Search

Delay-sensitive task offloading in a device-to-device assisted mobile edge computing (D2D-MEC) system with energy harvesting devices is a critical challenge due to the dynamic load level at edge nodes and the variability in harvested energy. In this paper, we propose a joint dynamic task offloading and CPU frequency control scheme for delay-sensitive tasks in a D2D-MEC system, taking into account the intricacies of multi-slot tasks, characterized by diverse processing speeds and data transmission rates. Our methodology involves meticulous modeling of task arrival and service processes using queuing systems, coupled with the strategic utilization of D2D communication to alleviate edge server load and prevent network congestion effectively. Central to our solution is the formulation of average task delay optimization as a challenging nonlinear integer programming problem, requiring intelligent decision making regarding task offloading for each generated task at active mobile devices and CPU frequency adjustments at discrete time slots. To navigate the intricate landscape of the extensive discrete action space, we design an efficient multi-agent DRL learning algorithm named MAOC, which is based on MAPPO, to minimize the average task delay by dynamically determining task-offloading decisions and CPU frequencies. MAOC operates within a centralized training with decentralized execution (CTDE) framework, empowering individual mobile devices to make decisions autonomously based on their unique system states. Experimental results demonstrate its swift convergence and operational efficiency, and it outperforms other baseline algorithms. [ABSTRACT FROM AUTHOR]

Environmental effects may lead to cracking, stiffness loss, brace damage, and other damages in bridges, frame structures, buildings, etc. Structural Health Monitoring (SHM) technology could prevent catastrophic events by detecting damage early. In recent years, Deep Learning (DL) has developed rapidly and has been applied to SHM to detect, localize, and evaluate diverse damages through efficient feature extraction. This paper analyzes 337 articles through a systematic literature review to investigate the application of DL for SHM in the operation and maintenance phase of facilities from three perspectives: data, DL algorithms, and applications. Firstly, the data types in SHM and the corresponding collection methods are summarized and analyzed. The most common data types are vibration signals and images, accounting for 80% of the literature studied. Secondly, the popular DL algorithm types and application areas are reviewed, of which CNN accounts for 60%. Then, this article carefully analyzes the specific functions of DL application for SHM based on the facility's characteristics. The most scrutinized study focused on cracks, accounting for 30 percent of research papers. Finally, challenges and trends in applying DL for SHM are discussed. Among the trends, the Structural Health Monitoring Digital Twin (SHMDT) model framework is suggested in response to the trend of strong coupling between SHM technology and Digital Twin (DT), which can advance the digitalization, visualization, and intelligent management of SHM. [ABSTRACT FROM AUTHOR]

The advancement of machine learning in industrial applications has necessitated the development of tailored solutions to address specific challenges, particularly in multi-class classification tasks. This study delves into the customization of loss functions within the eXtreme Gradient Boosting (XGBoost) algorithm, which is a critical step in enhancing the algorithm's performance for specific applications. Our research is motivated by the need for precision and efficiency in the industrial domain, where the implications of misclassification can be substantial. We focus on the drill-wear analysis of melamine-faced chipboard, a common material in furniture production, to demonstrate the impact of custom loss functions. The paper explores several variants of Weighted Softmax Loss Functions, including Edge Penalty and Adaptive Weighted Softmax Loss, to address the challenges of class imbalance and the heightened importance of accurately classifying edge classes. Our findings reveal that these custom loss functions significantly reduce critical errors in classification without compromising the overall accuracy of the model. This research not only contributes to the field of industrial machine learning by providing a nuanced approach to loss function customization but also underscores the importance of context-specific adaptations in machine learning algorithms. The results showcase the potential of tailored loss functions in balancing precision and efficiency, ensuring reliable and effective machine learning solutions in industrial settings. [ABSTRACT FROM AUTHOR]

Ship fire may result in significant damage to its structure and large economic loss. Hence, the prompt identification of fires is essential in order to provide prompt reactions and effective mitigation strategies. However, conventional detection systems exhibit limited efficacy and accuracy in detecting targets, which has been mostly attributed to limitations imposed by distance constraints and the motion of ships. Although the development of deep learning algorithms provides a potential solution, the computational complexity of ship fire detection algorithm pose significant challenges. To solve this, this paper proposes a lightweight ship fire detection algorithm based on YOLOv8n. Initially, a dataset, including more than 4000 unduplicated images and their labels, is established before training. In order to ensure the performance of algorithms, both fire inside ship rooms and also fire on board are considered. Then after tests, YOLOv8n is selected as the model with the best performance and fastest speed from among several advanced object detection algorithms. GhostnetV2-C2F is then inserted in the backbone of the algorithm for long-range attention with inexpensive operation. In addition, spatial and channel reconstruction convolution (SCConv) is used to reduce redundant features with significantly lower complexity and computational costs for real-time ship fire detection. For the neck part, omni-dimensional dynamic convolution is used for the multi-dimensional attention mechanism, which also lowers the parameters. After these improvements, a lighter and more accurate YOLOv8n algorithm, called Ship-Fire Net, was proposed. The proposed method exceeds 0.93, both in precision and recall for fire and smoke detection in ships. In addition, the mAP@0.5 reaches about 0.9. Despite the improvement in accuracy, Ship-Fire Net also has fewer parameters and lower FLOPs compared to the original, which accelerates its detection speed. The FPS of Ship-Fire Net also reaches 286, which is helpful for real-time ship fire monitoring. [ABSTRACT FROM AUTHOR]

Given that fingerprint localization methods can be effectively modeled as supervised learning problems, machine learning has been employed for indoor localization tasks based on fingerprint methods. However, it is often challenging for popular machine learning models to effectively capture the unstructured data features inherent in fingerprint data that are generated in diverse propagation environments. In this paper, we propose an indoor localization algorithm based on a high-order graph neural network (HoGNNLoc) to enhance the accuracy of indoor localization and improve localization stability in dynamic environments. The algorithm first designs an adjacency matrix based on the spatial relative locations of access points (APs) to obtain a graph structure; on this basis, a high-order graph neural network is constructed to extract and aggregate the features; finally, the designed fully connected network is used to achieve the regression prediction of the location of the target to be located. The experimental results on our self-built dataset show that the proposed algorithm achieves localization accuracy within 1.29 m at 80% of the cumulative distribution function (CDF) points. The improvements are 59.2%, 51.3%, 36.1%, and 22.7% compared to the K-nearest neighbors (KNN), deep neural network (DNN), simple graph convolutional network (SGC), and graph attention network (GAT). Moreover, even with a 30% reduction in fingerprint data, the proposed algorithm exhibits stable localization performance. On a public dataset, our proposed localization algorithm can also show better performance. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) and network-enabled smart devices are crucial to the digitally interconnected society of the present day. However, the increased reliance on IoT devices increases their susceptibility to malicious activities within network traffic, posing significant challenges to cybersecurity. As a result, both system administrators and end users are negatively affected by these malevolent behaviours. Intrusion-detection systems (IDSs) are commonly deployed as a cyber attack defence mechanism to mitigate such risks. IDS plays a crucial role in identifying and preventing cyber hazards within IoT networks. However, the development of an efficient and rapid IDS system for the detection of cyber attacks remains a challenging area of research. Moreover, IDS datasets contain multiple features, so the implementation of feature selection (FS) is required to design an effective and timely IDS. The FS procedure seeks to eliminate irrelevant and redundant features from large IDS datasets, thereby improving the intrusion-detection system's overall performance. In this paper, we propose a hybrid wrapper-based feature-selection algorithm that is based on the concepts of the Cellular Automata (CA) engine and Tabu Search (TS)-based aspiration criteria. We used a Random Forest (RF) ensemble learning classifier to evaluate the fitness of the selected features. The proposed algorithm, CAT-S, was tested on the TON_IoT dataset. The simulation results demonstrate that the proposed algorithm, CAT-S, enhances classification accuracy while simultaneously reducing the number of features and the false positive rate. [ABSTRACT FROM AUTHOR]

