Sensors

24 pages, 985 KiB

Open AccessArticle

Obfuscated Malware Detection and Classification in Network Traffic Leveraging Hybrid Large Language Models and Synthetic Data

by Mehwish Naseer, Farhan Ullah, Samia Ijaz, Hamad Naeem, Amjad Alsirhani, Ghadah Naif Alwakid and Abdullah Alomari

Sensors 2025, 25(1), 202; https://doi.org/10.3390/s25010202 - 1 Jan 2025

Abstract

Android malware detection remains a critical issue for mobile security. Cybercriminals target Android since it is the most popular smartphone operating system (OS). Malware detection, analysis, and classification have become diverse research areas. This paper presents a smart sensing model based on large [...] Read more.

Android malware detection remains a critical issue for mobile security. Cybercriminals target Android since it is the most popular smartphone operating system (OS). Malware detection, analysis, and classification have become diverse research areas. This paper presents a smart sensing model based on large language models (LLMs) for developing and classifying network traffic-based Android malware. The network traffic that constantly connects Android apps may contain harmful components that may damage these apps. However, one of the main challenges in developing smart sensing systems for malware analysis is the scarcity of traffic data due to privacy concerns. To overcome this, a two-step smart sensing model Syn-detect is proposed. The first step involves generating synthetic TCP malware traffic data with malicious content using GPT-2. These data are then preprocessed and used in the second step, which focuses on malware classification. This phase leverages a fine-tuned LLM, Bidirectional Encoder Representations from Transformers (BERT), with classification layers. BERT is responsible for tokenization, generating word embeddings, and classifying malware. The Syn-detect model was tested on two Android malware datasets: CIC-AndMal2017 and CIC-AAGM2017. The model achieved an accuracy of 99.8% on CIC-AndMal2017 and 99.3% on CIC-AAGM2017. The Matthew’s Correlation Coefficient (MCC) values for the predictions were 99% for CIC-AndMal2017 and 98% for CIC-AAGM2017. These results demonstrate the strong performance of the Syn-detect smart sensing model. Compared to the latest research in Android malware classification, the model outperformed other approaches, delivering promising results. Full article

(This article belongs to the Special Issue AI Technology for Cybersecurity and IoT Applications)

21 pages, 1375 KiB

Open AccessArticle

Influence of the Transducer-Mounting Method on the Radiation Performance of Acoustic Sources Used in Monopole Acoustic Logging While Drilling

by Jiale Wang, Xiaohua Che, Wenxiao Qiao, ShengYue Tao and Qiqi Zhao

Sensors 2025, 25(1), 201; https://doi.org/10.3390/s25010201 - 1 Jan 2025

Abstract

Transducers used in acoustic logging while drilling (ALWD) must be mounted on a drill collar, and their radiation performance is dependent on the employed mounting method. Herein, the complex transmitting voltage response of a while-drilling (WD) monopole acoustic source was calculated through finite-element [...] Read more.

Transducers used in acoustic logging while drilling (ALWD) must be mounted on a drill collar, and their radiation performance is dependent on the employed mounting method. Herein, the complex transmitting voltage response of a while-drilling (WD) monopole acoustic source was calculated through finite-element harmonic-response analysis. Subsequently, the acoustic pressure waveform radiated by the source driven by a half-sine excitation voltage signal was calculated using the complex transmitting voltage response. The calculation results were compared with those obtained using finite-element transient analysis to verify the accuracy of the calculation method. The influence of transducer-mounting methods on the radiation performance of the monopole acoustic source was examined by modifying the material and structural dimensions of the coupling medium between the transducer and drill collar as well as the material and thickness of the protective cover. Numerical simulations were performed, and a transducer-mounting method suitable for ALWD was proposed based on the simulation results. Results showed that soft rubber (as the coupling material; thickness = 2 mm) enabled the WD monopole acoustic source to radiate robust acoustic energy in an infinite fluid. Increasing the height of the coupling material enhanced the radiated acoustic energy and reduced axial vibrations on the drill collar. The radiated acoustic pressure signal was unaffected by a steel protective cover (thickness = 0.5 mm). Conversely, increasing the cover thickness reduced the energy of the radiated acoustic signal. With increasing pulse width of the half-sine excitation voltage signal, the amplitude of the radiated acoustic pressure of the transducer initially increased and then declined, reaching a maximum at a pulse width that was 0.6 times the resonant period. Overall, the findings help in designing acoustic-source structures and excitation signals for ALWD tools. Full article

