Search

Real-time computation tasks in vehicular edge computing (VEC) provide convenience for vehicle users. However, the efficiency of task offloading seriously affects the quality of service (QoS). The predictive-mode task offloading is limited by computation resources, storage resources and the timeliness of vehicle trajectory data. Meanwhile, machine learning is difficult to deploy on edge servers. In this paper, we propose a vehicle trajectory prediction method based on the vehicle frequent pattern for task offloading in VEC. First, in the initialization stage, a T-pattern prediction tree (TPPT) is constructed based on the historical vehicle trajectory data. Secondly, when predicting the vehicle trajectory, the vehicle frequent itemset with the largest vehicle trajectory support is found in the vehicle frequent itemset of the TPPT. Finally, in the update stage, the TPPT is updated in real time with the predicted vehicle trajectory results. Meanwhile, based on the proposed prediction method, the strategies of task offloading and optimization algorithm are designed to minimize energy consumption with time constraints. The experiments are carried out on real-vehicle datasets and the Capital Bikeshare datasets. The results show that compared with the baseline T-pattern method, the accuracy of the prediction method is improved by more than 10% and the prediction efficiency is improved by more than 6.5 times. The vehicle trajectory prediction method based on the vehicle frequent pattern has high accuracy and prediction efficiency, which can solve the problem of vehicle trajectory prediction for task offloading. [ABSTRACT FROM AUTHOR]

A brief summary of the content associated with each of the chosen papers belonging to the Special Issue is given as follows: Advanced, vibration-based fault diagnosis and vibration control methods for mechanical and electrical systems should be useful for condition monitoring and vibration control designs. Kuo et al. [[8]] conducted a vibration test, conversion, and analysis of the signals, using characteristic extraction and machine learning with neural networks to obtain the failure mode diagnosis of a rotor-bearing system. Fault diagnosis and vibration control are the tracking of any aspect of an industry mechanical components' performance using reliably measured data and analytical simulations in conjunction with the heuristic experience, so that the current and expected future performance of the machine for at least the most critical limit events can be described in a proactive manner. Despite a lot of advancement in the field of fault diagnosis and vibration control methods, the advanced industry faces the following challenges while developing accurate fault diagnosis solutions. [Extracted from the article]

The integration of wearable sensor technology and machine learning algorithms has significantly transformed the field of intelligent medical rehabilitation. These innovative technologies enable the collection of valuable movement, muscle, or nerve data during the rehabilitation process, empowering medical professionals to evaluate patient recovery and predict disease development more efficiently. This systematic review aims to study the application of wearable sensor technology and machine learning algorithms in different disease rehabilitation training programs, obtain the best sensors and algorithms that meet different disease rehabilitation conditions, and provide ideas for future research and development. A total of 1490 studies were retrieved from two databases, the Web of Science and IEEE Xplore, and finally 32 articles were selected. In this review, the selected papers employ different wearable sensors and machine learning algorithms to address different disease rehabilitation problems. Our analysis focuses on the types of wearable sensors employed, the application of machine learning algorithms, and the approach to rehabilitation training for different medical conditions. It summarizes the usage of different sensors and compares different machine learning algorithms. It can be observed that the combination of these two technologies can optimize the disease rehabilitation process and provide more possibilities for future home rehabilitation scenarios. Finally, the present limitations and suggestions for future developments are presented in the study. [ABSTRACT FROM AUTHOR]

In low-voltage distribution systems, the load types are complex, so traditional detection methods cannot effectively identify series arc faults. To address this problem, this paper proposes an arc fault detection method based on multimodal feature fusion. Firstly, the different mode features of the current signal are extracted by mathematical statistics, Fourier transform, wavelet packet transform, and continuous wavelet transform. The different modal features include one-dimensional features, such as time-domain features, frequency-domain features, and wavelet packet energy features, and two-dimensional features of time-spectrum images. Secondly, the extracted features are preprocessed and prioritized for importance based on different machine learning algorithms to improve the feature data quality. The features of higher importance are input into an arc fault detection model. Finally, an arc fault detection model is constructed based on a one-dimensional convolutional network and a deep residual shrinkage network to achieve high accuracy. The proposed detection method has higher detection accuracy and better performance compared with the arc fault detection method based on single-mode features. [ABSTRACT FROM AUTHOR]

In this paper, a novel railway track monitoring approach is proposed that employs acceleration responses measured on an in-service train to detect the loss of stiffness in the track sub-layers. An Artificial Neural Network (ANN) algorithm is developed that works with the energies of the train acceleration responses. A numerical model of a half-car train coupled with a track profile is employed to simulate the train vertical acceleration. The energy of acceleration signals measured from 100 traversing trains is used to train the ANN for healthy track conditions. The energy is calculated every 15 m along the track, each of which is called a slice. In the monitoring phase, the trained ANN is used to predict the energies of a set of train crossings. The predicted energies are compared with the simulated ones and represented as the prediction error. The damage is modeled by reducing the soil stiffness at the sub-ballast layer that represents hanging sleepers. A damage indicator (DI) based on the prediction error is proposed to visualize the differences in the predicted energies for different damage cases. In addition, a sensitivity analysis is performed where the impact of signal noise, slice sizes, and the presence of multiple damaged locations on the performance of the DI is assessed. [ABSTRACT FROM AUTHOR]

Driving behaviour analysis has drawn much attention in recent years due to the dramatic increase in the number of traffic accidents and casualties, and based on many studies, there is a relationship between the driving environment or behaviour and the driver's state. To the best of our knowledge, these studies mostly investigate relationships between one vital sign and the driving circumstances either inside or outside the cabin. Hence, our paper provides an analysis of the correlation between the driver state (vital signs, eye state, and head pose) and both the vehicle maneuver actions (caused by the driver) and external events (carried out by other vehicles or pedestrians), including the proximity to other vehicles. Our methodology employs several models developed in our previous work to estimate respiratory rate, heart rate, blood pressure, oxygen saturation, head pose, eye state from in-cabin videos, and the distance to the nearest vehicle from out-cabin videos. Additionally, new models have been developed using Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) to classify the external events from out-cabin videos, as well as a Decision Tree classifier to detect the driver's maneuver using accelerometer and gyroscope sensor data. The dataset used includes synchronized in-cabin/out-cabin videos and sensor data, allowing for the estimation of the driver state, proximity to other vehicles and detection of external events, and driver maneuvers. Therefore, the correlation matrix was calculated between all variables to be analysed. The results indicate that there is a weak correlation connecting both the maneuver action and the overtaking external event on one side and the heart rate and the blood pressure (systolic and diastolic) on the other side. In addition, the findings suggest a correlation between the yaw angle of the head and the overtaking event and a negative correlation between the systolic blood pressure and the distance to the nearest vehicle. Our findings align with our initial hypotheses, particularly concerning the impact of performing a maneuver or experiencing a cautious event, such as overtaking, on heart rate and blood pressure due to the agitation and tension resulting from such events. These results can be the key to implementing a sophisticated safety system aimed at maintaining the driver's stable state when aggressive external events or maneuvers occur. [ABSTRACT FROM AUTHOR]

