Recognizing human emotions by machines is a complex task. Deep learning models attempt to automate this process by rendering machines to exhibit learning capabilities. However, identifying human emotions from speech with good performance is still challenging. With the advent of deep learning algorithms, this problem has been addressed recently. However, most research work in the past focused on feature extraction as only one method for training. In this research, we have explored two different methods of extracting features to address effective speech emotion recognition. Initially, two-way feature extraction is proposed by utilizing super convergence to extract two sets of potential features from the speech data. For the first set of features, principal component analysis (PCA) is applied to obtain the first feature set. Thereafter, a deep neural network (DNN) with dense and dropout layers is implemented. In the second approach, mel-spectrogram images are extracted from audio files, and the 2D images are given as input to the pre-trained VGG-16 model. Extensive experiments and an in-depth comparative analysis over both the feature extraction methods with multiple algorithms and over two datasets are performed in this work. The RAVDESS dataset provided significantly better accuracy than using numeric features on a DNN.Making a new font requires graphical designs for all base characters, and this designing process consumes lots of time and human resources. Especially for languages including a large number of combinations of consonants and vowels, it is a heavy burden to design all such combinations independently. Automatic font generation methods have been proposed to reduce this labor-intensive design problem. Most of the methods are GAN-based approaches, and they are limited to generate the trained fonts. In some previous methods, they used two encoders, one for content, the other for style, but their disentanglement of content and style is not sufficiently effective in generating arbitrary fonts. Arbitrary font generation is a challenging task because learning text and font design separately from given font images is very difficult, where the font images have both text content and font style in each image. In this paper, we propose a new automatic font generation method to solve this disentanglement problem. First, we use two stacked inputs, i.e., images with the same text but different font style as content input and images with the same font style but different text as style input. Second, we propose new consistency losses that force any combination of encoded features of the stacked inputs to have the same values. In our experiments, we proved that our method can extract consistent features of text contents and font styles by separating content and style encoders and this works well for generating unseen font design from a small number of reference font images that are human-designed. Comparing to the previous methods, the font designs generated with our method showed better quality both qualitatively and quantitatively than those with the previous methods for Korean, Chinese, and English characters. e.g., 17.84 lower FID in unseen font compared to other methods.Road traffic accidents regarding commercial vehicles have been demonstrated as an important culprit restricting the steady development of the social economy, which are closely related to the distracted behavior of drivers. However, the existing driver’s distracted behavior surveillance systems for monitoring and preventing the distracted behavior of drivers still have some shortcomings such as fewer recognition objects and scenarios. This study aims to provide a more comprehensive methodological framework to demonstrate the significance of enlarging the recognition objects, scenarios and types of the existing driver’s distracted behavior recognition systems. The driver’s posture characteristics were primarily analyzed to provide the basis of the subsequent modeling. Five CNN sub-models were established for different posture categories and to improve the efficiency of recognition, accompanied by a holistic multi-cascaded CNN framework. To suggest the best model, image data sets of commercial vehicle driver postures including 117,410 daytime images and 60,480 night images were trained and tested. The findings demonstrate that compared to the non-cascaded models, both daytime and night cascaded models show better performance. Besides, the night models exhibit worse accuracy and better speed relative to their daytime model counterparts for both non-cascaded and cascaded models. This study could be used to develop countermeasures to improve driver safety and provide helpful information for the design of the driver’s real-time monitoring and warning system as well as the automatic driving system. Future research could be implemented to combine the vehicle state parameters with the driver’s microscopic behavior to establish a more comprehensive proactive surveillance system.Multi-hole probes can simultaneously measure the velocity and direction of a flow field, obtain the distribution of the flow field in a three-dimensional space, and obtain the vortex information in the flow field. Moreover, a multi-hole probe needs to be calibrated while in use; therefore, a three-coordinate, multi-directional rotatable testing system, which can measure the flow field at any position and at any angle, was designed herein. A hemispherical seven-hole probe was calibrated with this test system, and the flow field around cylinders of different diameters was measured to obtain the pressure distribution and vortex shedding frequency. Furthermore, the designed test system’s ability to perform a multi-angle and multi-azimuth testing during the calibration of a multi-hole probe was verified. Simultaneously, through data mining of the multi-hole probe, vortices were measured, and periodic vortices were detected.Thousands of energy-aware sensors have been placed for monitoring in a variety of scenarios, such as manufacturing, control systems, disaster management, flood control and so on, requiring time-critical energy-efficient solutions to extend their lifetime. This paper proposes reinforcement learning (RL) based dynamic data streams for time-critical IoT systems in energy-aware IoT devices. The designed solution employs the Q-Learning algorithm. The proposed mechanism has the potential to adjust the data transport rate based on the amount of