sensors-logo

Journal Browser

Journal Browser

Sensor Data Fusion Based on Deep Learning for Computer Vision and Medical Applications

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Intelligent Sensors".

Deadline for manuscript submissions: closed (25 May 2022) | Viewed by 43609

Special Issue Editors


E-Mail Website
Guest Editor
Department of Intelligent Mechatronics Engineering, Sejong University, Seoul 05006, Republic of Korea
Interests: computer vision; human–computer interaction; biometrics; medical image processing and understanding; artificial intelligence; deep learning
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of Korea
Interests: deep learning; semantic segmentation; image classification; medical image analysis; computer-aided diagnosis (CAD); biometrics (finger vein and iris segmentation)
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Computer Science, University of Warwick, Coventry CV4 7AL, UK
Interests: medical image analysis; weakly supervised learning; reinforcement learning; computer aided diagnosis (CAD)
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Computer Science and Engineering, University of New South Wales, Sydney, Australia
Interests: image segmentation; image classification; medical image analysis; biometrics (fingerprints and iris segmentation); deep learning
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Computer Science and Engineering, University of New South Wales, Sydney, Australia
Interests: database usability; advanced data analytics; graph data management
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

It is our pleasure to invite submissions to this Special Issue on “Sensor Data Fusion Based on Deep Learning for Computer Vision and Medical Applications”.

Recent advancements have led to the extensive use of various sensors, such as visible light, near-infrared (NIR), thermal camera sensors, fundus cameras, H&E stains, endoscopy, OCT cameras, and magnetic resonance imaging sensors, in a variety of applications in computer vision, biometrics, video surveillance, image compression and image restoration, medical image analysis, computer-aided diagnosis, etc. Research related to sensor and data fusion, information processing and merging, and fusion architecture for the cooperative perception and risk assessment is needed for computer vision and medical applications. Indeed, prior to ensuring a high level of accuracy in the deployment of computer vision and deep learning applications, it is necessary to guarantee high-quality and real-time perception mechanisms. While computer vision technology has matured, its performance is still affected by various environmental factors, and recent approaches have been attempted to fuse data from various sensors based on deep learning techniques to guarantee higher accuracy. The objective of this Special Issue is to invite high-quality, state-of-the-art research papers that deal with challenging issues in deep-learning-based computer vision and medical applications. We solicit original papers of unpublished and completed research that are not currently under review by any other conference/magazine/journal. Topics of interest include, but are not limited to, the following:

  • Computer vision by various camera sensors;
  • Biometrics and spoof detection by various camera sensors;
  • Image classification using various, NIR, VL camera sensors;
  • Detection and localization by deep learning by various cameras;
  • Deep-learning-based object segmentation/instance segmentation by media sensors;
  • Medical image processing and analysis by various camera sensors;
  • Deep learning by various camera sensors;
  • Multiple-approach fusion that combines deep learning techniques and conventional methods on images obtained by various camera sensors.

Dr. Rizwan Ali Naqvi
Dr. Muhammad Arsalan
Dr. Talha Qaiser
Dr. Tariq Mahmood Khan
Dr. Imran Razzak
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Sensor data fusion
  • Image processing
  • Deep feature fusion
  • Image/video-based classification
  • Semantic segmentation/instance segmentation
  • Medical image analysis
  • Computer-aided diagnosis
  • Computer vision
  • Fusion for biometrics
  • Fusion for medical applications
  • Fusion for semantic information
  • Smart sensors

Published Papers (11 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Editorial

Jump to: Research

4 pages, 174 KiB  
Editorial
Sensor Data Fusion Based on Deep Learning for Computer Vision Applications and Medical Applications
by Rizwan Ali Naqvi, Muhammad Arsalan, Talha Qaiser, Tariq Mahmood Khan and Imran Razzak
Sensors 2022, 22(20), 8058; https://doi.org/10.3390/s22208058 - 21 Oct 2022
Cited by 4 | Viewed by 1685
Abstract
Sensor fusion is the process of merging data from many sources, such as radar, lidar and camera sensors, to provide less uncertain information compared to the information collected from single source [...] Full article