This paper explores the potential for communication-efficient federated learning (FL) in modern distributed systems. FL is an emerging distributed machine learning technique that allows for the distributed training of a single machine learning model across multiple geographically distributed clients. This paper surveys the various approaches to communication-efficient FL, including model updates, compression techniques, resource management for the edge and cloud, and client selection. We also review the various optimization techniques associated with communication-efficient FL, such as compression schemes and structured updates. Finally, we highlight the current research challenges and discuss the potential future directions for communication-efficient FL. [ABSTRACT FROM AUTHOR]

High efficiency and safety are critical factors in ensuring the optimal performance and reliability of systems and equipment across various industries. Fault monitoring (FM) techniques play a pivotal role in this regard by continuously monitoring system performance and identifying the presence of faults or abnormalities. However, traditional FM methods face limitations in fully capturing the complex interactions within a system and providing real-time monitoring capabilities. To overcome these challenges, Digital Twin (DT) technology has emerged as a promising solution to enhance existing FM practices. By creating a virtual replica or digital copy of a physical equipment or system, DT offers the potential to revolutionize fault monitoring approaches. This paper aims to explore and discuss the diverse range of predictive methods utilized in DT and their implementations in FM across industries. Furthermore, it will showcase successful implementations of DT in FM across a wide array of industries, including manufacturing, energy, transportation, and healthcare. The utilization of DT in FM enables a comprehensive understanding of system behavior and performance by leveraging real-time data, advanced analytics, and machine learning algorithms. By integrating physical and virtual components, DT facilitates the monitoring and prediction of faults, providing valuable insights into the system's health and enabling proactive maintenance and decision making. [ABSTRACT FROM AUTHOR]

Fire incidents occurring onboard ships cause significant consequences that result in substantial effects. Fires on ships can have extensive and severe wide-ranging impacts on matters such as the safety of the crew, cargo, the environment, finances, reputation, etc. Therefore, timely detection of fires is essential for quick responses and powerful mitigation. The study in this research paper presents a fire detection technique based on YOLOv7 (You Only Look Once version 7), incorporating improved deep learning algorithms. The YOLOv7 architecture, with an improved E-ELAN (extended efficient layer aggregation network) as its backbone, serves as the basis of our fire detection system. Its enhanced feature fusion technique makes it superior to all its predecessors. To train the model, we collected 4622 images of various ship scenarios and performed data augmentation techniques such as rotation, horizontal and vertical flips, and scaling. Our model, through rigorous evaluation, showcases enhanced capabilities of fire recognition to improve maritime safety. The proposed strategy successfully achieves an accuracy of 93% in detecting fires to minimize catastrophic incidents. Objects having visual similarities to fire may lead to false prediction and detection by the model, but this can be controlled by expanding the dataset. However, our model can be utilized as a real-time fire detector in challenging environments and for small-object detection. Advancements in deep learning models hold the potential to enhance safety measures, and our proposed model in this paper exhibits this potential. Experimental results proved that the proposed method can be used successfully for the protection of ships and in monitoring fires in ship port areas. Finally, we compared the performance of our method with those of recently reported fire-detection approaches employing widely used performance matrices to test the fire classification results achieved. [ABSTRACT FROM AUTHOR]

The paper focuses on the importance of prompt and efficient process fault detection in contemporary manufacturing industries, where product quality and safety protocols are critical. The study compares the efficiencies of two techniques for process fault detection: Kernel Principal Component Analysis (KPCA) and the observer method. Both techniques are applied to observe water volume variation within a hydraulic system comprising three tanks. PCA is an unsupervised learning technique used for dimensionality reduction and pattern recognition. It is an extension of Principal Component Analysis (PCA) that utilizes kernel functions to transform data into higher-dimensional spaces, where it becomes easier to separate classes or identify patterns. In this paper, KPCA is applied to detect faults in the hydraulic system by analyzing the variation in water volume. The observer method originates from control theory and is utilized to estimate the internal states of a system based on its output measurements. It is commonly used in control systems to estimate the unmeasurable or hidden states of a system, which is crucial for ensuring proper control and fault detection. In this study, the observer method is applied to the hydraulic system to estimate the water volume variations within the three tanks. The paper presents a comparative study of these two techniques applied to the hydraulic system. The results show that both KPCA and the observer method perform similarly in detecting faults within the system. This similarity in performance highlights the efficacy of these techniques and their potential adaptability in various fault diagnosis scenarios within modern manufacturing processes. [ABSTRACT FROM AUTHOR]

Algorithms for machine learning have found extensive use in numerous fields and applications. One important aspect of effectively utilizing these algorithms is tuning the hyperparameters to match the specific task at hand. The selection and configuration of hyperparameters directly impact the performance of machine learning models. Achieving optimal hyperparameter settings often requires a deep understanding of the underlying models and the appropriate optimization techniques. While there are many automatic optimization techniques available, each with its own advantages and disadvantages, this article focuses on hyperparameter optimization for well-known machine learning models. It explores cutting-edge optimization methods such as metaheuristic algorithms, deep learning-based optimization, Bayesian optimization, and quantum optimization, and our paper focused mainly on metaheuristic and Bayesian optimization techniques and provides guidance on applying them to different machine learning algorithms. The article also presents real-world applications of hyperparameter optimization by conducting tests on spatial data collections for landslide susceptibility mapping. Based on the experiment's results, both Bayesian optimization and metaheuristic algorithms showed promising performance compared to baseline algorithms. For instance, the metaheuristic algorithm boosted the random forest model's overall accuracy by 5% and 3%, respectively, from baseline optimization methods GS and RS, and by 4% and 2% from baseline optimization methods GA and PSO. Additionally, for models like KNN and SVM, Bayesian methods with Gaussian processes had good results. When compared to the baseline algorithms RS and GS, the accuracy of the KNN model was enhanced by BO-TPE by 1% and 11%, respectively, and by BO-GP by 2% and 12%, respectively. For SVM, BO-TPE outperformed GS and RS by 6% in terms of performance, while BO-GP improved results by 5%. The paper thoroughly discusses the reasons behind the efficiency of these algorithms. By successfully identifying appropriate hyperparameter configurations, this research paper aims to assist researchers, spatial data analysts, and industrial users in developing machine learning models more effectively. The findings and insights provided in this paper can contribute to enhancing the performance and applicability of machine learning algorithms in various domains. [ABSTRACT FROM AUTHOR]

Finding ways to enable seamless communication between deaf and able-bodied individuals has been a challenging and pressing issue. This paper proposes a solution to this problem by designing a low-cost data glove that utilizes multiple inertial sensors with the purpose of achieving efficient and accurate sign language recognition. In this study, four machine learning models—decision tree (DT), support vector machine (SVM), K-nearest neighbor method (KNN), and random forest (RF)—were employed to recognize 20 different types of dynamic sign language data used by deaf individuals. Additionally, a proposed attention-based mechanism of long and short-term memory neural networks (Attention-BiLSTM) was utilized in the process. Furthermore, this study verifies the impact of the number and position of data glove nodes on the accuracy of recognizing complex dynamic sign language. Finally, the proposed method is compared with existing state-of-the-art algorithms using nine public datasets. The results indicate that both the Attention-BiLSTM and RF algorithms have the highest performance in recognizing the twenty dynamic sign language gestures, with an accuracy of 98.85% and 97.58%, respectively. This provides evidence for the feasibility of our proposed data glove and recognition methods. This study may serve as a valuable reference for the development of wearable sign language recognition devices and promote easier communication between deaf and able-bodied individuals. [ABSTRACT FROM AUTHOR]