(This article belongs to the Section Physical Sensors)

27 pages, 4721 KiB

Open AccessArticle

Vision Sensor for Automatic Recognition of Human Activities via Hybrid Features and Multi-Class Support Vector Machine

by Saleha Kamal, Haifa F. Alhasson, Mohammed Alnusayri, Mohammed Alatiyyah, Hanan Aljuaid, Ahmad Jalal and Hui Liu

Sensors 2025, 25(1), 200; https://doi.org/10.3390/s25010200 - 1 Jan 2025

Abstract

Over recent years, automated Human Activity Recognition (HAR) has been an area of concern for many researchers due to its widespread application in surveillance systems, healthcare environments, and many more. This has led researchers to develop coherent and robust systems that efficiently perform [...] Read more.

Over recent years, automated Human Activity Recognition (HAR) has been an area of concern for many researchers due to its widespread application in surveillance systems, healthcare environments, and many more. This has led researchers to develop coherent and robust systems that efficiently perform HAR. Although there have been many efficient systems developed to date, still, there are many issues to be addressed. There are several elements that contribute to the complexity of the task, making it more challenging to detect human activities, i.e., (i) poor lightning conditions; (ii) different viewing angles; (iii) intricate clothing styles; (iv) diverse activities with similar gestures; and (v) limited availability of large datasets. However, through effective feature extraction, we can develop resilient systems for higher accuracies. During feature extraction, we aim to extract unique key body points and full-body features that exhibit distinct attributes for each activity. Our proposed system introduces an innovative approach for the identification of human activity in outdoor and indoor settings by extracting effective spatio-temporal features, along with a Multi-Class Support Vector Machine, which enhances the model’s performance to accurately identify the activity classes. The experimental findings show that our model outperforms others in terms of classification, accuracy, and generalization, indicating its efficient analysis on benchmark datasets. Various performance metrics, including mean recognition accuracy, precision, F1 score, and recall assess the effectiveness of our model. The assessment findings show a remarkable recognition rate of around 88.61%, 87.33, 86.5%, and 81.25% on the BIT-Interaction dataset, UT-Interaction dataset, NTU RGB + D 120 dataset, and PKUMMD dataset, respectively. Full article

(This article belongs to the Special Issue Sensors for Human Activity Recognition: 3rd Edition)

18 pages, 3649 KiB

Open AccessArticle

Intelligent Beam-Hopping-Based Grant-Free Random Access in Secure IoT-Oriented Satellite Networks

by Zhongliang Deng and Yicheng Liao

Sensors 2025, 25(1), 199; https://doi.org/10.3390/s25010199 - 1 Jan 2025

Abstract

This research presents an intelligent beam-hopping-based grant-free random access (GFRA) architecture designed for secure Internet of Things (IoT) communications in Low Earth Orbit (LEO) satellite networks. In light of the difficulties associated with facilitating extensive device connectivity while ensuring low latency and high [...] Read more.

This research presents an intelligent beam-hopping-based grant-free random access (GFRA) architecture designed for secure Internet of Things (IoT) communications in Low Earth Orbit (LEO) satellite networks. In light of the difficulties associated with facilitating extensive device connectivity while ensuring low latency and high reliability, we present a beam-hopping GFRA (BH-GFRA) scheme that enhances access efficiency and reduces resource collisions. Three distinct resource-hopping schemes, random hopping, group hopping, and orthogonal group hopping, are examined and utilized within the framework. This technique utilizes orthogonal resource allocation algorithms to facilitate efficient resource sharing, effectively tackling the irregular and dynamic traffic. Also, a kind of activity mechanism is proposed based on the constraints of the spatio-temporal distribution of devices. We assess the system’s performance through a thorough mathematical analysis. Furthermore, we ascertain the access delay and success rate to evaluate its capability to serve a substantial number of IoT devices under satellite–terrestrial delay and interference of massive connections. The suggested method demonstrably improves connection, stability, and access efficiency in 6G IoT satellite networks, meeting the rigorous demands of next-generation IoT applications. Full article

(This article belongs to the Special Issue Advances in Security for Emerging Intelligent Systems)

18 pages, 43650 KiB

Open AccessArticle

The Realization of a Three-Dimensional Temperature Measurement System with a Two-Dimensional Sensor Array and the Demonstration of the Deformation Effect of Gravity on the Heating Patterns

by Dogan Can Samuk and Oguzhan Cakir

Sensors 2025, 25(1), 198; https://doi.org/10.3390/s25010198 - 1 Jan 2025

Abstract

Electric heaters are widely used owing to their portability, fast heating, single-focus heating, and energy efficiency advantages. Manufacturers provide customers with information on the power consumption and energy efficiency classes of heaters but do not provide any information on heating patterns. Knowing the [...] Read more.

