Search

Since the beginning of the COVID-19 pandemic, many works have been published proposing solutions to the problems that arose in this scenario. In this vein, one of the topics that attracted the most attention is the development of computer-based strategies to detect COVID-19 from thoracic medical imaging, such as chest X-ray (CXR) and computerized tomography scan (CT scan). By searching for works already published on this theme, we can easily find thousands of them. This is partly explained by the fact that the most severe worldwide pandemic emerged amid the technological advances recently achieved, and also considering the technical facilities to deal with the large amount of data produced in this context. Even though several of these works describe important advances, we cannot overlook the fact that others only use well-known methods and techniques without a more relevant and critical contribution. Hence, differentiating the works with the most relevant contributions is not a trivial task. The number of citations obtained by a paper is probably the most straightforward and intuitive way to verify its impact on the research community. Aiming to help researchers in this scenario, we present a review of the top-100 most cited papers in this field of investigation according to the Google Scholar search engine. We evaluate the distribution of the top-100 papers taking into account some important aspects, such as the type of medical imaging explored, learning settings, segmentation strategy, explainable artificial intelligence (XAI), and finally, the dataset and code availability. [ABSTRACT FROM AUTHOR]

With the rapid development and widespread application of blockchain technology in recent years, smart contracts running on blockchains often face security vulnerability problems, resulting in significant economic losses. Unlike traditional programs, smart contracts cannot be modified once deployed, and vulnerabilities cannot be remedied. Therefore, the vulnerability detection of smart contracts has become a research focus. Most existing vulnerability detection methods are based on rules defined by experts, which are inefficient and have poor scalability. Although there have been studies using machine learning methods to extract contract features for vulnerability detection, the features considered are singular, and it is impossible to fully utilize smart contract information. In order to overcome the limitations of existing methods, this paper proposes a smart contract vulnerability detection method based on deep learning and multimodal decision fusion. This method also considers the code semantics and control structure information of smart contracts. It integrates the source code, operation code, and control-flow modes through the multimodal decision fusion method. The deep learning method extracts five features used to represent contracts and achieves high accuracy and recall rates. The experimental results show that the detection accuracy of our method for arithmetic vulnerability, re-entrant vulnerability, transaction order dependence, and Ethernet locking vulnerability can reach 91.6%, 90.9%, 94.8%, and 89.5%, respectively, and the detected AUC values can reach 0.834, 0.852, 0.886, and 0.825, respectively. This shows that our method has a good vulnerability detection effect. Furthermore, ablation experiments show that the multimodal decision fusion method contributes significantly to the fusion of different modalities. [ABSTRACT FROM AUTHOR]

Biosensors are devices composed of a biorecognition part and of a transduction part. A review is conducted on the progress of the use of low-cost sensors in healthcare monitoring, the algorithms used to process sensor data and the wireless communication techniques [[11]]. [Extracted from the article]

Enhancing the management and monitoring of oil and gas processes demands the development of precise predictive analytic techniques. Over the past two years, oil and its prediction have advanced significantly using conventional and modern machine learning techniques. Several review articles detail the developments in predictive maintenance and the technical and non-technical aspects of influencing the uptake of big data. The absence of references for machine learning techniques impacts the effective optimization of predictive analytics in the oil and gas sectors. This review paper offers readers thorough information on the latest machine learning methods utilized in this industry's predictive analytical modeling. This review covers different forms of machine learning techniques used in predictive analytical modeling from 2021 to 2023 (91 articles). It provides an overview of the details of the papers that were reviewed, describing the model's categories, the data's temporality, field, and name, the dataset's type, predictive analytics (classification, clustering, or prediction), the models' input and output parameters, the performance metrics, the optimal model, and the model's benefits and drawbacks. In addition, suggestions for future research directions to provide insights into the potential applications of the associated knowledge. This review can serve as a guide to enhance the effectiveness of predictive analytics models in the oil and gas industries. [ABSTRACT FROM AUTHOR]

With the continuous development of automotive intelligence, vehicle occupant detection technology has received increasing attention. Despite various types of research in this field, a simple, reliable, and highly private detection method is lacking. This paper proposes a method for vehicle occupant detection using millimeter-wave radar. Specifically, the paper outlines the system design for vehicle occupant detection using millimeter-wave radar. By collecting the raw signals of FMCW radar and applying Range-FFT and DoA estimation algorithms, a range–azimuth heatmap was generated, visually depicting the current status of people inside the vehicle. Furthermore, utilizing the collected range–azimuth heatmap of passengers, this paper integrates the Faster R-CNN deep learning networks with radar signal processing to identify passenger information. Finally, to test the performance of the detection method proposed in this article, an experimental verification was conducted in a car and the results were compared with those of traditional machine learning algorithms. The findings indicated that the method employed in this experiment achieves higher accuracy, reaching approximately 99%. [ABSTRACT FROM AUTHOR]

In today's world, a significant amount of global energy is used in buildings. Unfortunately, a lot of this energy is wasted, because electrical appliances are not used properly or efficiently. One way to reduce this waste is by detecting, learning, and predicting when people are present in buildings. To do this, buildings need to become "smart" and "cognitive" and use modern technologies to sense when and how people are occupying the buildings. By leveraging this information, buildings can make smart decisions based on recently developed methods. In this paper, we provide a comprehensive overview of recent advancements in Internet of Things (IoT) technologies that have been designed and used for the monitoring of indoor environmental conditions within buildings. Using these technologies is crucial to gathering data about the indoor environment and determining the number and presence of occupants. Furthermore, this paper critically examines both the strengths and limitations of each technology in predicting occupant behavior. In addition, it explores different methods for processing these data and making future occupancy predictions. Moreover, we highlight some challenges, such as determining the optimal number and location of sensors and radars, and provide a detailed explanation and insights into these challenges. Furthermore, the paper explores possible future directions, including the security of occupants' data and the promotion of energy-efficient practices such as localizing occupants and monitoring their activities within a building. With respect to other survey works on similar topics, our work aims to both cover recent sensory approaches and review methods used in the literature for estimating occupancy. [ABSTRACT FROM AUTHOR]

Water constitutes an indispensable resource crucial for the sustenance of humanity, as it plays an integral role in various sectors such as agriculture, industrial processes, and domestic consumption. Even though water covers 71% of the global land surface, governments have been grappling with the challenge of ensuring the provision of safe water for domestic use. A contributing factor to this situation is the persistent contamination of available water sources rendering them unfit for human consumption. A common contaminant, pesticides are not frequently tested for despite their serious effects on biodiversity. Pesticide determination in water quality assessment is a challenging task because the procedures involved in the extraction and detection are complex. This reduces their popularity in many monitoring campaigns despite their harmful effects. If the existing methods of pesticide analysis are adapted by leveraging new technologies, then information concerning their presence in water ecosystems can be exposed. Furthermore, beyond the advantages conferred by the integration of wireless sensor networks (WSNs), the Internet of Things (IoT), Machine Learning (ML), and big data analytics, a notable outcome is the attainment of a heightened degree of granularity in the information of water ecosystems. This paper discusses methods of pesticide detection in water, emphasizing the possible use of electrochemical sensors, biosensors, and paper-based sensors in wireless sensing. It also explores the application of WSNs in water, the IoT, computing models, ML, and big data analytics, and their potential for integration as technologies useful for pesticide monitoring in water. [ABSTRACT FROM AUTHOR]