In this paper, we present a two stages solution to 3D vehicle detection and segmentation. The first stage depends on the combination of EfficientNetB3 architecture with multiparallel residual blocks (inspired by CenterNet architecture) for 3D localization and poses estimation for vehicles on the scene. The second stage takes the output of the first stage as input (cropped car images) to train EfficientNet B3 for the image recognition task. Using predefined 3D Models, we substitute each vehicle on the scene with its match using the rotation matrix and translation vector from the first stage to get the 3D detection bounding boxes and segmentation masks. We trained our models on an open-source dataset (ApolloCar3D). Our method outperforms all published solutions in terms of 6 degrees of freedom error (6 DoF err). [ABSTRACT FROM AUTHOR]

In recent years, anomaly detection and machine learning for intrusion detection systems have been used to detect anomalies on Internet of Things networks. These systems rely on machine and deep learning to improve the detection accuracy. However, the robustness of the model depends on the number of datasamples available, quality of the data, and the distribution of the data classes. In the present paper, we focused specifically on the amount of data and class imbalanced since both parameters are key in IoT due to the fact that network traffic is increasing exponentially. For this reason, we propose a framework that uses a big data methodology with Hadoop–Spark to train and test multi-class and binary classification with one-vs-rest strategy for intrusion detection using the entire BoT IoT dataset. Thus, we evaluate all the algorithms available in Hadoop–Spark in terms of accuracy and processing time. In addition, since the BoT IoT dataset used is highly imbalanced, we also improve the accuracy for detecting minority classes by generating more datasamples using a Conditional Tabular Generative Adversarial Network (CTGAN). In general, our proposed model outperforms other published models including our previous model. Using our proposed methodology, the F1-score of one of the minority class, i.e., Theft attack was improved from 42% to 99%. [ABSTRACT FROM AUTHOR]

The synthesis between face sketches and face photos has important application values in law enforcement and digital entertainment. In cases of a lack of paired sketch-photo data, this paper proposes an unsupervised model to solve the problems of missing key facial details and a lack of realism in the synthesized images of existing methods. The model is built on the CycleGAN architecture. To retain more semantic information in the target domain, a multi-scale feature extraction module is inserted before the generator. In addition, the convolutional block attention module is introduced into the generator to enhance the ability of the model to extract important feature information. Via CBAM, the model improves the quality of the converted image and reduces the artifacts caused by image background interference. Next, in order to preserve more identity information in the generated photo, this paper constructs the multi-level cycle consistency loss function. Qualitative experiments on CUFS and CUFSF public datasets show that the facial details and edge structures synthesized by our model are clearer and more realistic. Meanwhile the performance indexes of structural similarity and peak signal-to-noise ratio in quantitative experiments are also significantly improved compared with other methods. [ABSTRACT FROM AUTHOR]

When a vehicle is being driven, it is excited by the road roughness and generates its own vibration. In order to improve the vehicle's riding comfort and the physical–mental health of passengers in the vehicle, this paper proposes a formulation method for a comfortable speed strategy and the technical route of its application. According to international standard ISO 2631-1, the relationship between the weighted root-mean-square acceleration value and comfortable vehicle speed is analyzed. The simulation test platform of the road roughness signal and vehicle vibration signal is built by using the filtering white noise method and the second Lagrange equation through Matlab/Simulink. Combined with the simulation platform, this paper extracts seven characteristics with statistical properties from the time-domain signal and obtains 500 sample data. Random forest (RF), extreme learning machine (ELM), and radial basis function neural network (RBF-NN) are applied to identify roads. Two comfortable speed strategy formulation methods based on the improved simulated annealing (ISA) algorithm are proposed and compared according to the solution effect of each grade of comfortable speed. The results show that the simulated signals of each grade road roughness are accurate. Road recognition can be effectively carried out using the statistical characteristics of vehicle vibration acceleration signals. ELM has high recognition accuracy and fast execution speed. The ISA-II algorithm has a low solution error of comfortable speed and a low computation time. The comfortable speed of the research vehicle on different road grades showed a great difference. [ABSTRACT FROM AUTHOR]

It is important to reduce the danger of collecting flame image data sets by compositing flame images by computer. In this paper, a Global-Local mask Generative Adversarial Network (FGL-GAN) is proposed to address the current status of low quality composite flame images. First, FGL-GAN adopts a hierarchical Global-Local generator structure, to locally render high-quality flame halo and reflection, while also maintaining a consistent global style. Second, FGL-GAN incorporates the fire mask as part of the input of the generation module, which improves the rendering quality of flame halo and reflection. A new data augmentation technique for flame image compositing is used in the network training process to reconstruct the background and reduce the influence of distractors on the network. Finally, FGL-GAN introduces the idea of contrastive learning to speed up network fitting and reduce blurriness in composite images. Comparative experiments show that the images composited by FGL-GAN have achieved better performance in qualitative and quantitative evaluation than mainstream GAN. Ablation study shows the effectiveness of the hierarchical Global-Local generator structure, fire mask, data augmentation, and MONCE loss of FGL-GAN. Therefore, a large number of new flame images can be composited by FGL-GAN, which can provide extensive test data for fire detection equipment, based on deep learning algorithms. [ABSTRACT FROM AUTHOR]

Fitness is important in people's lives. Good fitness habits can improve cardiopulmonary capacity, increase concentration, prevent obesity, and effectively reduce the risk of death. Home fitness does not require large equipment but uses dumbbells, yoga mats, and horizontal bars to complete fitness exercises and can effectively avoid contact with people, so it is deeply loved by people. People who work out at home use social media to obtain fitness knowledge, but learning ability is limited. Incomplete fitness is likely to lead to injury, and a cheap, timely, and accurate fitness detection system can reduce the risk of fitness injuries and can effectively improve people's fitness awareness. In the past, many studies have engaged in the detection of fitness movements, among which the detection of fitness movements based on wearable devices, body nodes, and image deep learning has achieved better performance. However, a wearable device cannot detect a variety of fitness movements, may hinder the exercise of the fitness user, and has a high cost. Both body-node-based and image-deep-learning-based methods have lower costs, but each has some drawbacks. Therefore, this paper used a method based on deep transfer learning to establish a fitness database. After that, a deep neural network was trained to detect the type and completeness of fitness movements. We used Yolov4 and Mediapipe to instantly detect fitness movements and stored the 1D fitness signal of movement to build a database. Finally, MLP was used to classify the 1D signal waveform of fitness. In the performance of the classification of fitness movement types, the mAP was 99.71%, accuracy was 98.56%, precision was 97.9%, recall was 98.56%, and the F1-score was 98.23%, which is quite a high performance. In the performance of fitness movement completeness classification, accuracy was 92.84%, precision was 92.85, recall was 92.84%, and the F1-score was 92.83%. The average FPS in detection was 17.5. Experimental results show that our method achieves higher accuracy compared to other methods. [ABSTRACT FROM AUTHOR]