Electric heaters are widely used owing to their portability, fast heating, single-focus heating, and energy efficiency advantages. Manufacturers provide customers with information on the power consumption and energy efficiency classes of heaters but do not provide any information on heating patterns. Knowing the heating pattern enables users to select the correct heater, which has a significant effect on comfort, health, energy efficiency, industrial process performance, plant growth, and climate change. In previous studies, two-dimensional temperature measurements were performed using sensor arrays. However, the three-dimensional heating patterns of the heaters have not been extracted, and the deformation effect of gravity on the heating patterns has not been demonstrated. In this study, a temperature measurement system with 64 temperature sensors placed at equal intervals in the xz-plane was designed and implemented. Then, the fan heater was moved along the y-axis at intervals of 10 cm from 0 to 100 cm, and three-dimensional heating patterns were obtained for different fan voltages. As part of the research objectives, the deformation effect of gravity on the heating pattern was revealed, and the shift in the maximum temperature point on the +z-axis was measured. The mathematical formula for the maximum temperature value was derived based on the fan voltage and the distance between the heater and the sensor array. The goodness-of-fit statistical values for the derived mathematical formula for the 55 temperature measurements were calculated as the root mean square error of 1.9543 and R-squared of 99.43%, demonstrating the accuracy of the presented model. Full article

(This article belongs to the Special Issue Signal Processing for Sensors)

► Show Figures

Figure 1

26 pages, 5594 KiB

Open AccessArticle

Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave Radar

by Yukun Gao, Lin Cao, Zongmin Zhao, Dongfeng Wang, Chong Fu and Yanan Guo

Sensors 2025, 25(1), 197; https://doi.org/10.3390/s25010197 - 1 Jan 2025

Abstract

Human activity recognition by radar sensors plays an important role in healthcare and smart homes. However, labeling a large number of radar datasets is difficult and time-consuming, and it is difficult for models trained on insufficient labeled data to obtain exact classification results. [...] Read more.

Human activity recognition by radar sensors plays an important role in healthcare and smart homes. However, labeling a large number of radar datasets is difficult and time-consuming, and it is difficult for models trained on insufficient labeled data to obtain exact classification results. In this paper, we propose a multiscale residual weighted classification network with large-scale, medium-scale, and small-scale residual networks. Firstly, an MRW image encoder is used to extract salient feature representations from all time-Doppler images through contrastive learning. This can extract the representative vector of each image and also obtain the pre-training parameters of the MRW image encoder. During the pre-training process, large-scale residual networks, medium-scale residual networks, and small-scale residual networks are used to extract global information, texture information, and semantic information, respectively. Moreover, the time–channel weighting mechanism can allocate weights to important time and channel dimensions to achieve more effective extraction of feature information. The model parameters obtained from pre-training are frozen, and the classifier is added to the backend. Finally, the classifier is fine-tuned using a small amount of labeled data. In addition, we constructed a new dataset with eight dangerous activities. The proposed MRW-CN model was trained on this dataset and achieved a classification accuracy of 96.9%. We demonstrated that our method achieves state-of-the-art performance. The ablation analysis also demonstrated the role of multi-scale convolutional kernels and time–channel weighting mechanisms in classification. Full article

(This article belongs to the Section Biomedical Sensors)

21 pages, 21033 KiB

Open AccessArticle

EBR-YOLO: A Lightweight Detection Method for Non-Motorized Vehicles Based on Drone Aerial Images

by Meijia Zhou, Xuefen Wan, Yi Yang, Jie Zhang, Siwen Li, Shubo Zhou and Xueqin Jiang

Sensors 2025, 25(1), 196; https://doi.org/10.3390/s25010196 - 1 Jan 2025

Abstract

Modern city construction focuses on developing smart transportation, but the recognition of the large number of non-motorized vehicles in the city is still not sufficient. Compared to fixed recognition equipment, drones have advantages in image acquisition due to their flexibility and maneuverability. With [...] Read more.