This document is an editorial for a special issue titled "Machine Learning in Computer Vision and Image Sensing: Theory and Applications." The editorial highlights the diverse applications of machine learning (ML) models in various domains such as medical imaging, signal processing, remote sensing, and human activity detection. The special issue includes 11 papers that cover topics such as image segmentation, fluvial navigation, Alzheimer's disease classification, pneumothorax detection, lung cancer malignancy prediction, amniotic fluid volume detection, COVID-19 detection, and Parkinson's disease detection. The papers showcase the progress and potential of ML models in computer vision applications and provide valuable insights for future research. [Extracted from the article]

This paper investigates a method for precise mapping of human arm movements using sEMG signals. A multi-channel approach captures the sEMG signals, which, combined with the accurately calculated joint angles from an Inertial Measurement Unit, allows for action recognition and mapping through deep learning algorithms. Firstly, signal acquisition and processing were carried out, which involved acquiring data from various movements (hand gestures, single-degree-of-freedom joint movements, and continuous joint actions) and sensor placement. Then, interference signals were filtered out through filters, and the signals were preprocessed using normalization and moving averages to obtain sEMG signals with obvious features. Additionally, this paper constructs a hybrid network model, combining Convolutional Neural Networks and Artificial Neural Networks, and employs a multi-feature fusion algorithm to enhance the accuracy of gesture recognition. Furthermore, a nonlinear fitting between sEMG signals and joint angles was established based on a backpropagation neural network, incorporating momentum term and adaptive learning rate adjustments. Finally, based on the gesture recognition and joint angle prediction model, prosthetic arm control experiments were conducted, achieving highly accurate arm movement prediction and execution. This paper not only validates the potential application of sEMG signals in the precise control of robotic arms but also lays a solid foundation for the development of more intuitive and responsive prostheses and assistive devices. [ABSTRACT FROM AUTHOR]

This paper presents a visual compass method utilizing global features, specifically spherical moments. One of the primary challenges faced by photometric methods employing global features is the variation in the image caused by the appearance and disappearance of regions within the camera's field of view as it moves. Additionally, modeling the impact of translational motion on the values of global features poses a significant challenge, as it is dependent on scene depths, particularly for non-planar scenes. To address these issues, this paper combines the utilization of image masks to mitigate abrupt changes in global feature values and the application of neural networks to tackle the modeling challenge posed by translational motion. By employing masks at various locations within the image, multiple estimations of rotation corresponding to the motion of each selected region can be obtained. Our contribution lies in offering a rapid method for implementing numerous masks on the image with real-time inference speed, rendering it suitable for embedded robot applications. Extensive experiments have been conducted on both real-world and synthetic datasets generated using Blender. The results obtained validate the accuracy, robustness, and real-time performance of the proposed method compared to a state-of-the-art method. [ABSTRACT FROM AUTHOR]

Smart buildings use advanced technologies to automate building functions. One important function is occupancy detection using Internet of Things (IoT) sensors for smart buildings. Occupancy information is useful information to reduce energy consumption by automating building functions such as lighting, heating, ventilation, and air conditioning systems. The information is useful to improve indoor air quality by ensuring that ventilation systems are used only when and where they are needed. Additionally, it is useful to enhance building security by detecting unusual or unexpected occupancy levels and triggering appropriate responses, such as alarms or alerts. Occupancy information is useful for many other applications, such as emergency response, plug load energy management, point-of-interest identification, etc. However, the accuracy of occupancy detection is limited by factors such as real-time occupancy data, sensor placement, privacy concerns, and the presence of pets or objects that can interfere with sensor reading. With the rapid development of IoT sensor technologies and the increasing need for smart building solutions, there is a growing interest in occupancy detection techniques. There is a need to provide a comprehensive survey of these technologies. Although there are some exciting survey papers, they all have limited scopes with different focuses. Therefore, this paper provides a comprehensive overview of the current state-of-the-art occupancy detection methods (including both traditional algorithms and machine learning algorithms) and devices with their advantages and limitations. It surveys and compares fundamental technologies (such as sensors, algorithms, etc.) for smart buildings. Furthermore, the survey provides insights and discussions, which can help researchers, practitioners, and stakeholders develop more effective occupancy detection solutions for smart buildings. [ABSTRACT FROM AUTHOR]

The cooperative, connected, and automated mobility (CCAM) infrastructure plays a key role in understanding and enhancing the environmental perception of autonomous vehicles (AVs) driving in complex urban settings. However, the deployment of CCAM infrastructure necessitates the efficient selection of the computational processing layer and deployment of machine learning (ML) and deep learning (DL) models to achieve greater performance of AVs in complex urban environments. In this paper, we propose a computational framework and analyze the effectiveness of a custom-trained DL model (YOLOv8) when deployed in diverse devices and settings at the vehicle-edge-cloud-layered architecture. Our main focus is to understand the interplay and relationship between the DL model's accuracy and execution time during deployment at the layered framework. Therefore, we investigate the trade-offs between accuracy and time by the deployment process of the YOLOv8 model over each layer of the computational framework. We consider the CCAM infrastructures, i.e., sensory devices, computation, and communication at each layer. The findings reveal that the performance metrics results (e.g., 0.842 mAP@0.5) of deployed DL models remain consistent regardless of the device type across any layer of the framework. However, we observe that inference times for object detection tasks tend to decrease when the DL model is subjected to different environmental conditions. For instance, the Jetson AGX (non-GPU) outperforms the Raspberry Pi (non-GPU) by reducing inference time by 72%, whereas the Jetson AGX Xavier (GPU) outperforms the Jetson AGX ARMv8 (non-GPU) by reducing inference time by 90%. A complete average time comparison analysis for the transfer time, preprocess time, and total time of devices Apple M2 Max, Intel Xeon, Tesla T4, NVIDIA A100, Tesla V100, etc., is provided in the paper. Our findings direct the researchers and practitioners to select the most appropriate device type and environment for the deployment of DL models required for production. [ABSTRACT FROM AUTHOR]