Research

Jump to: Editorial

16 pages, 2466 KiB  
Article
Performance Analysis of State-of-the-Art CNN Architectures for LUNA16
by Iftikhar Naseer, Sheeraz Akram, Tehreem Masood, Arfan Jaffar, Muhammad Adnan Khan and Amir Mosavi
Sensors 2022, 22(12), 4426; https://doi.org/10.3390/s22124426 - 11 Jun 2022
Cited by 34 | Viewed by 4335
Abstract
The convolutional neural network (CNN) has become a powerful tool in machine learning (ML) that is used to solve complex problems such as image recognition, natural language processing, and video analysis. Notably, the idea of exploring convolutional neural network architecture has gained substantial [...] Read more.
The convolutional neural network (CNN) has become a powerful tool in machine learning (ML) that is used to solve complex problems such as image recognition, natural language processing, and video analysis. Notably, the idea of exploring convolutional neural network architecture has gained substantial attention as well as popularity. This study focuses on the intrinsic various CNN architectures: LeNet, AlexNet, VGG16, ResNet-50, and Inception-V1, which have been scrutinized and compared with each other for the detection of lung cancer using publicly available LUNA16 datasets. Furthermore, multiple performance optimizers: root mean square propagation (RMSProp), adaptive moment estimation (Adam), and stochastic gradient descent (SGD), were applied for this comparative study. The performances of the three CNN architectures were measured for accuracy, specificity, sensitivity, positive predictive value, false omission rate, negative predictive value, and F1 score. The experimental results showed that the CNN AlexNet architecture with the SGD optimizer achieved the highest validation accuracy for CT lung cancer with an accuracy of 97.42%, misclassification rate of 2.58%, 97.58% sensitivity, 97.25% specificity, 97.58% positive predictive value, 97.25% negative predictive value, false omission rate of 2.75%, and F1 score of 97.58%. AlexNet with the SGD optimizer was the best and outperformed compared to the other state-of-the-art CNN architectures. Full article
Show Figures

Figure 1

14 pages, 2013 KiB  
Article
A Long Short-Term Memory Biomarker-Based Prediction Framework for Alzheimer’s Disease
by Anza Aqeel, Ali Hassan, Muhammad Attique Khan, Saad Rehman, Usman Tariq, Seifedine Kadry, Arnab Majumdar and Orawit Thinnukool
Sensors 2022, 22(4), 1475; https://doi.org/10.3390/s22041475 - 14 Feb 2022
Cited by 22 | Viewed by 2924
Abstract
The early prediction of Alzheimer’s disease (AD) can be vital for the endurance of patients and establishes as an accommodating and facilitative factor for specialists. The proposed work presents a robotized predictive structure, dependent on machine learning (ML) methods for the forecast of [...] Read more.
The early prediction of Alzheimer’s disease (AD) can be vital for the endurance of patients and establishes as an accommodating and facilitative factor for specialists. The proposed work presents a robotized predictive structure, dependent on machine learning (ML) methods for the forecast of AD. Neuropsychological measures (NM) and magnetic resonance imaging (MRI) biomarkers are deduced and passed on to a recurrent neural network (RNN). In the RNN, we have used long short-term memory (LSTM), and the proposed model will predict the biomarkers (feature vectors) of patients after 6, 12, 21 18, 24, and 36 months. These predicted biomarkers will go through fully connected neural network layers. The NN layers will then predict whether these RNN-predicted biomarkers belong to an AD patient or a patient with a mild cognitive impairment (MCI). The developed methodology has been tried on an openly available informational dataset (ADNI) and accomplished an accuracy of 88.24%, which is superior to the next-best available algorithms. Full article
Show Figures

Figure 1

19 pages, 12434 KiB  
Article
3DMesh-GAR: 3D Human Body Mesh-Based Method for Group Activity Recognition
by Muhammad Saqlain, Donguk Kim, Junuk Cha, Changhwa Lee, Seongyeong Lee and Seungryul Baek
Sensors 2022, 22(4), 1464; https://doi.org/10.3390/s22041464 - 14 Feb 2022
Cited by 4 | Viewed by 3710
Abstract
Group activity recognition is a prime research topic in video understanding and has many practical applications, such as crowd behavior monitoring, video surveillance, etc. To understand the multi-person/group action, the model should not only identify the individual person’s action in the context but [...] Read more.
Group activity recognition is a prime research topic in video understanding and has many practical applications, such as crowd behavior monitoring, video surveillance, etc. To understand the multi-person/group action, the model should not only identify the individual person’s action in the context but also describe their collective activity. A lot of previous works adopt skeleton-based approaches with graph convolutional networks for group activity recognition. However, these approaches are subject to limitation in scalability, robustness, and interoperability. In this paper, we propose 3DMesh-GAR, a novel approach to 3D human body Mesh-based Group Activity Recognition, which relies on a body center heatmap, camera map, and mesh parameter map instead of the complex and noisy 3D skeleton of each person of the input frames. We adopt a 3D mesh creation method, which is conceptually simple, single-stage, and bounding box free, and is able to handle highly occluded and multi-person scenes without any additional computational cost. We implement 3DMesh-GAR on a standard group activity dataset: the Collective Activity Dataset, and achieve state-of-the-art performance for group activity recognition. Full article
Show Figures

