Mobile Sensor Research Articles

MLSTL-WSN: machine learning-based intrusion detection using SMOTETomek in WSNs

In the domain of cyber-physical systems, wireless sensor networks (WSNs) play a pivotal role as infrastructures, encompassing both stationary and mobile sensors. These sensors self-organize and establish multi-hop connections for communication, collectively sensing, gathering, processing, and transmitting data about their surroundings. Despite their significance, WSNs face rapid and detrimental attacks that can disrupt functionality. Existing intrusion detection methods for WSNs encounter challenges such as low detection rates, computational overhead, and false alarms. These issues stem from sensor node resource constraints, data redundancy, and high correlation within the network. To address these challenges, we propose an innovative intrusion detection approach that integrates machine learning (ML) techniques with the Synthetic Minority Oversampling Technique Tomek Link (SMOTE-TomekLink) algorithm. This blend synthesizes minority instances and eliminates Tomek links, resulting in a balanced dataset that significantly enhances detection accuracy in WSNs. Additionally, we incorporate feature scaling through standardization to render input features consistent and scalable, facilitating more precise training and detection. To counteract imbalanced WSN datasets, we employ the SMOTE-Tomek resampling technique, mitigating overfitting and underfitting issues. Our comprehensive evaluation, using the wireless sensor network dataset (WSN-DS) containing 374,661 records, identifies the optimal model for intrusion detection in WSNs. The standout outcome of our research is the remarkable performance of our model. In binary classification scenarios, it achieves an accuracy rate of 99.78%, and in multiclass classification scenarios, it attains an exceptional accuracy rate of 99.92%. These findings underscore the efficiency and superiority of our proposal in the context of WSN intrusion detection, showcasing its effectiveness in detecting and mitigating intrusions in WSNs.

Dynamic clustering via branched deep learning enhances personalization of stress prediction from mobile sensor data

College students experience ever-increasing levels of stress, leading to a wide range of health problems. In this context, monitoring and predicting students’ stress levels is crucial and, fortunately, made possible by the growing support for data collection via mobile devices. However, predicting stress levels from mobile phone data remains a challenging task, and off-the-shelf deep learning models are inapplicable or inefficient due to data irregularity, inter-subject variability, and the “cold start problem”. To overcome these challenges, we developed a platform named Branched CALM-Net that aims to predict students’ stress levels through dynamic clustering in a personalized manner. This is the first platform that leverages the branching technique in a multitask setting to achieve personalization and continuous adaptation. Our method achieves state-of-the-art performance in predicting student stress from mobile sensor data collected as part of the Dartmouth StudentLife study, with a ROC AUC 37% higher and a PR AUC surpassing that of the nearest baseline models. In the cold-start online learning setting, Branched CALM-Net outperforms other models, attaining an average F1 score of 87% with just 1 week of training data for a new student, which shows it is reliable and effective at predicting stress levels from mobile data.

Structured Isosurface Mapping of 3-D Scalar Fields While Seeking Extremum With Mobile Sensor Networks

Structured Isosurface Mapping of 3-D Scalar Fields While Seeking Extremum With Mobile Sensor Networks

Lessons and Untapped Potential of Smartphone-Based Physical Activity Interventions for Mental Health: Narrative Review.

Physical activity has well-known and broad health benefits, including antidepressive and anxiolytic effects. However, only approximately half of Americans meet even the minimum exercise recommendations. Individuals with anxiety, depression, or related conditions are even less likely to do so. With the advent of mobile sensors and phones, experts have quickly noted the utility of technology for the enhanced measurement of and intervention for physical activity. In addition to being more accessible than in-person approaches, technology-driven interventions may uniquely engage key mechanisms of behavior change such as self-awareness. This study aims to provide a narrative overview and specific recommendations for future research on smartphone-based physical activity interventions for psychological disorders or concerns. In this paper, we summarized early efforts to adapt and test smartphone-based or smartphone-supported physical activity interventions for mental health. The included articles described or reported smartphone-delivered or smartphone-supported interventions intended to increase physical activity or reduce sedentary behavior and included an emotional disorder, concern, or symptom as an outcome measure. We attempted to extract details regarding the intervention designs, trial designs, study populations, outcome measures, and inclusion of adaptations specifically for mental health. In taking a narrative lens, we drew attention to the type of work that has been done and used these exemplars to discuss key directions to build on. To date, most studies have examined mental health outcomes as secondary or exploratory variables largely in the context of managing medical concerns (eg, cancer and diabetes). Few trials have recruited psychiatric populations or explicitly aimed to target psychiatric concerns. Consequently, although there are encouraging signals that smartphone-based physical activity interventions could be feasible, acceptable, and efficacious for individuals with mental illnesses, this remains an underexplored area. Promising avenues for tailoring validated smartphone-based interventions include adding psychoeducation (eg, the relationship between depression, physical activity, and inactivity), offering psychosocial treatment in parallel (eg, cognitive restructuring), and adding personalized coaching. To conclude, we offer specific recommendations for future research, treatment development, and implementation in this area, which remains open and promising for flexible, highly scalable support.

