Sensors, Volume 23, Issue 8 (April-2 2023) – 395 articles

Grain yield (GY) prediction based on non-destructive UAV-based spectral sensing could make screening of large field trials more efficient and objective. However, the transfer of models remains challenging, and is affected by location, year-dependent weather conditions and measurement dates. Therefore, this study evaluates GY modelling across years and locations, considering the effect of measurement dates within years. Based on a previous study, we used a normalized difference red edge (NDRE1) index with PLS (partial least squares) regression, trained and tested with the data of individual dates and date combinations, respectively. While strong differences in model performance were observed between test datasets, i.e., different trials, as well as between measurement dates, the effect of the train datasets was comparably small. Generally, within-trials models achieved better predictions (max. R² = 0.27–0.81), but R²-values for the best across-trials models were lower only by 0.03–0.13. Within train and test datasets, measurement dates had a strong influence on model performance. While measurements during flowering and early milk ripeness were confirmed for within- and across-trials models, later dates were less useful for across-trials models. For most test sets, multi-date models revealed to improve predictions compared to individual-date models. Full article

Reinforcement learning (RL) methods for energy saving and greening have recently appeared in the field of autonomous driving. In inter-vehicle communication (IVC), a feasible and increasingly popular research direction of RL is to obtain the optimal action decision of agents in a special environment. This paper presents the application of reinforcement learning in the vehicle communication simulation framework (Veins). In this research, we explore the application of reinforcement learning algorithms in a green cooperative adaptive cruise control (CACC) platoon. Our aim is to train member vehicles to react appropriately in the event of a severe collision involving the leading vehicle. We seek to reduce collision damage and optimize energy consumption by encouraging behavior that conforms to the platoon’s environmentally friendly aim. Our study provides insight into the potential benefits of using reinforcement learning algorithms to improve the safety and efficiency of CACC platoons while promoting sustainable transportation. The policy gradient algorithm used in this paper has good convergence in the calculation of the minimum energy consumption problem and the optimal solution of vehicle behavior. In terms of energy consumption metrics, the policy gradient algorithm is used first in the IVC field for training the proposed platoon problem. It is a feasible training decision-planning algorithm for solving the minimization of energy consumption caused by decision making in platoon avoidance behavior. Full article

The anatomical complexity of brachial plexus injury requires specialized in-depth diagnostics. The clinical examination should include clinical neurophysiology tests, especially with reference to the proximal part, with innovative devices used as sources of precise functional diagnostics. However, the principles and clinical usefulness of this technique are not fully described. The aim of this study was to reinvestigate the clinical usefulness of motor evoked potential (MEP) induced by a magnetic field applied over the vertebrae and at Erb’s point to assess the neural transmission of brachial plexus motor fibers. Seventy-five volunteer subjects were randomly chosen to participate in the research. The clinical studies included an evaluation of the upper extremity sensory perception in dermatomes C5–C8 based on von Frey’s tactile monofilament method, and proximal and distal muscle strength by Lovett’s scale. Finally, 42 healthy people met the inclusion criteria. Magnetic and electrical stimuli were applied to assess the motor function of the peripheral nerves of the upper extremity and magnetic stimulus was applied to study the neural transmission from the C5–C8 spinal roots. The parameters of compound muscle action potential (CMAP) recorded during electroneurography and MEP induced by magnetic stimulation were analyzed. Because the conduction parameters for the groups of women and men were comparable, the final statistical analysis covered 84 tests. The parameters of the potentials generated by electrical stimulus were comparable to those of the potentials induced by magnetic impulse at Erb’s point. The amplitude of the CMAP was significantly higher following electrical stimulation than that of the MEP following magnetic stimulation for all the examined nerves, in the range of 3–7%. The differences in the potential latency values evaluated in CMAP and MEP did not exceed 5%. The results show a significantly higher amplitude of potentials after stimulation of the cervical roots compared to potentials evoked at Erb’s point (C5, C6 level). At the C8 level, the amplitude was lower than the potentials evoked at Erb’s point, varying in the range of 9–16%. We conclude that magnetic field stimulation enables the recording of the supramaximal potential, similar to that evoked by an electric impulse, which is a novel result. Both types of excitation can be used interchangeably during an examination, which is essential for clinical application. Magnetic stimulation was painless in comparison with electrical stimulation according to the results of a pain visual analog scale (3 vs. 5.5 on average). MEP studies with advanced sensor technology allow evaluation of the proximal part of the peripheral motor pathway (between the cervical root level and Erb’s point, and via trunks of the brachial plexus to the target muscles) following the application of stimulus over the vertebrae. Full article

