is critical in the deployment and maintenance of novel IoT and 5G networks. The process of bootstrapping is required to establish a secure data exchange between IoT devices and data-driven platforms. It entails, among other steps, authentication, authorization, and credential management. Nevertheless, there are few efforts dedicated to providing service access authentication in the area of constrained IoT devices connected to recent wireless networks such as narrowband IoT (NB-IoT) and 5G. Therefore, this paper presents the adaptation of bootstrapping protocols to be compliant with the 3GPP specifications in order to enable the 5G feature of secondary authentication for constrained IoT devices. To allow the secondary authentication and key establishment in NB-IoT and 4G/5G environments, we have adapted two Extensible Authentication Protocol (EAP) lower layers, i.e., PANATIKI and LO-CoAP-EAP. In fact, this approach presents the evaluation of both aforementioned EAP lower layers, showing the contrast between a current EAP lower layer standard, i.e., PANA, and one specifically designed with the constraints of IoT, thus providing high flexibility and scalability in the bootstrapping process in 5G networks. The proposed solution is evaluated to prove its efficiency and feasibility, being one of the first efforts to support secure service authentication and key establishment for constrained IoT devices in 5G environments. Full article

(This article belongs to the Special Issue Selected Papers from the 3rd Global IoT Summit)

► Show Figures

Figure 1

11 pages, 3461 KiB

Open AccessEditor’s ChoiceArticle

Modelling Remote Sensing Reflectance to Detect Dispersed Oil at Sea

by Emilia Baszanowska, Zbigniew Otremba and Jacek Piskozub

Sensors 2020, 20(3), 863; https://doi.org/10.3390/s20030863 - 6 Feb 2020

Cited by 16 | Viewed by 2717

Abstract

This paper presents a model of upwelling radiation above the seawater surface in the event of a threat of dispersed oil. The Monte Carlo method was used to simulate a large number of solar photons in the water, eventually obtaining values of remote [...] Read more.

This paper presents a model of upwelling radiation above the seawater surface in the event of a threat of dispersed oil. The Monte Carlo method was used to simulate a large number of solar photons in the water, eventually obtaining values of remote sensing reflectance (R_rs). Analyses were performed for the optical properties of seawater characteristic for the Gulf of Gdańsk (southern Baltic Sea). The case of seawater contaminated by dispersed oil at a concentration of 10 ppm was also discussed for different wind speeds. Two types of oils with extremely different optical properties (refraction and absorption coefficients) were taken into account for consideration. The optical properties (absorption and scattering coefficients and angular light scattering distribution) of the oil-in-water dispersion system were determined using the Mie theory. The spectral index for oil detection in seawater for different wind conditions was determined based on the results obtained for reflectance at selected wavelengths in the range 412–676 nm. The determined spectral index for seawater free of oil achieves higher values for seawater contaminated by oil. The analysis of the values of the spectral indices calculated for 28 combinations of wavelengths was used to identify the most universal spectral index of R_rs for 555 nm/440 nm for dispersed oil detection using any optical parameters. Full article

(This article belongs to the Special Issue Remote Sensing of Ocean Colour: Theory and Applications)

► Show Figures

Figure 1

43 pages, 2321 KiB

Open AccessFeature PaperEditor’s ChoiceArticle

5G support for Industrial IoT Applications— Challenges, Solutions, and Research gaps

by Pal Varga, Jozsef Peto, Attila Franko, David Balla, David Haja, Ferenc Janky, Gabor Soos, Daniel Ficzere, Markosz Maliosz and Laszlo Toka

Sensors 2020, 20(3), 828; https://doi.org/10.3390/s20030828 - 4 Feb 2020

Cited by 173 | Viewed by 25942

Abstract

Industrial IoT has special communication requirements, including high reliability, low latency, flexibility, and security. These are instinctively provided by the 5G mobile technology, making it a successful candidate for supporting Industrial IoT (IIoT) scenarios. The aim of this paper is to identify current [...] Read more.