Modern city construction focuses on developing smart transportation, but the recognition of the large number of non-motorized vehicles in the city is still not sufficient. Compared to fixed recognition equipment, drones have advantages in image acquisition due to their flexibility and maneuverability. With the dataset collected from aerial images taken by drones, this study proposed a novel lightweight architecture for small objection detection based on YOLO framework, named EBR-YOLO. Firstly, since the targets in the application scenario are generally small, the number of Backbone layers is reduced, and the AZML module is proposed to enrich the detail information and enhance the model learning capability. Secondly, the C2f module is reconstructed using part of the convolutional PConv to reduce the network’s computational volume and improve the detection speed. Finally, the downsampling operation is reshaped by combining with the introduced ADown module to further reduce the computational amount of the model. The experimental results show that the algorithm achieves an mAP of 98.9% and an FPS of 89.8 on the self-built dataset of this paper, which is only 0.2% and 0.3 lower compared to the original YOLOv8 network, respectively, and the number of parameters is 70% lower compared to the baseline, which ensures the accuracy and computational speed of the model while reducing its computational volume greatly. At the same time, the model generalization experiments are carried out on the UCAS-AOD and CARPK datasets, and the performance of the model is almost the same as the baseline. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

20 pages, 2821 KiB

Open AccessArticle

Delay/Disruption Tolerant Networking Performance Characterization in Cislunar Relay Communication Architecture

by Ding Wang, Ethan Wang and Ruhai Wang

Sensors 2025, 25(1), 195; https://doi.org/10.3390/s25010195 - 1 Jan 2025

Abstract

Future 7G/8G networks are expected to integrate both terrestrial Internet and space-based networks. Space networks, including inter-planetary Internet such as cislunar and deep-space networks, will become an integral part of future 7G/8G networks. Vehicle-to-everything (V2X) communication networks will also be a significant component [...] Read more.

Future 7G/8G networks are expected to integrate both terrestrial Internet and space-based networks. Space networks, including inter-planetary Internet such as cislunar and deep-space networks, will become an integral part of future 7G/8G networks. Vehicle-to-everything (V2X) communication networks will also be a significant component of 7G/8G networks. Therefore, space networks will eventually integrate with V2X communication networks, with both space vehicles (or spacecrafts) and terrestrial vehicles involved. DTN is the only candidate networking technology for future heterogeneous space communication networks. In this work, we study possible concatenations of different DTN convergence layer protocol adapters (CLAs) over a cislunar relay communication architecture. We present a performance characterization of the concatenations of different CLAs and the associated data transport protocols in an experimental manner. The performance of different concatenations is compared over a typical primary and secondary cislunar relay architecture. The intent is to find out which network relay path and DTN protocol configuration has the best performance over the end-to-end cislunar path. Full article

(This article belongs to the Special Issue Vehicle-to-Everything (V2X) Communication Networks 2024–2025)

► Show Figures

Figure 1

23 pages, 6756 KiB

Open AccessArticle

Vehicle Target Detection of Autonomous Driving Vehicles in Foggy Environments Based on an Improved YOLOX Network

by Zhaohui Liu, Huiru Zhang and Lifei Lin

Sensors 2025, 25(1), 194; https://doi.org/10.3390/s25010194 - 1 Jan 2025

Abstract

To address the problems that exist in the target detection of vehicle-mounted visual sensors in foggy environments, a vehicle target detection method based on an improved YOLOX network is proposed. Firstly, to address the issue of vehicle target feature loss in foggy traffic [...] Read more.

To address the problems that exist in the target detection of vehicle-mounted visual sensors in foggy environments, a vehicle target detection method based on an improved YOLOX network is proposed. Firstly, to address the issue of vehicle target feature loss in foggy traffic scene images, specific characteristics of fog-affected imagery are integrated into the network training process. This not only augments the training data but also improves the robustness of the network in foggy environments. Secondly, the YOLOX network is optimized by adding attention mechanisms and an image enhancement module to improve feature extraction and training. Additionally, by combining this with the characteristics of foggy environment images, the loss function is optimized to further improve the target detection performance of the network in foggy environments. Finally, transfer learning is applied during the training process, which not only accelerates network convergence and shortens the training time but also further improves the robustness of the network in different environments. Compared with YOLOv5, YOLOv7, and Faster R-CNN networks, the mAP of the improved network increased by 13.57%, 10.3%, and 9.74%, respectively. The results of the comparative experiments from different aspects illustrated that the proposed method significantly enhances the detection performance for vehicle targets in foggy environments. Full article

(This article belongs to the Section Sensing and Imaging)