renewable energy resources that are available, to ensure collecting reliable data while also taking into account the sensor battery lifetime. The solution was evaluated using historical data for solar radiation levels, which shows that the proposed solution can increase the amount of transmitted data up to 23%, ensuring the continuous operation of the device.In this article, we propose a reliable and low-latency Long Range Wide Area Network (LoRaWAN) solution for environmental monitoring in factories at major accident risk (FMAR). In particular, a low power wearable device for sensing the toxic inflammable gases inside an industrial plant is designed with the purpose of avoiding peculiar risks and unwanted accidents to occur. Moreover, the detected data have to be urgently and reliably delivered to remote server to trigger preventive immediate actions so as to improve the machine operation. In these settings, LoRaWAN has been identified as the most proper communications technology to the needs owing to the availability of off the shelf devices and software. Hence, we assess the technological limits of LoRaWAN in terms of latency and reliability and we propose a fully LoRaWAN compliant solution to overcome these limits. The proposed solution envisages coordinated end device (ED) transmissions through the use of Downlink Control Packets (DCPs). Experimental results validate the proposed method in terms of service requirements for the considered FMAR scenario.Controlling active and passive systems in buildings with the aim of optimizing energy efficiency and maintaining occupants’ comfort is the major task of building management systems. However, most of these systems use a predefined configuration, which usually do not match the occupants’ preferences. Therefore, occupancy detection is imperative for energy use management mainly in residential and industrial buildings. Most works related to data-driven-based occupancy detection have used batch learning techniques, which need to store first and then train the data. It is not appropriate for a non-stationary environment. Therefore, this work sheds more light on the use of non-stationary machine learning techniques. To this end, three machine learning algorithms for stream data processing are presented, tested, and evaluated in term of accuracy and resources performance (i.e., RAM, CPU), with the aim of predicting the number of occupants in smart buildings. A platform architecture that integrates IoT technologies with stream machine learning is implemented and deployed. The experimental results show the effectiveness of this approach and illustrate that the number of occupants can be predicted with an accuracy of more than 83% and without resource wasting (i.e., time of CPU use varied between 0.04s and 3.85 ⋅ 10-11 GB of RAM could be exploited per hour).Slip-resistant footwear can prevent fall-related injuries on icy surfaces. Winter footwear slip resistance can be measured by the Maximum Achievable Angle (MAA) test, which measures the steepest ice-covered incline that participants can walk up and down without experiencing a slip. However, the MAA test requires the use of a human observer to detect slips, which increases the variability of the test. The objective of this study was to develop and evaluate an automated slip detection algorithm for walking on level and inclined ice surfaces to be used with the MAA test to replace the need for human observers. Kinematic data were collected from nine healthy young adults walking up and down on ice surfaces in a range from 0° to 12° using an optical motion capture system. Our algorithm segmented these data into steps and extracted features as inputs to two linear support vector machine classifiers. The two classifiers were trained, optimized, and validated to classify toe slips and heel slips, respectively. A total of approximately 11,000 steps from 9 healthy participants were collected, which included approximately 4700 slips. Our algorithm was able to detect slips with an overall F1 score of 90.1%. In addition, the algorithm was able to accurately classify backward toe slips, forward toe slips, backward heel slips, and forward heel slips with F1 scores of 97.3%, 54.5%, 80.9%, and 86.5%, respectively.A rare and valuable Palaeolithic wooden point, presumably belonging to a hunting weapon, was found in the Ljubljanica River in Slovenia in 2008. In order to prevent complete decay, the waterlogged wooden artefact had to undergo conservation treatment, which usually involves some expected deformations of structure and shape. To investigate these changes, a series of surface-based 3D models of the artefact were created before, during and after the conservation process. Unfortunately, the surface-based 3D models were not sufficient to understand the internal processes inside the wooden artefact (cracks, cavities, fractures). Since some of the surface-based 3D models were taken with a microtomographic scanner, we decided to create a volumetric 3D model from the available 2D tomographic images. In order to have complete control and greater flexibility in creating the volumetric 3D model than is the case with commercial software, we decided to implement our own algorithm. In fact, two algorithms were implemented for the construction of surface-based 3D models and for the construction of volumetric 3D models, using (1) unsegmented 2D images CT and (2) segmented 2D images CT. The results were positive in comparison with commercial software and new information was obtained about the actual state and causes of the deformation of the artefact. Such models could be a valuable aid in the selection of appropriate conservation and restoration methods and techniques in cultural heritage research.The purpose of this research was to analyze the possibilities for the application of vibration signals in real-time train and track control. Proper experiments must be performed for the validation of the methods. Research on vibration in the context of transport must entail many of the different nonlinear dynamic forces that may occur while driving. Therefore, the paper addresses two research cases. The developed application contains the identification of movement and dynamics and the evaluation of the technical state of the rail track. The statistics and resultant vector methods are presented. The paper presents other useful metrics to describe the dynamical properties of the driving train. The angle of the