Industrial IoT has special communication requirements, including high reliability, low latency, flexibility, and security. These are instinctively provided by the 5G mobile technology, making it a successful candidate for supporting Industrial IoT (IIoT) scenarios. The aim of this paper is to identify current research challenges and solutions in relation to 5G-enabled Industrial IoT, based on the initial requirements and promises of both domains. The methodology of the paper follows the steps of surveying state-of-the art, comparing results to identify further challenges, and drawing conclusions as lessons learned for each research domain. These areas include IIoT applications and their requirements; mobile edge cloud; back-end performance tuning; network function virtualization; and security, blockchains for IIoT, Artificial Intelligence support for 5G, and private campus networks. Beside surveying the current challenges and solutions, the paper aims to provide meaningful comparisons for each of these areas (in relation to 5G-enabled IIoT) to draw conclusions on current research gaps. Full article

(This article belongs to the Section Internet of Things)

► Show Figures

Figure 1

16 pages, 12224 KiB

Open AccessEditor’s ChoiceArticle

Accuracy of Trajectory Tracking Based on Nonlinear Guidance Logic for Hydrographic Unmanned Surface Vessels

by Andrzej Stateczny, Pawel Burdziakowski, Klaudia Najdecka and Beata Domagalska-Stateczna

Sensors 2020, 20(3), 832; https://doi.org/10.3390/s20030832 - 4 Feb 2020

Cited by 34 | Viewed by 4022

Abstract

A new trend in recent years for hydrographic measurement in water bodies is the use of unmanned surface vehicles (USVs). In the process of navigation by USVs, it is particularly important to control position precisely on the measuring profile. Precise navigation with respect [...] Read more.

A new trend in recent years for hydrographic measurement in water bodies is the use of unmanned surface vehicles (USVs). In the process of navigation by USVs, it is particularly important to control position precisely on the measuring profile. Precise navigation with respect to the measuring profile avoids registration of redundant data and thus saves time and survey costs. This article addresses the issue of precise navigation of the hydrographic unit on the measuring profile with the use of a nonlinear adaptive autopilot. The results of experiments concerning hydrographic measurements performed in real conditions using an USV are discussed. Full article

(This article belongs to the Special Issue Remote Sensing in Vessel Detection and Navigation)

► Show Figures

Figure 1

25 pages, 10331 KiB

Open AccessEditor’s ChoiceArticle

Evaluating the Vulnerability of Several Geodetic GNSS Receivers under Chirp Signal L1/E1 Jamming

by Matej Bažec, Franc Dimc and Polona Pavlovčič-Prešeren

Sensors 2020, 20(3), 814; https://doi.org/10.3390/s20030814 - 3 Feb 2020

Cited by 16 | Viewed by 4601

Abstract

Understanding the factors that might intentionally influence the reception of global navigation satellite system (GNSS) signals can be a challenging topic today. The focus of this research is to evaluate the vulnerability of geodetic GNSS receivers under the use of a low-cost L1/E1 [...] Read more.

Understanding the factors that might intentionally influence the reception of global navigation satellite system (GNSS) signals can be a challenging topic today. The focus of this research is to evaluate the vulnerability of geodetic GNSS receivers under the use of a low-cost L1/E1 frequency jammer. A suitable area for testing was established in Slovenia. Nine receivers from different manufacturers were under consideration in this study. While positioning, intentional 3-minute jammings were performed by a jammer that was located statically at different distances from receivers. Furthermore, kinematic disturbances were performed using a jammer placed in a vehicle that passed the testing area at various speeds. An analysis of different scenarios indicated that despite the use of an L1/E1 jammer, the GLONASS (Russian: Globalnaya Navigatsionnaya Sputnikovaya Sistema) and Galileo signals were also affected, either due to the increased carrier-to-noise-ratio (C/N₀) or, in the worst cases, by a loss-of-signal. A jammer could substantially affect the position, either with a lack of any practical solution or even with a wrong position. Maximal errors in the carrier-phase positions, which should be considered a concern for geodesy, differed by a few metres from the exact solution. The factor that completely disabled the signal reception was the proximity of a jammer, regardless of its static or kinematic mode. Full article