The popularity of video services such as video call or video on-demand has made it impossible for people to live without them in their daily lives. It can be anticipated that the explosive growth of vehicular communication owing to the widespread use of in-vehicle video infotainment applications in the future will result in increasing fragmentation and congestion of the wireless transmission spectrum. Accordingly, effective bandwidth management algorithms are demanded to achieve efficient communication and stable scalability in next-generation vehicular networks. To the best of our current knowledge, a noticeable gap remains in the existing literature regarding the application of the latest advancements in network communication technologies. Specifically, this gap is evident in the lack of exploration regarding how cutting-edge technologies can be effectively employed to optimize bandwidth allocation, especially in the realm of video service applications within the forthcoming vehicular networks. In light of this void, this paper presents a seamless integration of cutting-edge 6G communication technologies, such as terahertz (THz) and visible light communication (VLC), with the existing 5G millimeter-wave and sub-6 GHz base stations. This integration facilitates the creation of a network environment characterized by high transmission rates and extensive coverage. Our primary aim is to ensure the uninterrupted playback of real-time video applications for vehicle users. These video applications encompass video conferencing, live video, and on-demand video services. The outcomes of our simulations convincingly indicate that the proposed strategy adeptly addresses the challenge of bandwidth competition among vehicle users. Moreover, it notably boosts the efficient utilization of bandwidth from less crowded base stations, optimizes the fulfillment of bandwidth prerequisites for various video applications, and elevates the overall video quality experienced by users. Consequently, our findings serve as a successful validation of the practicality and effectiveness of the proposed methodology. [ABSTRACT FROM AUTHOR]

Cloud computing plays an important role in every IT sector. Many tech giants such as Google, Microsoft, and Facebook as deploying their data centres around the world to provide computation and storage services. The customers either submit their job directly or they take the help of the brokers for the submission of the jobs to the cloud centres. The preliminary aim is to reduce the overall power consumption which was ignored in the early days of cloud development. This was due to the performance expectations from cloud servers as they were supposed to provide all the services through their services layers IaaS, PaaS, and SaaS. As time passed and researchers came up with new terminologies and algorithmic architecture for the reduction of power consumption and sustainability, other algorithmic anarchies were also introduced, such as statistical oriented learning and bioinspired algorithms. In this paper, an indepth focus has been done on multiple approaches for migration among virtual machines and find out various issues among existing approaches. The proposed work utilizes elastic scheduling inspired by the smart elastic scheduling algorithm (SESA) to develop a more energy-efficient VM allocation and migration algorithm. The proposed work uses cosine similarity and bandwidth utilization as additional utilities to improve the current performance in terms of QoS. The proposed work is evaluated for overall power consumption and service level agreement violation (SLA-V) and is compared with related state of art techniques. A proposed algorithm is also presented in order to solve problems found during the survey. [ABSTRACT FROM AUTHOR]

This paper presents a state-of-the-art estimation technique by cross-combining a number n of filters for high-precision, reliable and robust vehicle sideslip angle state estimation, over a full range of vehicle operations irrespective of the driving mission and disruptions that may occur in the system. A machine-learning algorithm based on decision trees connects several filters together to switch between them according to the driving context, ensuring the best possible state estimate for relatively small and large sideslip angle values. In conjunction with the above-mentioned aspects, a seamless transition between different vehicle models is attained by observing the key parameters characterizing the lateral motion of the vehicle. The tests conducted using a prototype vehicle on a snow-covered track confirm the effectiveness and reliability of the proposed approach. [ABSTRACT FROM AUTHOR]

Due to subjectivity in refereeing, the results of race walking are often questioned. To overcome this limitation, artificial-intelligence-based technologies have demonstrated their potential. The paper aims at presenting WARNING, an inertial-based wearable sensor integrated with a support vector machine algorithm to automatically identify race-walking faults. Two WARNING sensors were used to gather the 3D linear acceleration related to the shanks of ten expert race-walkers. Participants were asked to perform a race circuit following three race-walking conditions: legal, illegal with loss-of-contact and illegal with knee-bent. Thirteen machine learning algorithms, belonging to the decision tree, support vector machine and k-nearest neighbor categories, were evaluated. An inter-athlete training procedure was applied. Algorithm performance was evaluated in terms of overall accuracy, F1 score and G-index, as well as by computing the prediction speed. The quadratic support vector was confirmed to be the best-performing classifier, achieving an accuracy above 90% with a prediction speed of 29,000 observations/s when considering data from both shanks. A significant reduction of the performance was assessed when considering only one lower limb side. The outcomes allow us to affirm the potential of WARNING to be used as a referee assistant in race-walking competitions and during training sessions. [ABSTRACT FROM AUTHOR]

Intrusion detection systems (IDS) play a crucial role in securing networks and identifying malicious activity. This is a critical problem in cyber security. In recent years, metaheuristic optimization algorithms and deep learning techniques have been applied to IDS to improve their accuracy and efficiency. Generally, optimization algorithms can be used to boost the performance of IDS models. Deep learning methods, such as convolutional neural networks, have also been used to improve the ability of IDS to detect and classify intrusions. In this paper, we propose a new IDS model based on the combination of deep learning and optimization methods. First, a feature extraction method based on CNNs is developed. Then, a new feature selection method is used based on a modified version of Growth Optimizer (GO), called MGO. We use the Whale Optimization Algorithm (WOA) to boost the search process of the GO. Extensive evaluation and comparisons have been conducted to assess the quality of the suggested method using public datasets of cloud and Internet of Things (IoT) environments. The applied techniques have shown promising results in identifying previously unknown attacks with high accuracy rates. The MGO performed better than several previous methods in all experimental comparisons. [ABSTRACT FROM AUTHOR]