resultant horizontal and vertical accelerations is defined for the evaluation of the current position of cabin. It is calculated as an inverse tangent function of current longitudinal and transverse, longitudinal and vertical, transverse, and vertical accelerations. Additionally, the resultant vectors of accelerations are calculated.Power inversion (PI) is a known adaptive beamforming algorithm that is widely used in wireless communication systems for anti-jamming purposes. The PI algorithm is typically implemented in a digital domain, which requires the radio-frequency signals to be down-converted into base-band signals, and then sampled by ADCs. In practice, the down-conversion circuit will introduce phase noises into the base-band signals, which may degrade the performance of the algorithm. At present, the impacts of phase noise on the PI algorithm have not been studied, according to the open literature, which is, however, important for practical design. Therefore, in this paper, we present a theoretical analysis on the impacts, provide a new mathematical model of the PI algorithm, and offer a closed-form formula of the interference cancellation ratio (ICR) to quantify the relations between the algorithm performance and the phase noise level, as well as the number of auxiliary antennas. We find that the ICR in decibel decreases logarithmically linearly with the phase noise variance. In addition, the ICR improves with an increasing number of auxiliary antennas, but the increment is upper-bounded. The above findings are verified with both simulated and measured phase noise data.This study evaluates the impacts of slot tagging and training data length on joint natural language understanding (NLU) models for medication management scenarios using chatbots in Spanish. In this study, we define the intents (purposes of the sentences) for medication management scenarios and two types of slot tags. For training the model, we generated four datasets, combining long/short sentences with long/short slots, while for testing, we collect the data from real interactions of users with a chatbot. For the comparative analysis, we chose six joint NLU models (SlotRefine, stack-propagation framework, SF-ID network, capsule-NLU, slot-gated modeling, and a joint SLU-LM model) from the literature. The results show that the best performance (with a sentence-level semantic accuracy of 68.6%, an F1-score of 76.4% for slot filling, and an accuracy of 79.3% for intent detection) is achieved using short sentences and short slots. Our results suggest that joint NLU models trained with short slots yield better results than those trained with long slots for the slot filling task. The results also indicate that short slots could be a better choice for the dialog system because of their simplicity. Importantly, the work demonstrates that the performance of the joint NLU models can be improved by selecting the correct slot configuration according to the usage scenario.Achieving the accurate perception of occluded objects for autonomous vehicles is a challenging problem. Human vision can always quickly locate important object regions in complex external scenes, while other regions are only roughly analysed or ignored, defined as the visual attention mechanism. However, the perception system of autonomous vehicles cannot know which part of the point cloud is in the region of interest. Therefore, it is meaningful to explore how to use the visual attention mechanism in the perception system of autonomous driving. In this paper, we propose the model of the spatial attention frustum to solve object occlusion in 3D object detection. The spatial attention frustum can suppress unimportant features and allocate limited neural computing resources to critical parts of the scene, thereby providing greater relevance and easier processing for higher-level perceptual reasoning tasks. To ensure that our method maintains good reasoning ability when faced with occluded objects with only a partial structure, we propose a local feature aggregation module to capture more complex local features of the point cloud. Finally, we discuss the projection constraint relationship between the 3D bounding box and the 2D bounding box and propose a joint anchor box projection loss function, which will help to improve the overall performance of our method. The results of the KITTI dataset show that our proposed method can effectively improve the detection accuracy of occluded objects. Our method achieves 89.46%, 79.91% and 75.53% detection accuracy in the easy, moderate, and hard difficulty levels of the car category, and achieves a 6.97% performance improvement especially in the hard category with a high degree of occlusion. Our one-stage method does not need to rely on another refining stage, comparable to the accuracy of the two-stage method.In this paper, a novel path planning algorithm with Reinforcement Learning is proposed based on the topological map. The proposed algorithm has a two-level structure. At the first level, the proposed method generates the topological area using the region dynamic growth algorithm based on the grid map. In the next level, the Multi-SARSA method divided into two layers is applied to find a near-optimal global planning path, in which the artificial potential field method, first of all, is used to initialize the first Q table for faster learning speed, and then the second Q table is initialized with the connected domain obtained by topological map, which provides the prior information. A combination of the two algorithms makes the algorithm easier to converge. Simulation experiments for path planning have been executed. The results indicate that the method proposed in this paper can find the optimal path with a shorter path length, which demonstrates the effectiveness of the presented method.Static posturography assessed with force platforms is a procedure used to obtain objective estimates related to postural adjustments. However, controlling multiple intrinsic and extrinsic factors influencing the diagnostic accuracy is essential to obtain reliable measurements and recommend its use with clinical or research purposes. We aimed to analyze how different environmental acoustic conditions affect the test-retest reliability and to analyze the most appropriate number of trials to calculate a valid mean average score. A diagnostic accuracy study was conducted enrolling 27 healthy volunteers. All procedures were taken considering consistent device settings, posture, feet position, recording time, and illumination of the room. Three trials were recorded in a silent environment (35-40 dB) and three trials were recorded in a noisy environment (85-90 dB). Results showed comparable reliability estimates for both acoustic conditions (ICC = 0.453-0.962 and 0.621-0.952), but silent conditions demonstrated better sensitivity to changes (MDC = 13.6-76%). Mean average calculations from 2 and 3 trials showed no statistically significant differences (p > 0.05). Cross-sectional studies can be conducted under noisy or silent conditions as no significantly different scores were obtained (p > 0.05) and ICC were comparable (except oscillation area). However, longitudinal studies should consider silent conditions as they demonstrated better sensitivity to real changes not derived from measurement errors.The proportion of new energy in power systems is increasing yearly. How to deal with the adverse impact of new energy output uncertainty on its participation in trading from the mechanism level is an urgent problem in China that must be solved. A source grid load storage (SGLS) continuous trading mechanism and a multi-time scale trading simulation method are proposed which meet the needs of Chinese new energy consumption and satisfies the trading needs of Chinese power market players. Firstly, the connection mechanism of mid-long term, day-ahead, and intra-day SGLS interactive trading is established, and the meaning and ways of continuous development are defined. Secondly, the clearing model of SGLS trading based on the continuous trading mechanism is established to provide mathematical models and strategic methods for various resources to participate in SGLS trading. Then, the multi-time scale trading simulation of SGLS based on the continuous trading mechanism is carried out to obtain the trading strategies of different trading subjects. The example results show that compared with the trading mechanism based on deviation assessment, the one-day trading cost is reduced by 4.20% and the consumption rate of new energy is increased by 6.53%. It can be seen that the mid-long term-day-ahead-day SGLS interactive trading connection mechanism has advantages in reducing trading costs and improving the consumption rate of new energy. It can flexibly deal with the trading scenario of domestic new energy consumption and new energy reverse peak shaving, which has an effect on the adverse impact of trading and operation deviation caused by source load uncertainty on trading.This work presents a novel landing assistance system (LAS) capable of locating a drone for a safe landing after its inspection mission. The location of the drone is achieved by a fusion of ultra-wideband (UWB), inertial measurement unit (IMU) and magnetometer data. Unlike other typical landing assistance systems, the UWB fixed sensors are placed around a 2 × 2 m landing platform and two tags are attached to the drone. Since this type of set-up is suboptimal for UWB location systems, a new positioning algorithm is proposed for a correct performance. First, an extended Kalman filter (EKF) algorithm is used to calculate the position of each tag, and then both positions are combined for a more accurate and robust localisation. As a result, the obtained positioning errors can be reduced by 50% compared to a typical UWB-based landing assistance system. Moreover, due to the small demand of space, the proposed landing assistance system can be used almost anywhere and is deployed easily.Capacitive proximity sensing is widespread in our everyday life, but no sensor for biomedical optics takes advantage of this technology to monitor the probe attachment to the subject’s skin. In particular, when using optical monitoring devices, the capability to quantitatively measure the probe contact can significantly improve data quality and ensure the subject’s safety. We present a custom novel optical probe based on a flexible printed circuit board which integrates a capacitive contact sensor, 3D-printed optic fiber holders and an accelerometer sensor. The device can be effectively adopted during continuous monitoring optical measurements to detect contact quality, motion artifacts, probe detachment and ensure optimal signal quality.In this paper, we aim to open up new perspectives in the field of autonomous aerial surveillance and target tracking systems, by exploring an alternative that, surprisingly, and to the best of the authors’ knowledge, has not been addressed in that context by the research community thus far. It can be summarized by the following two questions. Under the scope of such applications, what are the implications and possibilities offered by mounting several steerable cameras onboard of each aerial agent? Second, how can optimization algorithms benefit from this new framework, in their attempt to provide more efficient and cost-effective solutions on these areas? The paper presents the idea as an additional degree of freedom to be exploited, which can enable more efficient alternatives in the deployment of such applications. As an initial approach, the problem of the optimal positioning with respect to a set of targets of one single agent, equipped with several onboard tracking cameras with different or variable focal lengths, is addressed. As a consequence of this allowed heterogeneity in focal lengths, the notion of distance needs to be adapted into a notion of optical range, as the agent can trade longer Euclidean distances for correspondingly longer focal lengths. Moreover, the proposed optimization indices try to balance, in an optimal way, the verticality of the viewpoints along with the optical range to the targets. Under these premises, several positioning strategies are proposed and comparatively evaluated.In this article, we introduce explainable methods to understand how Human Activity Recognition (HAR) mobile systems perform based on the chosen validation strategies. Our results introduce a new way to discover potential bias problems that overestimate the prediction accuracy of an algorithm because of the inappropriate choice of validation methodology. We show how the SHAP (Shapley additive explanations) framework, used in literature to explain the predictions of any machine learning model, presents itself as a tool that can provide graphical insights into how human activity recognition models achieve their results. Now it is possible to analyze which features are important to a HAR system in each validation methodology in a simplified way. We not only demonstrate that the validation procedure k-folds cross-validation (k-CV), used in most works to evaluate the expected error in a HAR system, can overestimate by about 13% the prediction accuracy in three public datasets but also choose a different feature set when compared with the universal model. Combining explainable methods with machine learning algorithms has the potential to help new researchers look inside the decisions of the machine learning algorithms, avoiding most times the overestimation of prediction accuracy, understanding relations between features, and finding bias before deploying the system in real-world scenarios.In this paper, a Distributed Nonlinear Dynamic Inversion (DNDI)-based consensus protocol is designed to achieve the bipartite consensus of nonlinear agents over a signed graph. DNDI inherits the advantage of nonlinear dynamic inversion theory, and the application to the bipartite problem is a new idea. Moreover, communication noise is considered to make the scenario more realistic. The convergence study provides a solid theoretical base, and a realistic simulation study shows the effectiveness of the proposed protocol.Damage identification is a key problem in the field of structural health monitoring, which is of great significance to improve the reliability and safety of engineering structures. In the past, the structural strain damage identification method based on specific damage index needs the designer to have rich experience and background knowledge, and the designed damage index is hard to apply to different structures. In this paper, a U-shaped efficient structural strain damage identification network SDFormer (structural damage transformer) based on self-attention feature is proposed. SDFormer regards the problem of structural strain damage identification as an image segmentation problem, and introduces advanced image segmentation technology for structural damage identification. This network takes the strain field map of the structure as the input, and then outputs the predicted damage location and level. In the SDFormer, the low-level and high-level features are smoothly fused by skip connection, and the self-attention module is used to obtain damage feature information, to effectively improve the performance of the model. SDFormer can directly construct the mapping between strain field map and damage distribution without complex damage index design. While ensuring the accuracy, it improves the identification efficiency. The effectiveness and accuracy of the model are verified by numerical experiments, and the performance of an advanced convolutional neural network is compared. The results show that SDFormer has better performance than the advanced convolutional neural network. Further, an anti-noise experiment is designed to verify the anti-noise and robustness of the model. The anti-noise performance of SDFormer is better than that of the comparison model in the anti-noise experimental results, which proves that the model has good anti-noise and robustness.An evaluation of decision fusion methods based on Dempster-Shafer Theory (DST) and its modifications is presented in the article, studied over real biometric data from the engineered multimodal banking client verification system. First, the approaches for multimodal biometric data fusion for verification are explained. Then the proposed implementation of comparison scores fusion is presented, including details on the application of DST, required modifications, base probability, and mass conversions. Next, the biometric verification process is described, and the engineered biometric banking system principles are provided. Finally, the validation results of three fusion approaches on synthetic and real data are presented and discussed, considering the desired outcome manifested by minimized false non-match rates for various assumed thresholds and biometric verification techniques.Mid-to-high altitude Unmanned Aerial Vehicle (UAV) imagery can provide important remote sensing information between satellite and low altitude platforms, and vehicle detection in mid-to-high altitude UAV images plays a crucial role in land monitoring and disaster relief. However, the high background complexity of images and limited pixels of objects challenge the performance of tiny vehicle detection. Traditional methods suffer from poor adaptation ability to complex backgrounds, while deep neural networks (DNNs) have inherent defects in feature extraction of tiny objects with finite pixels. To address the issue above, this paper puts forward a vehicle detection method combining the DNNs-based and traditional methods for mid-to-high altitude UAV images. We first employ the deep segmentation network to exploit the co-occurrence of the road and vehicles, then detect tiny vehicles based on visual attention mechanism with spatial-temporal constraint information. Experimental results show that the proposed method achieves effective detection of tiny vehicles in complex backgrounds. In addition, ablation experiments are performed to inspect the effectiveness of each component, and comparative experiments on tinier objects are carried out to prove the superior generalization performance of our method in detecting vehicles with a limited size of 5 × 5 pixels or less.The traction converter is one of the key components of high-speed trains. Current and voltage sensor faults in the converter may lead to feedback values deviation and system degradation, which will bring security risks to the train. This paper proposes a real-time fault diagnosis method for grid current, DC-link voltage and stator current sensor faults in the traction converter with two stator current sensors, which can not only detect and locate faults but also identify the types of faults. Moreover, the faults considered in this paper are incipient. First, the DC-link model is established, and the fault is detected by the residual of the DC-link voltage. Next, the differential of DC-link voltage residual is calculated, which is applied to fault location. Then, according to the change of the differential values, different fault types are determined. Finally, the hardware-in-the-loop (HIL) platform is built and the effectiveness and accuracy of the proposed method are verified by the HIL tests.Blood cancer, or leukemia, has a negative impact on the