Suresh Chavhan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Suresh Chavhan has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Deepak Gupta
Maharaja Agrasen Institute of Technology, New Delhi, India
12 shared publications - Joel Jose Puga Coelho Rodrigues
Federal University of Piauí (UFPI)
9 shared publications Ashish Khanna
Department of Computer Science and Engineering, Maharaja Agrasen Institute of Technology, New Delhi, India
6 shared publicationsPallapa Venkataram
5 shared publications- Chandana Nagaraju
Department of Electronics and Telecommunication Engineering, Siddaganga Institute of Technology, Tumakuru, Tumakuru, India
4 shared publications - Ahmed Alkhayyat
Islamic University
3 shared publications
Latest Publications
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 85-90
Poster: Distributed Deep Learning-Based CQI Prediction for UAV-Assisted URLLC V2X Networks
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 85-90
Open AccessPoster: Distributed Deep Learning-Based CQI Prediction for UAV-Assisted URLLC V2X Networks
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (12) , 27395-27404
EdgeAI-Assisted Intent-Based Dynamic Scheduler Selection Resource Allocation Strategy for V2X
The lack of resources to meet the exponentially growing number of users is one of the major problems, along with shortages of computing resources, security issues, vulnerability, reliability, concerns, and complexity. This article aims to achieve the maximum efficiency in resource allocation (RA). The resources will be allocated to users based on their intent and needs, with the assistance of an ML model and edge computing. Intelligent RA by dynamically changing the scheduler algorithm yields much greater efficiency than traditional methods. The dynamic scenario simulation implemented in NS3, the dynamic allocation of resources through different algorithms for various scenarios, and the verification of the results show that the proposed methodology will increase the efficiency in RA for each user according to the environment, without compromising on parameters such as QoS, SINR, delay, and throughput.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (12) , 27395-27404
EdgeAI-Assisted Intent-Based Dynamic Scheduler Selection Resource Allocation Strategy for V2X
The lack of resources to meet the exponentially growing number of users is one of the major problems, along with shortages of computing resources, security issues, vulnerability, reliability, concerns, and complexity. This article aims to achieve the maximum efficiency in resource allocation (RA). The resources will be allocated to users based on their intent and needs, with the assistance of an ML model and edge computing. Intelligent RA by dynamically changing the scheduler algorithm yields much greater efficiency than traditional methods. The dynamic scenario simulation implemented in NS3, the dynamic allocation of resources through different algorithms for various scenarios, and the verification of the results show that the proposed methodology will increase the efficiency in RA for each user according to the environment, without compromising on parameters such as QoS, SINR, delay, and throughput.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 72 (1) , 2433-2442
Energy-Aware Sparse Federated Learning Framework for Secure Edge Healthcare and Consumer IoMT Devices
In today’s world, the healthcare sector faces significant challenges in terms of computational efficiency, real-time responsiveness, and data privacy. These challenges are very sensitive in the Internet of Medical Things (IoMT) environments, where there is a need for secure and timely monitoring, control, and decision-making. This paper proposes a novel framework that integrates sparse learning with federated learning to address these challenges. The proposed method improves performance by optimizing resource utilization, minimizing communication and computational overhead, and preserving the privacy of sensitive medical data achieved by transmitting only relevant model parameters. The framework is demonstrated by experimental validation using pneumonia and COVID-19 datasets, and performance analysis is compared with the traditional centralized technique, with the performance parameters including accuracy, energy consumption, and computational and communication time. These results show the potential of the framework deployment in a real-time environment, and it has potential in developing efficient, privacy-preserving, and sustainable IoMT applications.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 72 (1) , 2433-2442
Energy-Aware Sparse Federated Learning Framework for Secure Edge Healthcare and Consumer IoMT Devices
In today’s world, the healthcare sector faces significant challenges in terms of computational efficiency, real-time responsiveness, and data privacy. These challenges are very sensitive in the Internet of Medical Things (IoMT) environments, where there is a need for secure and timely monitoring, control, and decision-making. This paper proposes a novel framework that integrates sparse learning with federated learning to address these challenges. The proposed method improves performance by optimizing resource utilization, minimizing communication and computational overhead, and preserving the privacy of sensitive medical data achieved by transmitting only relevant model parameters. The framework is demonstrated by experimental validation using pneumonia and COVID-19 datasets, and performance analysis is compared with the traditional centralized technique, with the performance parameters including accuracy, energy consumption, and computational and communication time. These results show the potential of the framework deployment in a real-time environment, and it has potential in developing efficient, privacy-preserving, and sustainable IoMT applications.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-11