(This article belongs to the Special Issue GNSS Data Processing and Navigation)

► Show Figures

Figure 1

18 pages, 1302 KiB

Open AccessEditor’s ChoiceArticle

Detection and Mitigation of DoS and DDoS Attacks in IoT-Based Stateful SDN: An Experimental Approach

by Jesús Galeano-Brajones, Javier Carmona-Murillo, Juan F. Valenzuela-Valdés and Francisco Luna-Valero

Sensors 2020, 20(3), 816; https://doi.org/10.3390/s20030816 - 3 Feb 2020

Cited by 105 | Viewed by 13117

Abstract

The expected advent of the Internet of Things (IoT) has triggered a large demand of embedded devices, which envisions the autonomous interaction of sensors and actuators while offering all sort of smart services. However, these IoT devices are limited in computation, storage, and [...] Read more.

The expected advent of the Internet of Things (IoT) has triggered a large demand of embedded devices, which envisions the autonomous interaction of sensors and actuators while offering all sort of smart services. However, these IoT devices are limited in computation, storage, and network capacity, which makes them easy to hack and compromise. To achieve secure development of IoT, it is necessary to engineer scalable security solutions optimized for the IoT ecosystem. To this end, Software Defined Networking (SDN) is a promising paradigm that serves as a pillar in the fifth generation of mobile systems (5G) that could help to detect and mitigate Denial of Service (DoS) and Distributed DoS (DDoS) threats. In this work, we propose to experimentally evaluate an entropy-based solution to detect and mitigate DoS and DDoS attacks in IoT scenarios using a stateful SDN data plane. The obtained results demonstrate for the first time the effectiveness of this technique targeting real IoT data traffic. Full article

(This article belongs to the Special Issue Monitoring of Security Properties in IoT and Emerging Technologies)

► Show Figures

Figure 1

18 pages, 817 KiB

Open AccessEditor’s ChoiceArticle

IoT Based Architecture for Model Predictive Control of HVAC Systems in Smart Buildings

by Raffaele Carli, Graziana Cavone, Sarah Ben Othman and Mariagrazia Dotoli

Sensors 2020, 20(3), 781; https://doi.org/10.3390/s20030781 - 31 Jan 2020

Cited by 85 | Viewed by 14411

Abstract

The efficient management of Heating Ventilation and Air Conditioning (HVAC) systems in smart buildings is one of the main applications of the Internet of Things (IoT) paradigm. In this paper we propose an IoT based architecture for the implementation of Model Predictive Control [...] Read more.

The efficient management of Heating Ventilation and Air Conditioning (HVAC) systems in smart buildings is one of the main applications of the Internet of Things (IoT) paradigm. In this paper we propose an IoT based architecture for the implementation of Model Predictive Control (MPC) of HVAC systems in real environments. The considered MPC algorithm optimizes on line, in a closed-loop control fashion, both the indoor thermal comfort and the related energy consumption for a single zone environment. Thanks to the proposed IoT based architecture, the sensing, control, and actuating subsystems are all connected to the Internet, and a remote interface with the HVAC control system is guaranteed to end-users. In particular, sensors and actuators communicate with a remote database server and a control unit, which provides the control actions to be actuated in the HVAC system; users can set remotely the control mode and related set-points of the system; while comfort and environmental indices are transferred via the Internet and displayed on the end-users’ interface. The proposed IoT based control architecture is implemented and tested in a campus building at the Polytechnic of Bari (Italy) in a proof of concept perspective. The effectiveness of the proposed control algorithm is assessed in the real environment evaluating both the thermal comfort results and the energy savings with respect to a classical thermostat regulation approach. Full article

(This article belongs to the Special Issue Sensor Based Smart Grid in Internet of Things Era)

► Show Figures

Figure 1

24 pages, 1716 KiB

Open AccessEditor’s ChoiceArticle

Detection of Atrial Fibrillation Episodes in Long-Term Heart Rhythm Signals Using a Support Vector Machine

by Robert Czabanski, Krzysztof Horoba, Janusz Wrobel, Adam Matonia, Radek Martinek, Tomasz Kupka, Michal Jezewski, Radana Kahankova, Janusz Jezewski and Jacek M. Leski