► Show Figures

Figure 1

17 pages, 3463 KiB

Open AccessArticle

Design and Implementation of a Binary Phase-Shift Keying Frequency Diverse Array: Considerations and Challenges

by Nicholas R. Munson, Bill Correll, Jr., Justin K. A. Henry, Ram M. Narayanan and Travis D. Bufler

Sensors 2025, 25(1), 193; https://doi.org/10.3390/s25010193 - 1 Jan 2025

Abstract

The frequency diverse array (FDA) is an architecture capable of beamforming in both range and angle, improving upon the traditional phased array (PA) which can only achieve beamforming in angle. The FDA employing directional modulation (DM) for secure directional communications (SDC) can reduce [...] Read more.

The frequency diverse array (FDA) is an architecture capable of beamforming in both range and angle, improving upon the traditional phased array (PA) which can only achieve beamforming in angle. The FDA employing directional modulation (DM) for secure directional communications (SDC) can reduce bit error rates (BERs) in both range and angle, again improving upon the traditional PA which can only reduce BER in angle. In this paper, we document the challenges involved in the design and implementation of a two-element linear FDA employing fast-time binary phase-shift keying (BPSK) modulations. We also show that the experimentally collected field data match well with the results of simulations based on our analytical model. Full article

(This article belongs to the Section Remote Sensors)

19 pages, 8284 KiB

Open AccessArticle

Multi-Scale Contrastive Learning with Hierarchical Knowledge Synergy for Visible-Infrared Person Re-Identification

by Yongheng Qian and Su-Kit Tang

Sensors 2025, 25(1), 192; https://doi.org/10.3390/s25010192 - 1 Jan 2025

Abstract

Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality retrieval task to match a person across different spectral camera views. Most existing works focus on learning shared feature representations from the final embedding space of advanced networks to alleviate modality differences between visible and [...] Read more.

Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality retrieval task to match a person across different spectral camera views. Most existing works focus on learning shared feature representations from the final embedding space of advanced networks to alleviate modality differences between visible and infrared images. However, exclusively relying on high-level semantic information from the network’s final layers can restrict shared feature representations and overlook the benefits of low-level details. Different from these methods, we propose a multi-scale contrastive learning network (MCLNet) with hierarchical knowledge synergy for VI-ReID. MCLNet is a novel two-stream contrastive deep supervision framework designed to train low-level details and high-level semantic representations simultaneously. MCLNet utilizes supervised contrastive learning (SCL) at each intermediate layer to strengthen visual representations and enhance cross-modality feature learning. Furthermore, a hierarchical knowledge synergy (HKS) strategy for pairwise knowledge matching promotes explicit information interaction across multi-scale features and improves information consistency. Extensive experiments on three benchmarks demonstrate the effectiveness of MCLNet. Full article

(This article belongs to the Special Issue Artificial Intelligence in Computer Vision: Methods and Applications—2nd Edition)

26 pages, 39543 KiB

Open AccessArticle

Knowledge Distillation-Enhanced Behavior Transformer for Decision-Making of Autonomous Driving

by Rui Zhao, Yuze Fan, Yun Li, Dong Zhang, Fei Gao, Zhenhai Gao and Zhengcai Yang

Sensors 2025, 25(1), 191; https://doi.org/10.3390/s25010191 - 1 Jan 2025

Abstract

Autonomous driving has demonstrated impressive driving capabilities, with behavior decision-making playing a crucial role as a bridge between perception and control. Imitation Learning (IL) and Reinforcement Learning (RL) have introduced innovative approaches to behavior decision-making in autonomous driving, but challenges remain. On one [...] Read more.

Autonomous driving has demonstrated impressive driving capabilities, with behavior decision-making playing a crucial role as a bridge between perception and control. Imitation Learning (IL) and Reinforcement Learning (RL) have introduced innovative approaches to behavior decision-making in autonomous driving, but challenges remain. On one hand, RL’s policy networks often lack sufficient reasoning ability to make optimal decisions in highly complex and stochastic environments. On the other hand, the complexity of these environments leads to low sample efficiency in RL, making it difficult to efficiently learn driving policies. To address these challenges, we propose an innovative Knowledge Distillation-Enhanced Behavior Transformer (KD-BeT) framework. Building on the successful application of Transformers in large language models, we introduce the Behavior Transformer as the policy network in RL, using observation–action history as input for sequential decision-making, thereby leveraging the Transformer’s contextual reasoning capabilities. Using a teacher–student paradigm, we first train a small-capacity teacher model quickly and accurately through IL, then apply knowledge distillation to accelerate RL’s training efficiency and performance. Simulation results demonstrate that KD-BeT maintains fast convergence and high asymptotic performance during training. In the CARLA NoCrash benchmark tests, KD-BeT outperforms other state-of-the-art methods in terms of traffic efficiency and driving safety, offering a novel solution for addressing real-world autonomous driving tasks. Full article

