Article
Engineering, Multidisciplinary
Chuijie Zeng, Tao Qin, Wei Tan, Chuan Lin, Zhaoqiang Zhu, Jing Yang, Shangwei Yuan
Summary: This paper proposes an improved wild horse optimizer algorithm (IWHO) to tackle the problem of network coverage and connectivity in heterogeneous wireless sensor networks (HWSNs). The IWHO combines the WHO algorithm and Golden Sine Algorithm (Golden-SA) to improve accuracy and convergence speed. It also incorporates opposition-based learning and the Cauchy variation strategy to avoid local optima and expand the search space. Experimental results demonstrate that the IWHO outperforms seven other algorithms in optimization capability. Validation experiments in different simulated environments show that the IWHO achieves better sensor connectivity and coverage ratio compared to other algorithms. After optimization, the HWSN achieves coverage and connectivity ratios of 98.51% and 20.04%, respectively, which decrease to 97.79% and 17.44% when obstacles are added.
Article
Chemistry, Analytical
Frantz Tossa, Wahabou Abdou, Keivan Ansari, Eugene C. Ezin, Pierre Gouton
Summary: Wireless sensor networks have important applications in both research and domestic use, where their main role is to collect and transmit data from a region of interest to a base station. This paper tackles the problem of deploying sensors to ensure maximum coverage and connectivity, using a genetic algorithm to find the best positions. The results show that the algorithm covers all forms of the area for a given number of sensors and maximizes coverage while guaranteeing connectivity.
Article
Computer Science, Information Systems
Ruihong Jiang, Ke Xiong, Hong-Chuan Yang, Jie Cao, Zhangdui Zhong, Bo Ai
Summary: This article studies the coverage performance of UAV-assisted SWIPT networks in rich scattering scenarios, and analyzes the influence of nonlinear and linear energy harvesting models. The results show that PS-based systems have superior coverage performance compared to TS-based systems, and the nonlinear model yields more reliable results. Additionally, the linear model introduces greater bias for TS-based systems.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Xinmiao Lu, Yuhan Wei, Qiong Wu, Cunfang Yang, Dongyuan Li, Liyu Zhang, Ying Zhou
Summary: This paper proposes a coverage hole patching algorithm with a priority mechanism, which can improve network coverage, reduce node redundancy, and balance resource allocation in hybrid heterogeneous wireless sensor networks.
Article
Engineering, Electrical & Electronic
Babak Mahmoudi, Homayun Motameni, Hosein Mohamadi
Summary: The target coverage problem in directional sensor networks is a major challenge due to their limited angle of view. Multiple sensors are required for coverage, but changes in sensor availability due to various factors can result in an under-provisioned network. This paper proposes a hybrid model that integrates a genetic algorithm (GA) and Tabu search (TS) to identify a subset of sensors with appropriate working directions for balanced coverage. Experimental results demonstrate the superiority of the algorithm compared to greedy and learning automat-based algorithms.
IET COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Bhargavi Dande, Chih-Yung Chang, Wen-Hwa Liao, Diptendu Sinha Roy
Summary: This study proposed an area coverage algorithm called MSQAC, which considers rechargeable sensors and utilizes solar-powered energy to maximize surveillance quality for a given monitoring area by applying the Probabilistic Sensing Model.
IEEE SENSORS JOURNAL
(2022)
Article
Computer Science, Information Systems
Tuo Shi, Jianzhong Li, Hong Gao, Zhipeng Cai
Summary: This paper introduces the features of battery-free wireless sensor network (BF-WSN), defines a new coverage problem in BF-WSN, and proposes several algorithms to solve it. Extensive simulations demonstrate the effectiveness and efficiency of these algorithms.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2022)
Article
Computer Science, Interdisciplinary Applications
Tan D. Lam, Dung T. Huynh
Summary: In this paper, we study two problems in wireless sensor networks equipped with k directional antennas (3 <= k <= 4). The first problem, called antenna orientation (AO), aims to minimize the required range for symmetric connectivity by replacing omni-directional antennas with directional antennas. We propose an O(n log n) time algorithm for this problem. The second problem, called antenna orientation and power assignment (AOPA), aims to minimize the total power assignment while inducing an SCCG with the orientation of antennas and range assignment. We show that our solution for the AO problem also approximates the AOPA problem with a ratio of O(1). Simulation results demonstrate the superior performance of our algorithms, especially when k = 3.
JOURNAL OF COMBINATORIAL OPTIMIZATION
(2023)
Article
Chemistry, Analytical
Dieyan Liang, Hong Shen, Lin Chen
Summary: This study formulates and analyzes a generic coverage optimization problem in mobile sensor networks, proving its NP-hardness and devising four heuristic or approximate algorithms to solve it. Experimental results validate the effectiveness of these algorithms in various parameter settings.
Article
Computer Science, Information Systems
Xiaojian Zhu, Mengchu Zhou, Abdullah Abusorrah
Summary: This article investigates the design and deployment of a rechargeable CSN to achieve full-view coverage for monitoring and recognizing objects at target points. The problem is formulated as an integer linear program and solved using a greedy heuristic and a differential evolution algorithm. Extensive simulation results show that the latter achieves higher success rate and solution quality but requires more time compared to the former.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Electrical & Electronic
Gong Chen, Yonghua Xiong, Jinhua She, Min Wu, Krzysztof Galkowski
Summary: This paper discusses the construction of target-barriers in wireless sensor networks, introducing the Virtual Target-barrier Construction (VTBC) method and using a distributed particle swarm optimization algorithm to achieve optimal coverage of closed virtual barrier curves. Simulation results demonstrate that VTBC outperforms other methods.
IEEE SENSORS JOURNAL
(2021)
Article
Robotics
Yi-fan Chung, Solmaz S. Kia
Summary: We propose a distributed deployment solution for providing service to densely populated targets in a finite area. We use a distributed algorithm to estimate the target density distribution and solve a mass transport problem to allocate agents to target clusters. Experimental results demonstrate the effectiveness of our solution for sensor deployment in event detection.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Computer Science, Information Systems
Xueyang Hu, Tian Liu, Tao Shu
Summary: This article proposes a new coverage model called (k, alpha)-coverage for intelligent surface (RIS) to overcome the performance degradation in millimeter-wave (mmWave) directional communication. By considering the impact of path direction difference, the proposed model increases the robustness of mmWave communication by providing alternative non line-of-sight (NLoS) paths when the line-of-sight is blocked. The article also presents methods for deterministic and random RIS deployment schemes and provides simulation results to validate the effectiveness of the proposed model.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Juan Chang, Xiaohong Shen, Weigang Bai, Xiangxiang Li
Summary: In this paper, a high-energy-efficient barrier coverage strategy based on nodes alliance is proposed for intrusion detection in underwater sensor networks. By optimizing the virtual sensor quantity, this strategy achieves high detection probability and low energy consumption simultaneously.
IEEE SENSORS JOURNAL
(2022)
Article
Chemistry, Analytical
Junaid Akram, Hafiz Suliman Munawar, Abbas Z. Kouzani, M. A. Pervez Mahmud
Summary: Wireless sensor networks are widely utilized in various settings, but the limited power and target monitoring issues have been challenges. This study proposes an adaptive learning automata algorithm to schedule sensor nodes, achieving both target coverage and power saving. Experimental results demonstrate the effectiveness of the proposed method for scheduling sensor nodes.
Article
Computer Science, Information Systems
Swati Chopade, Hari Prabhat Gupta, Rahul Mishra, Aman Oswal, Preti Kumari, Tanima Dutta
Summary: This paper presents a sensor-based river water quality assessment system using deep neural network (DNN). The system estimates the water quality index (WQI) for labeling lab samples and uses automatic annotation technique to assign labels to sensory data instances. The labeled instances are then used to build a DNN classifier for predicting water quality. The system achieves high accuracy even with noisy labels.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Rahul Mishra, Hari Prabhat Gupta, Preti Kumari, Doug Young Suh, Md Jalil Piran
Summary: This paper presents a Fog computing-based scheme for assisting passengers by offloading and reallocating tasks, aiming to reduce energy consumption and communication delay. It supports the execution within a given time constraint and minimal execution cost in a dynamic environment.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2022)
Editorial Material
Computer Science, Hardware & Architecture
Uttam Ghosh, Hellen Maziku, Hari Prabhat Gupta, Biplab Sikdar, Joel J. P. C. Rodrigues
IEEE CONSUMER ELECTRONICS MAGAZINE
(2022)
Article
Computer Science, Theory & Methods
Rahul Mishra, Hari Gupta
Summary: Deep Neural Networks (DNNs) are popular for their high performance and automated feature extraction capability. However, their deployment on resource-constrained IoT devices is challenging due to the requirements of computation, energy, and storage. Various compression techniques have been proposed to reduce the energy, storage, and computation requirements of DNNs with minimal accuracy compromise. This article provides a comprehensive overview of existing literature on DNN compression techniques and discusses their challenges and applications in IoT.
ACM COMPUTING SURVEYS
(2023)
Editorial Material
Engineering, Electrical & Electronic
Hari Prabhat Gupta, Uttam Ghosh, Biplab Sikdar, Tanima Dutta, Jan Faigl, Venkat R. R. Bhethanabotla, Kunal Mondal
Summary: Communicable diseases spread quickly through infectious mediums among people and animals, such as bacteria and viruses. The recent global outbreak of COVID-19 has motivated researchers to use smart sensor technologies to detect, prevent, and control the spread of communicable diseases. Smart sensors, including biosensors, wearable sensors, unmanned vehicles, and bedsheet sensors, collect real-time data on the transmissibility of diseases, which can be processed using advanced machine-learning techniques. The use of smart sensors helps facilitate more accurate diagnoses of communicable disease viruses.
IEEE SENSORS JOURNAL
(2023)
Article
Automation & Control Systems
Chitranjan Singh, Preti Kumari, Rahul Mishra, Hari Prabhat Gupta, Tanima Dutta
Summary: This article proposes an approach for securely processing a given IIoT task within an allowable response time. The approach uses game theory to estimate the fractions of the task to be containerized on different machines and maximizes the system utility.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Automation & Control Systems
Rahul Mishra, Hari Prabhat Gupta, Ramakant Kumar, Tanima Dutta
Summary: Augmented intelligence is an innovative extension of artificial intelligence that enables human experts to take control of machine decisions and facilitates intelligent decision-making using IoT. This article presents a method to enhance the lifespan of unmanned aerial vehicle networks through augmented intelligence and evaluates it using existing datasets.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Editorial Material
Computer Science, Hardware & Architecture
Uttam Ghosh, Hellen Maziku, Hari Prabhat Gupta, Biplab Sikdar, Joel J. P. C. Rodrigues
IEEE CONSUMER ELECTRONICS MAGAZINE
(2023)
Article
Computer Science, Information Systems
Rahul Mishra, Ashish Gupta, Hari Prabhat Gupta
Summary: The availability of various sensors in smartphones makes it easier and more convenient to collect data on human locomotion activities. A recognition approach can utilize this data to recognize the user's mode of locomotion, such as cycling, biking, or driving a car. This mode recognition helps in accurately estimating transportation expenditure, travel time, and planning journeys. However, the accuracy of recognition approaches depends heavily on correctly annotated labels in the training dataset, which can be noisy due to annotation methods. This paper proposes a locomotion mode recognition approach that can handle noisy labels by building an ensemble model using three different deep learning-based models.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Telecommunications
Swati Sandeep Chopade, Hari Prabhat Gupta, Tanima Dutta
Summary: The Internet of Things (IoT) in healthcare has shifted from conventional hospital-based care to patient-centric, distributed care. IoT-enabled intelligent health monitoring systems utilize sensors and devices to monitor patients 24/7. IoT has transformed healthcare device architecture and improved the application of complex systems.
WIRELESS PERSONAL COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Atul Chaudhary, Rahul Mishra, Hari Prabhat Gupta, K. K. Shukla
Summary: Restrictive public health measures like isolation and quarantine are used to reduce the transmission of the pandemic virus. Due to their vulnerability to COVID-19, older adults are specifically advised to stay at home. The increasing demand for assistive technologies for people with special needs during the pandemic has led to the popularity of smart home systems, which can provide better services through activity prediction. This paper proposes a multi-task activity prediction system using wearable sensors and environmental sensors to sense daily activities of older adults, and evaluates its performance through experiments on real datasets.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Cybernetics
Aishwarya Soni, Tanima Dutta, Nitika Nigam, Deepali Verma, Hari Prabhat Gupta
Summary: This article presents a network model called SESANet for detecting faint text edges in noisy environments. It accurately localizes text in situations with poor contrast and illumination, and demonstrates superior performance on publicly available datasets.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Engineering, Civil
Ramakant Kumar, Rahul Mishra, Hari Prabhat Gupta
Summary: Intelligent Transportation System (ITS) can improve vehicle health, driver safety, and passenger comfort, but sharing ITS information for machine and deep learning models raises concerns about data privacy and security. Federated learning provides privacy-preserving model training without sharing data, but imperfect labels may be a challenge. This paper proposes a federated learning approach for ITS that handles imperfect labels and uses a Long-Range network for efficient communication.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Cybernetics
B. Shilpa, Hari Prabhat Gupta, Rajesh Kumar Jha
Summary: A low-cost data transmission system for smart buildings is developed using the long-range communication protocol and deep learning techniques. The system compresses and transmits the multivariate time series data generated by smart building sensors, while also reducing transmission noise. Experimental results demonstrate the effectiveness of the system, especially when a finite number of distinct edge device types are selected.
IEEE SYSTEMS MAN AND CYBERNETICS MAGAZINE
(2023)
Article
Computer Science, Cybernetics
Chitranjan Singh, Rahul Mishra, Hari Prabhat Gupta, Garvit Banga
Summary: This article proposes a secure patient monitoring system using federated learning, which performs training on local devices and preserves data privacy and security by only sending weight matrices to the server for aggregation. The system intelligently divides participants into clusters based on available resources and trains suitable models on each cluster. High-performing clusters distill knowledge to improve the performance of small-size clusters. Experimental results demonstrate the successful operation of the proposed system under unequal resource conditions.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)