Federated learning (FL) in mobile edge computing has emerged as a promising machine-learning paradigm in the Internet of Things, enabling distributed training without exposing private data. It allows multiple mobile devices (MDs) to collaboratively create a global model. FL not only addresses the issue of private data exposure but also alleviates the burden on a centralized server, which is common in conventional centralized learning. However, a critical issue in FL is the imposed computing for local training on multiple MDs, which often have limited computing capabilities. This limitation poses a challenge for MDs to actively contribute to the training process. To tackle this problem, this paper proposes an adaptive dataset management (ADM) scheme, aiming to reduce the burden of local training on MDs. Through an empirical study on the influence of dataset size on accuracy improvement over communication rounds, we confirm that the amount of dataset has a reduced impact on accuracy gain. Based on this finding, we introduce a discount factor that represents the reduced impact of the size of the dataset on the accuracy gain over communication rounds. To address the ADM problem, which involves determining how much the dataset should be reduced over classes while considering both the proposed discounting factor and Kullback–Leibler divergence (KLD), a theoretical framework is presented. The ADM problem is a non-convex optimization problem. To solve it, we propose a greedy-based heuristic algorithm that determines a suboptimal solution with low complexity. Simulation results demonstrate that our proposed scheme effectively alleviates the training burden on MDs while maintaining acceptable training accuracy. [ABSTRACT FROM AUTHOR]

This document provides summaries of various research papers published in the journal Sensors. The summaries cover a wide range of topics, including personalized medicine, laser ranging, memristive interfaces, face and person detection, IoT data visualization, monitoring elderly activities, auditory illusions, brain connectivity, corona discharges, thermal data analysis, vital signal detection, and eye-blink artifact removal. The document showcases the contributions and findings of each study, offering valuable insights for researchers and library patrons interested in these areas of study. [Extracted from the article]

This study aims to enhance diagnostic capabilities for optimising the performance of the anaerobic sewage treatment lagoon at Melbourne Water's Western Treatment Plant (WTP) through a novel machine learning (ML)-based monitoring strategy. This strategy employs ML to make accurate probabilistic predictions of biogas performance by leveraging diverse real-life operational and inspection sensor and other measurement data for asset management, decision making, and structural health monitoring (SHM). The paper commences with data analysis and preprocessing of complex irregular datasets to facilitate efficient learning in an artificial neural network. Subsequently, a Bayesian mixture density neural network model incorporating an attention-based mechanism in bidirectional long short-term memory (BiLSTM) was developed. This probabilistic approach uses a distribution output layer based on the Gaussian mixture model and Monte Carlo (MC) dropout technique in estimating data and model uncertainties, respectively. Furthermore, systematic hyperparameter optimisation revealed that the optimised model achieved a negative log-likelihood (NLL) of 0.074, significantly outperforming other configurations. It achieved an accuracy approximately 9 times greater than the average model performance (NLL = 0.753) and 22 times greater than the worst performing model (NLL = 1.677). Key factors influencing the model's accuracy, such as the input window size and the number of hidden units in the BiLSTM layer, were identified, while the number of neurons in the fully connected layer was found to have no significant impact on accuracy. Moreover, model calibration using the expected calibration error was performed to correct the model's predictive uncertainty. The findings suggest that the inherent data significantly contribute to the overall uncertainty of the model, highlighting the need for more high-quality data to enhance learning. This study lays the groundwork for applying ML in transforming high-value assets into intelligent structures and has broader implications for ML in asset management, SHM applications, and renewable energy sectors. [ABSTRACT FROM AUTHOR]

Human action recognition (HAR) is growing in machine learning with a wide range of applications. One challenging aspect of HAR is recognizing human actions while playing music, further complicated by the need to recognize the musical notes being played. This paper proposes a deep learning-based method for simultaneous HAR and musical note recognition in music performances. We conducted experiments on Morin khuur performances, a traditional Mongolian instrument. The proposed method consists of two stages. First, we created a new dataset of Morin khuur performances. We used motion capture systems and depth sensors to collect data that includes hand keypoints, instrument segmentation information, and detailed movement information. We then analyzed RGB images, depth images, and motion data to determine which type of data provides the most valuable features for recognizing actions and notes in music performances. The second stage utilizes a Spatial Temporal Attention Graph Convolutional Network (STA-GCN) to recognize musical notes as continuous gestures. The STA-GCN model is designed to learn the relationships between hand keypoints and instrument segmentation information, which are crucial for accurate recognition. Evaluation on our dataset demonstrates that our model outperforms the traditional ST-GCN model, achieving an accuracy of 81.4%. [ABSTRACT FROM AUTHOR]

This paper focuses on the use of smart manufacturing in lathe-cutting tool machines, which can experience thermal deformation during long-term processing, leading to displacement errors in the cutting head and damage to the final product. This study uses time-series thermal compensation to develop a predictive system for thermal displacement in machine tools, which is applicable in the industry using edge computing technology. Two experiments were carried out to optimize the temperature prediction models and predict the displacement of five axes at the temperature points. First, an examination is conducted to determine possible variances in time-series data. This analysis is based on the data obtained for the changes in time, speed, torque, and temperature at various locations of the machine tool. Using the viable machine-learning models determined, the study then examines various cutting settings, temperature points, and machine speeds to forecast the future five-axis displacement. Second, to verify the precision of the models created in the initial phase, other time-series models are examined and trained in the subsequent phase, and their effectiveness is compared to the models acquired in the first phase. This work also included training seven models of WNN, LSTNet, TPA-LSTM, XGBoost, BiLSTM, CNN, and GA-LSTM. The study found that the GA-LSTM model outperforms the other three best models of the LSTM, GRU, and XGBoost models with an average precision greater than 90%. Based on the analysis of training time and model precision, the study concluded that a system using LSTM, GRU, and XGBoost should be designed and applied for thermal compensation using edge devices such as the Raspberry Pi. [ABSTRACT FROM AUTHOR]

In the railway sector, rolling stock and infrastructure must be maintained in perfect condition to ensure reliable and safe operation for passengers. Climate change is affecting the urban and regional infrastructure through sea level rise, water accumulations, river flooding, and other increased-frequency extreme natural situations (heavy rains or snows) which pose a challenge to maintenance. In this paper, the use of artificial intelligence based on predictive maintenance implementation is proposed for the early detection of degraded conditions of a bridge due to extreme climatic conditions. For this prediction, continuous monitoring is proposed, with the aim of establishing alarm thresholds to detect dangerous situations, so restrictions could be determined to mitigate the risk. However, one of the main challenges for railway infrastructure managers nowadays is the high cost of monitoring large infrastructures. In this work, a methodology for monitoring railway infrastructures to define the optimal number of transductors that are economically viable and the thresholds according to which infrastructure managers can make decisions concerning traffic safety is proposed. The methodology consists of three phases that use the application of machine learning (Random Forest) and artificial cognitive systems (LSTM recurrent neural networks). [ABSTRACT FROM AUTHOR]