Bi-LSTM-Based Train Fault Detection System Using Edge Computing and IoT for Enhanced Railway Safety
Rapid transit systems are a vital part of the public transportation system, providing safety, minimizing cost, and reducing travel times. Existing railway systems face significant issues, like cracks or faults on the track, collisions, bogie disconnections, etc. If these challenges are not solved in time and tracks are not appropriately maintained, it will lead to substantial economic losses and life-threatening risks. We propose a Bi-LSTM-based train fault detection system using edge computing and IoT to solve these issues. The proposed system optimizes piezoelectric-based sensors and microphones along the track to collect vibration data from passing trains. These data are analyzed, processed, and trained at a nearby NVIDIA AGX Xavier edge device using the Bi-LSTM model, which extracts the various data features. The model provides a detection criterion that will be used to decide whether the track is faulty or non-faulty, predict the collision possibilities, detect bogey disconnections, etc. The proposed system is simulated in Ansys simulation software, Spectrometry, and Python, and it is exhaustively tested in real-time using the piezoelectric sensor, microphone, UWB short-range communication technology, and NVIDIA Jetson AGX Xavier module as an edge device integrated with the ThingSpeak cloud platform. The proposed system’s results show more effectiveness, accuracy, and timely detection of faults and boggy disconnections.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-11
Bi-LSTM-Based Train Fault Detection System Using Edge Computing and IoT for Enhanced Railway Safety
Rapid transit systems are a vital part of the public transportation system, providing safety, minimizing cost, and reducing travel times. Existing railway systems face significant issues, like cracks or faults on the track, collisions, bogie disconnections, etc. If these challenges are not solved in time and tracks are not appropriately maintained, it will lead to substantial economic losses and life-threatening risks. We propose a Bi-LSTM-based train fault detection system using edge computing and IoT to solve these issues. The proposed system optimizes piezoelectric-based sensors and microphones along the track to collect vibration data from passing trains. These data are analyzed, processed, and trained at a nearby NVIDIA AGX Xavier edge device using the Bi-LSTM model, which extracts the various data features. The model provides a detection criterion that will be used to decide whether the track is faulty or non-faulty, predict the collision possibilities, detect bogey disconnections, etc. The proposed system is simulated in Ansys simulation software, Spectrometry, and Python, and it is exhaustively tested in real-time using the piezoelectric sensor, microphone, UWB short-range communication technology, and NVIDIA Jetson AGX Xavier module as an edge device integrated with the ThingSpeak cloud platform. The proposed system’s results show more effectiveness, accuracy, and timely detection of faults and boggy disconnections.
- 11 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (17) , 34720-34730
Energy-Efficient-Enabled Edge-AI-IoT Integrated Traffic Incident Analysis and Avoidance of Secondary Incidents
Intelligent transportation systems (ITSs) use information communication and technologies to provide road safety, traffic control, traffic congestion, accident avoidance, etc. Traffic accidents cause huge disruption of vehicle movements, road blockages, traffic jams, etc., known as secondary traffic incidents. These incidents in turn lead to huge ${\mathrm { CO}}_{2}$ emissions and fuel consumption (FC), which directly impact the environment, reduce vehicle mileage, and unnecessary fuel waste. To reduce or avoid secondary traffic incidents, in this article, we propose an Edge-AI-IoT integrated energy efficient system to detect, analyze, and predict the primary and secondary incidents. The proposed system uses the existing sensor technology like accelerometer, tilt, etc., to detect the accident and severity levels using Edge-AI-IoT, locally it analyzes and predicts the secondary incidents. The proposed system has been exhaustively simulated using real-time scenarios in OMENT++, Veins, and SUMO, and it was tested using the NVIDIA Jetson AGX Xavier edge-device integrated with the ThingSpeak cloud platform. The proposed system is tested with performance parameters, such as clearance time, accident detection, density of vehicles, speed of vehicles, ${\mathrm { CO}}_{2}$ emissions, and FC at different times of day. The simulation and real-time tested results show its real-time deployment.