Structural health monitoring (SHM) systems are used to analyze the health of infrastructures such as bridges, using data from various types of sensors. While SHM systems consist of various stages, feature extraction and pattern recognition steps are the most important. Consequently, signal processing techniques in the feature extraction stage and machine learning algorithms in the pattern recognition stage play an effective role in analyzing the health of bridges. In other words, there exists a plethora of signal processing techniques and machine learning algorithms, and the selection of the appropriate technique/algorithm is guided by the limitations of each technique/algorithm. The selection also depends on the requirements of SHM in terms of damage identification level and operating conditions. This has provided the motivation to conduct a Systematic literature review (SLR) of feature extraction techniques and pattern recognition algorithms for the structural health monitoring of bridges. The existing literature reviews describe the current trends in the field with different focus aspects. However, a systematic literature review that presents an in-depth comparative study of different applications of machine learning algorithms in the field of SHM of bridges does not exist. Furthermore, there is a lack of analytical studies that investigate the SHM systems in terms of several design considerations including feature extraction techniques, analytical approaches (classification/ regression), operational functionality levels (diagnosis/prognosis) and system implementation techniques (data-driven/model-based). Consequently, this paper identifies 45 recent research practices (during 2016–2023), pertaining to feature extraction techniques and pattern recognition algorithms in SHM for bridges through an SLR process. First, the identified research studies are classified into three different categories: supervised learning algorithms, neural networks and a combination of both. Subsequently, an in-depth analysis of various machine learning algorithms is performed in each category. Moreover, the analysis of selected research studies (total = 45) in terms of feature extraction techniques is made, and 25 different techniques are identified. Furthermore, this article also explores other design considerations like analytical approaches in the pattern recognition process, operational functionality and system implementation. It is expected that the outcomes of this research may facilitate the researchers and practitioners of the domain during the selection of appropriate feature extraction techniques, machine learning algorithms and other design considerations according to the SHM system requirements. [ABSTRACT FROM AUTHOR]

With the exponential growth of data, solving classification or regression tasks by mining time series data has become a research hotspot. Commonly used methods include machine learning, artificial neural networks, and so on. However, these methods only extract the continuous or discrete features of sequences, which have the drawbacks of low information utilization, poor robustness, and computational complexity. To solve these problems, this paper innovatively uses Wasserstein distance instead of Kullback–Leibler divergence and uses it to construct an autoencoder to learn discrete features of time series. Then, a hidden Markov model is used to learn the continuous features of the sequence. Finally, stacking is used to ensemble the two models to obtain the final model. This paper experimentally verifies that the ensemble model has lower computational complexity and is close to state-of-the-art classification accuracy. [ABSTRACT FROM AUTHOR]

Quality inspection in the industrial production field is experiencing a strong technological development that benefits from the combination of vision-based techniques with artificial intelligence algorithms. This paper initially addresses the problem of defect identification for circularly symmetric mechanical components, characterized by the presence of periodic elements. In the specific case of knurled washers, we compare the performances of a standard algorithm for the analysis of grey-scale image with a Deep Learning (DL) approach. The standard algorithm is based on the extraction of pseudo-signals derived from the conversion of the grey scale image of concentric annuli. In the DL approach, the component inspection is shifted from the entire sample to specific areas repeated along the object profile where the defect may occur. The standard algorithm provides better results in terms of accuracy and computational time with respect to the DL approach. Nevertheless, DL reaches accuracy higher than 99% when performance is evaluated targeting the identification of damaged teeth. The possibility of extending the methods and the results to other circularly symmetrical components is analyzed and discussed. [ABSTRACT FROM AUTHOR]

The failure of insulators may seriously threaten the safe operation of the power system, where the state detection of high-voltage insulators is a must for the normal and safe operation of the power system. Based on the data of insulators in aerial images, this work explored an enhanced particle swarm algorithm to optimize the parameters of the support vector machine. A support vector machine model was therefore established for the identification of the normal and defective states of the insulators. This methodology works with the structure minimization principle of SVM and the characteristics of particle swarm fast optimization. First, the aerial insulator image was segmented as a target by way of the seed region growth based on double-layer cascade morphological improvements, and then, HOG features plus GLCM features were extracted as sample data. Finally, an ameliorated PSO-SVM classifier was designed to realize insulator state identification. Comparisons were made between PSO-SVM and conventional machine learning algorithms, SVM and Random Forest, and an optimization algorithm, Gray Wolf Optimization Support Vector Machine (GWO-SVM), and advanced neural network CNN. The experimental results showed that the performance of the algorithm proposed in this paper touched the top level, where the recognition accuracy rate was 92.11%, the precision rate 90%, the recall rate 94.74%, and the F1-score 92.31%. [ABSTRACT FROM AUTHOR]

Indoor 3D positioning is useful in multistory buildings, such as shopping malls, libraries, and airports. This study focuses on indoor 3D positioning using wireless access points (AP) in an environment without adding additional hardware facilities in large-scale complex places. The integration of a deep learning algorithm into indoor 3D positioning is studied, and a 3D dynamic positioning model based on temporal fingerprints is proposed. In contrast to the traditional positioning models with a single input, the proposed method uses a sliding time window to build a temporal fingerprint chip as the input of the positioning model to provide abundant information for positioning. Temporal information can be used to distinguish locations with similar fingerprint vectors and to improve the accuracy and robustness of positioning. Moreover, deep learning has been applied for the automatic extraction of spatiotemporal features. A temporal convolutional network (TCN) feature extractor is proposed in this paper, which adopts a causal convolution mechanism, dilated convolution mechanism, and residual connection mechanism and is not limited by the size of the convolution kernel. It is capable of learning hidden information and spatiotemporal relationships from the input features and the extracted spatiotemporal features are connected with a deep neural network (DNN) regressor to fit the complex nonlinear mapping relationship between the features and position coordinates to estimate the 3D position coordinates of the target. Finally, an open-source public dataset was used to verify the performance of the localization algorithm. Experimental results demonstrated the effectiveness of the proposed positioning model and a comparison between the proposed model and existing models proved that the proposed model can provide more accurate three-dimensional position coordinates. [ABSTRACT FROM AUTHOR]

Monitoring a patient's vital signs is considered one of the most challenging problems in telehealth systems, especially when patients reside in remote locations. Companies now use IoT devices such as wearable devices to participate in telehealth systems. However, the steady adoption of wearables can result in a significant increase in the volume of data being collected and transmitted. As these devices run on limited battery power, they can run out of power quickly due to the high processing requirements of the device for data collection and transmission. Given the importance of medical data, it is imperative that all transmitted data adhere to strict integrity and availability requirements. Reducing the volume of healthcare data and the frequency of transmission can improve a device's battery life via an inference algorithm. Furthermore, this approach creates issues for improving transmission metrics related to accuracy and efficiency, which are traded-off against each other, with increasing accuracy reducing efficiency. This paper demonstrates that machine learning (ML) can be used to overcome the trade-off problem. The damped least-squares algorithm (DLSA) is used to enhance both metrics by taking fewer samples for transmission whilst maintaining accuracy. The algorithm is tested with a standard heart rate dataset to compare the metrics. The results showed that the DLSA provides the best performance, with an efficiency of 3.33 times for reduced sample data size and an accuracy of 95.6%, with similar accuracies observed in seven different sampling cases adopted for testing that demonstrate improved efficiency. This proposed method significantly improve both metrics using ML without sacrificing one metric over the other compared to existing methods with high efficiency. [ABSTRACT FROM AUTHOR]