(This article belongs to the Section Vehicular Sensing)

27 pages, 5902 KiB

Open AccessReview

A Survey of Deep Anomaly Detection in Multivariate Time Series: Taxonomy, Applications, and Directions

by Fengling Wang, Yiyue Jiang, Rongjie Zhang, Aimin Wei, Jingming Xie and Xiongwen Pang

Sensors 2025, 25(1), 190; https://doi.org/10.3390/s25010190 - 1 Jan 2025

Abstract

Multivariate time series anomaly detection (MTSAD) can effectively identify and analyze anomalous behavior in complex systems, which is particularly important in fields such as financial monitoring, industrial equipment fault detection, and cybersecurity. MTSAD requires simultaneously analyze temporal dependencies and inter-variable relationships have prompted [...] Read more.

Multivariate time series anomaly detection (MTSAD) can effectively identify and analyze anomalous behavior in complex systems, which is particularly important in fields such as financial monitoring, industrial equipment fault detection, and cybersecurity. MTSAD requires simultaneously analyze temporal dependencies and inter-variable relationships have prompted researchers to develop specialized deep learning models to detect anomalous patterns. In this paper, we conducted a structured and comprehensive overview of the latest techniques in deep learning for multivariate time series anomaly detection methods. Firstly, we proposed a taxonomy for the anomaly detection strategies from the perspectives of learning paradigms and deep learning models, and then provide a systematic review that emphasizes their advantages and drawbacks. We also organized the public datasets for time series anomaly detection along with their respective application domains. Finally, open issues for future research on MTSAD were identified. Full article

(This article belongs to the Section Intelligent Sensors)

24 pages, 1256 KiB

Open AccessArticle

Automatic Cleaning of Time Series Data in Rural Internet of Things Ecosystems That Use Nomadic Gateways

by Jerzy Dembski, Agata Kołakowska and Bogdan Wiszniewski

Sensors 2025, 25(1), 189; https://doi.org/10.3390/s25010189 - 1 Jan 2025

Abstract

A serious limitation to the deployment of IoT solutions in rural areas may be the lack of available telecommunications infrastructure enabling the continuous collection of measurement data. A nomadic computing system, using a UAV carrying an on-board gateway, can handle this; it leads, [...] Read more.

A serious limitation to the deployment of IoT solutions in rural areas may be the lack of available telecommunications infrastructure enabling the continuous collection of measurement data. A nomadic computing system, using a UAV carrying an on-board gateway, can handle this; it leads, however, to a number of technical challenges. One is the intermittent collection of data from ground sensors governed by weather conditions for the UAV measurement missions. Therefore, each sensor should be equipped with software that allows for the cleaning of collected data before transmission to the fly-over nomadic gateway from erroneous, misleading, or otherwise redundant data—to minimize their volume and fit them in the limited transmission window. This task, however, may be a barrier for end devices constrained in several ways, such as limited energy reserve, insufficient computational capability of their MCUs, and short transmission range of their RAT modules. In this paper, a comprehensive approach to these problems is proposed, which enables the implementation of an anomaly detector in time series data with low computational demand. The proposed solution uses the analysis of the physics of the measured signals and is based on a simple anomaly model whose parameters can be optimized using popular AI techniques. It was validated during a full 10-month vegetation period in a real Rural IoT system deployed by Gdańsk Tech. Full article

(This article belongs to the Special Issue Application of UAV and Sensing in Precision Agriculture)

► Show Figures

Figure 1

26 pages, 12506 KiB

Open AccessArticle

Hierarchical Optimization Segmentation and Parameter Extraction of Street Trees Based on Topology Checking and Boundary Analysis from LiDAR Point Clouds

by Yuan Kou, Xianjun Gao, Yue Zhang, Tianqing Liu, Guanxing An, Fen Ye, Yongyu Tian and Yuhan Chen

Sensors 2025, 25(1), 188; https://doi.org/10.3390/s25010188 - 1 Jan 2025

Abstract

Roadside tree segmentation and parameter extraction play an essential role in completing the virtual simulation of road scenes. Point cloud data of roadside trees collected by LiDAR provide important data support for achieving assisted autonomous driving. Due to the interference from trees and [...] Read more.