- 11 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (17) , 34720-34730
Energy-Efficient-Enabled Edge-AI-IoT Integrated Traffic Incident Analysis and Avoidance of Secondary Incidents
Intelligent transportation systems (ITSs) use information communication and technologies to provide road safety, traffic control, traffic congestion, accident avoidance, etc. Traffic accidents cause huge disruption of vehicle movements, road blockages, traffic jams, etc., known as secondary traffic incidents. These incidents in turn lead to huge ${\mathrm { CO}}_{2}$ emissions and fuel consumption (FC), which directly impact the environment, reduce vehicle mileage, and unnecessary fuel waste. To reduce or avoid secondary traffic incidents, in this article, we propose an Edge-AI-IoT integrated energy efficient system to detect, analyze, and predict the primary and secondary incidents. The proposed system uses the existing sensor technology like accelerometer, tilt, etc., to detect the accident and severity levels using Edge-AI-IoT, locally it analyzes and predicts the secondary incidents. The proposed system has been exhaustively simulated using real-time scenarios in OMENT++, Veins, and SUMO, and it was tested using the NVIDIA Jetson AGX Xavier edge-device integrated with the ThingSpeak cloud platform. The proposed system is tested with performance parameters, such as clearance time, accident detection, density of vehicles, speed of vehicles, ${\mathrm { CO}}_{2}$ emissions, and FC at different times of day. The simulation and real-time tested results show its real-time deployment.
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 1926-1934
Next Generation Intelligent Traffic Signal Control: Empowering Electronics Consumers With Edge-AIoT Capabilities
Traffic congestion has become a major issue that is being faced by the majority of road users. The increasing vehicle usage, and the lack of space and funds to construct new transport infrastructure, further complicates the issue. In this scenario, it is important to come up with an intelligent and economical solution that improves the quality of road users’ service. The problem with the traffic handling framework is signal timings are fixed which is not adaptive to the density of vehicles. To address this issue we propose an Edge-Augument Artificial Intelligence of Things (AIoT) road user cooperation for traffic management. The proposed system efficiently utilizes electronic devices to learn and adapt to changing traffic conditions in real-time. By optimizing the traffic signal timings based on the actual traffic conditions, adaptive systems reduce delay, improve traffic flow, reduce fuel consumption and pollution, and improve the electronics consumers’ and road users’ experiences. The proposed system has been tested with real-time experiments by integrating Electronic devices like cameras, smartphones, and AGX Xavier (edge device) with Cloud (ThingSpeak). The proposed system is verified by simulating the proposed system in the SUMO traffic simulator and its reliability is concluded by comparing the waiting time, depart delay, running, and halt time with the existing traditional method.
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 1926-1934
Next Generation Intelligent Traffic Signal Control: Empowering Electronics Consumers With Edge-AIoT Capabilities
Traffic congestion has become a major issue that is being faced by the majority of road users. The increasing vehicle usage, and the lack of space and funds to construct new transport infrastructure, further complicates the issue. In this scenario, it is important to come up with an intelligent and economical solution that improves the quality of road users’ service. The problem with the traffic handling framework is signal timings are fixed which is not adaptive to the density of vehicles. To address this issue we propose an Edge-Augument Artificial Intelligence of Things (AIoT) road user cooperation for traffic management. The proposed system efficiently utilizes electronic devices to learn and adapt to changing traffic conditions in real-time. By optimizing the traffic signal timings based on the actual traffic conditions, adaptive systems reduce delay, improve traffic flow, reduce fuel consumption and pollution, and improve the electronics consumers’ and road users’ experiences. The proposed system has been tested with real-time experiments by integrating Electronic devices like cameras, smartphones, and AGX Xavier (edge device) with Cloud (ThingSpeak). The proposed system is verified by simulating the proposed system in the SUMO traffic simulator and its reliability is concluded by comparing the waiting time, depart delay, running, and halt time with the existing traditional method.
- 16 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. PP (19328184) , 1-12
AI-Empowered Game Theoretic-Enabled Dynamic Electric Vehicles Charging Price Scheme in Smart City
The huge number of electric vehicles (EVs) penetration resulted in the rapid deployment of charging stations as well as an increase in electricity demands. Due to this, there is a growing interest in the load balance in the power grid. In the power grid, whenever there is a decrease in the overall usable voltage and reactive power, harmonics will be injected, which affects the overall power quality of the grid. In addition to the abovementioned issues, most of the existing works face issues, such as an imbalance of load at the grid, inefficient utilization of resources, and nonoptimal power transactions cost. To reduce and avoid the abovementioned issues, we propose a real-time intelligent method-based energy utilization, conservation, and optimal price at the grid and charging stations using artificial intelligence (AI). We develop the IEEE 69 bus test system and analyze the grid and charging stations. Using the analyzed factors of the grid and charging station, designed an edge-computing enabled optimal charging price scheme using the game theoretic approach. The designed system provides efficient utilization, energy conservation, and adaptive optimal charging price for EVs at charging stations. Discrete-time event simulator is developed to test the proposed scheme with parameters, such as arrival rates, queue length, and reactive power. The proposed scheme's results (analytical, simulation, and comparison) show adaptability and realism.