Vehicle fault detection and diagnosis (VFDD) along with predictive maintenance (PdM) are indispensable for early diagnosis in order to prevent severe accidents due to mechanical malfunction in urban environments. This paper proposes an early voiceprint driving fault identification system using machine learning algorithms for classification. Previous studies have examined driving fault identification, but less attention has focused on using voiceprint features to locate corresponding faults. This research uses 43 different common vehicle mechanical malfunction condition voiceprint signals to construct the dataset. These datasets were filtered by linear predictive coefficient (LPC) and wavelet transform(WT). After the original voiceprint fault sounds were filtered and obtained the main fault characteristics, the deep neural network (DNN), convolutional neural network (CNN), and long short-term memory (LSTM) architectures are used for identification. The experimental results show that the accuracy of the CNN algorithm is the best for the LPC dataset. In addition, for the wavelet dataset, DNN has the best performance in terms of identification performance and training time. After cross-comparison of experimental results, the wavelet algorithm combined with DNN can improve the identification accuracy by up to 16.57% compared with other deep learning algorithms and reduce the model training time by up to 21.5% compared with other algorithms. Realizing the cross-comparison of recognition results through various machine learning methods, it is possible for the vehicle to proactively remind the driver of the real-time potential hazard of vehicle machinery failure. [ABSTRACT FROM AUTHOR]

Light field (LF) image depth estimation is a critical technique for LF-related applications such as 3D reconstruction, target detection, and tracking. The refocusing property of LF images provide rich information for depth estimations; however, it is still challenging in cases of occlusion regions, edge regions, noise interference, etc. The epipolar plane image (EPI) of LF can effectively deal with the depth estimation because of its characteristics of multidirectionality and pixel consistency—in which the LF depth estimations are converted to calculate the EPI slope. This paper proposed an EPI LF depth estimation algorithm based on a directional relationship model and attention mechanism. Unlike the subaperture LF depth estimation method, the proposed method takes EPIs as input images. Specifically, a directional relationship model was used to extract direction features of the horizontal and vertical EPIs, respectively. Then, a multiviewpoint attention mechanism combining channel attention and spatial attention is used to give more weight to the EPI slope information. Subsequently, multiple residual modules are used to eliminate the redundant features that interfere with the EPI slope information—in which a small stride convolution operation is used to avoid losing key EPI slope information. The experimental results revealed that the proposed algorithm outperformed the compared algorithms in terms of accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we present a design method for a wideband non-uniformly spaced linear array (NUSLA), with both symmetric and asymmetric geometries, using the modified reinforcement learning algorithm (MORELA). We designed a cost function that provided freedom to the beam pattern by setting limits only on the beam width (BW) and side-lobe level (SLL) in order to satisfy the desired BW and SLL in the wide band. We added the scan angle condition to the cost function to design the scanned beam pattern, as the ability to scan a beam in the desired direction is important in various applications. In order to prevent possible pointing angle errors for asymmetric NUSLA, we employed a penalty function to ensure the peak at the desired direction. Modified reinforcement learning algorithm (MORELA), which is a reinforcement learning-based algorithm used to determine a global optimum of the cost function, is applied to optimize the spacing and weights of the NUSLA by minimizing the proposed cost function. The performance of the proposed scheme was verified by comparing it with that of existing heuristic optimization algorithms via computer simulations. [ABSTRACT FROM AUTHOR]

Remote monitoring of bearing conditions, using wireless sensor network (WSN), is a developing trend in the industrial field. In complicated industrial environments, WSN face three main constraints: low energy, less memory, and low operational capability. Conventional data-compression methods, which concentrate on data compression only, cannot overcome these limitations. Aiming at these problems, this paper proposed a compressed data acquisition and reconstruction scheme based on Compressed Sensing (CS) which is a novel signal-processing technique and applied it for bearing conditions monitoring via WSN. The compressed data acquisition is realized by projection transformation and can greatly reduce the data volume, which needs the nodes to process and transmit. The reconstruction of original signals is achieved in the host computer by complicated algorithms. The bearing vibration signals not only exhibit the sparsity property, but also have specific structures. This paper introduced the block sparse Bayesian learning (BSBL) algorithm which works by utilizing the block property and inherent structures of signals to reconstruct CS sparsity coefficients of transform domains and further recover the original signals. By using the BSBL, CS reconstruction can be improved remarkably. Experiments and analyses showed that BSBL method has good performance and is suitable for practical bearing-condition monitoring. [ABSTRACT FROM AUTHOR]

The problems of the neural network-based nonuniformity correction algorithm for infrared focal plane arrays mainly concern slow convergence speed and ghosting artifacts. In general, the more stringent the inhibition of ghosting, the slower the convergence speed. The factors that affect these two problems are the estimated desired image and the learning rate. In this paper, we propose a learning rate rule that combines adaptive threshold edge detection and a temporal gate. Through the noise estimation algorithm, the adaptive spatial threshold is related to the residual nonuniformity noise in the corrected image. The proposed learning rate is used to effectively and stably suppress ghosting artifacts without slowing down the convergence speed. The performance of the proposed technique was thoroughly studied with infrared image sequences with both simulated nonuniformity and real nonuniformity. The results show that the deghosting performance of the proposed method is superior to that of other neural network-based nonuniformity correction algorithms and that the convergence speed is equivalent to the tested deghosting methods. [ABSTRACT FROM AUTHOR]

We live in a period when smart devices gather a large amount of data from a variety of sensors and it is often the case that decisions are taken based on them in a more or less autonomous manner. Still, many of the inputs do not prove to be essential in the decision-making process; hence, it is of utmost importance to find the means of eliminating the noise and concentrating on the most influential attributes. In this sense, we put forward a method based on the swarm intelligence paradigm for extracting the most important features from several datasets. The thematic of this paper is a novel implementation of an algorithm from the swarm intelligence branch of the machine learning domain for improving feature selection. The combination of machine learning with the metaheuristic approaches has recently created a new branch of artificial intelligence called learnheuristics. This approach benefits both from the capability of feature selection to find the solutions that most impact on accuracy and performance, as well as the well known characteristic of swarm intelligence algorithms to efficiently comb through a large search space of solutions. The latter is used as a wrapper method in feature selection and the improvements are significant. In this paper, a modified version of the salp swarm algorithm for feature selection is proposed. This solution is verified by 21 datasets with the classification model of K-nearest neighborhoods. Furthermore, the performance of the algorithm is compared to the best algorithms with the same test setup resulting in better number of features and classification accuracy for the proposed solution. Therefore, the proposed method tackles feature selection and demonstrates its success with many benchmark datasets. [ABSTRACT FROM AUTHOR]

A novel classification model, named the quantum-behaved particle swarm optimization (QPSO)-based weighted multiple kernel extreme learning machine (QWMK-ELM), is proposed in this paper. Experimental validation is carried out with two different electronic nose (e-nose) datasets. Being different from the existing multiple kernel extreme learning machine (MK-ELM) algorithms, the combination coefficients of base kernels are regarded as external parameters of single-hidden layer feedforward neural networks (SLFNs). The combination coefficients of base kernels, the model parameters of each base kernel, and the regularization parameter are optimized by QPSO simultaneously before implementing the kernel extreme learning machine (KELM) with the composite kernel function. Four types of common single kernel functions (Gaussian kernel, polynomial kernel, sigmoid kernel, and wavelet kernel) are utilized to constitute different composite kernel functions. Moreover, the method is also compared with other existing classification methods: extreme learning machine (ELM), kernel extreme learning machine (KELM), k-nearest neighbors (KNN), support vector machine (SVM), multi-layer perceptron (MLP), radical basis function neural network (RBFNN), and probabilistic neural network (PNN). The results have demonstrated that the proposed QWMK-ELM outperforms the aforementioned methods, not only in precision, but also in efficiency for gas classification. [ABSTRACT FROM AUTHOR]