This paper is dedicated to the investigation of the metrological properties of phase-sensitive reflectometric measurement systems, with a particular focus on addressing the non-uniformity of responses along optical fibers. The authors highlight challenges associated with the stochastic distribution of Rayleigh reflectors in fiber optic systems and propose a methodology for assessing response non-uniformity using both cross-correlation algorithms and machine learning approaches, using chirped-reflectometry as an example. The experimental process involves simulating deformation impact by altering the light source's wavelength and utilizing a chirped-reflectometer to estimate response non-uniformity. This paper also includes a comparison of results obtained from cross-correlation and neural network-based algorithms, revealing that the latter offers more than 34% improvement in accuracy when measuring phase differences. In conclusion, the study demonstrates how this methodology effectively evaluates response non-uniformity along different sections of optical fibers. [ABSTRACT FROM AUTHOR]

This paper provides a review of various machine learning approaches that have appeared in the literature aimed at individualizing or personalizing the amplification settings of hearing aids. After stating the limitations associated with the current one-size-fits-all settings of hearing aid prescriptions, a spectrum of studies in engineering and hearing science are discussed. These studies involve making adjustments to prescriptive values in order to enable preferred and individualized settings for a hearing aid user in an audio environment of interest to that user. This review gathers, in one place, a comprehensive collection of works that have been conducted thus far with respect to achieving the personalization or individualization of the amplification function of hearing aids. Furthermore, it underscores the impact that machine learning can have on enabling an improved and personalized hearing experience for hearing aid users. This paper concludes by stating the challenges and future research directions in this area. [ABSTRACT FROM AUTHOR]

One of the main lines of research in distributed learning in recent years is the one related to Federated Learning (FL). In this work, a decentralized Federated Learning algorithm based on consensus (CoL) is applied to Wireless Ad-hoc Networks (WANETs), where the agents communicate with other agents to share their learning model as they are available to the wireless connection range. When deploying a set of agents, it is essential to study whether all the WANET agents will be reachable before the deployment. The paper proposes to explore it by generating a simulation close to the real world using a framework (FIVE) that allows the easy development and modification of simulations based on Unity and SPADE agents. A fruit orchard with autonomous tractors is presented as a case study. The paper also presents how and why the concept of artifact has been included in the above-mentioned framework as a way to highlight the importance of some devices used in the environment that have to be located in specific places to ensure the full connection of the system. This inclusion is the first step to allow Digital Twins to be modeled with this framework, now allowing a Digital Shadow of those devices. [ABSTRACT FROM AUTHOR]

This survey provides a comprehensive overview of traditional techniques and deep learning-based methodologies for monocular visual odometry (VO), with a focus on displacement measurement applications. This paper outlines the fundamental concepts and general procedures for VO implementation, including feature detection, tracking, motion estimation, triangulation, and trajectory estimation. This paper also explores the research challenges inherent in VO implementation, including scale estimation and ground plane considerations. The scientific literature is rife with diverse methodologies aiming to overcome these challenges, particularly focusing on the problem of accurate scale estimation. This issue has been typically addressed through the reliance on knowledge regarding the height of the camera from the ground plane and the evaluation of feature movements on that plane. Alternatively, some approaches have utilized additional tools, such as LiDAR or depth sensors. This survey of approaches concludes with a discussion of future research challenges and opportunities in the field of monocular visual odometry. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is a machine learning (ML) technique that enables collaborative model training without sharing raw data, making it ideal for Internet of Things (IoT) applications where data are distributed across devices and privacy is a concern. Wireless Sensor Networks (WSNs) play a crucial role in IoT systems by collecting data from the physical environment. This paper presents a comprehensive survey of the integration of FL, IoT, and WSNs. It covers FL basics, strategies, and types and discusses the integration of FL, IoT, and WSNs in various domains. The paper addresses challenges related to heterogeneity in FL and summarizes state-of-the-art research in this area. It also explores security and privacy considerations and performance evaluation methodologies. The paper outlines the latest achievements and potential research directions in FL, IoT, and WSNs and emphasizes the significance of the surveyed topics within the context of current technological advancements. [ABSTRACT FROM AUTHOR]

The main purpose of this paper is to provide information on how to create a convolutional neural network (CNN) for extracting features from EEG signals. Our task was to understand the primary aspects of creating and fine-tuning CNNs for various application scenarios. We considered the characteristics of EEG signals, coupled with an exploration of various signal processing and data preparation techniques. These techniques include noise reduction, filtering, encoding, decoding, and dimension reduction, among others. In addition, we conduct an in-depth analysis of well-known CNN architectures, categorizing them into four distinct groups: standard implementation, recurrent convolutional, decoder architecture, and combined architecture. This paper further offers a comprehensive evaluation of these architectures, covering accuracy metrics, hyperparameters, and an appendix that contains a table outlining the parameters of commonly used CNN architectures for feature extraction from EEG signals. [ABSTRACT FROM AUTHOR]

Heart rate is an essential vital sign to evaluate human health. Remote heart monitoring using cheaply available devices has become a necessity in the twenty-first century to prevent any unfortunate situation caused by the hectic pace of life. In this paper, we propose a new method based on the transformer architecture with a multi-skip connection biLSTM decoder to estimate heart rate remotely from videos. Our method is based on the skin color variation caused by the change in blood volume in its surface. The presented heart rate estimation framework consists of three main steps: (1) the segmentation of the facial region of interest (ROI) based on the landmarks obtained by 3DDFA; (2) the extraction of the spatial and global features; and (3) the estimation of the heart rate value from the obtained features based on the proposed method. This paper investigates which feature extractor performs better by captioning the change in skin color related to the heart rate as well as the optimal number of frames needed to achieve better accuracy. Experiments were conducted using two publicly available datasets (LGI-PPGI and Vision for Vitals) and our own in-the-wild dataset (12 videos collected by four drivers). The experiments showed that our approach achieved better results than the previously published methods, making it the new state of the art on these datasets. [ABSTRACT FROM AUTHOR]

This paper addresses the issue of how to endow robots with motion skills, flexibility, and adaptability similar to human arms. It innovatively proposes a hybrid-primitive-frame-based robot skill learning algorithm and utilizes the policy improvement with a path integral algorithm to optimize the parameters of the hybrid primitive framework, enabling robots to possess skills similar to human arms. Firstly, the end of the robot is dynamically modeled using an admittance control model to give the robot flexibility. Secondly, the dynamic movement primitives are employed to model the robot's motion trajectory. Additionally, novel stiffness primitives and damping primitives are introduced to model the stiffness and damping parameters in the impedance model. The combination of the dynamic movement primitives, stiffness primitives, and damping primitives is called the hybrid primitive framework. Simulated experiments are designed to validate the effectiveness of the hybrid-primitive-frame-based robot skill learning algorithm, including point-to-point motion under external force disturbance and trajectory tracking under variable stiffness conditions. [ABSTRACT FROM AUTHOR]