A Review of Fault Detecting Devices for Belt Conveyor Idlers

The shift towards automated inspection methods represents considerable progress in conveyor system maintenance, enhancing safety and efficiency while posing challenges in data analysis and implementation costs. This study critically analyses sensor technologies and inspection methods for detecting faults in conveyor belt idlers, highlighting their essential role in preserving the operational integrity of industrial conveyor systems. By synthesizing various research findings, the study assesses the effectiveness of different sensor devices in identifying defects, including built-in sensors, fixed sensor options like acoustic, ultrasonic sensors, cameras, accelerometers, and Distributed Optical Fibre Sensors (DOFS), as well as mobile sensor systems. Our findings emphasize the accuracy of robot-based systems in identifying bearing defects, the comprehensive coverage provided by drones for medium-scale inspections, the constant monitoring offered by integrated idler sensors, and the ability of fixed sensors to detect mechanical faults despite environmental challenges. This research adds to the ongoing discussion on enhancing conveyor system dependability through technological advancements, providing insights into potential future developments that could further refine maintenance strategies in the sector.

Modeling multiple sclerosis using mobile and wearable sensor data

Multiple sclerosis (MS) is a neurological disease of the central nervous system that is the leading cause of non-traumatic disability in young adults. Clinical laboratory tests and neuroimaging studies are the standard methods to diagnose and monitor MS. However, due to infrequent clinic visits, it is fundamental to identify remote and frequent approaches for monitoring MS, which enable timely diagnosis, early access to treatment, and slowing down disease progression. In this work, we investigate the most reliable, clinically useful, and available features derived from mobile and wearable devices as well as their ability to distinguish people with MS (PwMS) from healthy controls, recognize MS disability and fatigue levels. To this end, we formalize clinical knowledge and derive behavioral markers to characterize MS. We evaluate our approach on a dataset we collected from 55 PwMS and 24 healthy controls for a total of 489 days conducted in free-living conditions. The dataset contains wearable sensor data – e.g., heart rate – collected using an arm-worn device, smartphone data – e.g., phone locks – collected through a mobile application, patient health records – e.g., MS type – obtained from the hospital, and self-reports – e.g., fatigue level – collected using validated questionnaires administered via the mobile application. Our results demonstrate the feasibility of using features derived from mobile and wearable sensors to monitor MS. Our findings open up opportunities for continuous monitoring of MS in free-living conditions and can be used to evaluate and guide the effectiveness of treatments, manage the disease, and identify participants for clinical trials.

Speech recognition based on mobile sensor networks application in English education intelligent assisted learning system

With the popularity of English learning and the development of mobile technology, the development of intelligent assisted learning system has become an effective learning method. The purpose of this study is to improve the speech recognition performance of English education intelligent learning assistance system by using mobile sensor networks, and improve the learning effect of learners. This paper uses a speech recognition algorithm based on mobile sensor network to acquire learners' speech signals with multiple sensor nodes. By preprocessing and feature extraction of acquired signals, machine learning algorithm is applied to recognize them, thus improving the recognition accuracy. The experimental results show that compared with traditional speech recognition methods, the speech recognition system based on mobile sensor network has better performance in the case of background noise and speaker change. When learners use the system to learn English, they can get more accurate and reliable speech recognition results, improve the learning effect and interactive experience, and provide a more effective learning tool for English learners.