This paper develops a new hybrid, open-source, cross-platform 3D smart home simulator, OpenSHS, for dataset generation. OpenSHS offers an opportunity for researchers in the field of the Internet of Things (IoT) and machine learning to test and evaluate their models. Following a hybrid approach, OpenSHS combines advantages from both interactive and model-based approaches. This approach reduces the time and efforts required to generate simulated smart home datasets. We have designed a replication algorithm for extending and expanding a dataset. A small sample dataset produced, by OpenSHS, can be extended without affecting the logical order of the events. The replication provides a solution for generating large representative smart home datasets. We have built an extensible library of smart devices that facilitates the simulation of current and future smart home environments. Our tool divides the dataset generation process into three distinct phases: first design: the researcher designs the initial virtual environment by building the home, importing smart devices and creating contexts; second, simulation: the participant simulates his/her context-specific events; and third, aggregation: the researcher applies the replication algorithm to generate the final dataset. We conducted a study to assess the ease of use of our tool on the System Usability Scale (SUS). [ABSTRACT FROM AUTHOR]

The algorithm and the results of a nonlinear detector using a machine learning technique called support vector machine (SVM) on an efficient modulation system with high data rate and low energy consumption is presented in this paper. Simulation results showed that the performance achieved by the SVM detector is comparable to that of a conventional threshold decision (TD) detector. The two detectors detect the received signals together with the special impacting filter (SIF) that can improve the energy utilization efficiency. However, unlike the TD detector, the SVM detector concentrates not only on reducing the BER of the detector, but also on providing accurate posterior probability estimates (PPEs), which can be used as soft-inputs of the LDPC decoder. The complexity of this detector is considered in this paper by using four features and simplifying the decision function. In addition, a bandwidth efficient transmission is analyzed with both SVM and TD detector. The SVM detector is more robust to sampling rate than TD detector. We find that the SVM is suitable for extended binary phase shift keying (EBPSK) signal detection and can provide accurate posterior probability for LDPC decoding. [ABSTRACT FROM AUTHOR]

In the era of mobile internet, Location Based Services (LBS) have developed dramatically. Seamless Indoor and Outdoor Navigation and Localization (SNAL) has attracted a lot of attention. No single positioning technology was capable of meeting the various positioning requirements in different environments. Selecting different positioning techniques for different environments is an alternative method. Detecting the users' current environment is crucial for this technique. In this paper, we proposed to detect the indoor/outdoor environment automatically without high energy consumption. The basic idea was simple: we applied a machine learning algorithm to classify the neighboring Global System for Mobile (GSM) communication cellular base station's signal strength in different environments, and identified the users' current context by signal pattern recognition. We tested the algorithm in four different environments. The results showed that the proposed algorithm was capable of identifying open outdoors, semi-outdoors, light indoors and deep indoors environments with 100% accuracy using the signal strength of four nearby GSM stations. The required hardware and signal are widely available in our daily lives, implying its high compatibility and availability. [ABSTRACT FROM AUTHOR]

The size of one's pupil can indicate one's physical condition and mental state. When we search related papers about AI and the pupil, most studies focused on eye-tracking. This paper proposes an algorithm that can calculate pupil size based on a convolution neural network (CNN). Usually, the shape of the pupil is not round, and 50% of pupils can be calculated using ellipses as the best fitting shapes. This paper uses the major and minor axes of an ellipse to represent the size of pupils and uses the two parameters as the output of the network. Regarding the input of the network, the dataset is in video format (continuous frames). Taking each frame from the videos and using these to train the CNN model may cause overfitting since the images are too similar. This study used data augmentation and calculated the structural similarity to ensure that the images had a certain degree of difference to avoid this problem. For optimizing the network structure, this study compared the mean error with changes in the depth of the network and the field of view (FOV) of the convolution filter. The result shows that both deepening the network and widening the FOV of the convolution filter can reduce the mean error. According to the results, the mean error of the pupil length is 5.437% and the pupil area is 10.57%. It can operate in low-cost mobile embedded systems at 35 frames per second, demonstrating that low-cost designs can be used for pupil size prediction. [ABSTRACT FROM AUTHOR]

During the processing and planting of soybeans, it is greatly significant that a reliable, rapid, and accurate technique is used to detect soybean varieties. Traditional chemical analysis methods of soybean variety sampling (e.g., mass spectrometry and high-performance liquid chromatography) are destructive and time-consuming. In this paper, a robust and accurate method for nondestructive soybean classification is developed through hyperspectral imaging and ensemble machine learning algorithms. Image acquisition, preprocessing, and feature selection are used to obtain different types of soybean hyperspectral features. Based on these features, one of ensemble classifiers-random subspace linear discriminant (RSLD) algorithm is used to classify soybean seeds. Compared with the linear discrimination (LD) and linear support vector machine (LSVM) methods, the results show that the RSLD algorithm in this paper is more stable and reliable. In classifying soybeans in 10, 15, 20, and 25 categories, the RSLD method achieves the highest classification accuracy. When 155 features are used to classify 15 types of soybeans, the classification accuracy of the RSLD method reaches 99.2%, while the classification accuracies of the LD and LSVM methods are only 98.6% and 69.7%, respectively. Therefore, the ensemble classification algorithm RSLD can maintain high classification accuracy when different types and different classification features are used. [ABSTRACT FROM AUTHOR]

Copper is an important national resource, which is widely used in various sectors of the national economy. The traditional detection of copper content in copper ore has the disadvantages of being time-consuming and high cost. Due to the many drawbacks of traditional detection methods, this paper proposes a new method for detecting copper content in copper ore, that is, through the spectral information of copper ore content detection method. First of all, we use chemical methods to analyze the copper content in a batch of copper ores, and accurately obtain the copper content in those ores. Then we do spectrometric tests on this batch of copper ore, and get accurate spectral data of copper ore. Based on the data obtained, we propose a new two hidden layer extreme learning machine algorithm with variable hidden layer nodes and use the regularization standard to constrain the extreme learning machine. Finally, the prediction model of copper content in copper ore is established by using the algorithm. Experiments show that this method of detecting copper ore content using spectral information is completely feasible, and the algorithm proposed in this paper can detect the copper content in copper ores faster and more accurately. [ABSTRACT FROM AUTHOR]

Generative adversarial network (GAN) has been regarded as a promising solution to many machine learning problems, and it comprises of a generator and discriminator, determining patterns and anomalies in the input data. However, GANs have several common failure modes. Typically, a mode collapse occurs when a GAN fails to fit the set optimizations and leads to several instabilities in the generative model, diminishing the capability to generate new content regardless of the dataset. In this paper, we study conditional limiter solutions for mode collapse for the Intrusion Detection System (IDS) Control Flow GAN (ICF-GAN) model. Specifically, the ICF-GAN's mode collapse instances are limited by a mini-batch method that significantly improves the model accuracy. Performance evaluation is conducted using numerical results obtained from experiments. [ABSTRACT FROM AUTHOR]

Pyroelectric infrared (PIR) sensors are widely used as a presence trigger, but the analog output of PIR sensors depends on several other aspects, including the distance of the body from the PIR sensor, the direction and speed of movement, the body shape and gait. In this paper, we present an empirical study of human movement detection and identification using a set of PIR sensors. We have developed a data collection module having two pairs of PIR sensors orthogonally aligned and modified Fresnel lenses. We have placed three PIR-based modules in a hallway for monitoring people; one module on the ceiling; two modules on opposite walls facing each other. We have collected a data set from eight subjects when walking in three different conditions: two directions (back and forth), three distance intervals (close to one wall sensor, in the middle, close to the other wall sensor) and three speed levels (slow, moderate, fast). We have used two types of feature sets: a raw data set and a reduced feature set composed of amplitude and time to peaks; and passage duration extracted from each PIR sensor. We have performed classification analysis with well-known machine learning algorithms, including instance-based learning and support vector machine. Our findings show that with the raw data set captured from a single PIR sensor of each of the three modules, we could achieve more than 92% accuracy in classifying the direction and speed of movement, the distance interval and identifying subjects. We could also achieve more than 94% accuracy in classifying the direction, speed and distance and identifying subjects using the reduced feature set extracted from two pairs of PIR sensors of each of the three modules. [ABSTRACT FROM AUTHOR]

An accurate step length estimation can provide valuable information to different applications such as indoor positioning systems or it can be helpful when analyzing the gait of a user, which can then be used to detect various gait impairments that lead to a reduced step length (caused by e.g., Parkinson's disease or multiple sclerosis). In this paper, we focus on the estimation of the step length using machine learning techniques that could be used in an indoor positioning system. Previous step length algorithms tried to model the length of a step based on measurements from the accelerometer and some tuneable (user-specific) parameters. Machine-learning-based step length estimation algorithms eliminate these parameters to be tuned. Instead, to adapt these algorithms to different users, it suffices to provide examples of the length of multiple steps for different persons to the machine learning algorithm, so that in the training phase the algorithm can learn to predict the step length for different users. Until now, these machine learning algorithms were trained with features that were chosen intuitively. In this paper, we consider a systematic feature selection algorithm to be able to determine the features from a large collection of features, resulting in the best performance. This resulted in a step length estimator with a mean absolute error of 3.48 cm for a known test person and 4.19 cm for an unknown test person, while current state-of-the-art machine-learning-based step length estimators resulted in a mean absolute error of 4.94 cm and 6.27 cm for respectively a known and unknown test person. [ABSTRACT FROM AUTHOR]

Following the continuous development of the information technology, the concept of dense urban networks has evolved as well. The powerful tools, like machine learning, break new ground in smart network and interface design. In this paper the concept of using deep learning for estimating the radio channel parameters of the LTE (Long Term Evolution) radio interface is presented. It was proved that the deep learning approach provides a significant gain (almost 40%) with 10.7% compared to the linear model with the lowest RMSE (Root Mean Squared Error) 17.01%. The solution can be adopted as a part of the data allocation algorithm implemented in the telemetry devices equipped with the 4G radio interface, or, after the adjustment, the NB-IoT (Narrowband Internet of Things), to maximize the reliability of the services in harsh indoor or urban environments. Presented results also prove the existence of the inverse proportional dependence between the number of hidden layers and the number of historical samples in terms of the obtained RMSE. The increase of the historical data memory allows using models with fewer hidden layers while maintaining a comparable RMSE value for each scenario, which reduces the total computational cost. [ABSTRACT FROM AUTHOR]

Iris biometric detection provides contactless authentication, preventing the spread of COVID-19-like contagious diseases. However, these systems are prone to spoofing attacks attempted with the help of contact lenses, replayed video, and print attacks, making them vulnerable and unsafe. This paper proposes the iris liveness detection (ILD) method to mitigate spoofing attacks, taking global-level features of Thepade's sorted block truncation coding (TSBTC) and local-level features of the gray-level co-occurrence matrix (GLCM) of the iris image. Thepade's SBTC extracts global color texture content as features, and GLCM extracts local fine-texture details. The fusion of global and local content presentation may help distinguish between live and non-live iris samples. The fusion of Thepade's SBTC with GLCM features is considered in experimental validations of the proposed method. The features are used to train nine assorted machine learning classifiers, including naïve Bayes (NB), decision tree (J48), support vector machine (SVM), random forest (RF), multilayer perceptron (MLP), and ensembles (SVM + RF + NB, SVM + RF + RT, RF + SVM + MLP, J48 + RF + MLP) for ILD. Accuracy, precision, recall, and F-measure are used to evaluate the performance of the projected ILD variants. The experimentation was carried out on four standard benchmark datasets, and our proposed model showed improved results with the feature fusion approach. The proposed fusion approach gave 99.68% accuracy using the RF + J48 + MLP ensemble of classifiers, immediately followed by the RF algorithm, which gave 95.57%. The better capability of iris liveness detection will improve human–computer interaction and security in the cyber-physical space by improving person validation. [ABSTRACT FROM AUTHOR]

Multi-sensor fusion intends to boost the general reliability of a decision-making procedure or allow one sensor to compensate for others' shortcomings. This field has been so prominent that authors have proposed many different fusion approaches, or "architectures" as we call them when they are structurally different, so it is now challenging to prescribe which one is better for a specific collection of sensors and a particular application environment, other than by trial and error. We propose an approach capable of predicting the best fusion architecture (from predefined options) for a given dataset. This method involves the construction of a meta-dataset where statistical characteristics from the original dataset are extracted. One challenge is that each dataset has a different number of variables (columns). Previous work took the principal component analysis's first k components to make the meta-dataset columns coherent and trained machine learning classifiers to predict the best fusion architecture. In this paper, we take a new route to build the meta-dataset. We use the Sequential Forward Floating Selection algorithm and a T transform to reduce the features and match them to a given number, respectively. Our findings indicate that our proposed method could improve the accuracy in predicting the best sensor fusion architecture for multiple domains. [ABSTRACT FROM AUTHOR]

Critical Infrastructures (CIs) are sensible targets. They could be physically damaged by natural or human actions, causing service disruptions, economic losses, and, in some extreme cases, harm to people. They, therefore, need a high level of protection against possible unintentional and intentional events. In this paper, we show a logical architecture that exploits information from both physical and cybersecurity systems to improve the overall security in a power plant scenario. We propose a Machine Learning (ML)-based anomaly detection approach to detect possible anomaly events by jointly correlating data related to both the physical and cyber domains. The performance evaluation showed encouraging results—obtained by different ML algorithms—which highlights how our proposed approach is able to detect possible abnormal situations that could not have been detected by using only information from either the physical or cyber domain. [ABSTRACT FROM AUTHOR]

Classification is one of the data mining problems receiving enormous attention in the database community. Although artificial neural networks (ANNs) have been successfully applied in a wide range of machine learning applications, they are however often regarded as black boxes, i.e., their predictions cannot be explained. To enhance the explanation of ANNs, a novel algorithm to extract symbolic rules from ANNs has been proposed in this paper. ANN methods have not been effectively utilized for data mining tasks because how the classifications were made is not explicitly stated as symbolic rules that are suitable for verification or interpretation by human experts. With the proposed approach, concise symbolic rules with high accuracy, that are easily explainable, can be extracted from the trained ANNs. Extracted rules are comparable with other methods in terms of number of rules, average number of conditions for a rule, and the accuracy. The effectiveness of the proposed approach is clearly demonstrated by the experimental results on a set of benchmark data mining classification problems. [ABSTRACT FROM AUTHOR]

Capability assessment plays a crucial role in the demonstration and construction of equipment. To improve the accuracy and stability of capability assessment, we study the neural network learning algorithms in the field of capability assessment and index sensitivity. Aiming at the problem of overfitting and parameter optimization in neural network learning, the paper proposes an improved machine learning algorithm—the Ensemble Learning Based on Policy Optimization Neural Networks (ELPONN) with the policy optimization and ensemble learning. This algorithm presents an optimized neural network learning algorithm through different strategies evolution, and builds an ensemble learning model of multi-intelligent algorithms to assess the capability and analyze the sensitivity of the indexes. Through the assessment of capabilities, the algorithm effectively avoids parameter optimization from entering the minimum point in performance to improve the accuracy of equipment capability assessment, which is significantly better than previous neural network assessment methods. The experimental results show that the mean relative error is 4.10%, which is better than BP, GABP, and early stopping. The ELPONN algorithm has better accuracy and stability performance, and meets the requirements of capability assessment. [ABSTRACT FROM AUTHOR]

In machine learning and data science, feature selection is considered as a crucial step of data preprocessing. When we directly apply the raw data for classification or clustering purposes, sometimes we observe that the learning algorithms do not perform well. One possible reason for this is the presence of redundant, noisy, and non-informative features or attributes in the datasets. Hence, feature selection methods are used to identify the subset of relevant features that can maximize the model performance. Moreover, due to reduction in feature dimension, both training time and storage required by the model can be reduced as well. In this paper, we present a tri-stage wrapper-filter-based feature selection framework for the purpose of medical report-based disease detection. In the first stage, an ensemble was formed by four filter methods—Mutual Information, ReliefF, Chi Square, and Xvariance—and then each feature from the union set was assessed by three classification algorithms—support vector machine, naïve Bayes, and k-nearest neighbors—and an average accuracy was calculated. The features with higher accuracy were selected to obtain a preliminary subset of optimal features. In the second stage, Pearson correlation was used to discard highly correlated features. In these two stages, XGBoost classification algorithm was applied to obtain the most contributing features that, in turn, provide the best optimal subset. Then, in the final stage, we fed the obtained feature subset to a meta-heuristic algorithm, called whale optimization algorithm, in order to further reduce the feature set and to achieve higher accuracy. We evaluated the proposed feature selection framework on four publicly available disease datasets taken from the UCI machine learning repository, namely, arrhythmia, leukemia, DLBCL, and prostate cancer. Our obtained results confirm that the proposed method can perform better than many state-of-the-art methods and can detect important features as well. Less features ensure less medical tests for correct diagnosis, thus saving both time and cost. [ABSTRACT FROM AUTHOR]

A low-cost machine learning (ML) algorithm is proposed and discussed for spatial tracking of unknown, correlated signals in localized, ad-hoc wireless sensor networks. Each sensor is modeled as one neuron and a selected subset of these neurons are called to identify the spatial signal. The algorithm is implemented in two phases of spatial modeling and spatial tracking. The spatial signal is modeled using its M iso-contour lines at levels { ℓ j } j = 1 M and those sensors that their sensor observations are in Δ margin of any of these levels report their sensor observations to the fusion center (FC) for spatial signal reconstruction. In spatial modeling phase, the number of these contour lines, their levels and a proper Δ are identified. In this phase, the algorithm may either use adaptive-weight stochastic gradient or scaled stochastic gradient method to select a proper Δ. Additive white Gaussian noise (AWGN) with zero mean is assumed along with the sensor observations. To reduce the observation noise's effect, each sensor applies moving average filter on its observation to drastically reduce the effect of noise. The modeling performance, the cost and the convergence of the algorithm are discussed based on extensive computer simulations and reasoning. The algorithm is proposed for climate and environmental monitoring. In this paper, the percentage of wireless sensors that initiate a communication attempt is assumed as cost. The performance evaluation results show that the proposed spatial tracking approach is low-cost and can model the spatial signal over time with the same performance as that of spatial modeling. [ABSTRACT FROM AUTHOR]

Wireless Sensor Networks (WSNs) continue to face two major challenges: energy and security. As a consequence, one of the WSN-related security tasks is to protect them from Denial of Service (DoS) and Distributed DoS (DDoS) attacks. Machine learning-based systems are the only viable option for these types of attacks, as traditional packet deep scan systems depend on open field inspection in transport layer security packets and the open field encryption trend. Moreover, network data traffic will become more complex due to increases in the amount of data transmitted between WSN nodes as a result of increasing usage in the future. Therefore, there is a need to use feature selection techniques with machine learning in order to determine which data in the DoS detection process are most important. This paper examined techniques for improving DoS anomalies detection along with power reservation in WSNs to balance them. A new clustering technique was introduced, called the CH_Rotations algorithm, to improve anomaly detection efficiency over a WSN's lifetime. Furthermore, the use of feature selection techniques with machine learning algorithms in examining WSN node traffic and the effect of these techniques on the lifetime of WSNs was evaluated. The evaluation results showed that the Water Cycle (WC) feature selection displayed the best average performance accuracy of 2%, 5%, 3%, and 3% greater than Particle Swarm Optimization (PSO), Simulated Annealing (SA), Harmony Search (HS), and Genetic Algorithm (GA), respectively. Moreover, the WC with Decision Tree (DT) classifier showed 100% accuracy with only one feature. In addition, the CH_Rotations algorithm improved network lifetime by 30% compared to the standard LEACH protocol. Network lifetime using the WC + DT technique was reduced by 5% compared to other WC + DT-free scenarios. [ABSTRACT FROM AUTHOR]

Exhaled breath analysis has become more and more popular as a supplementary tool for medical diagnosis. However, the number of variables that have to be taken into account forces researchers to develop novel algorithms for proper data interpretation. This paper presents a system for analyzing exhaled air with the use of various sensors. Breath simulations with acetone as a diabetes biomarker were performed using the proposed e-nose system. The XGBoost algorithm for diabetes detection based on artificial breath analysis is presented. The results have shown that the designed system based on the XGBoost algorithm is highly selective for acetone, even at low concentrations. Moreover, in comparison with other commonly used algorithms, it was shown that XGBoost exhibits the highest performance and recall. [ABSTRACT FROM AUTHOR]

In this paper, we propose a prediction algorithm, the combination of Long Short-Term Memory (LSTM) and attention model, based on machine learning models to predict the vision coordinates when watching 360-degree videos in a Virtual Reality (VR) or Augmented Reality (AR) system. Predicting the vision coordinates while video streaming is important when the network condition is degraded. However, the traditional prediction models such as Moving Average (MA) and Autoregression Moving Average (ARMA) are linear so they cannot consider the nonlinear relationship. Therefore, machine learning models based on deep learning are recently used for nonlinear predictions. We use the Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural network methods, originated in Recurrent Neural Networks (RNN), and predict the head position in the 360-degree videos. Therefore, we adopt the attention model to LSTM to make more accurate results. We also compare the performance of the proposed model with the other machine learning models such as Multi-Layer Perceptron (MLP) and RNN using the root mean squared error (RMSE) of predicted and real coordinates. We demonstrate that our model can predict the vision coordinates more accurately than the other models in various videos. [ABSTRACT FROM AUTHOR]