blood and/or bone marrow of children and adults. Acute lymphocytic leukemia (ALL) and acute myeloid leukemia (AML) are two sub-types of acute leukemia. The Internet of Medical Things (IoMT) and artificial intelligence have allowed for the development of advanced technologies to assist in recently introduced medical procedures. Hence, in this paper, we propose a new intelligent IoMT framework for the automated classification of acute leukemias using microscopic blood images. The workflow of our proposed framework includes three main stages, as follows. First, blood samples are collected by wireless digital microscopy and sent to a cloud server. Second, the cloud server carries out automatic identification of the blood conditions-either leukemias or healthy-utilizing our developed generative adversarial network (GAN) classifier. Finally, the classification results are sent to a hematologist for medical approval. The developed GAN classifier was successfully evaluated on two public data sets ALL-IDB and ASH image bank. It achieved the best accuracy scores of 98.67% for binary classification (ALL or healthy) and 95.5% for multi-class classification (ALL, AML, and normal blood cells), when compared with existing state-of-the-art methods. The results of this study demonstrate the feasibility of our proposed IoMT framework for automated diagnosis of acute leukemia tests. Clinical realization of this blood diagnosis system is our future work.As the world’s population is aging, and since access to ambient sensors has become easier over the past years, activity recognition in smart home installations has gained increased scientific interest. The majority of published papers in the literature focus on single-resident activity recognition. While this is an important area, especially when focusing on elderly people living alone, multi-resident activity recognition has potentially more applications in smart homes. Activity recognition for multiple residents acting concurrently can be treated as a multilabel classification problem (MLC). In this study, an experimental comparison between different MLC algorithms is attempted. Three different techniques were implemented RAkELd, classifier chains, and binary relevance. These methods are evaluated using the ARAS and CASAS public datasets. Results obtained from experiments have shown that using MLC can recognize activities performed by multiple people with high accuracy. While RAkELd had the best performance, the rest of the methods had on-par results.Failure in dynamic structures poses a pressing need for fault detection systems. Interconnected sensor nodes of wireless sensor networks (WSN) offer a solution by communicating information about their surroundings. Nonetheless, these battery-powered sensors have an immense labor cost and require periodical battery maintenance and replacement. Batteries pose a significant environmental threat that is expected to cause irreversible damage to the ecosystem. We introduce a fully integrated vibration-powered energy harvester sensor system that is interfaced with a custom-developed fault detection app. Vibrations are used to power a radio frequency (RF) transmitter that is integrated with the vibration sensor subunit. The harvester-sensor unit is comprised of dual moving magnets that are bordered by coil windings for power and signal generation. The power generated from the harvester is used to operate the transmitter while the signal generated from the sensor is transmitted as a vibration signal. Transmitted values are streamed into a high precision fault detection app capable of detecting the frequency of vibrations with an error of 1%. The app employs an FFT algorithm on the transmitted data and notifies the user when a threshold vibration level is reached. The total energy consumed by the transmitter is 0.894 µJ at a 3 V operation. The operable acceleration of the system is 0.7 g [m/s2] at 5-10.6 Hz.Music is an invaluable tool to improve affective valence during exercise, with the potential contribution of a mechanism called rhythmic entrainment. However, several methodological limitations impair our current understanding of the effect of music on relevant psychophysiological responses to exercise, including breathing variables. This study presents conceptual, methodological, and operational insight favoring the investigation of the effect of music on breathing during exercise. Three tools were developed for the quantification of the presence, degree, and magnitude of music-locomotor, locomotor-breathing, and music-breathing entrainment. The occurrence of entrainment was assessed during 30 min of moderate cycling exercise performed either when listening to music or not, and was complemented by the recording of relevant psychophysiological and mechanical variables. Respiratory frequency and expiratory time were among the physiological variables that were affected to a greater extent by music during exercise, and a significant (p < 0.05) music-breathing entrainment was found in all 12 participants. These findings suggest the importance of evaluating the effect of music on breathing responses to exercise, with potential implications for exercise prescription and adherence, and for the development of wearable devices simultaneously measuring music, locomotor, and breathing signals.The purpose of this study was to determine the effect of fatigue on impact shock wave attenuation and assess how human biomechanics relate to shock attenuation during running. In this paper, we propose a new methodology for the analysis of shock events occurring during the proposed experimental procedure. Our approach is based on the Shock Response Spectrum (SRS), which is a frequency-based function that is used to indicate the magnitude of vibration due to a shock or a transient event. Five high level CrossFit athletes who ran at least three times per week and who were free from musculoskeletal injury volunteered to take part in this study. Two Micromachined Microelectromechanical Systems (MEMS) accelerometers (RunScribe®, San Francisco, CA, USA) were used for this experiment. The two RunScribe pods were mounted on top of the foot in the shoelaces. All five athletes performed three maximum intensity runs the 1st run was performed after a brief warmup with no prior exercise, then the 2nd and the 3rd run were performed in a fatigued state. Prior to the 2nd and the 3rd run, the athletes were asked to perform at maximum intensity