Parkinson's Disease (PD) is a complex neurodegenerative disorder characterized by a spectrum of motor and non-motor symptoms, prominently featuring the freezing of gait (FOG), which significantly impairs patients' quality of life. Despite extensive research, the precise mechanisms underlying FOG remain elusive, posing challenges for effective management and treatment. This paper presents a comprehensive meta-analysis of FOG prediction and detection methodologies, with a focus on the integration of wearable sensor technology and machine learning (ML) approaches. Through an exhaustive review of the literature, this study identifies key trends, datasets, preprocessing techniques, feature extraction methods, evaluation metrics, and comparative analyses between ML and non-ML approaches. The analysis also explores the utilization of cueing devices. The limited adoption of explainable AI (XAI) approaches in FOG prediction research represents a significant gap. Improving user acceptance and comprehension requires an understanding of the logic underlying algorithm predictions. Current FOG detection and prediction research has a number of limitations, which are identified in the discussion. These include issues with cueing devices, dataset constraints, ethical and privacy concerns, financial and accessibility restrictions, and the requirement for multidisciplinary collaboration. Future research avenues center on refining explainability, expanding and diversifying datasets, adhering to user requirements, and increasing detection and prediction accuracy. The findings contribute to advancing the understanding of FOG and offer valuable guidance for the development of more effective detection and prediction methodologies, ultimately benefiting individuals affected by PD. [ABSTRACT FROM AUTHOR]

The annotation of magnetic resonance imaging (MRI) images plays an important role in deep learning-based MRI segmentation tasks. Semi-automatic annotation algorithms are helpful for improving the efficiency and reducing the difficulty of MRI image annotation. However, the existing semi-automatic annotation algorithms based on deep learning have poor pre-annotation performance in the case of insufficient segmentation labels. In this paper, we propose a semi-automatic MRI annotation algorithm based on semi-weakly supervised learning. In order to achieve a better pre-annotation performance in the case of insufficient segmentation labels, semi-supervised and weakly supervised learning were introduced, and a semi-weakly supervised learning segmentation algorithm based on sparse labels was proposed. In addition, in order to improve the contribution rate of a single segmentation label to the performance of the pre-annotation model, an iterative annotation strategy based on active learning was designed. The experimental results on public MRI datasets show that the proposed algorithm achieved an equivalent pre-annotation performance when the number of segmentation labels was much less than that of the fully supervised learning algorithm, which proves the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The transition to a low-carbon economy is one of the main challenges of our time. In this context, solar energy, along with many other technologies, has been developed to optimize performance. For example, solar trackers follow the sun's path to increase the generation capacity of photovoltaic plants. However, several factors need consideration to further optimize this process. Important variables include the distance between panels, surface reflectivity, bifacial panels, and climate variations throughout the day. Thus, this paper proposes an artificial intelligence-based algorithm for solar trackers that takes all these factors into account—mainly weather variations and the distance between solar panels. The methodology can be replicated anywhere in the world, and its effectiveness has been validated in a real solar plant with bifacial panels located in northeastern Brazil. The algorithm achieved gains of up to 7.83% on a cloudy day and obtained an average energy gain of approximately 1.2% when compared to a commercial solar tracker algorithm. [ABSTRACT FROM AUTHOR]

The growing urban population and traffic congestion underline the importance of building pedestrian-friendly environments to encourage walking as a preferred mode of transportation. However, a major challenge remains, which is the absence of such pedestrian-friendly walking environments. Identifying locations and routes with high pedestrian concentration is critical for improving pedestrian-friendly walking environments. This paper presents a quantitative method to map pedestrian walking behavior by utilizing real-time data from mobile phone sensors, focusing on the University of Moratuwa, Sri Lanka, as a case study. This holistic method integrates new urban data, such as location-based service (LBS) positioning data, and data clustering with unsupervised machine learning techniques. This study focused on the following three criteria for quantifying walking behavior: walking speed, walking time, and walking direction inside the experimental research context. A novel signal processing method has been used to evaluate speed signals, resulting in the identification of 622 speed clusters using K-means clustering techniques during specific morning and evening hours. This project uses mobile GPS signals and machine learning algorithms to track and classify pedestrian walking activity in crucial sites and routes, potentially improving urban walking through mapping. [ABSTRACT FROM AUTHOR]

This paper introduces a cutting-edge data architecture designed for a smart advertising context, prioritizing efficient data flow and performance, robust security, while guaranteeing data privacy and integrity. At the core of this study lies the application of federated learning (FL) as the primary methodology, which emphasizes the authenticity and privacy of data while promptly discarding irrelevant or fraudulent information. Our innovative data model employs a semi-random role assignment strategy based on a variety of criteria to efficiently collect and amalgamate data. The architecture is composed of model nodes, data nodes, and validator nodes, where the role of each node is determined by factors such as computational capability, interconnection quality, and historical performance records. A key feature of our proposed system is the selective engagement of a subset of nodes for modeling and validation, optimizing resource use and minimizing data loss. The AROUND social network platform serves as a real-world case study, illustrating the efficacy of our data architecture in a practical setting. Both simulated and real implementations of our architecture showcase its potential to dramatically curtail network traffic and average CPU usage, while preserving the accuracy of the FL model. Remarkably, the system is capable of achieving over a 50% reduction in both network traffic and average CPU usage even when the user count escalates by twenty-fold. The click rate, user engagement, and other parameters have also been evaluated, proving that the proposed architecture's advantages do not affect the smart advertising accuracy. These findings highlight the proposed architecture's capacity to scale efficiently and maintain high performance in smart advertising environments, making it a valuable contribution to the evolving landscape of digital marketing and FL. [ABSTRACT FROM AUTHOR]

With the escalation in the size and complexity of modern Denial of Service attacks, there is a need for research in the context of Machine Learning (ML) used in attack execution and defense against such attacks. This paper investigates the potential use of ML in generating behavioral telemetry data using Long Short-Term Memory network and spoofing requests for the analyzed traffic to look legitimate. For this research, a custom testing environment was built that listens for mouse and keyboard events and analyzes them accordingly. While the economic feasibility of this attack currently limits its immediate threat, advancements in technology could make it more cost-effective for attackers in the future. Therefore, proactive development of countermeasures remains essential to mitigate potential risks and stay ahead of evolving attack methods. [ABSTRACT FROM AUTHOR]

Measuring pilot mental workload (MWL) is crucial for enhancing aviation safety. However, MWL is a multi-dimensional construct that could be affected by multiple factors. Particularly, in the context of a more automated cockpit setting, the traditional methods of assessing pilot MWL may face challenges. Heart rate variability (HRV) has emerged as a potential tool for detecting pilot MWL during real-flight operations. This review aims to investigate the relationship between HRV and pilot MWL and to assess the performance of machine-learning-based MWL detection systems using HRV parameters. A total of 29 relevant papers were extracted from three databases for review based on rigorous eligibility criteria. We observed significant variability across the reviewed studies, including study designs and measurement methods, as well as machine-learning techniques. Inconsistent results were observed regarding the differences in HRV measures between pilots under varying levels of MWL. Furthermore, for studies that developed HRV-based MWL detection systems, we examined the diverse model settings and discovered that several advanced techniques could be used to address specific challenges. This review serves as a practical guide for researchers and practitioners who are interested in employing HRV indicators for evaluating MWL and wish to incorporate cutting-edge techniques into their MWL measurement approaches. [ABSTRACT FROM AUTHOR]

Within research on the cross-view geolocation of UAVs, differences in image sources and interference from similar scenes pose huge challenges. Inspired by multimodal machine learning, in this paper, we design a single-stream pyramid transformer network (SSPT). The backbone of the model uses the self-attention mechanism to enrich its own internal features in the early stage and uses the cross-attention mechanism in the later stage to refine and interact with different features to eliminate irrelevant interference. In addition, in the post-processing part of the model, a header module is designed for upsampling to generate heat maps, and a Gaussian weight window is designed to assign label weights to make the model converge better. Together, these methods improve the positioning accuracy of UAV images in satellite images. Finally, we also use style transfer technology to simulate various environmental changes in order to expand the experimental data, further proving the environmental adaptability and robustness of the method. The final experimental results show that our method yields significant performance improvement: The relative distance score (RDS) of the SSPT-384 model on the benchmark UL14 dataset is significantly improved from 76.25% to 84.40%, while the meter-level accuracy (MA) of 3 m, 5 m, and 20 m is increased by 12%, 12%, and 10%, respectively. For the SSPT-256 model, the RDS has been increased to 82.21%, and the meter-level accuracy (MA) of 3 m, 5 m, and 20 m has increased by 5%, 5%, and 7%, respectively. It still shows strong robustness on the extended thermal infrared (TIR), nighttime, and rainy day datasets. [ABSTRACT FROM AUTHOR]

The integration of cutting-edge technologies such as the Internet of Things (IoT), robotics, and machine learning (ML) has the potential to significantly enhance the productivity and profitability of traditional fish farming. Farmers using traditional fish farming methods incur enormous economic costs owing to labor-intensive schedule monitoring and care, illnesses, and sudden fish deaths. Another ongoing issue is automated fish species recommendation based on water quality. On the one hand, the effective monitoring of abrupt changes in water quality may minimize the daily operating costs and boost fish productivity, while an accurate automatic fish recommender may aid the farmer in selecting profitable fish species for farming. In this paper, we present AquaBot, an IoT-based system that can automatically collect, monitor, and evaluate the water quality and recommend appropriate fish to farm depending on the values of various water quality indicators. A mobile robot has been designed to collect parameter values such as the pH, temperature, and turbidity from all around the pond. To facilitate monitoring, we have developed web and mobile interfaces. For the analysis and recommendation of suitable fish based on water quality, we have trained and tested several ML algorithms, such as the proposed custom ensemble model, random forest (RF), support vector machine (SVM), decision tree (DT), K-nearest neighbor (KNN), logistic regression (LR), bagging, boosting, and stacking, on a real-time pond water dataset. The dataset has been preprocessed with feature scaling and dataset balancing. We have evaluated the algorithms based on several performance metrics. In our experiment, our proposed ensemble model has delivered the best result, with 94% accuracy, 94% precision, 94% recall, a 94% F1-score, 93% MCC, and the best AUC score for multi-class classification. Finally, we have deployed the best-performing model in a web interface to provide cultivators with recommendations for suitable fish farming. Our proposed system is projected to not only boost production and save money but also reduce the time and intensity of the producer's manual labor. [ABSTRACT FROM AUTHOR]

The high-speed railway subgrade compaction quality is controlled by the compaction degree (K), with the maximum dry density (ρdmax) serving as a crucial indicator for its calculation. The current mechanisms and methods for determining the ρdmax still suffer from uncertainties, inefficiencies, and lack of intelligence. These deficiencies can lead to insufficient assessments for the high-speed railway subgrade compaction quality, further impacting the operational safety of high-speed railways. In this paper, a novel method for full-section assessment of high-speed railway subgrade compaction quality based on ML-interval prediction theory is proposed. Firstly, based on indoor vibration compaction tests, a method for determining the ρdmax based on the dynamic stiffness Krb turning point is proposed. Secondly, the Pso-OptimalML-Adaboost (POA) model for predicting ρdmax is determined based on three typical machine learning (ML) algorithms, which are back propagation neural network (BPNN), support vector regression (SVR), and random forest (RF). Thirdly, the interval prediction theory is introduced to quantify the uncertainty in ρdmax prediction. Finally, based on the Bootstrap-POA-ANN interval prediction model and spatial interpolation algorithms, the interval distribution of ρdmax across the full-section can be determined, and a model for full-section assessment of compaction quality is developed based on the compaction standard (95%). Moreover, the proposed method is applied to determine the optimal compaction thicknesses (H0), within the station subgrade test section in the southwest region. The results indicate that: (1) The PSO-BPNN-AdaBoost model performs better in the accuracy and error metrics, which is selected as the POA model for predicting ρdmax. (2) The Bootstrap-POA-ANN interval prediction model for ρdmax can construct clear and reliable prediction intervals. (3) The model for full-section assessment of compaction quality can provide the full-section distribution interval for K. Comparing the H0 of 50~60 cm and 60~70 cm, the compaction quality is better with the H0 of 40~50 cm. The research findings can provide effective techniques for assessing the compaction quality of high-speed railway subgrades. [ABSTRACT FROM AUTHOR]

This paper proposes a new method for recognizing, extracting, and processing Phase-Resolved Partial Discharge (PRPD) patterns from two-dimensional plots to identify specific defect types affecting electrical equipment without human intervention while retaining the principals that make PRPD analysis an effective diagnostic technique. The proposed method does not rely on training complex deep learning algorithms which demand substantial computational resources and extensive datasets that can pose significant hurdles for the application of on-line partial discharge monitoring. Instead, the developed Cosine Cluster Net (CCNet) model, which is an image processing pipeline, can extract and process patterns from any two-dimensional PRPD plot before employing the cosine similarity function to measure the likeness of the patterns to predefined templates of known defect types. The PRPD pattern recognition capabilities of the model were tested using several manually classified PRPD images available in the existing literature. The model consistently produced similarity scores that identified the same defect type as the one from the manual classification. The successful defect type reporting from the initial trials of the CCNet model together with the speed of the identification, which typically does not exceed four seconds, indicates potential for real-time applications. [ABSTRACT FROM AUTHOR]

This paper presents the results of a study on data preprocessing and modeling for predicting corrosion in water pipelines of a steel industrial plant. The use case is a cooling circuit consisting of both direct and indirect cooling. In the direct cooling circuit, water comes into direct contact with the product, whereas in the indirect one, it does not. In this study, advanced machine learning techniques, such as extreme gradient boosting and deep neural networks, have been employed for two distinct applications. Firstly, a virtual sensor was created to estimate the corrosion rate based on influencing process variables, such as pH and temperature. Secondly, a predictive tool was designed to foresee the future evolution of the corrosion rate, considering past values of both influencing variables and the corrosion rate. The results show that the most suitable algorithm for the virtual sensor approach is the dense neural network, with MAPE values of (25 ± 4)% and (11 ± 4)% for the direct and indirect circuits, respectively. In contrast, different results are obtained for the two circuits when following the predictive tool approach. For the primary circuit, the convolutional neural network yields the best results, with MAPE = 4% on the testing set, whereas for the secondary circuit, the LSTM recurrent network shows the highest prediction accuracy, with MAPE = 9%. In general, models employing temporal windows have emerged as more suitable for corrosion prediction, with model performance significantly improving with a larger dataset. [ABSTRACT FROM AUTHOR]

Region proposal-based detectors, such as Region-Convolutional Neural Networks (R-CNNs), Fast R-CNNs, Faster R-CNNs, and Region-Based Fully Convolutional Networks (R-FCNs), employ a two-stage process involving region proposal generation followed by classification. This approach is effective but computationally intensive and typically slower than proposal-free methods. Therefore, region proposal-free detectors are becoming popular to balance accuracy and speed. This paper proposes a proposal-free, fully convolutional network (PF-FCN) that outperforms other state-of-the-art, proposal-free methods. Unlike traditional region proposal-free methods, PF-FCN can generate a "box map" based on regression training techniques. This box map comprises a set of vectors, each designed to produce bounding boxes corresponding to the positions of objects in the input image. The channel and spatial contextualized sub-network are further designed to learn a "box map". In comparison to renowned proposal-free detectors such as CornerNet, CenterNet, and You Look Only Once (YOLO), PF-FCN utilizes a fully convolutional, single-pass method. By reducing the need for fully connected layers and filtering center points, the method considerably reduces the number of trained parameters and optimizes the scalability across varying input sizes. Evaluations of benchmark datasets suggest the effectiveness of PF-FCN: the proposed model achieved an mAP of 89.6% on PASCAL VOC 2012 and 71.7% on MS COCO, which are higher than those of the baseline Fully Convolutional One-Stage Detector (FCOS) and other classical proposal-free detectors. The results prove the significance of proposal-free detectors in both practical applications and future research. [ABSTRACT FROM AUTHOR]

Encryption is a fundamental security measure to safeguard data during transmission to ensure confidentiality while at the same time posing a great challenge for traditional packet and traffic inspection. In response to the proliferation of diverse network traffic patterns from Internet-of-Things devices, websites, and mobile applications, understanding and classifying encrypted traffic are crucial for network administrators, cybersecurity professionals, and policy enforcement entities. This paper presents a comprehensive survey of recent advancements in machine-learning-driven encrypted traffic analysis and classification. The primary goals of our survey are two-fold: First, we present the overall procedure and provide a detailed explanation of utilizing machine learning in analyzing and classifying encrypted network traffic. Second, we review state-of-the-art techniques and methodologies in traffic analysis. Our aim is to provide insights into current practices and future directions in encrypted traffic analysis and classification, especially machine-learning-based analysis. [ABSTRACT FROM AUTHOR]

In the last few decades, there has been an ongoing transformation of our healthcare system with larger use of sensors for remote care and artificial intelligence (AI) tools. In particular, sensors improved by new algorithms with learning capabilities have proven their value for better patient care. Sensors and AI systems are no longer only non-autonomous devices such as the ones used in radiology or surgical robots; there are novel tools with a certain degree of autonomy aiming to largely modulate the medical decision. Thus, there will be situations in which the doctor is the one making the decision and has the final say and other cases in which the doctor might only apply the decision presented by the autonomous device. As those are two hugely different situations, they should not be treated the same way, and different liability rules should apply. Despite a real interest in the promise of sensors and AI in medicine, doctors and patients are reluctant to use it. One important reason is a lack clear definition of liability. Nobody wants to be at fault, or even prosecuted, because they followed the advice from an AI system, notably when it has not been perfectly adapted to a specific patient. Fears are present even with simple sensors and AI use, such as during telemedicine visits based on very useful, clinically pertinent sensors; with the risk of missing an important parameter; and, of course, when AI appears "intelligent", potentially replacing the doctors' judgment. This paper aims to provide an overview of the liability of the health professional in the context of the use of sensors and AI tools in remote healthcare, analyzing four regimes: the contract-based approach, the approach based on breach of duty to inform, the fault-based approach, and the approach related to the good itself. We will also discuss future challenges and opportunities in the promising domain of sensors and AI use in medicine. [ABSTRACT FROM AUTHOR]

Malicious social bots pose a serious threat to social network security by spreading false information and guiding bad opinions in social networks. The singularity and scarcity of single organization data and the high cost of labeling social bots have given rise to the construction of federated models that combine federated learning with social bot detection. In this paper, we first combine the federated learning framework with the Relational Graph Convolutional Neural Network (RGCN) model to achieve federated social bot detection. A class-level cross entropy loss function is applied in the local model training to mitigate the effects of the class imbalance problem in local data. To address the data heterogeneity issue from multiple participants, we optimize the classical federated learning algorithm by applying knowledge distillation methods. Specifically, we adjust the client-side and server-side models separately: training a global generator to generate pseudo-samples based on the local data distribution knowledge to correct the optimization direction of client-side classification models, and integrating client-side classification models' knowledge on the server side to guide the training of the global classification model. We conduct extensive experiments on widely used datasets, and the results demonstrate the effectiveness of our approach in social bot detection in heterogeneous data scenarios. Compared to baseline methods, our approach achieves a nearly 3–10% improvement in detection accuracy when the data heterogeneity is larger. Additionally, our method achieves the specified accuracy with minimal communication rounds. [ABSTRACT FROM AUTHOR]

Advancements in imaging, computer vision, and automation have revolutionized various fields, including field-based high-throughput plant phenotyping (FHTPP). This integration allows for the rapid and accurate measurement of plant traits. Deep Convolutional Neural Networks (DCNNs) have emerged as a powerful tool in FHTPP, particularly in crop segmentation—identifying crops from the background—crucial for trait analysis. However, the effectiveness of DCNNs often hinges on the availability of large, labeled datasets, which poses a challenge due to the high cost of labeling. In this study, a deep learning with bagging approach is introduced to enhance crop segmentation using high-resolution RGB images, tested on the NU-Spidercam dataset from maize plots. The proposed method outperforms traditional machine learning and deep learning models in prediction accuracy and speed. Remarkably, it achieves up to 40 % higher Intersection-over-Union (IoU) than the threshold method and 11 % over conventional machine learning, with significantly faster prediction times and manageable training duration. Crucially, it demonstrates that even small labeled datasets can yield high accuracy in semantic segmentation. This approach not only proves effective for FHTPP but also suggests potential for broader application in remote sensing, offering a scalable solution to semantic segmentation challenges. This paper is accompanied by publicly available source code. [ABSTRACT FROM AUTHOR]

Centrifugal pumps are essential in many industrial processes. An accurate operation diagnosis of centrifugal pumps is crucial to ensure their reliable operation and extend their useful life. In real industry applications, many centrifugal pumps lack flowmeters and accurate pressure sensors, and therefore, it is not possible to determine whether the pump is operating near its best efficiency point (BEP). This paper investigates the detection of off-design operation and cavitation for centrifugal pumps with accelerometers and current sensors. To this end, a centrifugal pump was tested under off-design conditions and various levels of cavitation. A three-axis accelerometer and three Hall-effect current sensors were used to collect vibration and stator current signals simultaneously under each state. Both kinds of signals were evaluated for their effectiveness in operation diagnosis. Signal processing methods, including wavelet threshold function, variational mode decomposition (VMD), Park vector modulus transformation, and a marginal spectrum were introduced for feature extraction. Seven families of machine learning-based classification algorithms were evaluated for their performance when used for off-design and cavitation identification. The obtained results, using both types of signals, prove the effectiveness of both approaches and the advantages of combining them in achieving the most reliable operation diagnosis results for centrifugal pumps. [ABSTRACT FROM AUTHOR]

Tool wear prediction is of great significance in industrial production. Current tool wear prediction methods mainly rely on the indirect estimation of machine learning, which focuses more on estimating the current tool wear state and lacks effective quantification of random uncertainty factors. To overcome these shortcomings, this paper proposes a novel method for predicting cutting tool wear. In the offline phase, the multiple degradation features were modeled using the Brownian motion stochastic process and a SVR model was trained for mapping the features and the tool wear values. In the online phase, the Bayesian inference was used to update the random parameters of the feature degradation model, and the future trend of the features was estimated using simulation samples. The estimation results were input into the SVR model to achieve in-advance prediction of the cutting tool wear in the form of distribution densities. An experimental tool wear dataset was used to verify the effectiveness of the proposed method. The results demonstrate that the method shows superiority in prediction accuracy and stability. [ABSTRACT FROM AUTHOR]

The current paper presents helical gearbox defect detection models built from raw vibration signals measured using a triaxial accelerometer. Gear faults, such as localized pitting, localized wear on helical pinion tooth flanks, and low lubricant level, are under observation for three rotating velocities of the actuator and three load levels at the speed reducer output. The emphasis is on the strong connection between the gear faults and the fundamental meshing frequency GMF, its harmonics, and the sidebands found in the vibration spectrum as an effect of the amplitude modulation (AM) and phase modulation (PM). Several sets of features representing powers on selected frequency bands or/and associated peak amplitudes from the vibration spectrum, and also, for comparison, time-domain and frequency-domain statistical feature sets, are proposed as predictors in the defect detection task. The best performing detection model, with a testing accuracy of 99.73%, is based on SVM (Support Vector Machine) with a cubic kernel, and the features used are the band powers associated with six GMF harmonics and two sideband pairs for all three accelerometer axes, regardless of the rotation velocities and the load levels. [ABSTRACT FROM AUTHOR]

Autonomous driving technology is considered the trend of future transportation. Millimeter-wave radar, with its ability for long-distance detection and all-weather operation, is a key sensor for autonomous driving. The development of various technologies in autonomous driving relies on extensive simulation testing, wherein simulating the output of real radar through radar models plays a crucial role. Currently, there are numerous distinctive radar modeling methods. To facilitate the better application and development of radar modeling methods, this study first analyzes the mechanism of radar detection and the interference factors it faces, to clarify the content of modeling and the key factors influencing modeling quality. Then, based on the actual application requirements, key indicators for measuring radar model performance are proposed. Furthermore, a comprehensive introduction is provided to various radar modeling techniques, along with the principles and relevant research progress. The advantages and disadvantages of these modeling methods are evaluated to determine their characteristics. Lastly, considering the development trends of autonomous driving technology, the future direction of radar modeling techniques is analyzed. Through the above content, this paper provides useful references and assistance for the development and application of radar modeling methods. [ABSTRACT FROM AUTHOR]

Predicting anomalies in manufacturing assembly lines is crucial for reducing time and labor costs and improving processes. For instance, in rocket assembly, premature part failures can lead to significant financial losses and labor inefficiencies. With the abundance of sensor data in the Industry 4.0 era, machine learning (ML) offers potential for early anomaly detection. However, current ML methods for anomaly prediction have limitations, with F1 measure scores of only 50% and 66% for prediction and detection, respectively. This is due to challenges like the rarity of anomalous events, scarcity of high-fidelity simulation data (actual data are expensive), and the complex relationships between anomalies not easily captured using traditional ML approaches. Specifically, these challenges relate to two dimensions of anomaly prediction: predicting when anomalies will occur and understanding the dependencies between them. This paper introduces a new method called Robust and Interpretable 2D Anomaly Prediction (RI2AP) designed to address both dimensions effectively. RI2AP is demonstrated on a rocket assembly simulation, showing up to a 30-point improvement in F1 measure compared to current ML methods. This highlights its potential to enhance automated anomaly prediction in manufacturing. Additionally, RI2AP includes a novel interpretation mechanism inspired by a causal-influence framework, providing domain experts with valuable insights into sensor readings and their impact on predictions. Finally, the RI2AP model was deployed in a real manufacturing setting for assembling rocket parts. Results and insights from this deployment demonstrate the promise of RI2AP for anomaly prediction in manufacturing assembly pipelines. [ABSTRACT FROM AUTHOR]

The recent rapid growth in Internet of Things (IoT) technologies is enriching our daily lives but significant information security risks in IoT fields have become apparent. In fact, there have been large-scale botnet attacks that exploit undiscovered vulnerabilities, known as zero-day attacks. Several intrusion detection methods based on network traffic monitoring have been proposed to address this issue. These methods employ federated learning to share learned attack information among multiple IoT networks, aiming to improve collective detection capabilities against attacks including zero-day attacks. Although their ability to detect zero-day attacks with high precision has been confirmed, challenges such as autonomous labeling of attacks from traffic information and attack information sharing between different device types still remain. To resolve the issues, this paper proposes IDAC, a novel intrusion detection method with autonomous attack candidate labeling and federated learning-based attack candidate sharing. The labeling of attack candidates in IDAC is executed using information autonomously extracted from traffic information, and the labeling can also be applied to zero-day attacks. The federated learning-based attack candidate sharing enables candidate aggregation from multiple networks, and it executes attack determination based on the aggregated similar candidates. Performance evaluations demonstrated that IDS with IDAC within networks based on attack candidates is feasible and achieved comparable detection performance against multiple attacks including zero-day attacks compared to the existing methods while suppressing false positives in the extraction of attack candidates. In addition, the sharing of autonomously extracted attack candidates from multiple networks improves both detection performance and the required time for attack detection. [ABSTRACT FROM AUTHOR]

Assessing mobility in daily life can provide significant insights into several clinical conditions, such as Chronic Obstructive Pulmonary Disease (COPD). In this paper, we present a comprehensive analysis of wearable devices' performance in gait speed estimation and explore optimal device combinations for everyday use. Using data collected from smartphones, smartwatches, and smart shoes, we evaluated the individual capabilities of each device and explored their synergistic effects when combined, thereby accommodating the preferences and possibilities of individuals for wearing different types of devices. Our study involved 20 healthy subjects performing a modified Six-Minute Walking Test (6MWT) under various conditions. The results revealed only little performance differences among devices, with the combination of smartwatches and smart shoes exhibiting superior estimation accuracy. Particularly, smartwatches captured additional health-related information and demonstrated enhanced accuracy when paired with other devices. Surprisingly, wearing all devices concurrently did not yield optimal results, suggesting a potential redundancy in feature extraction. Feature importance analysis highlighted key variables contributing to gait speed estimation, providing valuable insights for model refinement. [ABSTRACT FROM AUTHOR]

WiFi Channel State Information (CSI)-based human action recognition using convolutional neural networks (CNNs) has emerged as a promising approach for non-intrusive activity monitoring. However, the integrity and reliability of the reported performance metrics are susceptible to data leakage, wherein information from the test set inadvertently influences the training process, leading to inflated accuracy rates. In this paper, we conduct a critical analysis of a notable IEEE Sensors Journal study on WiFi CSI-based human action recognition, uncovering instances of data leakage resulting from the absence of subject-based data partitioning. Empirical investigation corroborates the lack of exclusivity of individuals across dataset partitions, underscoring the importance of rigorous data management practices. Furthermore, we demonstrate that employing data partitioning with respect to humans results in significantly lower precision rates than the reported 99.9% precision, highlighting the exaggerated nature of the original findings. Such inflated results could potentially discourage other researchers and impede progress in the field by fostering a sense of complacency. [ABSTRACT FROM AUTHOR]

The arising of the Cyber–Physical Systems' vision and concepts drives technological evolution toward a new architectural design for the infrastructure of an environment referred to as a Smart Environment. This perspective alters the way systems within Smart City landscapes are conceived, designed, and ultimately realized. Modular architecture, resource-sharing techniques, and precise deployment approaches (such as microservices-oriented or reliant on the FaaS paradigm) serve as the cornerstones of a Smart City cognizant of multiple Cyber–Physical Systems composing it. This paper presents a framework integrating Digital Decisioning, encompassing the automated combination of human-derived knowledge and data-derived knowledge (e.g., business rules and machine learning), to enhance decision-making processes and application definition within the Smart City context. [ABSTRACT FROM AUTHOR]

Photothermal techniques are infrared remote sensing techniques that have been used for biomedical applications, as well as industrial non-destructive testing (NDT). Machine learning is a branch of artificial intelligence, which includes a set of algorithms for learning from past data and analyzing new data, without being explicitly programmed to do so. In this paper, we first review the latest development of machine learning and its applications in photothermal techniques. Next, we present our latest work on machine learning for data analysis in opto-thermal transient emission radiometry (OTTER), which is a type of photothermal technique that has been extensively used in skin hydration, skin hydration depth profiles, skin pigments, as well as topically applied substances and skin penetration measurements. We have investigated different algorithms, such as random forest regression, gradient boosting regression, support vector machine (SVM) regression, and partial least squares regression, as well as deep learning neural network regression. We first introduce the theoretical background, then illustrate its applications with experimental results. [ABSTRACT FROM AUTHOR]

Low-cost ambient sensors have been identified as a promising technology for monitoring air pollution at a high spatio-temporal resolution. However, the pollutant data captured by these cost-effective sensors are less accurate than their conventional counterparts and require careful calibration to improve their accuracy and reliability. In this paper, we propose to leverage temporal information, such as the duration of time a sensor has been deployed and the time of day the reading was taken, in order to improve the calibration of low-cost sensors. This information is readily available and has so far not been utilized in the reported literature for the calibration of cost-effective ambient gas pollutant sensors. We make use of three data sets collected by research groups around the world, who gathered the data from field-deployed low-cost CO and NO2 sensors co-located with accurate reference sensors. Our investigation shows that using the temporal information as a co-variate can significantly improve the accuracy of common machine learning-based calibration techniques, such as Random Forest and Long Short-Term Memory. [ABSTRACT FROM AUTHOR]

Due to connectivity and automation trends, the medical device industry is experiencing increased demand for safety and security mechanisms. Anomaly detection has proven to be a valuable approach for ensuring safety and security in other industries, such as automotive or IT. Medical devices must operate across a wide range of values due to variations in patient anthropometric data, making anomaly detection based on a simple threshold for signal deviations impractical. For example, surgical robots directly contacting the patient's tissue require precise sensor data. However, since the deformation of the patient's body during interaction or movement is highly dependent on body mass, it is impossible to define a single threshold for implausible sensor data that applies to all patients. This also involves statistical methods, such as Z-score, that consider standard deviation. Even pure machine learning algorithms cannot be expected to provide the required accuracy simply due to the lack of available training data. This paper proposes using hybrid filters by combining dynamic system models based on expert knowledge and data-based models for anomaly detection in an operating room scenario. This approach can improve detection performance and explainability while reducing the computing resources needed on embedded devices, enabling a distributed approach to anomaly detection. [ABSTRACT FROM AUTHOR]

Bats play a pivotal role in maintaining ecological balance, and studying their behaviors offers vital insights into environmental health and aids in conservation efforts. Determining the presence of various bat species in an environment is essential for many bat studies. Specialized audio sensors can be used to record bat echolocation calls that can then be used to identify bat species. However, the complexity of bat calls presents a significant challenge, necessitating expert analysis and extensive time for accurate interpretation. Recent advances in neural networks can help identify bat species automatically from their echolocation calls. Such neural networks can be integrated into a complete end-to-end system that leverages recent internet of things (IoT) technologies with long-range, low-powered communication protocols to implement automated acoustical monitoring. This paper presents the design and implementation of such a system that uses a tiny neural network for interpreting sensor data derived from bat echolocation signals. A highly compact convolutional neural network (CNN) model was developed that demonstrated excellent performance in bat species identification, achieving an F1-score of 0.9578 and an accuracy rate of 97.5%. The neural network was deployed, and its performance was evaluated on various alternative edge devices, including the NVIDIA Jetson Nano and Google Coral. [ABSTRACT FROM AUTHOR]