To solve the problems of low accuracy, low real-time performance, poor robustness and others caused by the complex environment, this paper proposes a face mask recognition and standard wear detection algorithm based on the improved YOLO-v4. Firstly, an improved CSPDarkNet53 is introduced into the trunk feature extraction network, which reduces the computing cost of the network and improves the learning ability of the model. Secondly, the adaptive image scaling algorithm can reduce computation and redundancy effectively. Thirdly, the improved PANet structure is introduced so that the network has more semantic information in the feature layer. At last, a face mask detection data set is made according to the standard wearing of masks. Based on the object detection algorithm of deep learning, a variety of evaluation indexes are compared to evaluate the effectiveness of the model. The results of the comparations show that the mAP of face mask recognition can reach 98.3% and the frame rate is high at 54.57 FPS, which are more accurate compared with the exiting algorithm. [ABSTRACT FROM AUTHOR]

Technologies and services towards smart-vehicles and Intelligent-Transportation-Systems (ITS), continues to revolutionize many aspects of human life. This paper presents a detailed survey of current techniques and advancements in Automatic-Number-Plate-Recognition (ANPR) systems, with a comprehensive performance comparison of various real-time tested and simulated algorithms, including those involving computer vision (CV). ANPR technology has the ability to detect and recognize vehicles by their number-plates using recognition techniques. Even with the best algorithms, a successful ANPR system deployment may require additional hardware to maximize its accuracy. The number plate condition, non-standardized formats, complex scenes, camera quality, camera mount position, tolerance to distortion, motion-blur, contrast problems, reflections, processing and memory limitations, environmental conditions, indoor/outdoor or day/night shots, software-tools or other hardware-based constraint may undermine its performance. This inconsistency, challenging environments and other complexities make ANPR an interesting field for researchers. The Internet-of-Things is beginning to shape future of many industries and is paving new ways for ITS. ANPR can be well utilized by integrating with RFID-systems, GPS, Android platforms and other similar technologies. Deep-Learning techniques are widely utilized in CV field for better detection rates. This research aims to advance the state-of-knowledge in ITS (ANPR) built on CV algorithms; by citing relevant prior work, analyzing and presenting a survey of extraction, segmentation and recognition techniques whilst providing guidelines on future trends in this area. [ABSTRACT FROM AUTHOR]

The unique features of millimeter waves (mmWaves) motivate its leveraging to future, beyond-fifth-generation/sixth-generation (B5G/6G)-based device-to-device (D2D) communications. However, the neighborhood discovery and selection (NDS) problem still needs intelligent solutions due to the trade-off of investigating adjacent devices for the optimum device choice against the crucial beamform training (BT) overhead. In this paper, by making use of multiband (μW/mmWave) standard devices, the mmWave NDS problem is addressed using machine-learning-based contextual multi-armed bandit (CMAB) algorithms. This is done by leveraging the context information of Wi-Fi signal characteristics, i.e., received signal strength (RSS), mean, and variance, to further improve the NDS method. In this setup, the transmitting device acts as the player, the arms are the candidate mmWave D2D links between that device and its neighbors, while the reward is the average throughput. We examine the NDS's primary trade-off and the impacts of the contextual information on the total performance. Furthermore, modified energy-aware linear upper confidence bound (EA-LinUCB) and contextual Thomson sampling (EA-CTS) algorithms are proposed to handle the problem through reflecting the nearby devices' withstanding battery levels, which simulate real scenarios. Simulation results ensure the superior efficiency of the proposed algorithms over the single band (mmWave) energy-aware noncontextual MAB algorithms (EA-UCB and EA-TS) and traditional schemes regarding energy efficiency and average throughput with a reasonable convergence rate. [ABSTRACT FROM AUTHOR]

How to operate an unmanned aerial vehicle (UAV) safely and efficiently in an interactive environment is challenging. A large amount of research has been devoted to improve the intelligence of a UAV while performing a mission, where finding an optimal maneuver decision-making policy of the UAV has become one of the key issues when we attempt to enable the UAV autonomy. In this paper, we propose a maneuver decision-making algorithm based on deep reinforcement learning, which generates efficient maneuvers for a UAV agent to execute the airdrop mission autonomously in an interactive environment. Particularly, the training set of the learning algorithm by the Prioritized Experience Replay is constructed, that can accelerate the convergence speed of decision network training in the algorithm. It is shown that a desirable and effective maneuver decision-making policy can be found by extensive experimental results. [ABSTRACT FROM AUTHOR]

Learning accurate Bayesian Network (BN) structures of high-dimensional and sparse data is difficult because of high computation complexity. To learn the accurate structure for high-dimensional and sparse data faster, this paper adopts a divide and conquer strategy and proposes a block learning algorithm with a mutual information based K-means algorithm (BLMKM algorithm). This method utilizes an improved K-means algorithm to block the nodes in BN and a maximum minimum parents and children (MMPC) algorithm to obtain the whole skeleton of BN and find possible graph structures based on separated blocks. Then, a pruned dynamic programming algorithm is performed sequentially for all possible graph structures to get possible BNs and find the best BN by scoring function. Experiments show that for high-dimensional and sparse data, the BLMKM algorithm can achieve the same accuracy in a reasonable time compared with non-blocking classical learning algorithms. Compared to the existing block learning algorithms, the BLMKM algorithm has a time advantage on the basis of ensuring accuracy. The analysis of the real radar effect mechanism dataset proves that BLMKM algorithm can quickly establish a global and accurate causality model to find the cause of interference, predict the detecting result, and guide the parameters optimization. BLMKM algorithm is efficient for BN learning and has practical application value. [ABSTRACT FROM AUTHOR]

Human motion analysis using a smartphone-embedded accelerometer sensor provided important context for the identification of static, dynamic, and complex sequence of activities. Research in smartphone-based motion analysis are implemented for tasks, such as health status monitoring, fall detection and prevention, energy expenditure estimation, and emotion detection. However, current methods, in this regard, assume that the device is tightly attached to a pre-determined position and orientation, which might cause performance degradation in accelerometer data due to changing orientation. Therefore, it is challenging to accurately and automatically identify activity details as a result of the complexity and orientation inconsistencies of the smartphone. Furthermore, the current activity identification methods utilize conventional machine learning algorithms that are application dependent. Moreover, it is difficult to model the hierarchical and temporal dynamic nature of the current, complex, activity identification process. This paper aims to propose a deep stacked autoencoder algorithm, and orientation invariant features, for complex human activity identification. The proposed approach is made up of various stages. First, we computed the magnitude norm vector and rotation feature (pitch and roll angles) to augment the three-axis dimensions (3-D) of the accelerometer sensor. Second, we propose a deep stacked autoencoder based deep learning algorithm to automatically extract compact feature representation from the motion sensor data. The results show that the proposed integration of the deep learning algorithm, and orientation invariant features, can accurately recognize complex activity details using only smartphone accelerometer data. The proposed deep stacked autoencoder method achieved 97.13% identification accuracy compared to the conventional machine learning methods and the deep belief network algorithm. The results suggest the impact of the proposed method to improve a smartphone-based complex human activity identification framework. [ABSTRACT FROM AUTHOR]