Internet of Things (IoT) faces security concerns different from existing challenges in conventional information systems connected through the Internet because of their limited resources and heterogeneous network setups. This work proposes a novel framework for securing IoT objects, the key objective of which is to assign different Security Level Certificates (SLC) for IoT objects according to their hardware capabilities and protection measures implemented. Objects with SLCs, therefore, will be able to communicate with each other or with the Internet in a secure manner. The proposed framework is composed of five phases, namely: classification, mitigation guidelines, SLC assignment, communication plan, and legacy integration. The groundwork relies on the identification of a set of security attributes, termed security goals. By performing an analysis on common IoT attacks, we identify which of these security goals are violated for specific types of IoT. The feasibility and application of the proposed framework is illustrated at each phase using the smart home as a case study. We also provide qualitative arguments to demonstrate how the deployment of our framework solves IoT specific security challenges. Full article

The intelligent reflecting surface (IRS) is a cutting-edge technology for cost-effectively achieving future spectrum- and energy-efficient wireless communication. In particular, an IRS comprises many low-cost passive devices that can independently reflect the incident signal with a configurable phase shift to produce three-dimensional (3D) passive beamforming without transmitting Radio-Frequency (RF) chains. Thus, the IRS can be utilized to greatly improve wireless channel conditions and increase the dependability of communication systems. This article proposes a scheme for an IRS-equipped GEO satellite signal with proper channel modeling and system characterization. Gabor filter networks (GFNs) are jointly proposed for the extraction of distinct features and the classification of these features. Hybrid optimal functions are used to solve the estimated classification problem, and a simulation setup was designed along with proper channel modeling. The experimental results show that the proposed IRS-based methodology provides higher classification accuracy than the benchmark without the IRS methodology. Full article

The present study proposes a new, highly efficient fractal antenna with ultra-wideband (UWB) characteristics. The proposed patch offers a wide simulated operating band that reaches 8.3 GHz, a simulated gain that varies between 2.47 and 7.73 dB throughout the operating range, and a high simulated efficiency that comes to 98% due to the modifications made to the antenna geometry. The modifications carried out on the antenna are composed of several stages, a circular ring extracted from a circular antenna in which four rings are integrated and, in each ring, four other rings are integrated with a reduction factor of 3/8. To further improve the adaptation of the antenna, a modification of the shape of the ground plane is carried out. In order to test the simulation results, the prototype of the suggested patch was built and tested. The measurement results validate the suggested dual ultra-wideband antenna design approach, which demonstrates good compliance with the simulation. From the measured results, the suggested antenna with a compact volume of 40 × 24.5 × 1.6 mm³ asserts ultra-wideband operation with a measured impedance bandwidth of 7.33 GHz. A high measured efficiency of 92% and a measured gain of 6.52 dB is also achieved. The suggested UWB can effectively cover several wireless applications such as WLAN, WiMAX, and C and X bands. Full article

Pedestrian safety has been evaluated based on the mean number of pedestrian-involved collisions. Traffic conflicts have been used as a data source to supplement collision data because of their higher frequency and lower damage. Currently, the main source of traffic conflict observation is through video cameras that can efficiently gather rich data but can be limited by weather and lighting conditions. The utilization of wireless sensors to gather traffic conflict data can augment video sensors because of their robustness to adverse weather conditions and poor illumination. This study presents a prototype of a safety assessment system that utilizes ultra-wideband wireless sensors to detect traffic conflicts. A customized variant of time-to-collision is used to detect conflicts at different severity thresholds. Field trials are conducted using vehicle-mounted beacons and a phone to simulate sensors on vehicles and smart devices on pedestrians. Proximity measures are calculated in real-time to alert smartphones and prevent collisions, even in adverse weather conditions. Validation is conducted to assess the accuracy of time-to-collision measurements at various distances from the phone. Several limitations are identified and discussed, along with recommendations for improvement and lessons learned for future research and development. Full article

The activity of muscles during motion in one direction should be symmetrical when compared to the activity of the contralateral muscles during motion in the opposite direction, while symmetrical movements should result in symmetrical muscle activation. The literature lacks data on the symmetry of neck muscle activation. Therefore, this study aimed to analyse the activity of the upper trapezius (UT) and sternocleidomastoid (SCM) muscles at rest and during basic motions of the neck and to determine the symmetry of the muscle activation. Surface electromyography (sEMG) was collected from UT and SCM bilaterally during rest, maximum voluntary contraction (MVC) and six functional movements from 18 participants. The muscle activity was related to the MVC, and the Symmetry Index was calculated. The muscle activity at rest was 23.74% and 27.88% higher on the left side than on the right side for the UT and SCM, respectively. The highest asymmetries during motion were for the SCM for the right arc movement (116%) and for the UT in the lower arc movement (55%). The lowest asymmetry was recorded for extension–flexion movement for both muscles. It was concluded that this movement can be useful for assessing the symmetry of neck muscles’ activation. Further studies are required to verify the above-presented results, determine muscle activation patterns and compare healthy people to patients with neck pain. Full article

In Internet of Things (IoT) systems in which a large number of IoT devices are connected to each other and to third-party servers, it is crucial to verify whether each device operates appropriately. Although anomaly detection can help with this verification, individual devices cannot afford this process because of resource constraints. Therefore, it is reasonable to outsource anomaly detection to servers; however, sharing device state information with outside servers may raise privacy concerns. In this paper, we propose a method to compute the $L_p$ distance privately for even $p>2$ using inner product functional encryption and we use this method to compute an advanced metric, namely p-powered error, for anomaly detection in a privacy-preserving manner. We demonstrate implementations on both a desktop computer and Raspberry Pi device to confirm the feasibility of our method. The experimental results demonstrate that the proposed method is sufficiently efficient for use in real-world IoT devices. Finally, we suggest two possible applications of the proposed computation method for $L_p$ distance for privacy-preserving anomaly detection, namely smart building management and remote device diagnosis. Full article

Graphs are data structures that effectively represent relational data in the real world. Graph representation learning is a significant task since it could facilitate various downstream tasks, such as node classification, link prediction, etc. Graph representation learning aims to map graph entities to low-dimensional vectors while preserving graph structure and entity relationships. Over the decades, many models have been proposed for graph representation learning. This paper aims to show a comprehensive picture of graph representation learning models, including traditional and state-of-the-art models on various graphs in different geometric spaces. First, we begin with five types of graph embedding models: graph kernels, matrix factorization models, shallow models, deep-learning models, and non-Euclidean models. In addition, we also discuss graph transformer models and Gaussian embedding models. Second, we present practical applications of graph embedding models, from constructing graphs for specific domains to applying models to solve tasks. Finally, we discuss challenges for existing models and future research directions in detail. As a result, this paper provides a structured overview of the diversity of graph embedding models. Full article

Most pedestrian detection methods focus on bounding boxes based on fusing RGB with lidar. These methods do not relate to how the human eye perceives objects in the real world. Furthermore, lidar and vision can have difficulty detecting pedestrians in scattered environments, and radar can be used to overcome this problem. Therefore, the motivation of this work is to explore, as a preliminary step, the feasibility of fusing lidar, radar, and RGB for pedestrian detection that potentially can be used for autonomous driving that uses a fully connected convolutional neural network architecture for multimodal sensors. The core of the network is based on SegNet, a pixel-wise semantic segmentation network. In this context, lidar and radar were incorporated by transforming them from 3D pointclouds into 2D gray images with 16-bit depths, and RGB images were incorporated with three channels. The proposed architecture uses a single SegNet for each sensor reading, and the outputs are then applied to a fully connected neural network to fuse the three modalities of sensors. Afterwards, an up-sampling network is applied to recover the fused data. Additionally, a custom dataset of 60 images was proposed for training the architecture, with an additional 10 for evaluation and 10 for testing, giving a total of 80 images. The experiment results show a training mean pixel accuracy of 99.7% and a training mean intersection over union of 99.5%. Also, the testing mean of the IoU was 94.4%, and the testing pixel accuracy was 96.2%. These metric results have successfully demonstrated the effectiveness of using semantic segmentation for pedestrian detection under the modalities of three sensors. Despite some overfitting in the model during experimentation, it performed well in detecting people in test mode. Therefore, it is worth emphasizing that the focus of this work is to show that this method is feasible to be used, as it works regardless of the size of the dataset. Also, a bigger dataset would be necessary to achieve a more appropiate training. This method gives the advantage of detecting pedestrians as the human eye does, thereby resulting in less ambiguity. Additionally, this work has also proposed an extrinsic calibration matrix method for sensor alignment between radar and lidar based on singular value decomposition. Full article

Various edge collaboration schemes that rely on reinforcement learning (RL) have been proposed to improve the quality of experience (QoE). Deep RL (DRL) maximizes cumulative rewards through large-scale exploration and exploitation. However, the existing DRL schemes do not consider the temporal states using a fully connected layer. Moreover, they learn the offloading policy regardless of the importance of experience. They also do not learn enough because of their limited experiences in distributed environments. To solve these problems, we proposed a distributed DRL-based computation offloading scheme for improving the QoE in edge computing environments. The proposed scheme selects the offloading target by modeling the task service time and load balance. We implemented three methods to improve the learning performance. Firstly, the DRL scheme used the least absolute shrinkage and selection operator (LASSO) regression and attention layer to consider the temporal states. Secondly, we learned the optimal policy based on the importance of experience using the TD error and loss of the critic network. Finally, we adaptively shared the experience between agents, based on the strategy gradient, to solve the data sparsity problem. The simulation results showed that the proposed scheme achieved lower variation and higher rewards than the existing schemes. Full article

Reflection fiber temperature sensors functionalized with plasmonic nanocomposite material using intensity-based modulation are demonstrated for the first time. Characteristic temperature optical response of the reflective fiber sensor is experimentally tested using Au-incorporated nanocomposite thin films deposited on the fiber tip, and theoretically validated using a thin-film-optic-based optical waveguide model. By optimizing the Au concentration in a dielectric matrix, Au nanoparticles (NP) exhibit a localized surface plasmon resonance (LSPR) absorption band in a visible wavelength that shows a temperature sensitivity ~0.025%/°C as a result of electron–electron and electron–phonon scattering of Au NP and the surrounding matrix. Detailed optical material properties of the on-fiber sensor film are characterized using scanning electron microscopy (SEM) and focused-ion beam (FIB)-assisted transmission electron microscopy (TEM). Airy’s expression of transmission and reflection using complex optical constants of layered media is used to model the reflective optical waveguide. A low-cost wireless interrogator based on a photodiode transimpedance-amplifier (TIA) circuit with a low-pass filter is designed to integrate with the sensor. The converted analog voltage is wirelessly transmitted via 2.4 GHz Serial Peripheral Interface (SPI) protocols. Feasibility is demonstrated for portable, remotely interrogated next-generation fiber optic temperature sensors with future capability for monitoring additional parameters of interest. Full article

Nowadays, Brain–Computer Interfaces (BCIs) still captivate large interest because of multiple advantages offered in numerous domains, explicitly assisting people with motor disabilities in communicating with the surrounding environment. However, challenges of portability, instantaneous processing time, and accurate data processing remain for numerous BCI system setups. This work implements an embedded multi-tasks classifier based on motor imagery using the EEGNet network integrated into the NVIDIA Jetson TX2 card. Therefore, two strategies are developed to select the most discriminant channels. The former uses the accuracy based-classifier criterion, while the latter evaluates electrode mutual information to form discriminant channel subsets. Next, the EEGNet network is implemented to classify discriminant channel signals. Additionally, a cyclic learning algorithm is implemented at the software level to accelerate the model learning convergence and fully profit from the NJT2 hardware resources. Finally, motor imagery Electroencephalogram (EEG) signals provided by HaLT’s public benchmark were used, in addition to the k-fold cross-validation method. Average accuracies of 83.7% and 81.3% were achieved by classifying EEG signals per subject and motor imagery task, respectively. Each task was processed with an average latency of 48.7 ms. This framework offers an alternative for online EEG-BCI systems’ requirements, dealing with short processing times and reliable classification accuracy. Full article

Fiber-optic surface plasmon resonance (FOSPR) sensing technology has become an appealing candidate in biochemical sensing applications due to its distinguished capability of remote and point-of-care detection. However, FOSPR sensing devices with a flat plasmonic film on the optical fiber tip are seldom proposed with most reports concentrating on fiber sidewalls. In this paper, we propose and experimentally demonstrate the plasmonic coupled structure of a gold (Au) nanodisk array and a thin film integrated into the fiber facet, enabling the excitation of the plasmon mode on the planar gold film by strong coupling. This plasmonic fiber sensor is fabricated by the ultraviolet (UV) curing adhesive transferring technology from a planar substrate to a fiber facet. The experimental results demonstrate that the fabricated sensing probe has a bulk refractive index sensitivity of 137.28 nm/RIU and exhibits moderate surface sensitivity by measuring the spatial localization of its excited plasmon mode on Au film by layer-by-layer self-assembly technology. Furthermore, the fabricated plasmonic sensing probe enables the detection of bovine serum albumin (BSA) biomolecule with a detection limit of 19.35 μM. The demonstrated fiber probe here provides a potential strategy to integrate plasmonic nanostructure on the fiber facet with excellent sensing performance, which has a unique application prospect in the detection of remote, in situ, and in vivo invasion. Full article

Microbial fuel cells (MFCs) using rumen bacteria have been proposed as a power source for running devices inside cattle. In this study, we explored the key parameters of the conventional bamboo charcoal electrode in an attempt to improve the amount of electrical power generated by the microbial fuel cell. We evaluated the effects of the electrode’s surface area, thickness, and rumen content on power generation and determined that only the electrode’s surface area affects power generation levels. Furthermore, our observations and bacterial count on the electrode revealed that rumen bacteria concentrated on the surface of the bamboo charcoal electrode and did not penetrate the interior, explaining why only the electrode’s surface area affected power generation levels. A Copper (Cu) plate and Cu paper electrodes were also used to evaluate the effect of different electrodes on measuring the rumen bacteria MFC’s power potential, which had a temporarily higher maximum power point (MPP) compared to the bamboo charcoal electrode. However, the open circuit voltage and MPP decreased significantly over time due to the corrosion of the Cu electrodes. The MPP for the Cu plate electrode was 775 mW/m² and the MPP for the Cu paper electrode was 1240 mW/m², while the MPP for bamboo charcoal electrodes was only 18.7 mW/m². In the future, rumen bacteria MFCs are expected to be used as the power supply of rumen sensors. Full article

A heterostructured nanocomposite MCM-41<SFA> was formed using the encapsulation method, where a silicon dioxide matrix—MCM-41 was the host matrix and synthetic fulvic acid was the organic guest. Using the method of nitrogen sorption/desorption, a high degree of monoporosity in the studied matrix was established, with a maximum for the distribution of its pores with radii of 1.42 nm. According to the results of an X-ray structural analysis, both the matrix and the encapsulate were characterized by an amorphous structure, and the absence of a manifestation of the guest component could be caused by its nanodispersity. The electrical, conductive, and polarization properties of the encapsulate were studied with impedance spectroscopy. The nature of the changes in the frequency behavior of the impedance, dielectric permittivity, and tangent of the dielectric loss angle under normal conditions, in a constant magnetic field, and under illumination, was established. The obtained results indicated the manifestation of photo- and magneto-resistive and capacitive effects. In the studied encapsulate, the combination of a high value of ε and a value of the tgδ of less than 1 in the low-frequency range was achieved, which is a prerequisite for the realization of a quantum electric energy storage device. A confirmation of the possibility of accumulating an electric charge was obtained by measuring the I-V characteristic, which took on a hysteresis behavior. Full article

In this paper, defect detection and identification in aluminium joints is investigated based on guided wave monitoring. Guided wave testing is first performed on the selected damage feature from experiments, namely, the scattering coefficient, to prove the feasibility of damage identification. A Bayesian framework based on the selected damage feature for damage identification of three-dimensional joints of arbitrary shape and finite size is then presented. This framework accounts for both modelling and experimental uncertainties. A hybrid wave and finite element approach (WFE) is adopted to predict the scattering coefficients numerically corresponding to different size defects in joints. Moreover, the proposed approach leverages a kriging surrogate model in combination with WFE to formulate a prediction equation that links scattering coefficients to defect size. This equation replaces WFE as the forward model in probabilistic inference, resulting in a significant enhancement in computational efficiency. Finally, numerical and experimental case studies are used to validate the damage identification scheme. An investigation into how the location of sensors can impact the identified results is provided as well. Full article

In this article, a novel heterogeneous fusion of convolutional neural networks that combined an RGB camera and an active mmWave radar sensor for the smart parking meter is proposed. In general, the parking fee collector on the street outdoor surroundings by traffic flows, shadows, and reflections makes it an exceedingly tough task to identify street parking regions. The proposed heterogeneous fusion convolutional neural networks combine an active radar sensor and image input with specific geometric area, allowing them to detect the parking region against different tough conditions such as rain, fog, dust, snow, glare, and traffic flow. They use convolutional neural networks to acquire output results along with the individual training and fusion of RGB camera and mmWave radar data. To achieve real-time performance, the proposed algorithm has been implemented on a GPU-accelerated embedded platform Jetson Nano with a heterogeneous hardware acceleration methodology. The experimental results exhibit that the accuracy of the heterogeneous fusion method can reach up to 99.33% on average. Full article

This study explores the use of Multi-Objective Genetic Algorithm (MOGA) for thermodynamic characteristics of serrated plate-fin heat exchanger (PFHE) under numerical simulation method. Numerical investigations on the important structural parameters of the serrated fin and the j factor and the f factor of PFHE are conducted, and the experimental correlations about the j factor and the f factor are determined by comparing the simulation results with the experimental data. Meanwhile, based on the principle of minimum entropy generation, the thermodynamic analysis of the heat exchanger is investigated, and the optimization calculation is carried out by MOGA. The comparison results between optimized structure and original show that the j factor increases by 3.7%, the f factor decreases by 7.8%, and the entropy generation number decreases by 31%. From the data point of view, the optimized structure has the most obvious effect on the entropy generation number, which shows that the entropy generation number can be more sensitive to the irreversible changes caused by the structural parameters, and at the same time, the j factor is appropriately increased. Full article

Behavioral prediction modeling applies statistical techniques for classifying, recognizing, and predicting behavior using various data. However, performance deterioration and data bias problems occur in behavioral prediction. This study proposed that researchers conduct behavioral prediction using text-to-numeric generative adversarial network (TN-GAN)-based multidimensional time-series augmentation to minimize the data bias problem. The prediction model dataset in this study used nine-axis sensor data (accelerometer, gyroscope, and geomagnetic sensors). The ODROID N2+, a wearable pet device, collected and stored data on a web server. The interquartile range removed outliers, and data processing constructed a sequence as an input value for the predictive model. After using the z-score as a normalization method for sensor values, cubic spline interpolation was performed to identify the missing values. The experimental group assessed 10 dogs to identify nine behaviors. The behavioral prediction model used a hybrid convolutional neural network model to extract features and applied long short-term memory techniques to reflect time-series features. The actual and predicted values were evaluated using the performance evaluation index. The results of this study can assist in recognizing and predicting behavior and detecting abnormal behavior, capacities which can be applied to various pet monitoring systems. Full article

Maintaining physical activity is an important clinical goal for people with Parkinson’s disease (PwPD). We investigated the validity of two commercial activity trackers (ATs) to measure daily step counts. We compared a wrist- and a hip-worn commercial AT against the research-grade Dynaport Movemonitor (DAM) during 14 days of daily use. Criterion validity was assessed in 28 PwPD and 30 healthy controls (HCs) by a 2 × 3 ANOVA and intraclass correlation coefficients (ICC_2,1). The ability to measure daily step fluctuations compared to the DAM was studied by a 2 × 3 ANOVA and Kendall correlations. We also explored compliance and user-friendliness. Both the ATs and the DAM measured significantly fewer steps/day in PwPD compared to HCs (p < 0.01). Step counts derived from the ATs showed good to excellent agreement with the DAM in both groups (ICC_2,1 > 0.83). Daily fluctuations were detected adequately by the ATs, showing moderate associations with DAM-rankings. While compliance was high overall, 22% of PwPD were disinclined to use the ATs after the study. Overall, we conclude that the ATs had sufficient agreement with the DAM for the purpose of promoting physical activity in mildly affected PwPD. However, further validation is needed before clinical use can be widely recommended. Full article

Recently, many deep neural networks (DNN) have been proposed to solve the spectral reconstruction (SR) problem: recovering spectra from RGB measurements. Most DNNs seek to learn the relationship between an RGB viewed in a given spatial context and its corresponding spectra. Significantly, it is argued that the same RGB can map to different spectra depending on the context with respect to which it is seen and, more generally, that accounting for spatial context leads to improved SR. However, as it stands, DNN performance is only slightly better than the much simpler pixel-based methods where spatial context is not used. In this paper, we present a new pixel-based algorithm called A++ (an extension of the A+ sparse coding algorithm). In A+, RGBs are clustered, and within each cluster, a designated linear SR map is trained to recover spectra. In A++, we cluster the spectra instead in an attempt to ensure neighboring spectra (i.e., spectra in the same cluster) are recovered by the same SR map. A polynomial regression framework is developed to estimate the spectral neighborhoods given only the RGB values in testing, which in turn determines which mapping should be used to map each testing RGB to its reconstructed spectrum. Compared to the leading DNNs, not only does A++ deliver the best results, it is parameterized by orders of magnitude fewer parameters and has a significantly faster implementation. Moreover, in contradistinction to some DNN methods, A++ uses pixel-based processing, which is robust to image manipulations that alter the spatial context (e.g., blurring and rotations). Our demonstration on the scene relighting application also shows that, while SR methods, in general, provide more accurate relighting results compared to the traditional diagonal matrix correction, A++ provides superior color accuracy and robustness compared to the top DNN methods. Full article

Detecting plant disease severity could help growers and researchers study how the disease impacts cereal crops to make timely decisions. Advanced technology is needed to protect cereals that feed the increasing population using fewer chemicals; this may lead to reduced labor usage and cost in the field. Accurate detection of wheat stem rust, an emerging threat to wheat production, could inform growers to make management decisions and assist plant breeders in making line selections. A hyperspectral camera mounted on an unmanned aerial vehicle (UAV) was utilized in this study to evaluate the severity of wheat stem rust disease in a disease trial containing 960 plots. Quadratic discriminant analysis (QDA) and random forest classifier (RFC), decision tree classification, and support vector machine (SVM) were applied to select the wavelengths and spectral vegetation indices (SVIs). The trial plots were divided into four levels based on ground truth disease severities: class 0 (healthy, severity 0), class 1 (mildly diseased, severity 1–15), class 2 (moderately diseased, severity 16–34), and class 3 (severely diseased, highest severity observed). The RFC method achieved the highest overall classification accuracy (85%). For the spectral vegetation indices (SVIs), the highest classification rate was recorded by RFC, and the accuracy was 76%. The Green NDVI (GNDVI), Photochemical Reflectance Index (PRI), Red-Edge Vegetation Stress Index (RVS1), and Chlorophyll Green (Chl green) were selected from 14 SVIs. In addition, binary classification of mildly diseased vs. non-diseased was also conducted using the classifiers and achieved 88% classification accuracy. This highlighted that hyperspectral imaging was sensitive enough to discriminate between low levels of stem rust disease vs. no disease. The results of this study demonstrated that drone hyperspectral imaging can discriminate stem rust disease levels so that breeders can select disease-resistant varieties more efficiently. The detection of low disease severity capability of drone hyperspectral imaging can help farmers identify early disease outbreaks and enable more timely management of their fields. Based on this study, it is also possible to build a new inexpensive multispectral sensor to diagnose wheat stem rust disease accurately. Full article

Technological innovations enable rapid DNA analysis implementation possibilities. Concordantly, rapid DNA devices are being used in practice. However, the effects of implementing rapid DNA technologies in the crime scene investigation procedure have only been evaluated to a limited extent. In this study a field experiment was set up comparing 47 real crime scene cases following a rapid DNA analysis procedure outside of the laboratory (decentral), with 50 cases following the regular DNA analysis procedure at the forensic laboratory. The impact on duration of the investigative process, and on the quality of the analyzed trace results (97 blood and 38 saliva traces) was measured. The results of the study show that the duration of the investigation process has been significantly reduced in cases where the decentral rapid DNA procedure was deployed, compared to cases where the regular procedure was used. Most of the delay in the regular process lies in the procedural steps during the police investigation, not in the DNA analysis, which highlights the importance of an effective work process and having sufficient capacity available. This study also shows that rapid DNA techniques are less sensitive than regular DNA analysis equipment. The device used in this study was only to a limited extent suitable for the analysis of saliva traces secured at the crime scene and can mainly be used for the analysis of visible blood traces with an expected high DNA quantity of a single donor. Full article

This study characterized person-specific rates of change of total daily physical activity (TDPA) and identified correlates of this change. TDPA metrics were extracted from multiday wrist-sensor recordings from 1083 older adults (average age 81 years; 76% female). Thirty-two covariates were collected at baseline. A series of linear mixed-effect models were used to identify covariates independently associated with the level and annual rate of change of TDPA. Though, person-specific rates of change varied during a mean follow-up of 5 years, 1079 of 1083 showed declining TDPA. The average decline was 16%/year, with a 4% increased rate of decline for every 10 years of age older at baseline. Following variable selection using multivariate modeling with forward and then backward elimination, age, sex, education, and 3 of 27 non-demographic covariates including motor abilities, a fractal metric, and IADL disability remained significantly associated with declining TDPA accounting for 21% of its variance (9% non-demographic and 12% demographics covariates). These results show that declining TDPA occurs in many very old adults. Few covariates remained correlated with this decline and the majority of its variance remained unexplained. Further work is needed to elucidate the biology underlying TDPA and to identify other factors that account for its decline. Full article

This paper reports the architecture of a low-cost smart crutches system for mobile health applications. The prototype is based on a set of sensorized crutches connected to a custom Android application. Crutches were instrumented with a 6-axis inertial measurement unit, a uniaxial load cell, WiFi connectivity, and a microcontroller for data collection and processing. Crutch orientation and applied force were calibrated with a motion capture system and a force platform. Data are processed and visualized in real-time on the Android smartphone and are stored on the local memory for further offline analysis. The prototype’s architecture is reported along with the post-calibration accuracy for estimating crutch orientation (5° RMSE in dynamic conditions) and applied force (10 N RMSE). The system is a mobile-health platform enabling the design and development of real-time biofeedback applications and continuity of care scenarios, such as telemonitoring and telerehabilitation. Full article

This study proposes a visual tracking system that can detect and track multiple fast-moving appearance-varying targets simultaneously with 500 fps image processing. The system comprises a high-speed camera and a pan-tilt galvanometer system, which can rapidly generate large-scale high-definition images of the wide monitored area. We developed a CNN-based hybrid tracking algorithm that can robustly track multiple high-speed moving objects simultaneously. Experimental results demonstrate that our system can track up to three moving objects with velocities lower than 30 m per second simultaneously within an 8-m range. The effectiveness of our system was demonstrated through several experiments conducted on simultaneous zoom shooting of multiple moving objects (persons and bottles) in a natural outdoor scene. Moreover, our system demonstrates high robustness to target loss and crossing situations. Full article

Traditional cuff-based sphygmomanometers for measuring blood pressure can be uncomfortable and particularly unsuitable to use during sleep. A proposed alternative method uses dynamic changes in the pulse waveform over short intervals and replaces calibration with information from photoplethysmogram (PPG) morphology to provide a calibration-free approach using a single sensor. Results from 30 patients show a high correlation of 73.64% for systolic blood pressure (SBP) and 77.72% for diastolic blood pressure (DBP) between blood pressure estimated with the PPG morphology features and the calibration method. This suggests that the PPG morphology features could replace the calibration stage for a calibration-free method with similar accuracy. Applying the proposed methodology on 200 patients and testing on 25 new patients resulted in a mean error (ME) of −0.31 mmHg, a standard deviation of error (SDE) of 4.89 mmHg, a mean absolute error (MAE) of 3.32 mmHg for DBP and an ME of −4.02 mmHg, an SDE of 10.40 mmHg, and an MAE of 7.41 mmHg for SBP. These results support the potential for using a PPG signal for calibration-free cuffless blood pressure estimation and improving accuracy by adding information from cardiovascular dynamics to different methods in the cuffless blood pressure monitoring field. Full article

Both paper-based and computerized exams have a high level of cheating. It is, therefore, desirable to be able to detect cheating accurately. Keeping the academic integrity of student evaluations intact is one of the biggest issues in online education. There is a substantial possibility of academic dishonesty during final exams since teachers are not directly monitoring students. We suggest a novel method in this study for identifying possible exam-cheating incidents using Machine Learning (ML) approaches. The 7WiseUp behavior dataset compiles data from surveys, sensor data, and institutional records to improve student well-being and academic performance. It offers information on academic achievement, student attendance, and behavior in general. In order to build models for predicting academic accomplishment, identifying at-risk students, and detecting problematic behavior, the dataset is designed for use in research on student behavior and performance. Our model approach surpassed all prior three-reference efforts with an accuracy of 90% and used a long short-term memory (LSTM) technique with a dropout layer, dense layers, and an optimizer called Adam. Implementing a more intricate and optimized architecture and hyperparameters is credited with increased accuracy. In addition, the increased accuracy could have been caused by how we cleaned and prepared our data. More investigation and analysis are required to determine the precise elements that led to our model’s superior performance. Full article