Forthcoming and Online First Articles

International Journal of Sensor Networks

International Journal of Sensor Networks (IJSNet)

Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

Online First articles are published online here, before they appear in a journal issue. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.

Open AccessArticles marked with this Open Access icon are Online First articles. They are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

Register for our alerting service, which notifies you by email when new issues are published online.

We also offer which provide timely updates of tables of contents, newly published articles and calls for papers.

International Journal of Sensor Networks (9 papers in press)

Regular Issues

  • A Classification and Prediction Model with the Sparrow Search-Probabilistic Neural Network Algorithm for Transformer Fault Diagnosis   Order a copy of this article
    by Ling Hu, Lanlan Yin, Feng Mo, Zhixun Liang, Zhong Ruan, Yuting Wang 
    Abstract: We present a fault prediction model for transformers to improve the accuracy of transformer fault (TF) prediction. The model is predicated on a probabilistic neural network (PNN) that is optimised using three gas ratios with the help of the sparrow search algorithm (SSA). First, we monitor real-time gas concentrations and calculate the essential gas ratio by installing a smart gas sensor inside the transformer. Optimise the PNN by using the SSA algorithm. Subsequently, establish a mapping model between gas ratios and fault types. At last, we assess the model’s prediction performance by calculating the mean square error. The results we got demonstrate that this method achieves a prediction accuracy of 90%, which is superior to the back propagation (BP) network, the k-nearest neighbour (KNN), and the support vector machine (SVM). This research offers an efficient and dependable approach for TF prediction.
    Keywords: probabilistic neural network; PNN; transformer fault; sparrow search algorithm; SSA; transformer fault diagnosis; classification; prediction.
    DOI: 10.1504/IJSNET.2023.10061830
  • A Face Detection and Recognition Method Built on the Improved MobileFaceNet   Order a copy of this article
    by Zhengqiu Lu, Chunliang Zhou, Haiying Wang 
    Abstract: Face recognition has increasingly become the predominant biometric recognition technology for identity verification, propelled by advancements in deep learning technology. This study introduces a lightweight face detection and recognition method optimised for mobile devices with limited computational resources using an improved MobileFaceNet framework. Initially, the approach refines the network structure, elevating face detection efficiency through median filtering and a minimal bounding box constraint strategy grounded in the multitask convolutional neural network (MTCNN). Subsequently, to address the challenges of multi-pose in real-world scenarios of face detection, the method employs Affine Transformation for facial angle rotation and centre point adjustment, thus achieving accurate pose correction in facial images. The study presents a lightweight face recognition network model based on MobileFaceNet in its final phase. It improves the model by optimising the loss function and learning rate and reducing convolutional layers by integrating depthwise separable convolution. In addition, regarding the privacy security of face recognition information, it proposes a face information encryption scheme built on a fully homomorphic encryption algorithm. Experiments on prevalent face databases demonstrate that this model is better in recognition accuracy and network performance.
    Keywords: face detection; face recognition; MobileFaceNet; MTCNN; affine transformation.
    DOI: 10.1504/IJSNET.2024.10063149
  • Orientation and Trajectory-Specific Movement Assistance for Quadcopter Control using Machine Vision Input   Order a copy of this article
    by Yan Ru, Xin Zhang 
    Abstract: In recent years, quadcopter services have emerged under testing and trials for consumer and commercial applications. The trajectory and movement of the quadcopters will be aligned due to the external impact of building heights, winds, and other obstacles. Machine vision-based trajectory and movement alignment are pursued using orientation deflection detection. An orientation-specific trajectory assisted movement (OTAM) method is introduced in this article to address this issue. This method accounts for the obstacle's physical dimensions and the quadcopter trajectory for inducing the moving pathway. The pathway differences between the dimensions and trajectory are recurrently computed using neural learning. This computation calculates the trajectory and orientation using the quadcopter's vision (image) in its moving path. The recurrent learning process trains the process for safe movement without hitting/being obstructed by any obstacles. Based on the learning ability, the recommendations are provided for smooth movement and direction control of the quadcopter. The minor differences between the quadcopter's vision and the obstacle are classified for the next successful movement from the previous recurrences. Therefore, this proposed movement control method improves the accuracy under reduced error rates.
    Keywords: machine vision; neural network; pathway control; quadcopter orientation.
    DOI: 10.1504/IJSNET.2024.10063150
  • ADLoc: an angle-delay fingerprint localisation method for MIMO-OFDM systems   Order a copy of this article
    by Chenlin He, Xiaojun Wang, Jiyu Jiao, Lei Wang, Youjia Tong 
    Abstract: Fingerprint localisation has garnered increasing research interest owing to its exceptional reliability within non-line-of-sight scenarios. This paper introduces ADLoc, a novel angle-delay fingerprint localisation method for multiple input multiple output orthogonal frequency division multiplexing systems. We extract an angle delay channel frequency power fingerprint matrix from the systems channel state information. Chi-square distance is introduced as a fingerprint similarity criterion due to its good performance in classification problems. Then, a convolutional neural network classification-based method is proposed. Simulation results indicate that ADLoc demonstrates commendable efficacy in enhancing localisation accuracy and time.
    Keywords: fingerprint localisation; convolutional neural network; CNN; area classification; multiple-input multiple-output; MIMO; channel state information; CSI; non-line-of-sight; NLoS.
    DOI: 10.1504/IJSNET.2024.10063151
  • A Rotatable Battery Recognition Method Based on Improved YOLOv5   Order a copy of this article
    by Wenming Chen, Dongtai Liang, Wenhui Ding, Meng Wang, Zizhen Chen 
    Abstract: To realise end-to-end visual identification, positioning, and angle detection of cylindrical batteries, a rotated object recognition method based on YOLOv5 is proposed. Firstly, aiming at the problems of battery appearance scale variation and surface reflection, a recursive gated convolution and feature fusion module was added to the neck network to enhance the multi-scale feature extraction. Secondly, considering the boundary problem of angle range, a circular smooth label was introduced after the prediction network, and the logistic regression cross-entropy was used to realise rotation angle classification. Finally, a SIoU intersection ratio model was used to introduce an angle vector penalty index. The experimental results show that the parameters of rotated object detection model are reasonably optimised on the cylindrical battery dataset. The model accuracy reaches 98.6%, the recall rate reaches 97.2%, and the inference speed of single frame image reaches 10.5 ms, which meets the performance requirements of practical applications.
    Keywords: recursive gated convolution; rotated object detection; circular smooth label; CSL: battery detection.
    DOI: 10.1504/IJSNET.2024.10063254
  • A Hazardous Chemical Accident Prevention Method Based on Event Logic Graph   Order a copy of this article
    by Guanlin Chen, Zhenhua Kong, Wenyong Weng, Qi Lu, Wenfang Zhou 
    Abstract: In recent years, hazardous chemical accidents have occurred frequently at home and abroad, causing huge damage to the personal and property safety of the general public. This paper proposes a hazardous chemical accident prevention method based on an event logic graph associated with a sensor system to predict potential hazardous chemical accidents by extracting events from the accessible material safety data sheet data of hazardous chemicals, extracting event relationships for the extracted events, and inserting the extracted events into the graph database Neo4j. Finally, an early warning system is implemented based on the reasoning of the event map. This system can prevent disasters before they occur. In addition, after a catastrophe has occurred, this system can also analyse the causal chain of the accident, which is of profound significance whether it provides guidance for emergency rescue or disaster relief or inspects and upgrades the warehouse system afterward.
    Keywords: hazardous chemicals; event logic graph; early warning system; sensor.
    DOI: 10.1504/IJSNET.2024.10063256
  • Remote Sensing Enabled Sustainable Tomato Plant Health and Pest Surveillance Using Machine Learning Techniques   Order a copy of this article
    by Weijia Yu, Si Li 
    Abstract: To ensure long-term food security, it's vital to detect pests and diseases in crops. Traditional monitoring methods are labour-intensive and lack real-time info, leading to ineffective interventions. To address this, an advanced plant health monitoring (APHM) system that uses remote sensing technology and machine learning-based classification to effectively identify plant diseases and pests in tomato plants is proposed. The proposed system allows unmanned aerial vehicles (UAV) to take detailed aerial images of tomato fields, which are processed and input into a convolutional neural network with a generating adversarial imitation learning (CNN-GAIL) model. The CNN-GAIL model efficiently differentiates between healthy plants, weak plants, and pest presence by capitalising on temporal relationships in image sequences. The APHM system's ability to quickly identify and fix problems, combined with remote sensing and machine learning in precision agriculture, could improve crop health, reduce yield losses, and promote long-term sustainability.
    Keywords: plant disease; pest detection; remote sensing; convolutional neural network; CNN; generative adversarial imitation learning; GAIL; unmanned aerial vehicle; UAV.
    DOI: 10.1504/IJSNET.2024.10063258
  • Cooperative working performance of a dual-arm robot system optimized by a neural network adaptive preset control   Order a copy of this article
    by Xiaofei Chen, Han Zhao, Faliang Wang, Shengchao Zhen, Jie Fang 
    Abstract: This paper innovatively integrates preset performance control technology with adaptive neural network control targeting a dual-arm robot system with nonlinear uncertainties, developing a strategy demonstrating exceptional control performance under dynamic conditions. First, a comprehensive and precise co-control model for the dual-arm robot is constructed based on an in-depth analysis of robotic kinematics and dynamics. Subsequently, the system model's intrinsic uncertainties and external disturbances are studied and integrated into a unified uncertainty module. Based on this, neural networks are introduced as an excellent approximation tool to approximate the uncertainty module. Furthermore, by introducing preset performance control strategies and ingeniously transforming error constraints, the output constraint problem of the robot system is successfully solved, ensuring a significant improvement in system convergence speed and control accuracy. The effectiveness and superiority of the proposed adaptive neural network control strategy were verified through a series of simulation experiments in the MATLAB environment.
    Keywords: dual-arm robotic; preset performance; neural network; trajectory tracking.
    DOI: 10.1504/IJSNET.2024.10063267
  • Distributed Capacity Optimisation and Resource Allocation in Heterogeneous Mobile Networks using Advanced Serverless Connectivity Strategies   Order a copy of this article
    by Nan Zhou, YaNan Li, Amin Mohajer 
    Abstract: In response to the increasing complexity and diversity of heterogeneous mobile networks, this paper addresses the challenges posed by the increasing complexity and diversity of heterogeneous mobile networks, which require support for a wide range of applications and services with varying quality-of-service requirements. We proposed a novel approach to enhance network performance and efficiency in which, our methodology integrates artificial intelligence, machine learning, and serverless computing to develop a cognitive mobile network architecture that adapts in real-time to changing conditions. Additionally, we introduce a downlink resource management framework utilising game theory and optimisation algorithms, a hybrid power control and user association algorithm based on reinforcement learning, and a suite of distributed algorithms for intelligent task-offloading. Through extensive simulations and comparisons with existing methods, our approach demonstrates significant improvements in network performance and user satisfaction, achieving up to 25% and 40% reductions in network-wide throughput and energy consumption, respectively.
    Keywords: cognitive mobile network architecture; downlink resource management; hybrid power control and user association; UA; intelligent task-offloading; serverless computing.
    DOI: 10.1504/IJSNET.2024.10063556