Figure 1

22 pages, 6935 KiB  
Article
Multiclass Skin Lesion Classification Using Hybrid Deep Features Selection and Extreme Learning Machine
by Farhat Afza, Muhammad Sharif, Muhammad Attique Khan, Usman Tariq, Hwan-Seung Yong and Jaehyuk Cha
Sensors 2022, 22(3), 799; https://doi.org/10.3390/s22030799 - 21 Jan 2022
Cited by 86 | Viewed by 5707
Abstract
The variation in skin textures and injuries, as well as the detection and classification of skin cancer, is a difficult task. Manually detecting skin lesions from dermoscopy images is a difficult and time-consuming process. Recent advancements in the domains of the internet of [...] Read more.
The variation in skin textures and injuries, as well as the detection and classification of skin cancer, is a difficult task. Manually detecting skin lesions from dermoscopy images is a difficult and time-consuming process. Recent advancements in the domains of the internet of things (IoT) and artificial intelligence for medical applications demonstrated improvements in both accuracy and computational time. In this paper, a new method for multiclass skin lesion classification using best deep learning feature fusion and an extreme learning machine is proposed. The proposed method includes five primary steps: image acquisition and contrast enhancement; deep learning feature extraction using transfer learning; best feature selection using hybrid whale optimization and entropy-mutual information (EMI) approach; fusion of selected features using a modified canonical correlation based approach; and, finally, extreme learning machine based classification. The feature selection step improves the system’s computational efficiency and accuracy. The experiment is carried out on two publicly available datasets, HAM10000 and ISIC2018. The achieved accuracy on both datasets is 93.40 and 94.36 percent. When compared to state-of-the-art (SOTA) techniques, the proposed method’s accuracy is improved. Furthermore, the proposed method is computationally efficient. Full article
Show Figures

Figure 1

14 pages, 2840 KiB  
Article
Deep Learning Approach for Automatic Microaneurysms Detection
by Muhammad Mateen, Tauqeer Safdar Malik, Shaukat Hayat, Musab Hameed, Song Sun and Junhao Wen
Sensors 2022, 22(2), 542; https://doi.org/10.3390/s22020542 - 11 Jan 2022
Cited by 13 | Viewed by 4818
Abstract
In diabetic retinopathy (DR), the early signs that may lead the eyesight towards complete vision loss are considered as microaneurysms (MAs). The shape of these MAs is almost circular, and they have a darkish color and are tiny in size, which means they [...] Read more.
In diabetic retinopathy (DR), the early signs that may lead the eyesight towards complete vision loss are considered as microaneurysms (MAs). The shape of these MAs is almost circular, and they have a darkish color and are tiny in size, which means they may be missed by manual analysis of ophthalmologists. In this case, accurate early detection of microaneurysms is helpful to cure DR before non-reversible blindness. In the proposed method, early detection of MAs is performed using a hybrid feature embedding approach of pre-trained CNN models, named as VGG-19 and Inception-v3. The performance of the proposed approach was evaluated using publicly available datasets, namely “E-Ophtha” and “DIARETDB1”, and achieved 96% and 94% classification accuracy, respectively. Furthermore, the developed approach outperformed the state-of-the-art approaches in terms of sensitivity and specificity for microaneurysms detection. Full article
Show Figures

Figure 1

14 pages, 890 KiB  
Article
Evaluating the Dynamics of Bluetooth Low Energy Based COVID-19 Risk Estimation for Educational Institutes
by Abdulah Jeza Aljohani, Junaid Shuja, Waleed Alasmary and Abdulaziz Alashaikh
Sensors 2021, 21(19), 6667; https://doi.org/10.3390/s21196667 - 7 Oct 2021
Cited by 10 | Viewed by 2460
Abstract
COVID-19 tracing applications have been launched in several countries to track and control the spread of viruses. Such applications utilize Bluetooth Low Energy (BLE) transmissions, which are short range and can be used to determine infected and susceptible persons near an infected person. [...] Read more.
COVID-19 tracing applications have been launched in several countries to track and control the spread of viruses. Such applications utilize Bluetooth Low Energy (BLE) transmissions, which are short range and can be used to determine infected and susceptible persons near an infected person. The COVID-19 risk estimation depends on an epidemic model for the virus behavior and Machine Learning (ML) model to classify the risk based on time series distance of the nodes that may be infected. The BLE technology enabled smartphones continuously transmit beacons and the distance is inferred from the received signal strength indicators (RSSI). The educational activities have shifted to online teaching modes due to the contagious nature of COVID-19. The government policy makers decide on education mode (online, hybrid, or physical) with little technological insight on actual risk estimates. In this study, we analyze BLE technology to debate the COVID-19 risks in university block and indoor class environments. We utilize a sigmoid based epidemic model with varying thresholds of distance to label contact data with high risk or low risk based on features such as contact duration. Further, we train multiple ML classifiers to classify a person into high risk or low risk based on labeled data of RSSI and distance. We analyze the accuracy of the ML classifiers in terms of F-score, receiver operating characteristic (ROC) curve, and confusion matrix. Lastly, we debate future research directions and limitations of this study. We complement the study with open source code so that it can be validated and further investigated. Full article
Show Figures

Figure 1

21 pages, 12437 KiB  
Article
Development of Coral Investigation System Based on Semantic Segmentation of Single-Channel Images
by Hong Song, Syed Raza Mehdi, Yangfan Zhang, Yichun Shentu, Qixin Wan, Wenxin Wang, Kazim Raza and Hui Huang
Sensors 2021, 21(5), 1848; https://doi.org/10.3390/s21051848 - 6 Mar 2021
Cited by 11 | Viewed by 3275
Abstract
Among aquatic biota, corals provide shelter with sufficient nutrition to a wide variety of underwater life. However, a severe decline in the coral resources can be noted in the last decades due to global environmental changes causing marine pollution. Hence, it is of [...] Read more.
Among aquatic biota, corals provide shelter with sufficient nutrition to a wide variety of underwater life. However, a severe decline in the coral resources can be noted in the last decades due to global environmental changes causing marine pollution. Hence, it is of paramount importance to develop and deploy swift coral monitoring system to alleviate the destruction of corals. Performing semantic segmentation on underwater images is one of the most efficient methods for automatic investigation of corals. Firstly, to design a coral investigation system, RGB and spectral images of various types of corals in natural and artificial aquatic sites are collected. Based on single-channel images, a convolutional neural network (CNN) model, named DeeperLabC, is employed for the semantic segmentation of corals, which is a concise and modified deeperlab model with encoder-decoder architecture. Using ResNet34 as a skeleton network, the proposed model extracts coral features in the images and performs semantic segmentation. DeeperLabC achieved state-of-the-art coral segmentation with an overall mean intersection over union (IoU) value of 93.90%, and maximum F1-score of 97.10% which surpassed other existing benchmark neural networks for semantic segmentation. The class activation map (CAM) module also proved the excellent performance of the DeeperLabC model in binary classification among coral and non-coral bodies. Full article
Show Figures

Figure 1

25 pages, 4818 KiB  
Article
Human Sentiment and Activity Recognition in Disaster Situations Using Social Media Images Based on Deep Learning
by Amin Muhammad Sadiq, Huynsik Ahn and Young Bok Choi
Sensors 2020, 20(24), 7115; https://doi.org/10.3390/s20247115 - 11 Dec 2020
Cited by 12 | Viewed by 3244
Abstract
A rapidly increasing growth of social networks and the propensity of users to communicate their physical activities, thoughts, expressions, and viewpoints in text, visual, and audio material have opened up new possibilities and opportunities in sentiment and activity analysis. Although sentiment and activity [...] Read more.
A rapidly increasing growth of social networks and the propensity of users to communicate their physical activities, thoughts, expressions, and viewpoints in text, visual, and audio material have opened up new possibilities and opportunities in sentiment and activity analysis. Although sentiment and activity analysis of text streams has been extensively studied in the literature, it is relatively recent yet challenging to evaluate sentiment and physical activities together from visuals such as photographs and videos. This paper emphasizes human sentiment in a socially crucial field, namely social media disaster/catastrophe analysis, with associated physical activity analysis. We suggest multi-tagging sentiment and associated activity analyzer fused with a a deep human count tracker, a pragmatic technique for multiple object tracking, and count in occluded circumstances with a reduced number of identity switches in disaster-related videos and images. A crowd-sourcing study has been conducted to analyze and annotate human activity and sentiments towards natural disasters and related images in social networks. The crowdsourcing study outcome into a large-scale benchmark dataset with three annotations sets each resolves distinct tasks. The presented analysis and dataset will anchor a baseline for future research in the domain. We believe that the proposed system will contribute to more viable communities by benefiting different stakeholders, such as news broadcasters, emergency relief organizations, and the public in general. Full article
Show Figures

Figure 1

29 pages, 1112 KiB  
Article
Deep Feature Extraction and Classification of Android Malware Images
by Jaiteg Singh, Deepak Thakur, Farman Ali, Tanya Gera and Kyung Sup Kwak
Sensors 2020, 20(24), 7013; https://doi.org/10.3390/s20247013 - 8 Dec 2020
Cited by 68 | Viewed by 4766
Abstract
The Android operating system has gained popularity and evolved rapidly since the previous decade. Traditional approaches such as static and dynamic malware identification techniques require a lot of human intervention and resources to design the malware classification model. The real challenge lies with [...] Read more.
The Android operating system has gained popularity and evolved rapidly since the previous decade. Traditional approaches such as static and dynamic malware identification techniques require a lot of human intervention and resources to design the malware classification model. The real challenge lies with the fact that inspecting all files of the application structure leads to high processing time, more storage, and manual effort. To solve these problems, optimization algorithms and deep learning has been recently tested for mitigating malware attacks. This manuscript proposes Summing of neurAl aRchitecture and VisualizatiOn Technology for Android Malware identification (SARVOTAM). The system converts the malware non-intuitive features into fingerprint images to extract the quality information. A fine-tuned Convolutional Neural Network (CNN) is used to automatically extract rich features from visualized malware thus eliminating the feature engineering and domain expert cost. The experiments were done using the DREBIN dataset. A total of fifteen different combinations of the Android malware image sections were used to identify and classify Android malware. The softmax layer of CNN was substituted with machine learning algorithms like K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Random Forest (RF) to analyze the grayscale malware images. It is observed that CNN-SVM model outperformed original CNN as well as CNN-KNN, and CNN-RF. The classification results showed that our method is able to achieve an accuracy of 92.59% using Android certificates and manifest malware images. This paper reveals the lightweight solution and much precise option for malware identification. Full article
Show Figures

Figure 1

23 pages, 5537 KiB  
Article
Recognition of Pashto Handwritten Characters Based on Deep Learning
by Muhammad Sadiq Amin, Siddiqui Muhammad Yasir and Hyunsik Ahn
Sensors 2020, 20(20), 5884; https://doi.org/10.3390/s20205884 - 17 Oct 2020
Cited by 17 | Viewed by 3991
Abstract
Handwritten character recognition is increasingly important in a variety of automation fields, for example, authentication of bank signatures, identification of ZIP codes on letter addresses, and forensic evidence. Despite improved object recognition technologies, Pashto’s hand-written character recognition (PHCR) remains largely unsolved due to [...] Read more.
Handwritten character recognition is increasingly important in a variety of automation fields, for example, authentication of bank signatures, identification of ZIP codes on letter addresses, and forensic evidence. Despite improved object recognition technologies, Pashto’s hand-written character recognition (PHCR) remains largely unsolved due to the presence of many enigmatic hand-written characters, enormously cursive Pashto characters, and lack of research attention. We propose a convolutional neural network (CNN) model for recognition of Pashto hand-written characters for the first time in an unrestricted environment. Firstly, a novel Pashto handwritten character data set, “Poha”, for 44 characters is constructed. For preprocessing, deep fusion image processing techniques and noise reduction for text optimization are applied. A CNN model optimized in the number of convolutional layers and their parameters outperformed common deep models in terms of accuracy. Moreover, a set of benchmark popular CNN models applied to Poha is evaluated and compared with the proposed model. The obtained experimental results show that the proposed model is superior to other models with test accuracy of 99.64 percent for PHCR. The results indicate that our model may be a strong candidate for handwritten character recognition and automated PHCR applications. Full article
Show Figures

Figure 1

Back to TopTop