The use of drones has recently gained popularity in a diverse range of applications, such as aerial photography, agriculture, search and rescue operations, the entertainment industry, and more. However, misuse of drone technology can potentially lead to military threats, terrorist acts, as well as privacy and safety breaches. This emphasizes the need for effective and fast remote detection of potentially threatening drones. In this study, we propose a novel approach for automatic drone detection utilizing the usage of both radio frequency communication signals and acoustic signals derived from UAV rotor sounds. In particular, we propose the use of classical and deep machine-learning techniques and the fusion of RF and acoustic features for efficient and accurate drone classification. Distinct types of ML-based classifiers have been examined, including CNN- and RNN-based networks and the classical SVM method. The proposed approach has been evaluated with both frequency and audio features using common drone datasets, demonstrating better accuracy than existing state-of-the-art methods, especially in low SNR scenarios. The results presented in this paper show a classification accuracy of approximately 91% at an SNR ratio of − 10 dB using the LSTM network and fused features. [ABSTRACT FROM AUTHOR]

Indoor fires may cause casualties and property damage, so it is important to develop a system that predicts fires in advance. There have been studies to predict potential fires using sensor values, and they mostly exploited machine learning models or recurrent neural networks. In this paper, we propose a stack of Transformer encoders for fire prediction using multiple sensors. Our model takes the time-series values collected from the sensors as input, and predicts the potential fire based on the sequential patterns underlying the time-series data. We compared our model with traditional machine learning models and recurrent neural networks on two datasets. For a simple dataset, we found that the machine learning models are better than ours, whereas our model gave better performance for a complex dataset. This implies that our model has a greater potential for real-world applications that probably have complex patterns and scenarios. [ABSTRACT FROM AUTHOR]

Rapid global urbanization has led to a growing urban population, posing challenges in transportation management. Persistent issues such as traffic congestion, environmental pollution, and safety risks persist despite attempts to mitigate them, hindering urban progress. This paper focuses on the critical need for accurate traffic flow forecasting, considered one of the main effective solutions for containing traffic congestion in urban scenarios. The challenge of predicting traffic flow is addressed by proposing a two-level machine learning approach. The first level uses an unsupervised clustering model to extract patterns from sensor-generated data, while the second level employs supervised machine learning models. Although the proposed approach requires the availability of data from traffic sensors to realize the training of the machine learning models, it allows traffic flow prediction in urban areas without sensors. In order to verify the prediction capability of the proposed approach, a real urban scenario is considered. [ABSTRACT FROM AUTHOR]

Dynamic wireless charging (DWC) has emerged as a viable approach to mitigate range anxiety by ensuring continuous and uninterrupted charging for electric vehicles in motion. DWC systems rely on the length of the transmitter, which can be categorized into long-track transmitters and segmented coil arrays. The segmented coil array, favored for its heightened efficiency and reduced electromagnetic interference, stands out as the preferred option. However, in such DWC systems, the need arises to detect the vehicle's position, specifically to activate the transmitter coils aligned with the receiver pad and de-energize uncoupled transmitter coils. This paper introduces various machine learning algorithms for precise vehicle position determination, accommodating diverse ground clearances of electric vehicles and various speeds. Through testing eight different machine learning algorithms and comparing the results, the random forest algorithm emerged as superior, displaying the lowest error in predicting the actual position. [ABSTRACT FROM AUTHOR]

The growth in linked and autonomous vehicles has led to the emergence of vehicular ad hoc networks (VANETs) as a means to enhance road safety, traffic efficiency, and passenger comfort. However, VANETs face challenges in facilitating trustworthiness and high-quality services due to communication delays caused by traffic, dynamic topology changes, variable speeds, and other influencing factors. Hence, there is a need for a reliable data dissemination scheme capable of reducing communication delays among hops by identifying effective forwarder nodes. In this paper, we propose a novel, weighted, estimated, spider monkey-based, nature-inspired optimization (w-SMNO) method to generate a set of efficient relays. Additionally, we introduce a dynamic weight assignment and configuration model to enhance system accuracy using a neural network based on backpropagation with gradient descent optimization techniques to minimize errors in the machine learning model. The w-SMNO also incorporates a distinct algorithm for effective relay selection among multiple monkey spider groups. The simulation results demonstrate substantial improvements in w-SMNO, with a 35.7% increase in coverage, a 41.2% reduction in the end-to-end delay, a 36.4% improvement in the message delivery rate, and a 38.4% decrease in the collision rate compared to the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

The degradation of road pavements due to environmental factors is a pressing issue in infrastructure maintenance, necessitating precise identification of pavement distresses. The pavement condition index (PCI) serves as a critical metric for evaluating pavement conditions, essential for effective budget allocation and performance tracking. Traditional manual PCI assessment methods are limited by labor intensity, subjectivity, and susceptibility to human error. Addressing these challenges, this paper presents a novel, end-to-end automated method for PCI calculation, integrating deep learning and image processing technologies. The first stage employs a deep learning algorithm for accurate detection of pavement cracks, followed by the application of a segmentation-based skeleton algorithm in image processing to estimate crack width precisely. This integrated approach enhances the assessment process, providing a more comprehensive evaluation of pavement integrity. The validation results demonstrate a 95% accuracy in crack detection and 90% accuracy in crack width estimation. Leveraging these results, the automated PCI rating is achieved, aligned with standards, showcasing significant improvements in the efficiency and reliability of PCI evaluations. This method offers advancements in pavement maintenance strategies and potential applications in broader road infrastructure management. [ABSTRACT FROM AUTHOR]

This paper focuses on the emissions of the three most sold categories of light vehicles: sedans, SUVs, and pickups. The research is carried out through an innovative methodology based on GPS and machine learning in real driving conditions. For this purpose, driving data from the three best-selling vehicles in Ecuador are acquired using a data logger with GPS included, and emissions are measured using a PEMS in six RDE tests with two standardized routes for each vehicle. The data obtained on Route 1 are used to estimate the gears used during driving using the K-means algorithm and classification trees. Then, the relative importance of driving variables is estimated using random forest techniques, followed by the training of ANNs to estimate CO2, CO, NOX, and HC. The data generated on Route 2 are used to validate the obtained ANNs. These models are fed with a dataset generated from 324, 300, and 316 km of random driving for each type of vehicle. The results of the model were compared with the IVE model and an OBD-based model, showing similar results without the need to mount the PEMS on the vehicles for long test drives. The generated model is robust to different traffic conditions as a result of its training and validation using a large amount of data obtained under completely random driving conditions. [ABSTRACT FROM AUTHOR]

Ultrasonic diagnostics is the earliest way to predict industrial faults. Usually, a contact microphone is employed for detection, but the recording will be contaminated with noise. In this paper, a dataset that contains 10 main faults of pipelines and motors is analyzed from which 30 different features in the time and frequency domains are extracted. Afterward, for dimensionality reduction, principal component analysis (PCA), linear discriminant analysis (LDA), and t-distributed stochastic neighbor embedding (t-SNE) are performed. In the subsequent phase, recursive feature elimination (RFE) is employed as a strategic method to analyze and select the most relevant features for the classifiers. Next, predictive models consisting of k-Nearest Neighbor (KNN), Logistic Regression (LR), Decision Tree (DT), Gaussian Naive Bayes (GNB), and Support Vector Machine (SVM) are employed. Then, in order to solve the classification problem, a stacking classifier based on a meta-classifier which combines multiple classification models is introduced. Furthermore, the k-fold cross-validation technique is employed to assess the effectiveness of the model in handling new data for the evaluation of experimental results in ultrasonic fault detection. With the proposed method, the accuracy is around 5% higher over five cross folds with the least amount of variation. The timing evaluation of the meta model on the 64 MHz Cortex M4 microcontroller unit (MCU) revealed an execution time of 11 ms, indicating it could be a promising solution for real-time monitoring. [ABSTRACT FROM AUTHOR]