Human Activity Recognition Using Inertial Sensors in a Smartphone: Technical Background(Review)

Human Activity Recognition (HAR) stands at the intersection of machine learning, deep learning, and sensor technology, primarily focusing on leveraging inertial sensors in smartphones and wearable devices. This paper presents a comprehensive technical overview of HAR, examining the amalgamation of machine learning and deep learning systems while considering the data inputs from mobile and wearable inertial sensors. The review encompasses a broad spectrum of methodologies applied to HAR, ranging from classical machine learning algorithms to cutting-edge deep learning architectures. Emphasis is placed on the nuanced challenges and opportunities posed using inertial sensors in smartphones and wearables. This includes discussions on data preprocessing strategies, feature extraction methods, and model architectures, accounting for the unique characteristics of sensor data, such as noise, variability, and power consumption. The paper explores recent advancements, scrutinizing state-of-the-art approaches, innovative model architectures, and emerging trends in HAR. Through a comparative evaluation of various machine learning and deep learning techniques, the review aims to guide researchers and practitioners in selecting the most appropriate methods for HAR applications across diverse scenarios. In conclusion, this paper serves as an inclusive guide to the technical landscape of HAR, incorporating insights from both mobile and wearable inertial sensors. By synthesizing existing knowledge and addressing future research directions, it aims to propel advancements in developing robust and efficient systems for recognizing human activities, accommodating the evolving landscape of sensor technologies in mobile and wearable devices.

Game-theoretic learning for the coordination of drone teams in autonomous cooperative inspection

Without the need for an on-board pilot, drones are designed to accomplish dull, dangerous and dirty missions. However, if a mission exhibits a large operative area and/or several objectives, it may entail poor performance when executed by a single drone. Drone teams may overcome this issue by acting as mobile sensor networks for proximal sensing. In such networks, cooperative autonomy is a key enabling behaviour for achieving resilient and cost-efficient systems. This work implements cooperative autonomous behaviour in the form of a dynamic and decentralized mission planner for a multi-drone inspection mission. The proposed design exploits multi-agent task allocation, distributed route planning and game theory for the assignment of inspection tasks and for the processing of optimal routes in reasonable time frames and with limited communication. In detail, it applies the learning-in-games framework for the coordination within the inspection team, by studying some ad-hoc variants of best response and of log linear learning. Moreover, this work presents some numerical results of model-in-the-loop tests for a comparison between the learning-in-games approaches.

Multi-scenario PM2.5 distribution and dynamic exposure assessment of university community residents: Development and application of intelligent health risk management system integrated low-cost sensors

Exposure scenario and receptor behavior significantly affect PM2.5 exposure quantity of persons and resident groups, which in turn influenced indoor or outdoor air quality & health management. An Internet of Things (IoT) system, EnvironMax+, was developed to accurately and conveniently assess residential dynamic PM2.5 exposure state. A university community “QC”, as the application area, was divided into four exposure scenarios and five groups of residents. Low-cost mobile sensors and indoor/outdoor pollution migration (IOP) models jointly estimated multi-scenario real-time PM2.5 concentrations. Questionnaire was used to investigate residents' indoor activity characteristics. Mobile application (app) “Air health management (AHM)” could automatic collect residents' activity trajectory. At last, multi-scenario daily exposure concentrations of each residents-group were obtained. The results showed that residential exposure scenario was the most important one, where residents spend about 60 % of their daily time. Closing window was the most significant behavior affecting indoor contamination. The annual average PM2.5 concentration in the studied scenarios: residential scenario (RS) < public scenario (PS) < outdoor scenario (OS) < catering scenario (CS). Except for CS, the outdoor PM2.5 in other scenarios was higher than indoor by 5–10 μg/m3. The multi-scenario population weighted annual average exposure concentration was 37.1 μg/m3, which was 78 % of the annual average outdoor concentration. The exposure concentration of 5 groups: cooks > outdoor workers > indoor workers > students > the elderly, related to their daily activity time proportion in different exposure scenario.

Auto-localization algorithm for mobile sensor nodes in wireless sensor networks

Auto-localization algorithm for mobile sensor nodes in wireless sensor networks

Algorithms for Covering Barrier Points by Mobile Sensors with Line Constraint

We study the problem of covering barrier points by mobile sensors. Each sensor is represented by a point in the plane with the same covering range [Formula: see text] so that any point within distance [Formula: see text] from the sensor can be covered by the sensor. Given a set [Formula: see text] of [Formula: see text] points (called “barrier points”) and a set [Formula: see text] of [Formula: see text] points (representing the “sensors”) in the plane, the problem is to move the sensors so that each barrier point is covered by at least one sensor and the maximum movement of all sensors is minimized. The problem is NP-hard. In this paper, we consider two line-constrained variations of the problem and present efficient algorithms that improve the previous work. In the first problem, all sensors are given on a line [Formula: see text] and are required to move on [Formula: see text] only while the barrier points can be anywhere in the plane. We propose an [Formula: see text] time algorithm for the problem. We also consider the weighted case where each sensor has a weight; we give an [Formula: see text] time algorithm for this case. In the second problem, all barrier points are on [Formula: see text] while all sensors are in the plane but are required to move onto [Formula: see text] to cover all barrier points. We also solve the weighted case in [Formula: see text] time.