Roadside tree segmentation and parameter extraction play an essential role in completing the virtual simulation of road scenes. Point cloud data of roadside trees collected by LiDAR provide important data support for achieving assisted autonomous driving. Due to the interference from trees and other ground objects in street scenes caused by mobile laser scanning, there may be a small number of missing points in the roadside tree point cloud, which makes it familiar for under-segmentation and over-segmentation phenomena to occur in the roadside tree segmentation process. In addition, existing methods have difficulties in meeting measurement requirements for segmentation accuracy in the individual tree segmentation process. In response to the above issues, this paper proposes a roadside tree segmentation algorithm, which first completes the scene pre-segmentation through unsupervised clustering. Then, the over-segmentation and under-segmentation situations that occur during the segmentation process are processed and optimized through projection topology checking and tree adaptive voxel bound analysis. Finally, the overall high-precision segmentation of roadside trees is completed, and relevant parameters such as tree height, diameter at breast height, and crown area are extracted. At the same time, the proposed method was tested using roadside tree scenes. The experimental results show that our methods can effectively recognize all trees in the scene, with an average individual tree segmentation accuracy of 99.07%, and parameter extraction accuracy greater than 90%. Full article

(This article belongs to the Section Remote Sensors)

► Show Figures

Figure 1

19 pages, 429 KiB

Open AccessSystematic Review

Non-Invasive Continuous Glucose Monitoring in Patients Without Diabetes: Use in Cardiovascular Prevention—A Systematic Review

by Filip Wilczek, Jan Gerrit van der Stouwe, Gloria Petrasch and David Niederseer

Sensors 2025, 25(1), 187; https://doi.org/10.3390/s25010187 - 1 Jan 2025

Abstract

Continuous glucose monitoring (CGM) might provide immediate feedback regarding lifestyle choices such as diet and physical activity (PA). The impact of dietary habits and physical activity can be demonstrated in real time by providing continuous data on glucose levels and enhancing patient engagement [...] Read more.

Continuous glucose monitoring (CGM) might provide immediate feedback regarding lifestyle choices such as diet and physical activity (PA). The impact of dietary habits and physical activity can be demonstrated in real time by providing continuous data on glucose levels and enhancing patient engagement and adherence to lifestyle modifications. Originally developed for diabetic patients, its use has recently been extended to a non-diabetic population to improve cardiovascular health. However, since data in this population are scarce, the effect on cardiovascular outcomes is unclear. CGM may offer potential benefits for cardiovascular prevention in healthy individuals without diabetes. The aim of this systematic review is to evaluate the use of CGM in healthy non-diabetic individuals, focusing on its potential to guide lifestyle interventions in the context of cardiovascular prevention, which may ultimately reduce cardiovascular risk. Full article

(This article belongs to the Special Issue Wearable Sensors and Artificial Intelligence for Measuring Human Vital Signs: 2nd Edition)

► Show Figures

Figure 1

16 pages, 2527 KiB

Open AccessArticle

Development of Automatic Method for Glucose Detection Based on Platinum Octaethylporphyrin Sol–Gel Film with Long-Term Stability

by Yujie Niu, Yongda Wang, Lu Li, Xiyu Zhang and Ting Liu

Sensors 2025, 25(1), 186; https://doi.org/10.3390/s25010186 - 31 Dec 2024

Abstract

In this study, an approach has been proposed in response to the urgent need for a sensitive and stable method for glucose detection at low concentrations. Platinum octaethylporphyrin (PtOEP) was chosen as the probe and embedded into the matrix material to yield a [...] Read more.