The integration of machine learning and robotics brings promising potential to tackle the application challenges of mobile robot navigation in industries. The real-world environment is highly dynamic and unpredictable, with increasing necessities for efficiency and safety. This demands a multi-faceted approach that combines advanced sensing, robust obstacle detection, and avoidance mechanisms for an effective robot navigation experience. While hybrid methods with default robot operating system (ROS) navigation stack have demonstrated significant results, their performance in real time and highly dynamic environments remains a challenge. These environments are characterized by continuously changing conditions, which can impact the precision of obstacle detection systems and efficient avoidance control decision-making processes. In response to these challenges, this paper presents a novel solution that combines a rapidly exploring random tree (RRT)-integrated ROS navigation stack and a pre-trained YOLOv7 object detection model to enhance the capability of the developed work on the NAV-YOLO system. The proposed approach leveraged the high accuracy of YOLOv7 obstacle detection and the efficient path-planning capabilities of RRT and dynamic windows approach (DWA) to improve the navigation performance of mobile robots in real-world complex and dynamically changing settings. Extensive simulation and real-world robot platform experiments were conducted to evaluate the efficiency of the proposed solution. The result demonstrated a high-level obstacle avoidance capability, ensuring the safety and efficiency of mobile robot navigation operations in aviation environments. [ABSTRACT FROM AUTHOR]

Steel Plate Cold-Rolled Commercial (SPCC) steel is known to have long-term durability. However, it still undergoes corrosion when exposed to corrosive environments. This paper proposes an evaluation method for assessing the corrosion level of SPCC steel samples using eddy current testing (ECT), along with two different machine learning approaches. The objective is to classify the corrosion of the samples into two states: a less corroded state (state-1) and a highly corroded state (state-2). Generative and discriminative models were implemented for classification. The generative classifier was based on the Gaussian mixture model (GMM), while the discriminative model was based on the logistic regression model. The features used in the classification models are the peaks of the perturbated magnetic fields at two different frequencies. The performance of the classifiers was evaluated using metrics such as absolute error, accuracy, precision, recall, and F1 score. The results indicate that the GMM model is more conducive to categorizing states with higher levels of corrosion, while the logistic regression model is helpful in estimating states with lower levels of corrosion. Meanwhile, high classification accuracy can be achieved based on both methods using eddy current testing. [ABSTRACT FROM AUTHOR]

Through-wall radar human body pose recognition technology has broad applications in both military and civilian sectors. Identifying the current pose of targets behind walls and predicting subsequent pose changes are significant challenges. Conventional methods typically utilize radar information along with machine learning algorithms such as SVM and random forests to aid in recognition. However, these approaches have limitations, particularly in complex scenarios. In response to this challenge, this paper proposes a cross-modal supervised through-wall radar human body pose recognition method. By integrating information from both cameras and radar, a cross-modal dataset was constructed, and a corresponding deep learning network architecture was designed. During training, the network effectively learned the pose features of targets obscured by walls, enabling accurate pose recognition (e.g., standing, crouching) in scenarios with unknown wall obstructions. The experimental results demonstrated the superiority of the proposed method over traditional approaches, offering an effective and innovative solution for practical through-wall radar applications. The contribution of this study lies in the integration of deep learning with cross-modal supervision, providing new perspectives for enhancing the robustness and accuracy of target pose recognition. [ABSTRACT FROM AUTHOR]

Non-invasive detection of hemoglobin (Hb) concentration is of great clinical value for health screening and intraoperative blood transfusion. However, the accuracy and stability of non-invasive detection still need to be improved to meet clinical requirement. This paper proposes a non-invasive Hb detection method using ensemble extreme learning machine (EELM) regression based on eight-wavelength PhotoPlethysmoGraphic (PPG) signals. Firstly, a mathematical model for non-invasive Hb detection based on the Beer-Lambert law is established. Secondly, the captured eight-channel PPG signals are denoised and fifty-six feature values are extracted according to the derived mathematical model. Thirdly, a recursive feature elimination (RFE) algorithm is used to select the features that contribute most to the Hb prediction. Finally, a regression model is built by integrating several independent ELM models to improve prediction stability and accuracy. Experiments conducted on 249 clinical data points (199 cases as the training dataset and 50 cases as the test dataset) evaluate the proposed method, achieving a root mean square error (RMSE) of 1.72 g/dL and a Pearson correlation coefficient (PCC) of 0.76 (p < 0.01) between predicted and reference values. The results demonstrate that the proposed non-invasive Hb detection method exhibits a strong correlation with traditional invasive methods, suggesting its potential for non-invasive detection of Hb concentration. [ABSTRACT FROM AUTHOR]

The escalating reliance of modern society on information and communication technology has rendered it vulnerable to an array of cyber-attacks, with distributed denial-of-service (DDoS) attacks emerging as one of the most prevalent threats. This paper delves into the intricacies of DDoS attacks, which exploit compromised machines numbering in the thousands to disrupt data services and online commercial platforms, resulting in significant downtime and financial losses. Recognizing the gravity of this issue, various detection techniques have been explored, yet the quantity and prior detection of DDoS attacks has seen a decline in recent methods. This research introduces an innovative approach by integrating evolutionary optimization algorithms and machine learning techniques. Specifically, the study proposes XGB-GA Optimization, RF-GA Optimization, and SVM-GA Optimization methods, employing Evolutionary Algorithms (EAs) Optimization with Tree-based Pipelines Optimization Tool (TPOT)-Genetic Programming. Datasets pertaining to DDoS attacks were utilized to train machine learning models based on XGB, RF, and SVM algorithms, and 10-fold cross-validation was employed. The models were further optimized using EAs, achieving remarkable accuracy scores: 99.99% with the XGB-GA method, 99.50% with RF-GA, and 99.99% with SVM-GA. Furthermore, the study employed TPOT to identify the optimal algorithm for constructing a machine learning model, with the genetic algorithm pinpointing XGB-GA as the most effective choice. This research significantly advances the field of DDoS attack detection by presenting a robust and accurate methodology, thereby enhancing the cybersecurity landscape and fortifying digital infrastructures against these pervasive threats. [ABSTRACT FROM AUTHOR]

To satisfy the preference of each driver, the development of a Lane-Keeping Assistance (LKA) system that can adapt to individual drivers has become a research hotspot in recent years. However, existing studies have mostly relied on the assumption that the LKA characteristic aligned with the driver's preference is consistent with this driver's naturalistic driving characteristic. Nevertheless, this assumption may not always hold true, causing limitations to the effectiveness of this method. This paper proposes a novel method for a Driver-Adaptive Lane-Keeping Assistance (DALKA) system based on drivers' real preferences. First, metrics are extracted from collected naturalistic driving data using action point theory to describe drivers' naturalistic driving characteristics. Then, the subjective and objective evaluation method is introduced to obtain the real preference of each test driver for the LKA system. Finally, machine learning methods are employed to train a model that relates naturalistic driving characteristics to the drivers' real preferences, and the model-predicted preferences are integrated into the DALKA system. The developed DALKA system is then subjectively evaluated by the drivers. The results show that our DALKA system, developed using this method, can enhance or maintain the subjective evaluations of the LKA system for most drivers. [ABSTRACT FROM AUTHOR]

The Message Queuing Telemetry Transport (MQTT) protocol stands out as one of the foremost and widely recognized messaging protocols in the field. It is often used to transfer and manage data between devices and is extensively employed for applications ranging from smart homes and industrial automation to healthcare and transportation systems. However, it lacks built-in security features, thereby making it vulnerable to many types of attacks such as man-in-the-middle (MitM), buffer overflow, pre-shared key, brute force authentication, malformed data, distributed denial-of-service (DDoS) attacks, and MQTT publish flood attacks. Traditional methods for detecting MQTT attacks, such as deep neural networks (DNNs), k-nearest neighbor (KNN), linear discriminant analysis (LDA), and fuzzy logic, may exist. The increasing prevalence of device connectivity, sensor usage, and environmental scalability become the most challenging aspects that novel detection approaches need to address. This paper presents a new solution that leverages an H2O-based distributed machine learning (ML) framework to improve the security of the MQTT protocol in networks, particularly in IoT environments. The proposed approach leverages the strengths of the H2O algorithm and architecture to enable real-time monitoring and distributed detection and classification of anomalous behavior (deviations from expected activity patterns). By harnessing H2O's algorithms, the identification and timely mitigation of potential security threats are achieved. Various H2O algorithms, including random forests, generalized linear models (GLMs), gradient boosting machine (GBM), XGBoost, and the deep learning (DL) algorithm, have been assessed to determine the most reliable algorithm in terms of detection performance. This study encompasses the development of the proposed algorithm, including implementation details and evaluation results. To assess the proposed model, various evaluation metrics such as mean squared error (MSE), root-mean-square error (RMSE), mean per class error (MCE), and log loss are employed. The results obtained indicate that the H2OXGBoost algorithm outperforms other H2O models in terms of accuracy. This research contributes to the advancement of secure IoT networks and offers a practical approach to enhancing the security of MQTT communication channels through distributed detection and classification techniques. [ABSTRACT FROM AUTHOR]

Hyperspectral imaging (HSI) has become a very compelling technique in different scientific areas; indeed, many researchers use it in the fields of remote sensing, agriculture, forensics, and medicine. In the latter, HSI plays a crucial role as a diagnostic support and for surgery guidance. However, the computational effort in elaborating hyperspectral data is not trivial. Furthermore, the demand for detecting diseases in a short time is undeniable. In this paper, we take up this challenge by parallelizing three machine-learning methods among those that are the most intensively used: Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGB) algorithms using the Compute Unified Device Architecture (CUDA) to accelerate the classification of hyperspectral skin cancer images. They all showed a good performance in HS image classification, in particular when the size of the dataset is limited, as demonstrated in the literature. We illustrate the parallelization techniques adopted for each approach, highlighting the suitability of Graphical Processing Units (GPUs) to this aim. Experimental results show that parallel SVM and XGB algorithms significantly improve the classification times in comparison with their serial counterparts. [ABSTRACT FROM AUTHOR]

The field of learning-based navigation for mobile robots is experiencing a surge of interest from research and industry sectors. The application of this technology for visual aircraft inspection tasks within a maintenance, repair, and overhaul (MRO) hangar necessitates efficient perception and obstacle avoidance capabilities to ensure a reliable navigation experience. The present reliance on manual labour, static processes, and outdated technologies limits operation efficiency in the inherently dynamic and increasingly complex nature of the real-world hangar environment. The challenging environment limits the practical application of conventional methods and real-time adaptability to changes. In response to these challenges, recent years research efforts have witnessed advancement with machine learning integration aimed at enhancing navigational capability in both static and dynamic scenarios. However, most of these studies have not been specific to the MRO hangar environment, but related challenges have been addressed, and applicable solutions have been developed. This paper provides a comprehensive review of learning-based strategies with an emphasis on advancements in deep learning, object detection, and the integration of multiple approaches to create hybrid systems. The review delineates the application of learning-based methodologies to real-time navigational tasks, encompassing environment perception, obstacle detection, avoidance, and path planning through the use of vision-based sensors. The concluding section addresses the prevailing challenges and prospective development directions in this domain. [ABSTRACT FROM AUTHOR]

This article introduces an algorithm for detecting glucose and silicon levels in solution. The research focuses on addressing the critical need for accurate and efficient glucose monitoring, particularly in the context of diabetic management. Understanding and monitoring silicon levels in the body is crucial due to its significant role in various physiological processes. Silicon, while often overshadowed by other minerals, plays a vital role in bone health, collagen formation, and connective tissue integrity. Moreover, recent research suggests its potential involvement in neurological health and the prevention of certain degenerative diseases. Investigating silicon levels becomes essential for a comprehensive understanding of its impact on overall health and well-being and paves the way for targeted interventions and personalized healthcare strategies. The approach presented in this paper is based on the integration of hyperspectral data and artificial intelligence techniques. The algorithm investigates the effectiveness of two distinct models utilizing SVMR and a perceptron independently. SVMR is employed to establish a robust regression model that maps input features to continuous glucose and silicon values. The study outlines the methodology, including feature selection, model training, and evaluation metrics. Experimental results demonstrate the algorithm's effectiveness at accurately predicting glucose and silicon concentrations and showcases its potential for real-world application in continuous glucose and silicon monitoring systems. [ABSTRACT FROM AUTHOR]

In this paper, we present and evaluate a calibration-free mobile eye-traking system. The system's mobile device consists of three cameras: an IR eye camera, an RGB eye camera, and a front-scene RGB camera. The three cameras build a reliable corneal imaging system that is used to estimate the user's point of gaze continuously and reliably. The system auto-calibrates the device unobtrusively. Since the user is not required to follow any special instructions to calibrate the system, they can simply put on the eye tracker and start moving around using it. Deep learning algorithms together with 3D geometric computations were used to auto-calibrate the system per user. Once the model is built, a point-to-point transformation from the eye camera to the front camera is computed automatically by matching corneal and scene images, which allows the gaze point in the scene image to be estimated. The system was evaluated by users in real-life scenarios, indoors and outdoors. The average gaze error was 1.6∘ indoors and 1.69∘ outdoors, which is considered very good compared to state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