Integrating land use and traffic to spatial prediction of particulate matter

With degrading air quality and inefficient monitoring systems, spatial prediction of pollutants has become necessary. Air pollution exposure causes significant impacts on human health in urban areas around the world. The current study focuses on developing a deep learning model for spatial prediction of particulate matter at locations where the monitored data is unavailable. Delhi, India, is selected as the study area due to its high air pollution and fewer fixed monitoring stations throughout the city. The parameters used for the prediction modeling included PM2.5 from fixed monitoring stations, PM2.5 from mobile sensors, meteorological parameters (atmospheric temperature and relative humidity), traffic flow data, and land use parameters. The data is taken for six months, from November 2022 to April 2023, at an interval of 15 min. Four buffer sizes are used to find the spatial variability. The ANN model is used for the spatial predictions using the above-mentioned parameters. K-fold cross-validation is used to validate the robustness of the model. The SHAP summary plot is used to identify the feature importance of the features used in the model. It is observed that the integration of the land use data and traffic data increases the prediction capability of the model.

Novel Modification of Integrated Optimization Method for Sensor's Communication in Wi-Fi Public Networks.

A novel modification of IP networks integrated optimization method for heterogeneous networks, for example, the seamless Wi-Fi network serving simultaneously mobile users and wireless sensors, has been developed in this article. The mutual influence of signal reception, frequency-territorial planning, and routing procedures in heterogeneous networks have been analyzed in the case of simultaneous data transmission by both mobile users and wireless sensors. New principles for the listed procedures interaction and the basic functions for their describing are formulated. A novel modification of the integrated optimization method and its algorithm have been developed. The developed method's effectiveness has been analyzed for the IEEE 802.11ax network segment. Its result showed that the network load was decreased by an average of 20%, the data rate over the network as a whole increased for users and sensors by an average of 25% and 40%, respectively, and the sensors' lifetime increased by an average of 20% compared to the novel modification of the Collective Dynamic Routing method.

Variability in road surface temperature in urban road network – A case study making use of mobile measurements

Abstract This work presents the results of the research on the thermal state of the road surface measured by means of a mobile road condition sensor. A 15 km route circumnavigating the city centre and used by urban traffic was taken as the research area. Sixteen test runs were performed under summer and winter conditions. An analysis of the locations at which the rate of change of surface temperature had extreme values between consecutive test runs (which lasted around 25 min) was carried out. Based on that, critical sections of the test route were identified, and thus points characterised by readings deviating significantly from the mean values. Based on the thermal mapping methodology, an analysis of the rate of surface cooling was carried out. It was shown to be characterised by temporal (as well as spatial) non-uniformity. The rate of change of surface and air temperatures was calculated as a function of time, which was equal to −2.22 and −1.97°C/h, respectively. During the analysis, it came to light that hourly intervals represent the optimal frequency for thermal monitoring of a road network. Exceptions to the above are the aforementioned sections selected on the basis of the mobile measurements, in which permanent monitoring of road conditions via ESS stationary systems are recommended.

Ad Hoc Mesh Network Localization Using Ultra-Wideband for Mobile Robotics.

This article explores the implementation of high-accuracy GPS-denied ad hoc localization. Little research exists on ad hoc ultra-wideband-enabled localization systems with mobile and stationary nodes. This work aims to demonstrate the localization of bicycle-modeled robots in a non-static environment through a mesh network of mobile, stationary robots, and ultra-wideband sensors. The non-static environment adds a layer of complexity when actors can enter and exit the node's field of view. The method starts with an initial localization step where each unmanned ground vehicle (UGV) uses the surrounding, available anchors to derive an initial local or, if possible, global position estimate. The initial localization uses a simplified implementation of the iterative multi-iteration ad hoc localization system (AHLos). This estimate was refined using an unscented Kalman filter (UKF) following a constant turn rate and velocity magnitude model (CTRV). The UKF then fuses the robot's odometry and the range measurements from the Decawave ultra-wideband receivers stationed on the network nodes. Through this position estimation stage, the robot broadcasts its estimated position to its neighbors to help the others further improve their localization estimates and localize themselves. This wave-like cycle of nodes helping to localize each other allows the network to act as a mobile ad hoc localization network.

Fuzzy cluster-based multi-node charging strategy in mobile sensor networks

Energy is crucial for the continuous operation of rechargeable sensor networks, and efficient energy replenishment strategies are vital for improving network performance. However, existing solutions primarily focus on stationary sensor networks, and there are fewer strategies for energy replenishment in mobile networks. Typically, a Mobile Car (MC) charges individual mobile nodes one to one. To address the mobility of sensor nodes and enhance the energy replenishment efficiency of the network, this paper proposes a fuzzy clustering-based multi-node charging strategy (MMCS) in Mobile Sensor Network (MSN). Firstly, an improved multi-factor fuzzy C-mean clustering algorithm (MFCM++) is designed to cluster nodes with similar moving directions and remaining energy. Secondly, the cuckoo search algorithm (CS) is utilized to determine the optimal charging position for each cluster based on the varying energy demand levels of mobile nodes, thereby reducing the cluster charging waiting time. Finally, a spatio-temporal factor-based cluster selection algorithm (STCS) is developed to determine the order of cluster charging and select the next cluster to be charged. Extensive simulation results demonstrate that MMCS effectively enhances network performance, reduces energy costs, and addresses the energy problem in large-scale MSNs

Mechanism analysis of regulating Turing instability and Hopf bifurcation of malware propagation in mobile wireless sensor networks

A dynamical model is constructed to depict the spatial-temporal evolution of malware in mobile wireless sensor networks (MWSNs). Based on such a model, we design a hybrid control scheme combining parameter perturbation and state feedback to effectively manipulate the spatiotemporal dynamics of malware propagation. The hybrid control can not only suppress the Turing instability caused by diffusion factor but can also adjust the occurrence of Hopf bifurcation induced by time delay. Numerical simulation results show that the hybrid control strategy can efficiently manipulate the transmission dynamics to achieve our expected desired properties, thus reducing the harm of malware propagation to MWSNs.

Uncovering the Limitations and Insights of Packet Status Prediction Models in IEEE 802.15.4-Based Wireless Networks and Insights from Data Science

Wireless networks play a pivotal role in various domains, including industrial automation, autonomous vehicles, robotics, and mobile sensor networks. This research investigates the critical issue of packet loss in modern wireless networks and aims to identify the conditions within a network’s environment that lead to such losses. We propose a packet status prediction model for data packets that travel through a wireless network based on the IEEE 802.15.4 standard and are exposed to five different types of interference in a controlled experimentation environment. The proposed model focuses on the packetization process and its impact on network robustness. This study explores the challenges posed by packet loss, particularly in the context of interference, and puts forth the hypothesis that specific environmental conditions are linked to packet loss occurrences. The contribution of this work lies in advancing our understanding of the conditions leading to packet loss in wireless networks. Data are retrieved with a single CC2531 USB Dongle Packet Sniffer, whose pieces of information on packets become the features of each packet from which the classifier model will gather the training data with the aim of predicting whether a packet will unsuccessfully arrive at its destination. We found that interference causes more packet loss than that caused by various devices using a WiFi communication protocol simultaneously. In addition, we found that the most important predictors are network strength and packet size; low network strength tends to lead to more packet loss, especially for larger packets. This study contributes to the ongoing efforts to predict and mitigate packet loss, emphasizing the need for adaptive models in dynamic wireless environments.

IMU-Based Fitness Activity Recognition Using CNNs for Time Series Classification.

Mobile fitness applications provide the opportunity to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user's current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of daily living activities. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning (ML) methods commonly used in HAR. Although CNN architectures achieve at least 94% test accuracy in all scenarios, two traditional ML architectures surpass them in the default scenario, with support vector machines (SVMs) achieving 99.00 ± 0.34% test accuracy. The removal of all sensors except one foot sensor reduced the performance of traditional ML architectures but improved the performance of CNN architectures on our data set, with our Scaling-FCN reaching the highest accuracy of 99.86 ± 0.11% on the test set. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively, although traditional ML architectures can still compete with or even surpass CNNs when favorable input data are utilized.