- 16 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. PP (19328184) , 1-12
AI-Empowered Game Theoretic-Enabled Dynamic Electric Vehicles Charging Price Scheme in Smart City
The huge number of electric vehicles (EVs) penetration resulted in the rapid deployment of charging stations as well as an increase in electricity demands. Due to this, there is a growing interest in the load balance in the power grid. In the power grid, whenever there is a decrease in the overall usable voltage and reactive power, harmonics will be injected, which affects the overall power quality of the grid. In addition to the abovementioned issues, most of the existing works face issues, such as an imbalance of load at the grid, inefficient utilization of resources, and nonoptimal power transactions cost. To reduce and avoid the abovementioned issues, we propose a real-time intelligent method-based energy utilization, conservation, and optimal price at the grid and charging stations using artificial intelligence (AI). We develop the IEEE 69 bus test system and analyze the grid and charging stations. Using the analyzed factors of the grid and charging station, designed an edge-computing enabled optimal charging price scheme using the game theoretic approach. The designed system provides efficient utilization, energy conservation, and adaptive optimal charging price for EVs at charging stations. Discrete-time event simulator is developed to test the proposed scheme with parameters, such as arrival rates, queue length, and reactive power. The proposed scheme's results (analytical, simulation, and comparison) show adaptability and realism.
- 9 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (21) , 18951-18960
Edge-Empowered Communication-Based Vehicle and Pedestrian Trajectory Perception System for Smart Cities
Road traffic crashes are one of the prime issues in the world. Every year 1.35 million people die, 20 to 50 million fatal injuries, and many incur a disability due to road traffic crashes. 50% of the total death, injuries, and disabilities are among vulnerable road users (VRUs), such as motorcyclists, cyclists, and pedestrians. Among these VRUs, highly vulnerable is pedestrians. In this paper, we are dealing with providing safety and alert system to pedestrians and vehicles to reduce and/or avoid the causes of road traffic crashes in metropolitan areas. In this paper, we develop a cooperative communication framework between pedestrians and nearby vehicles as well as traffic light systems using mobile agent systems and apps. The proposed cooperative communication framework controls the mobility of vehicles as well as pedestrians to avoid accidents. We have developed an application that will notify the pedestrian if there is any automobile within the range of 200 meters of the pedestrian. If there are any vehicles in this range, using direct Wi-Fi, connect the vehicles and pedestrians to notify them about their presence of them. The proposed system is implemented and tested in real-time as well as simulated in the SUMO, Veins, OMNeT++, and MiXiM simulator. The proposed systems results (real-time, simulation, and comparison) show real-time deployability, accuracy, and reliability.
- 9 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (21) , 18951-18960
Edge-Empowered Communication-Based Vehicle and Pedestrian Trajectory Perception System for Smart Cities
Road traffic crashes are one of the prime issues in the world. Every year 1.35 million people die, 20 to 50 million fatal injuries, and many incur a disability due to road traffic crashes. 50% of the total death, injuries, and disabilities are among vulnerable road users (VRUs), such as motorcyclists, cyclists, and pedestrians. Among these VRUs, highly vulnerable is pedestrians. In this paper, we are dealing with providing safety and alert system to pedestrians and vehicles to reduce and/or avoid the causes of road traffic crashes in metropolitan areas. In this paper, we develop a cooperative communication framework between pedestrians and nearby vehicles as well as traffic light systems using mobile agent systems and apps. The proposed cooperative communication framework controls the mobility of vehicles as well as pedestrians to avoid accidents. We have developed an application that will notify the pedestrian if there is any automobile within the range of 200 meters of the pedestrian. If there are any vehicles in this range, using direct Wi-Fi, connect the vehicles and pedestrians to notify them about their presence of them. The proposed system is implemented and tested in real-time as well as simulated in the SUMO, Veins, OMNeT++, and MiXiM simulator. The proposed systems results (real-time, simulation, and comparison) show real-time deployability, accuracy, and reliability.
- 24 November 2022
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 124 (1-2) , 633-645
In-process detection of miniature size holes in cold-rolled steel strips
- 24 November 2022
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 124 (1-2) , 633-645
In-process detection of miniature size holes in cold-rolled steel strips