Sensors 2020, 20(3), 765; https://doi.org/10.3390/s20030765 - 30 Jan 2020

Cited by 48 | Viewed by 10557

Abstract

Atrial fibrillation (AF) is a serious heart arrhythmia leading to a significant increase of the risk for occurrence of ischemic stroke. Clinically, the AF episode is recognized in an electrocardiogram. However, detection of asymptomatic AF, which requires a long-term monitoring, is more efficient [...] Read more.

Atrial fibrillation (AF) is a serious heart arrhythmia leading to a significant increase of the risk for occurrence of ischemic stroke. Clinically, the AF episode is recognized in an electrocardiogram. However, detection of asymptomatic AF, which requires a long-term monitoring, is more efficient when based on irregularity of beat-to-beat intervals estimated by the heart rate (HR) features. Automated classification of heartbeats into AF and non-AF by means of the Lagrangian Support Vector Machine has been proposed. The classifier input vector consisted of sixteen features, including four coefficients very sensitive to beat-to-beat heart changes, taken from the fetal heart rate analysis in perinatal medicine. Effectiveness of the proposed classifier has been verified on the MIT-BIH Atrial Fibrillation Database. Designing of the LSVM classifier using very large number of feature vectors requires extreme computational efforts. Therefore, an original approach has been proposed to determine a training set of the smallest possible size that still would guarantee a high quality of AF detection. It enables to obtain satisfactory results using only 1.39% of all heartbeats as the training data. Post-processing stage based on aggregation of classified heartbeats into AF episodes has been applied to provide more reliable information on patient risk. Results obtained during the testing phase showed the sensitivity of 98.94%, positive predictive value of 98.39%, and classification accuracy of 98.86%. Full article

(This article belongs to the Special Issue Advanced Sensors and Signal Processing of Sensor Data: Recent Advances and Applications)

► Show Figures

Figure 1

39 pages, 3130 KiB

Open AccessEditor’s ChoiceReview

Sensors to Increase the Security of Underwater Communication Cables: A Review of Underwater Monitoring Sensors

by Dimitrios Eleftherakis and Raul Vicen-Bueno

Sensors 2020, 20(3), 737; https://doi.org/10.3390/s20030737 - 29 Jan 2020

Cited by 26 | Viewed by 12560

Abstract

Underwater communication cables transport large amounts of sensitive information between countries. This fact converts these cables into a critical infrastructure that must be protected. Monitoring the underwater cable environment is rare and any intervention is usually driven by cable faults. In the last [...] Read more.

Underwater communication cables transport large amounts of sensitive information between countries. This fact converts these cables into a critical infrastructure that must be protected. Monitoring the underwater cable environment is rare and any intervention is usually driven by cable faults. In the last few years, several reports raised issues about possible future malicious attacks on such cables. The main objective of this operational research and analysis (ORA) paper is to present an overview of different commercial and already available marine sensor technologies (acoustic, optic, magnetic and oceanographic) that could be used for autonomous monitoring of the underwater cable environment. These sensors could be mounted on different autonomous platforms, such as unmanned surface vehicles (USVs) or autonomous underwater vehicles (AUVs). This paper analyses a multi-threat sabotage scenario where surveying a transatlantic cable of 13,000 km, (reaching water depths up to 4000 m) is necessary. The potential underwater threats identified for such a scenario are: divers, anchors, fishing trawls, submarines, remotely operated vehicles (ROVs) and AUVs. The paper discusses the capabilities of the identified sensors to detect such identified threats for the scenario under study. It also presents ideas on the construction of periodic and permanent surveillance networks. Research study and results are focused on providing useful information to decision-makers in charge of designing surveillance capabilities to secure underwater communication cables. Full article

(This article belongs to the Special Issue Sensor Applications on Marine Recognition)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Editor’s Choice Articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI