Few studies have evaluated the effect of a secondary motor task on the standing posture based on nonlinear analysis. However, it is helpful to extract information related to the complexity, stability, and adaptability to the environment of the human postural system. This study aimed to analyze the effect of two motor tasks with different difficulty levels in motor performance complexity on the static standing posture in healthy young adults. Thirty-five healthy participants (23.08 ± 3.92 years) performed a postural single task (ST: keep a quiet standing posture) and two motor dual tasks (DT). i.e., mot-DT(A)—perform the ST while performing simultaneously an easy motor task (taking a smartphone out of a bag, bringing it to the ear, and putting it back in the bag)—and mot-DT(T)—perform the ST while performing a concurrent difficult motor task (typing on the smartphone keyboard). The approximate entropy (ApEn), Lyapunov exponent (LyE), correlation dimension (CoDim), and fractal dimension (detrending fluctuation analysis, DFA) for the mediolateral (ML) and anterior-posterior (AP) center-of-pressure (CoP) displacement were measured with a force plate while performing the tasks. A significant difference was found between the two motor dual tasks in ApEn, DFA, and CoDim-AP (p < 0.05). For the ML CoP direction, all nonlinear variables in the study were significantly different (p < 0.05) between ST and mot-DT(T), showing impairment in postural control during mot-DT(T) compared to ST. Differences were found across ST and mot-DT(A) in ApEn-AP and DFA (p < 0.05). The mot-DT(T) was associated with less effectiveness in postural control, a lower number of degrees of freedom, less complexity and adaptability of the dynamic system than the postural single task and the mot-DT(A). Full article

Recent advances both in hardware and software have facilitated the embedded intelligence (EI) research field, and enabled machine learning and decision-making integration in resource-scarce IoT devices and systems, realizing “conscious” and self-explanatory objects (smart objects). In the context of the broad use of WSNs in advanced IoT applications, this is the first work to provide an extreme-edge system, to address structural health monitoring (SHM) on polymethyl methacrylate (PPMA) thin-plate. To the best of our knowledge, state-of-the-art solutions primarily utilize impact positioning methods based on the time of arrival of the stress wave, while in the last decade machine learning data analysis has been performed, by more expensive and resource-abundant equipment than general/development purpose IoT devices, both for the collection and the inference stages of the monitoring system. In contrast to the existing systems, we propose a methodology and a system, implemented by a low-cost device, with the benefit of performing an online and on-device impact localization service from an agnostic perspective, regarding the material and the sensors’ location (as none of those attributes are used). Thus, a design of experiments and the corresponding methodology to build an experimental time-series dataset for impact detection and localization is proposed, using ceramic piezoelectric transducers (PZTs). The system is excited with a steel ball, varying the height from which it is released. Based on TinyML technology for embedding intelligence in low-power devices, we implement and validate random forest and shallow neural network models to localize in real-time (less than 400 ms latency) any occurring impacts on the structure, achieving higher than 90% accuracy. Full article

The advent of cost-effective sensors and the rise of the Internet of Things (IoT) presents the opportunity to monitor urban pollution at a high spatio-temporal resolution. However, these sensors suffer from poor accuracy that can be improved through calibration. In this paper, we propose to use One Dimensional Convolutional Neural Network (1DCNN) based calibration for low-cost carbon monoxide sensors and benchmark its performance against several Machine Learning (ML) based calibration techniques. We make use of three large data sets collected by research groups around the world from field-deployed low-cost sensors co-located with accurate reference sensors. Our investigation shows that 1DCNN performs consistently across all datasets. Gradient boosting regression, another ML technique that has not been widely explored for gas sensor calibration, also performs reasonably well. For all datasets, the introduction of temperature and relative humidity data improves the calibration accuracy. Cross-sensitivity to other pollutants can be exploited to improve the accuracy further. This suggests that low-cost sensors should be deployed as a suite or an array to measure covariate factors. Full article

Glyphosate (GLYP) is a broad-spectrum, nonselective, organic phosphine postemergence herbicide registered for many food and nonfood fields. Herein, we developed a biosensor (Mbs@dsDNA) based on carboxylated modified magnetic beads incubated with NH₂-polyA and then hybridized with polyT-glyphosate aptamer and complementary DNA. Afterwards, a quantitative detection method based on qPCR was established. When the glyphosate aptamer on Mbs@dsDNA specifically recognizes glyphosate, complementary DNA is released and then enters the qPCR signal amplification process. The linear range of the method was 0.6 μmol/L–30 mmol/L and the detection limit was set at 0.6 μmol/L. The recoveries in tap water ranged from 103.4 to 104.9% and the relative standard deviations (RSDs) were <1%. The aptamer proposed in this study has good potential for recognizing glyphosate. The detection method combined with qPCR might have good application prospects in detecting and supervising other pesticide residues. Full article

As one of the most remarkable indicators of physiological health, heart rate (HR) has become an unfailing investigation for researchers. Unlike many existing methods, this article proposes an approach to implement short-time HR estimation from electrocardiography in time series missing patterns. Benefiting from the rapid development of deep learning, we adopted a bidirectional long short-term memory model (Bi-LSTM) and temporal convolution network (TCN) to recover complete heartbeat signals from those with durations are less than one cardiac cycle, and the estimated HR from recovered segment combining the input and the predicted output. We also compared the performance of Bi-LSTM and TCN in PhysioNet dataset. Validating the method over a resting heart rate range of 60–120 bpm in the database without significant arrhythmias and a corresponding range of 30–150 bpm in the database with arrhythmias, we found that networks provide an estimated approach for incomplete signals in a fixed format. These results are consistent with real heartbeats in the normal heartbeat dataset (γ > 0.7, RMSE < 10) and in the arrhythmia database (γ > 0.6, RMSE < 30), verifying that HR could be estimated by models in advance. We also discussed the short-time limits for the predictive model. It could be used for physiological purposes such as mobile sensing in time-constrained scenarios, and providing useful insights for better time series analyses in missing data patterns. Full article

Aiming at the problem that the existing Point of Interest (POI) recommendation model in social network big data is difficult to extract deep feature information, a POI recommendation model based on deep learning in social networks and big data is proposed in this article. The input data are all gathered through intelligent sensors to apply some raw data pre-processing tasks and thus reduce the computational burden on the model. First, a POI static feature extraction method based on symmetric matrix decomposition is designed to capture the geographical location and POI category features in Location-Based Social Networking (LBSN). Second, the improved Continuous Bags-of-Words (CBOW) model is used to extract the semantic features in the user comment information, and realize the implicit vector representation of POI in geographic, category, semantic and temporal feature space. Finally, by adaptively selecting relevant check-in activities from the check-in history to learn and change user preferences, the Geographical-Spatiotemporal Gated Recurrent Unit Network (GSGRUN) can distinguish the user preferences of different check-in. Experiments show that when the length of the recommendation list is 15, the precision of the proposed algorithm on the loc-Gowalla data set is 0.0686, the recall is 0.0769, and the precision on the loc-Brightkite data set is 0.0659, the recall is 0.0835, both of which are better than the comparative recommendation methods. Therefore, compared with the comparison methods, the proposed method can significantly improve the performance of the POI recommendation system. Full article

IoT environments are becoming increasingly heterogeneous in terms of their distributions and included entities by collaboratively involving not only data centers known from Cloud computing but also the different types of third-party entities that can provide computing resources. To transparently provide such resources and facilitate trust between the involved entities, it is necessary to develop and implement smart contracts. However, when developing smart contracts, developers face many challenges and concerns, such as security, contracts’ correctness, a lack of documentation and/or design patterns, and others. To address this problem, we propose a new recommender system to facilitate the development and implementation of low-cost EVM-enabled smart contracts. The recommender system’s algorithm provides the smart contract developer with smart contract templates that match their requirements and that are relevant to the typology of the fog architecture. It mainly relies on OpenZeppelin, a modular, reusable, and secure smart contract library that we use when classifying the smart contracts. The evaluation results indicate that by using our solution, the smart contracts’ development times are overall reduced. Moreover, such smart contracts are sustainable for fog-computing IoT environments and applications in low-cost EVM-based ledgers. The recommender system has been successfully implemented in the ONTOCHAIN ecosystem, thus presenting its applicability. Full article

Mobile edge computing (MEC)-enabled satellite–terrestrial networks (STNs) can provide task computing services for Internet of Things (IoT) devices. However, since some applications’ tasks require huge amounts of computing resources, sometimes the computing resources of a local satellite’s MEC server are insufficient, but the computing resources of neighboring satellites’ MEC servers are redundant. Therefore, we investigated inter-satellite cooperation in MEC-enabled STNs. First, we designed a system model of the MEC-enabled STN architecture, where the local satellite and the neighboring satellites assist IoT devices in computing tasks through inter-satellite cooperation. The local satellite migrates some tasks to the neighboring satellites to utilize their idle resources. Next, the task completion delay minimization problem for all IoT devices is formulated and decomposed. Then, we propose an inter-satellite cooperative joint offloading decision and resource allocation optimization scheme, which consists of a task offloading decision algorithm based on the Grey Wolf Optimizer (GWO) algorithm and a computing resource allocation algorithm based on the Lagrange multiplier method. The optimal solution is obtained by continuous iterations. Finally, simulation results demonstrate that the proposed scheme achieves relatively better performance than other baseline schemes. Full article

A 1.4-dB Noise Figure (NF) four-stage K-band Monolithic Microwave Integrated Circuit (MMIC) Low-Noise Amplifier (LNA) in UMS 100 nm GaAs pHEMT technology is presented. The proposed circuit is designed to cover the 5G New Release n258 frequency band (24.25–27.58 GHz). Momentum EM post-layout simulations reveal the circuit achieves a minimum NF of 1.3 dB, a maximum gain of 34 dB, |S₁₁| better than –10 dB from 23 GHz to 29 GHz, a P_1dB of –18 dBm and an OIP3 of 24.5 dBm. The LNA draws a total current of 59.1 mA from a 2 V DC supply and results in a chip size of 3300 × 1800 µm² including pads. We present a design methodology focused on the selection of the active device size and DC bias conditions to obtain the lowest NF when source degeneration is applied. The design procedure ensures a minimum NF design by selecting a device which facilitates a simple input matching network implementation and obtains a reasonable input return loss thanks to the application of source degeneration. With this approach the input matching network is implemented with a shunt stub and a transmission line, therefore minimizing the contribution to the NF achieved by the first stage. Comparisons with similar works demonstrate the developed circuit is very competitive with most of the state-of-the-art solutions. Full article

Objective: In this paper, we propose a Sine chaos mapping-based improved sparrow search algorithm (SSA) to optimize the BP neural network for trajectory prediction of inland river vessels because of the problems of poor accuracy and easy trapping in local optimum in BP neural networks. Method: First, a standard BP model is constructed based on the AIS data of ships in the Yangtze River section. A Sine-BP model is built using Sine chaos mapping to assign neural network weights and thresholds. Finally, a Sine-SSA-BP model is built using the sparrow search algorithm (SSA) to solve the optimal solutions of the neural network weights and thresholds. Result: The Sine-SSA-BP model effectively improves the initialized population of uniform distribution, and reduces the problem that population intelligence algorithms tend to be premature. Conclusions: The test results show that the Sine-SSA-BP neural network has higher prediction accuracy and better stability than conventional LSTM and SVM, especially in the prediction of corners, which is in good agreement with the real ship navigation trajectory. Full article

The evolution towards next-generation Beyond 5G (B5G) networks will require not only innovation in transport technologies but also the adoption of smarter, more efficient operations of the use cases that are foreseen to be the high consumers of network resources in the next decades. Among different B5G use cases, the Digital Twin (DT) has been identified as a key high bandwidth-demanding use case. The creation and operation of a DT require the continuous collection of an enormous and widely distributed amount of sensor telemetry data which can overwhelm the transport layer. Therefore, the reduction in such transported telemetry data is an essential objective of smart use case operation. Moreover, deep telemetry data analysis, i.e., anomaly detection, can be executed in a hierarchical way to reduce the processing needed to perform such analysis in a centralized way. In this paper, we propose a smart management system consisting of a hierarchical architecture for telemetry sensor data analysis using deep autoencoders (AEs). The system contains AE-based methods for the adaptive compression of telemetry time series data using pools of AEs (called AAC), as well as for anomaly detection in single (called SS-AD) and multiple (called MS-AGD) sensor streams. Numerical results using experimental telemetry data show compression ratios of up to 64% with reconstruction errors of less than 1%, clearly improving upon the benchmark state-of-the-art methods. In addition, fast and accurate anomaly detection is demonstrated for both single and multiple-sensor scenarios. Finally, a great reduction in transport network capacity resources of 50% and more is obtained by smart use case operation for distributed DT scenarios. Full article

To realize permanent magnet synchronous motor (PMSM) in the full speed domain without speed sensor operation, a hybrid control method combining I/F startup and extended Kalman filter (EKF) is proposed in this paper. This method employs I/F startup to transition at low speed, effectively resolving the issue that the position estimation method based on the back electromotive force (EMF) model fails at zero speed and low speed, and converts to EKF for speed closed-loop vector control at medium and high speed. Moreover, a new feedback regulation mechanism as a solution to the problem of smooth switching between the two methods is proposed. First, the power angle is determined based on the relationship between the given I/F frequency and the estimated EKF position angle. Using the information of power angle, the damping torque of the system is increased to reduce velocity fluctuations during I/F startup. In addition, the balance point of current and position error angle is adjusted using the closed-loop information of position error angle to reduce the torque abrupt change before and after switching, thereby making the motor switching process to EKF speed closed-loop control more stable. Finally, simulation results are used to verify the effectiveness of the proposed scheme. Full article

(1) Background: Gamma cameras have wide applications in industry, including nuclear power plant monitoring, emergency response, and homeland security. The desirable properties of a gamma camera include small weight, good resolution, large field of view (FOV), and wide imageable source energy range. Compton cameras can have a 4π FOV but have limited sensitivity at low energy. Coded-aperture gamma cameras are operatable at a wide photon energy range but typically have a limited FOV and increased weight due to the thick heavy metal collimators and shielding. In our lab, we previously proposed a 4π-view gamma imaging approach with a 3D position-sensitive detector, with which each detector element acts as the collimator for other detector elements. We presented promising imaging performance for ^99mTc, ¹⁸F, and ¹³⁷Cs sources. However, the imaging performance for middle- and high-energy sources requires further improvement. (2) Methods: In this study, we present a new gamma camera design to achieve satisfactory imaging performance in a wide gamma energy range. The proposed gamma camera consists of interspaced bar-shaped GAGG (Ce) crystals and tungsten absorbers. The metal bars enhance collimation for high-energy gamma photons without sacrificing the FOV. We assembled a gamma camera prototype and conducted experiments to evaluate the gamma camera’s performance for imaging ⁵⁷Co, ¹³⁷Cs, and ⁶⁰Co point sources. (3) Results: Results show that the proposed gamma camera achieves a positioning accuracy of <3° for all gamma energies. It can clearly resolve two ¹³⁷Cs point sources with 10° separation, two ⁵⁷Co and two ⁶⁰Co point sources with 20° separation, as well as a 2 × 3 ¹³⁷Cs point-source array with 20° separation. (4) Conclusions: We conclude that the proposed gamma camera design has comprehensive merits, including portability, 4π-view FOV, and good angular resolution across a wide energy range. The presented approach has promising potential in nuclear security applications. Full article

Recently, due to the development of semiconductor technology, high-performance memory and digital convergence technology that integrates and implements various functions into one semiconductor chip has been regarded as the next-generation core technology. In the semiconductor manufacturing process, various motors are being applied for automated processes and high product reliability. However, dust and shaft loss due to mechanical friction of a general motor system composed of motor-bearing are problematic for semiconductor wafer processing. In addition, in the edge bread remove (EBR) process after the photoresist application process, a nozzle position control system for removing unnecessary portions of the wafer edge is absolutely necessary. Therefore, in this paper, in order to solve the problems occurring in the semiconductor process, a six-degrees-of-freedom (6-DOF) magnetic levitation system without shaft and bearing was designed for application to the semiconductor process system; and an integrated driving control algorithm for 6-DOF control (levitation, rotation, tilt (Roll–Pitch), X–Y axis movement) using the force of each current component derived through current vector control was proposed. Finally, the 6-DOF magnetic levitation system with the non-contact position sensors was fabricated and the validity of the 6-DOF magnetic levitation control method proposed in this paper was verified through a performance test using a prototype. Full article

In order to train receivers in American football in a targeted and individual manner, the strengths and weaknesses of the athletes must be evaluated precisely. As human resources are limited, it is beneficial to do it in an automated way. Automated passing machines are already given, therefore the motivation is to design a computer-based system that records and automatically evaluates the athlete’s catch attempts. The most fundamental evaluation would be whether the athlete has caught the pass successfully or not. An experiment was carried out to gain data about catch attempts that potentially contain information about the outcome of such. The experiment used a fully automated passing machine which can release passes on command. After a pass was released, an audio and a video sequence of the specific catch attempt was recorded. For this purpose, an audio-visual recording system was developed which was integrated into the passing machine. This system is used to create an audio and video dataset in the amount of 2276 recorded catch attempts. A Convolutional Neural Network (CNN) is used for feature extraction with downstream Long Short-Term Memory (LSTM) to classify the video data. Classification of the audio data is performed using a one-dimensional CNN. With the chosen neural network architecture, an accuracy of 92.19% was achieved in detecting whether a pass had been caught or not. The feasibility for automatic classification of catch attempts during automated catch training is confirmed with this result. Full article