In this study, an approach has been proposed in response to the urgent need for a sensitive and stable method for glucose detection at low concentrations. Platinum octaethylporphyrin (PtOEP) was chosen as the probe and embedded into the matrix material to yield a glucose-sensing film, i.e., Pt/TE-MTS, through a sol–gel process. The optical parameter (OP) was defined as the ratio of phosphorescence in the absence and presence of glucose, and the relationship between OP and glucose concentration (GC) was established in a theoretical way based on the Stern–Volmer equation and further obtained by photoluminescence measurement. OP exhibited a linear relationship with GC in a range of 0–720 μM. The time required by the photoluminescence of the film to reach equilibrium was measured to ensure the completion of the reaction, and it was found that the equilibrium time decreased as the GC increased. The photobleaching behavior and stabilization of the film were monitored, and the result showed that the film exhibited excellent resistance to photobleaching and was quite stable in an aqueous solution. Additionally, a LabVIEW-based GC-detection system was developed to achieve the practical application of the sensing film. In summary, the Pt/TE-MTS film exhibited high sensitivity in detecting the GC with excellent reproducibility, which is of high value in applications. Full article

(This article belongs to the Section Nanosensors)

19 pages, 1145 KiB

Open AccessArticle

Modeling of Electric Field and Dielectrophoretic Force in a Parallel-Plate Cell Separation Device with an Electrode Lid and Analytical Formulation Using Fourier Series

by Daiki Nishikawa, Yoshinori Seki and Shigeru Tada

Sensors 2025, 25(1), 185; https://doi.org/10.3390/s25010185 - 31 Dec 2024

Abstract

Dielectrophoresis (DEP) cell separation technology is an effective means of separating target cells which are only marginally present in a wide variety of cells. To develop highly efficient cell separation devices, detailed analysis of the nonuniform electric field’s intensity distribution within the device [...] Read more.

Dielectrophoresis (DEP) cell separation technology is an effective means of separating target cells which are only marginally present in a wide variety of cells. To develop highly efficient cell separation devices, detailed analysis of the nonuniform electric field’s intensity distribution within the device is needed, as it affects separation performance. Here we analytically expressed the distributions of the electric field and DEP force in a parallel-plate cell separation DEP device by employing electrostatic analysis through the Fourier series method. The solution was approximated by extrapolating a novel approximate equation as a boundary condition for the potential between adjacent fingers of interdigitated electrodes and changing the underlying differential equation into a solvable form. The distributions of the potential and electric fields obtained by the analytical solution were compared with those from numerical simulations using finite element method software to verify their accuracy. As a result, it was found that the two agreed well, and the analytical solution was obtained with good accuracy. Three-dimensional fluorescence imaging analysis was performed using live non-tumorigenic human mammary (MCF10A) cells. The distribution of cell clusters adsorbed on the interdigitated electrodes was compared with the analytically obtained distribution of the DEP force, and the mechanism underlying cell adsorption on the electrode surface was discussed. Furthermore, parametric analysis using the width and spacing of these electrodes as variables revealed that spacing is crucial for determining DEP force. The results suggested that for cell separation devices using interdigitated electrodes, optimization by adjusting electrode spacing could significantly enhance device performance. Full article

(This article belongs to the Special Issue Sensors Technologies for Measurements and Signal Processing)

18 pages, 1590 KiB

Open AccessArticle

Design and Evaluation of a Low-Cost Mount for Attaching a Laser Tracker’s SMR to a Robot Flange

by Florian Stöckl, Silvan Müller, Marcus Strand and Markus Gardill

Sensors 2025, 25(1), 184; https://doi.org/10.3390/s25010184 - 31 Dec 2024

Abstract

Robot calibration and modelling measurements are commonly performed using a laser tracker. To capture three-dimensional positions, a SMR is attached to the robot. While some researchers employ adhesive bonds for this purpose, such methods often result in inaccurate, unstable and non-repeatable SMR positioning, [...] Read more.

Robot calibration and modelling measurements are commonly performed using a laser tracker. To capture three-dimensional positions, a SMR is attached to the robot. While some researchers employ adhesive bonds for this purpose, such methods often result in inaccurate, unstable and non-repeatable SMR positioning, adversely affecting measurement precision and the traceability of research outcomes. To address these challenges, we investigated alternative methods for attaching an SMR to a robot’s flange to achieve both accuracy and repeatability. Additionally, we analysed measurement errors introduced when using a tool to attach the SMR to the flange. As a solution, we developed a 3D-printed mount designed for attachment to the flange. The mount’s accuracy was evaluated by assessing its eccentricity and the repeatability of the SMR placement. Experimental results demonstrated that the mount achieved an eccentricity radius of 0.35 mm and repeatability inaccuracies of

X = 0.075 mm

,

Y = 0.328 mm

, and

Z = 0.485 mm

. These values indicate that the mount provides sufficient accuracy to support calibration processes, ensures research traceability, and serves as a viable replacement for adhesive bonds. Full article

(This article belongs to the Special Issue Applied Robotics in Mechatronics and Automation)

Journal Description

Sensors

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI