Ashutosh Kumar Singh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ashutosh Kumar Singh has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Naveen Kumar
Department of Computer Science and Engineering, Sardar Vallabhbhai National Institute of Technology, Surat, India
8 shared publications - Aditya Bhushan
United College of Engineering and Research
5 shared publications Shashank Srivastava
Motilal Nehru National Institute of Technology Allahabad
5 shared publications- Shashank Srivastava
Department of Computer Science and Engineering, Motilal Nehru National Institute of Technology Allahabad, Prayagraj, India
5 shared publications - Richa Mishra
Department of Electronics and Communication, University of Allahabad, Prayagraj, India
4 shared publications Aditya Bhushan
Department of Computer Science and Engineering Motilal Nehru National Institute of Technology Allahabad Prayagraj India
3 shared publications
Latest Publications
- 10 September 2026
- Published by Wiley in Transactions on Emerging Telecommunications Technologies
- Vol. 37 (9)
Context‐Aware Network Traffic Prediction and Resource Allocation: An AI‐Enabled Network Slicing for Smart City
Smart cities represent a critical vertical use case that demands comprehensive attention in managing heterogeneous, temporal, and dynamically managed traffic demands. This dynamic management of smart city faces two primary challenges: (1) identification of AI‐driven approaches capable of managing heterogeneous, complex, and scalable smart city data, and (2) enabling efficient management and reallocation of network resources during sudden fluctuations in traffic demands. To address these challenges, this work first proposed a hybrid model that combines LSTM and Q‐learning for traffic prediction and resource optimization. Subsequently, LLM is incorporated to handle contextual information and dynamic resource reallocation in response to sudden fluctuations in traffic demand. Experimental results show that the proposed model achieves a prediction accuracy of 95%, a Normalized Mean Absolute Error (NMAE) of 0.032, and a Pearson's Correlation Coefficient (PCC) of 0.92, indicating a strong alignment between predicted and actual traffic loads. In addition, the latency variability is reduced by 15%, and the RL agent attains a cumulative reward of 250.5. The integrated LSTM‐Q‐learning‐LLM framework achieves a classification accuracy of 97.3%, demonstrating superior performance in handling dynamic network traffic scenarios. Analysis reveals that the proposed model outperforms individual LSTM and Q‐learning models, showing a 10% improvement in prediction accuracy, a 5% greater reduction in latency variability, and a higher cumulative reward during training. This work provides a solid foundation for the development of adaptive and intelligent network management systems in smart city environments.
- 10 September 2026
- Published by Wiley in Transactions on Emerging Telecommunications Technologies
- Vol. 37 (9)
Context‐Aware Network Traffic Prediction and Resource Allocation: An AI‐Enabled Network Slicing for Smart City
Smart cities represent a critical vertical use case that demands comprehensive attention in managing heterogeneous, temporal, and dynamically managed traffic demands. This dynamic management of smart city faces two primary challenges: (1) identification of AI‐driven approaches capable of managing heterogeneous, complex, and scalable smart city data, and (2) enabling efficient management and reallocation of network resources during sudden fluctuations in traffic demands. To address these challenges, this work first proposed a hybrid model that combines LSTM and Q‐learning for traffic prediction and resource optimization. Subsequently, LLM is incorporated to handle contextual information and dynamic resource reallocation in response to sudden fluctuations in traffic demand. Experimental results show that the proposed model achieves a prediction accuracy of 95%, a Normalized Mean Absolute Error (NMAE) of 0.032, and a Pearson's Correlation Coefficient (PCC) of 0.92, indicating a strong alignment between predicted and actual traffic loads. In addition, the latency variability is reduced by 15%, and the RL agent attains a cumulative reward of 250.5. The integrated LSTM‐Q‐learning‐LLM framework achieves a classification accuracy of 97.3%, demonstrating superior performance in handling dynamic network traffic scenarios. Analysis reveals that the proposed model outperforms individual LSTM and Q‐learning models, showing a 10% improvement in prediction accuracy, a 5% greater reduction in latency variability, and a higher cumulative reward during training. This work provides a solid foundation for the development of adaptive and intelligent network management systems in smart city environments.
- 7 February 2026
- Published by Elsevier in Computer Science Review
- Vol. 61
Aspect based sentiment analysis: A systematic review, taxonomy, applications, and future research directions
- 7 February 2026
- Published by Elsevier in Computer Science Review
- Vol. 61
Aspect based sentiment analysis: A systematic review, taxonomy, applications, and future research directions
- 11 November 2025
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 129
Harnessing AI for efficient EV charging and discharging infrastructure: Overcoming challenges and finding solutions
- 11 November 2025
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 129
Harnessing AI for efficient EV charging and discharging infrastructure: Overcoming challenges and finding solutions
- 27 October 2025
- Published by Springer Nature in Proceedings of the National Academy of Sciences, India Section A: Physical Sciences
- Vol. 95 (4) , 421-444
Effective Healthcare Traffic Management Through Machine Learning-Enabled Network Slicing
- 27 October 2025
- Published by Springer Nature in Proceedings of the National Academy of Sciences, India Section A: Physical Sciences
- Vol. 95 (4) , 421-444
Effective Healthcare Traffic Management Through Machine Learning-Enabled Network Slicing
- Open Access
- 15 October 2025
- Published by Elsevier in Urban Governance
- Vol. 5 (4) , 512-526
Governing smart city EV networks: A privacy-preserving, IOTA-based architecture for decentralized urban infrastructure
- 15 October 2025
- Published by Elsevier in Urban Governance
- Vol. 5 (4) , 512-526
Open AccessGoverning smart city EV networks: A privacy-preserving, IOTA-based architecture for decentralized urban infrastructure
- 3 September 2025
- Published by Wiley in Software: Practice and Experience
- Vol. 55 (12) , 1947-1974
Improving Energy Efficiency in Iot Edge Computing Through Dynamic Deep Q‐Network Based Resource Management
Background: With the rapid growth of IoT ecosystems, energy‐efficient resource allocation in edge computing has become critical. IoT devices produce dynamic, time‐sensitive workloads, demanding adaptive strategies that optimize energy usage without compromising performance. Existing methods often rely on static models or oversimplified assumptions, limiting their effectiveness in real‐world, variable environments. Objective: This work proposes a novel, reinforcement learning‐based framework leveraging Deep Q‐Networks (DQN) for dynamic, energy‐aware resource allocation in edge computing environments, aiming to improve scalability and adaptiveness in the face of fluctuating demands. Methods: The proposed approach utilizes Deep Q‐Networks to learn optimal resource allocation strategies based on real‐time system states. A replay buffer is incorporated to stabilize learning, and the impact of different discount factors is evaluated to balance short‐term energy use with long‐term efficiency. The framework is tested across varying device loads (10, 25, and 50 devices) to assess scalability and energy performance. Results: Experimental results demonstrate significant reductions in energy consumption: 10 devices consume an average of 0.150 kWh, 25 devices consume 0.203 kWh, and 50 devices consume 0.290 kWh over a fixed simulation period. Q‐values ranging from 4.41 to 5.41 confirm effective learning and optimized decision‐making, showcasing the system's ability to adapt to real‐time environmental changes. Conclusion: The proposed DQN‐based resource allocation framework effectively addresses the limitations of static models, offering a scalable, intelligent solution for energy‐efficient edge computing. This work contributes to sustainable IoT infrastructure by enabling responsive, adaptive, and optimized resource management in dynamic operational contexts. Future work includes real‐world deployment and further optimization under diverse workload conditions.
- 3 September 2025
- Published by Wiley in Software: Practice and Experience
- Vol. 55 (12) , 1947-1974
Improving Energy Efficiency in Iot Edge Computing Through Dynamic Deep Q‐Network Based Resource Management
Background: With the rapid growth of IoT ecosystems, energy‐efficient resource allocation in edge computing has become critical. IoT devices produce dynamic, time‐sensitive workloads, demanding adaptive strategies that optimize energy usage without compromising performance. Existing methods often rely on static models or oversimplified assumptions, limiting their effectiveness in real‐world, variable environments. Objective: This work proposes a novel, reinforcement learning‐based framework leveraging Deep Q‐Networks (DQN) for dynamic, energy‐aware resource allocation in edge computing environments, aiming to improve scalability and adaptiveness in the face of fluctuating demands. Methods: The proposed approach utilizes Deep Q‐Networks to learn optimal resource allocation strategies based on real‐time system states. A replay buffer is incorporated to stabilize learning, and the impact of different discount factors is evaluated to balance short‐term energy use with long‐term efficiency. The framework is tested across varying device loads (10, 25, and 50 devices) to assess scalability and energy performance. Results: Experimental results demonstrate significant reductions in energy consumption: 10 devices consume an average of 0.150 kWh, 25 devices consume 0.203 kWh, and 50 devices consume 0.290 kWh over a fixed simulation period. Q‐values ranging from 4.41 to 5.41 confirm effective learning and optimized decision‐making, showcasing the system's ability to adapt to real‐time environmental changes. Conclusion: The proposed DQN‐based resource allocation framework effectively addresses the limitations of static models, offering a scalable, intelligent solution for energy‐efficient edge computing. This work contributes to sustainable IoT infrastructure by enabling responsive, adaptive, and optimized resource management in dynamic operational contexts. Future work includes real‐world deployment and further optimization under diverse workload conditions.
- 19 August 2025
- Published by Springer Nature in International Journal of System Assurance Engineering and Management
- Vol. 17 (1) , 56-72
An optimized anomaly detection for bitcoin prices using LSTM and DBSCAN methods
- 19 August 2025
- Published by Springer Nature in International Journal of System Assurance Engineering and Management
- Vol. 17 (1) , 56-72
An optimized anomaly detection for bitcoin prices using LSTM and DBSCAN methods
- 19 June 2025
- Published by Springer Nature in Health and Technology
- Vol. 15 (4) , 787-800
A comparative analysis of YOLO models for efficient lung tumor detection using CT images
- 19 June 2025
- Published by Springer Nature in Health and Technology
- Vol. 15 (4) , 787-800
A comparative analysis of YOLO models for efficient lung tumor detection using CT images
- Open Access
- 8 February 2025
- Published by MECS Publisher in International Journal of Information Engineering and Electronic Business
- Vol. 17 (1) , 31-48
Analyzing the Energy Efficiency andSustainability Implications of IoT Tools in SmartHomes
This research endeavors to provide a thorough and insightful analysis of Internet of Things (IoT) tools within the context of smart homes. As the IoT continues to revolutionize the domestic landscape, understanding the integration, functionality, and user experience of these tools becomes paramount. The study surveys and categorizes prevalent IoT tools, encompassing sensors, processors, actuators, and databases. Integration capabilities are scrutinized, emphasizing interoperability and compatibility to ascertain the seamless incorporation of diverse IoT tools. Functional roles and contributions of each tool are dissected to illuminate their impact on automation, inter-connectivity, and overall control mechanisms in smart homes. The research extends its gaze to the user experience, exploring factors such as ease of use, reliability, and customization options, shaping the holistic perspective of IoT tools' impact on residents. Realworld implementations and case studies provide tangible insights into practical applications, while surveys and interviews capture user perspectives, forming a comprehensive view of the challenges and limitations associated with these tools. This study contributes valuable insights for informed decision-making, empowering both users and developers to navigate the evolving landscape of IoT tools within the realm of smart homes.
- 8 February 2025
- Published by MECS Publisher in International Journal of Information Engineering and Electronic Business
- Vol. 17 (1) , 31-48
Open AccessAnalyzing the Energy Efficiency andSustainability Implications of IoT Tools in SmartHomes
This research endeavors to provide a thorough and insightful analysis of Internet of Things (IoT) tools within the context of smart homes. As the IoT continues to revolutionize the domestic landscape, understanding the integration, functionality, and user experience of these tools becomes paramount. The study surveys and categorizes prevalent IoT tools, encompassing sensors, processors, actuators, and databases. Integration capabilities are scrutinized, emphasizing interoperability and compatibility to ascertain the seamless incorporation of diverse IoT tools. Functional roles and contributions of each tool are dissected to illuminate their impact on automation, inter-connectivity, and overall control mechanisms in smart homes. The research extends its gaze to the user experience, exploring factors such as ease of use, reliability, and customization options, shaping the holistic perspective of IoT tools' impact on residents. Realworld implementations and case studies provide tangible insights into practical applications, while surveys and interviews capture user perspectives, forming a comprehensive view of the challenges and limitations associated with these tools. This study contributes valuable insights for informed decision-making, empowering both users and developers to navigate the evolving landscape of IoT tools within the realm of smart homes.