for two minutes on an Assault AirBike to tire them. For all five athletes, there was a direct correlation between fatigue and an increase in the aggressiveness of the SRS. We noticed that for all five athletes for the 3rd run the average SRS peaks were significantly higher than for the 1st run and 2nd run (p < 0.01) at the same natural frequency of the athlete. This confirms our hypothesis that fatigue causes a decrease in the shock attenuation capacity of the musculoskeletal system thus potentially involving a higher risk of overuse injury.Gesture recognition plays an important role in smart homes, such as human-computer interaction, identity authentication, etc. Most of the existing WiFi signal-based approaches exploit a large number of channel state information (CSI) datasets to train a gestures classification model; however, these models require a large number of human participants to train, and are not robust to the recognition environment. To address this problem, we propose a WiFi signal-based gesture recognition system with matched averaging federated learning (WiMA). Since there are differences in the distribution of WiFi signal changes caused by the same gesture in different environments, the traditional federated parameter average algorithm seriously affects the recognition accuracy of the model. In WiMA, we exploit the neuron arrangement invariance of neural networks in parameter aggregation, which can improve the robustness of the gesture recognition model with heterogeneous CSI data of different training environments. We carried out experiments with seven participant users in a distributed gesture recognition environment. Experimental results show that the average accuracy of our proposed system is up to 90.4%, which is very close to the accuracy of state-of-the-art approaches with centralized training models.Emotion recognition using EEG has been widely studied to address the challenges associated with affective computing. Using manual feature extraction methods on EEG signals results in sub-optimal performance by the learning models. With the advancements in deep learning as a tool for automated feature engineering, in this work, a hybrid of manual and automatic feature extraction methods has been proposed. The asymmetry in different brain regions is captured in a 2D vector, termed the AsMap, from the differential entropy features of EEG signals. These AsMaps are then used to extract features automatically using a convolutional neural network model. The proposed feature extraction method has been compared with differential entropy and other feature extraction methods such as relative asymmetry, differential asymmetry and differential caudality. Experiments are conducted using the SJTU emotion EEG dataset and the DEAP dataset on different classification problems based on the number of classes. Results obtained indicate that the proposed method of feature extraction results in higher classification accuracy, outperforming the other feature extraction methods. The highest classification accuracy of 97.10% is achieved on a three-class classification problem using the SJTU emotion EEG dataset. Further, this work has also assessed the impact of window size on classification accuracy.Distributed generation connected with AC, DC, or hybrid loads and energy storage systems is known as a microgrid. Campus microgrids are an important load type. A university campus microgrids, usually, contains distributed generation resources, energy storage, and electric vehicles. The main aim of the microgrid is to provide sustainable, economical energy, and a reliable system. The advanced energy management system (AEMS) provides a smooth energy flow to the microgrid. Over the last few years, many studies were carried out to review various aspects such as energy sustainability, demand response strategies, control systems, energy management systems with different types of optimization techniques that are used to optimize the microgrid system. In this paper, a comprehensive review of the energy management system of campus microgrids is presented. In this survey, the existing literature review of different objective functions, renewable energy resources and solution tools are also reviewed. Furthermore, the research directions and related issues to be considered in future microgrid scheduling studies are also presented.Every human being experiences emotions daily, e.g., joy, sadness, fear, anger. These might be revealed through speech-words are often accompanied by our emotional states when we talk. Different acoustic emotional databases are freely available for solving the Emotional Speech Recognition (ESR) task. Unfortunately, many of them were generated under non-real-world conditions, i.e., actors played emotions, and recorded emotions were under fictitious circumstances where noise is non-existent. Another weakness in the design of emotion recognition systems is the scarcity of enough patterns in the available databases, causing generalization problems and leading to overfitting. This paper examines how different recording environmental elements impact system performance using a simple logistic regression algorithm. Specifically, we conducted experiments simulating different scenarios, using different levels of Gaussian white noise, real-world noise, and reverberation. The results from this research show a performance deterioration in all scenarios, increasing the error probability from 25.57% to 79.13% in the worst case. Additionally, a virtual enlargement method and a robust multi-scenario speech-based emotion recognition system are proposed. Our system’s average error probability of 34.57% is comparable to the best-case scenario with 31.55%. The findings support the prediction that simulated emotional speech databases do not offer sufficient closeness to real scenarios.The development of fibre optic sensors for measuring the refractive index is related to the creation of new periodic structures and demodulation algorithms for the measured spectrum. Recently, we proposed a double-comb Tilted fibre Bragg grating (DCTFBG) structure. In this article, we analyse such a structure for measuring the refractive index in comparison to a single classical structure. Increasing the number of modes causes a significant change in the Fourier spectrum of optical spectra. For the purpose of data pre-processing, we propose the Fourier Transform as a filtering method in the frequency domain. Then, we analyse separately the band-filtered optical spectra for several frequency ranges. For quantitative analysis, we use algorithms that use quantitative changes in the transmission, i.e., the method of the envelope and the length of the spectrum contour. We propose the use of the Hilbert transform as the envelope method. The second type of algorithms used are methods determining the shift of spectrum features along the wavelength axis. The method of determining the centre of gravity of the area bounded by the envelope and the maximum of the second derivative of the smoothed cumulative spectrum contour length is proposed here. Using the developed methods, the measurement resolution was achieved at the level of 2 × 10-5 refractive index unit.Diabetic retinopathy (DR) refers to the ophthalmological complications of diabetes mellitus. It is primarily a disease of the retinal vasculature that can lead to vision loss. Optical coherence tomography angiography (OCTA) demonstrates the ability to detect the changes in the retinal vascular system, which can help in the early detection of DR. In this paper, we describe a novel framework that can detect DR from OCTA based on capturing the appearance and morphological markers of the retinal vascular system. This new framework consists of the following main steps (1) extracting retinal vascular system from OCTA images based on using joint Markov-Gibbs Random Field (MGRF) model to model the appearance of OCTA images and (2) estimating the distance map inside the extracted vascular system to be used as imaging markers that describe the morphology of the retinal vascular (RV) system. The OCTA images, extracted vascular system, and the RV-estimated distance map is then composed into a three-dimensional matrix to be used as an input to a convolutional neural network (CNN). The main motivation for using this data representation is that it combines the low-level data as well as high-level processed data to allow the CNN to capture significant features to increase its ability to distinguish DR from the normal retina. This has been applied on multi-scale levels to include the original full dimension images as well as sub-images extracted from the original OCTA images. The proposed approach was tested on in-vivo data using about 91 patients, which were qualitatively graded by retinal experts. In addition, it was quantitatively validated using datasets based on three metrics sensitivity, specificity, and overall accuracy. Results showed the capability of the proposed approach, outperforming the current deep learning as well as features-based detecting DR approaches.Video stabilization is one of the most important features in consumer cameras. Even simple video stabilization algorithms may need to access the frames several times to generate a stabilized output image, which places a significant burden on the camera hardware. This high-memory-access requirement makes it difficult to implement video stabilization in real time on low-cost camera SoC. Reduction of the memory usage is a critical issue in camera hardware. This paper presents a structure and layout method to efficiently implement video stabilization for low-end hardware devices in terms of shared memory access amount. The proposed method places sub-components of video stabilization in a parasitic form in other processing blocks, and the sub-components reuse data read from other processing blocks without directly accessing data in the shared memory. Although the proposed method is not superior to the state-of-the-art methods applied in post-processing in terms of video quality, it provides sufficient performance to lower the cost of camera hardware for the development of real-time devices. According to my analysis, the proposed one reduces the memory access amount by 21.1 times compared to the straightforward method.As a consequence of swiftly growing populations in the urban areas, larger quantities of solid waste also form rapidly. Since urban local bodies are found to be unable to manage this perilous situation effectively, there is a high probability of risks relative to the environment and public health. A sudden change is indispensable in the existing systems that are developed for the collection, transportation, and disposal of solid waste, which are entangled in turmoil. However, Smart sensors and wireless technology enable cyber-physical systems to automate solid waste management, which will revolutionize the industry. This work presents a comprehensive study on the evolution of automation approaches in solid waste management systems. This study is enhanced by dissecting the available literature in solid waste management with Radio Frequency Identification (RFID), Wireless Sensor Networks (WSN), and Internet of Things (IoT)-based approaches and analyzing each category with a typical architecture, respectively. In addition, various communication technologies adopted in the aforementioned categories are critically analyzed to identify the best choice for the deployment of trash bins. From the survey, it is inferred that IoT-based systems are superior to other design approaches, and LoRaWAN is identified as the preferred communication protocol for the automation of solid waste handling systems in urban areas. Furthermore, the critical open research issues on state-of-the-art solid waste handling systems are identified and future directions to address the same topic are suggested.The Timed Up and Go test (TUG) is commonly used to estimate the fall risk in the elderly. Several ways to improve the predictive accuracy of TUG (cameras, multiple sensors, other clinical tests) have already been proposed. Here, we added a single wearable inertial measurement unit (IMU) to capture the residents’ body center-of-mass kinematics in view of improving TUG’s predictive accuracy. The aim is to find out which kinematic variables and residents’ characteristics are relevant for distinguishing faller from non-faller patients. Data were collected in 73 nursing home residents with the IMU placed on the lower back. Acceleration and angular velocity time series were analyzed during different subtasks of the TUG. Multiple logistic regressions showed that total time required, maximum angular velocity at the first half-turn, gender, and use of a walking aid were the parameters leading to the best predictive abilities of fall risk. The predictive accuracy of the proposed new test, called i + TUG, reached a value of 74.