This paper explores the energy-intensive cement industry, focusing on a plant in Greece and its mill and kiln unit. The data utilized include manipulated, non-manipulated, and uncontrolled variables. The non-manipulated variables are computed based on the machine learning (ML) models and selected by the minimum value of the normalized root mean square error (NRMSE) across nine (9) methods. In case the distribution of the data displayed in the user interface changes, the user should trigger the retrain of the AI models to ensure their accuracy and robustness. To form the objective function, the expert user should define the desired weight for each manipulated or non-manipulated variable through the user interface (UI), along with its corresponding constraints or target value. The user selects the variables involved in the objective function based on the optimization strategy, and the evaluation is based on the comparison of the optimized and the active value of the objective function. The differential evolution (DE) method optimizes the objective function that is formed by the linear combination of the selected variables. The results indicate that using DE improves the operation of both the cement mill and kiln, yielding a lower objective function value compared to the current values. [ABSTRACT FROM AUTHOR]

Autonomous sleep tracking at home has become inevitable in today's fast-paced world. A crucial aspect of addressing sleep-related issues involves accurately classifying sleep stages. This paper introduces a novel approach PSO–XGBoost, combining particle swarm optimisation (PSO) with extreme gradient boosting (XGBoost) to enhance the XGBoost model's performance. Our model achieves improved overall accuracy and faster convergence by leveraging PSO to fine-tune hyperparameters. Our proposed model utilises features extracted from EEG signals, spanning time, frequency, and time–frequency domains. We employed the Pz-oz signal dataset from the sleep-EDF expanded repository for experimentation. Our model achieves impressive metrics through stratified-K-fold validation on ten selected subjects: 95.4% accuracy, 95.4% F1-score, 95.4% precision, and 94.3% recall. The experiment results demonstrate the effectiveness of our technique, showcasing an average accuracy of 95%, outperforming traditional machine learning classifications. The findings revealed that the feature-shifting approach supplements the classification outcome by 3 to 4 per cent. Moreover, our findings suggest that prefrontal EEG derivations are ideal options and could open up exciting possibilities for using wearable EEG devices in sleep monitoring. The ease of obtaining EEG signals with dry electrodes on the forehead enhances the feasibility of this application. Furthermore, the proposed method demonstrates computational efficiency and holds significant value for real-time sleep classification applications. [ABSTRACT FROM AUTHOR]

Machine learning (ML) algorithms are increasingly applied to structure health monitoring (SHM) problems. However, their application to pile damage detection (PDD) is hindered by the complexity of the problem. A novel multi-sensor pile damage detection (MSPDD) method is proposed in this paper to extend the application of ML algorithms in the automatic identification of PDD. The time-series signals collected by multiple sensors during the pile integrity test are first processed by the traveling wave decomposition (TWD) theory and are then input into a hybrid one-dimensional (1D) convolutional and recurrent neural network. The hybrid neural network can achieve the automatic multi-task identification of pile damage detection based on the time series of MSPDD results. Finally, the analytical solution-based sample set is utilized to evaluate the performance of the proposed hybrid model. The outputs of the multi-task learning framework can provide a detailed description of the actual pile quality and provide strong support for the classification of pile quality as well. [ABSTRACT FROM AUTHOR]

Estimation of temporospatial clinical features of gait (CFs), such as step count and length, step duration, step frequency, gait speed, and distance traveled, is an important component of community-based mobility evaluation using wearable accelerometers. However, accurate unsupervised computerized measurement of CFs of individuals with Duchenne muscular dystrophy (DMD) who have progressive loss of ambulatory mobility is difficult due to differences in patterns and magnitudes of acceleration across their range of attainable gait velocities. This paper proposes a novel calibration method. It aims to detect steps, estimate stride lengths, and determine travel distance. The approach involves a combination of clinical observation, machine-learning-based step detection, and regression-based stride length prediction. The method demonstrates high accuracy in children with DMD and typically developing controls (TDs) regardless of the participant's level of ability. Fifteen children with DMD and fifteen TDs underwent supervised clinical testing across a range of gait speeds using 10 m or 25 m run/walk (10 MRW, 25 MRW), 100 m run/walk (100 MRW), 6-min walk (6 MWT), and free-walk (FW) evaluations while wearing a mobile-phone-based accelerometer at the waist near the body's center of mass. Following calibration by a trained clinical evaluator, CFs were extracted from the accelerometer data using a multi-step machine-learning-based process and the results were compared to ground-truth observation data. Model predictions vs. observed values for step counts, distance traveled, and step length showed a strong correlation (Pearson's r = −0.9929 to 0.9986, p < 0.0001). The estimates demonstrated a mean (SD) percentage error of 1.49% (7.04%) for step counts, 1.18% (9.91%) for distance traveled, and 0.37% (7.52%) for step length compared to ground-truth observations for the combined 6 MWT, 100 MRW, and FW tasks. Our study findings indicate that a single waist-worn accelerometer calibrated to an individual's stride characteristics using our methods accurately measures CFs and estimates travel distances across a common range of gait speeds in both DMD and TD peers. [ABSTRACT FROM AUTHOR]

A key necessity for the safe and autonomous flight of Unmanned Aircraft Systems (UAS) is their reliable perception of the environment, for example, to assess the safety of a landing site. For visual perception, Machine Learning (ML) provides state-of-the-art results in terms of performance, but the path to aviation certification has yet to be determined as current regulation and standard documents are not applicable to ML-based components due to their data-defined properties. However, the European Union Aviation Safety Agency (EASA) published the first usable guidance documents that take ML-specific challenges, such as data management and learning assurance, into account. In this paper, an important concept in this context is addressed, namely the Operational Design Domain (ODD) that defines the limitations under which a given ML-based system is designed to operate and function correctly. We investigated whether synthetic data can be used to complement a real-world training dataset which does not cover the whole ODD of an ML-based system component for visual object detection. The use-case in focus is the detection of humans on the ground to assess the safety of landing sites. Synthetic data are generated using the methods proposed in the EASA documents, namely augmentations, stitching and simulation environments. These data are used to augment a real-world dataset to increase ODD coverage during the training of Faster R-CNN object detection models. Our results give insights into the generation techniques and usefulness of synthetic data in the context of increasing ODD coverage. They indicate that the different types of synthetic images vary in their suitability but that augmentations seem to be particularly promising when there is not enough real-world data to cover the whole ODD. By doing so, our results contribute towards the adoption of ML technology in aviation and the reduction of data requirements for ML perception systems. [ABSTRACT FROM AUTHOR]

Ground reaction force (GRF) components can be estimated using insole pressure sensors. Principal component analysis in conjunction with machine learning (PCA-ML) methods are widely used for this task. PCA reduces dimensionality and requires pre-normalization. In this paper, we evaluated the impact of twelve pre-normalization methods using three PCA-ML methods on the accuracy of GRF component estimation. Accuracy was assessed using laboratory data from gold-standard force plate measurements. Data were collected from nine subjects during slow- and normal-speed walking activities. We tested the ANN (artificial neural network) and LS (least square) methods while also exploring support vector regression (SVR), a method not previously examined in the literature, to the best of our knowledge. In the context of our work, our results suggest that the same normalization method can produce the worst or the best accuracy results, depending on the ML method. For example, the body weight normalization method yields good results for PCA-ANN but the worst performance for PCA-SVR. For PCA-ANN and PCA-LS, the vector standardization normalization method is recommended. For PCA-SVR, the mean method is recommended. The final message is not to define a normalization method a priori independently of the ML method. [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]