Bharat Jyoti Ranjan Sahu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bharat Jyoti Ranjan Sahu has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Navrati Saxena
Department of Computer Science, San José State University, San Jose, CA 95192, USA
8 shared publications - Shatarupa Dash
Electrical and Computer Engineering Department, Sungkyunkwan University , Suwon, South Korea
4 shared publications - Shatarupa Dash
Department of Computer Science & Engineering, Institute of Technical Education and Research, Siksha ‘O’ Anusandhan Deemed to be University, Bhubaneswar, India
4 shared publications Abhishek Roy
System Design Laboratory, Network Division, Samsung Electronics, Suwon, South Korea
3 shared publications- Abhishek Roy
Network Division, Samsung Electronics
3 shared publications Shatarupa Dash
University of California San Francisco
3 shared publications
Latest Publications
- Open Access
- 22 September 2026
- Published by Springer Nature in Discover Applied Sciences
DRL driven energy efficient paging optimization framework based on adaptive handover for 5G and beyond networks
The rapid growth of 5G cellular networks and mobile user equipments (UEs) has increased control-plane signaling overhead due to frequent paging and handover operations. Existing works investigate handover optimization in connected mode but the efficient paging process remains an ongoing challenge because idle and inactive states require excessive energy in ultra-dense networks. The conventional static paging techniques create unnecessary paging coverage which results in duplicate signaling and resource waste without improving Quality of Service (QoS) results. The paper presents the DRL-driven Energy-Efficient Paging Monitoring and Adaptive Handover Optimization (D2-OEPM) framework as a solution for 5G network challenges. The proposed framework is able to optimize the adaptive Paging cycle management and dynamic handover control within a unified DRL-driven framework. The proposed framework achieves a 30% to 35% reduction in paging energy consumption and a 35% to 40% decrease in control-plane signaling overhead under an ultra-dense MATLAB Simulink environment. The ultra-dense environment has 500 UEs, 25 small cells, and a 128 ms adaptive paging cycle to analysis the performance of the work. The system achieves more than 95% handover success rate while maintaining Quality of Service (QoS) satisfaction levels above 94% through 3GPP-compliant A3/A5 mobility management and a multi-objective reward function. The proposed framework functions as an effective energy-conscious mobility management solution that scales to handle energy-efficient operations in ultra-dense 5G networks.
- 22 September 2026
- Published by Springer Nature in Discover Applied Sciences
Open AccessDRL driven energy efficient paging optimization framework based on adaptive handover for 5G and beyond networks
The rapid growth of 5G cellular networks and mobile user equipments (UEs) has increased control-plane signaling overhead due to frequent paging and handover operations. Existing works investigate handover optimization in connected mode but the efficient paging process remains an ongoing challenge because idle and inactive states require excessive energy in ultra-dense networks. The conventional static paging techniques create unnecessary paging coverage which results in duplicate signaling and resource waste without improving Quality of Service (QoS) results. The paper presents the DRL-driven Energy-Efficient Paging Monitoring and Adaptive Handover Optimization (D2-OEPM) framework as a solution for 5G network challenges. The proposed framework is able to optimize the adaptive Paging cycle management and dynamic handover control within a unified DRL-driven framework. The proposed framework achieves a 30% to 35% reduction in paging energy consumption and a 35% to 40% decrease in control-plane signaling overhead under an ultra-dense MATLAB Simulink environment. The ultra-dense environment has 500 UEs, 25 small cells, and a 128 ms adaptive paging cycle to analysis the performance of the work. The system achieves more than 95% handover success rate while maintaining Quality of Service (QoS) satisfaction levels above 94% through 3GPP-compliant A3/A5 mobility management and a multi-objective reward function. The proposed framework functions as an effective energy-conscious mobility management solution that scales to handle energy-efficient operations in ultra-dense 5G networks.
- Open Access
- 24 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 52654-52679
DTDP: Dynamic Traffic Demand Prediction for Energy-Aware Paging in Next-Generation Cellular Network
The exponential growth of mobile connectivity demands adaptive and energy-aware communication frameworks capable of sustaining Quality of Service (QoS) in dynamic 5G environments. Recent reports from the International Telecommunication Union (ITU) and Ericsson Mobility (2024) indicate that global data traffic has risen by over 60%. Such trends intensify paging activity and energy consumption in radio access networks. To address these challenges, this study introduces the Dynamic Traffic Demand Prediction (DTDP) framework, which integrates linear (ARIMA) and non-linear (XGBoost) forecasting models with an adaptive paging mechanism. DTDP predicts user traffic demand and dynamically adjust paging intervals to minimize signaling overhead and power usage. Experimental analysis confirms that DTDP enhances the energy efficiency up to 68.4% while maintaining acceptable QoS in terms of latency, packet delivery ratio, and paging success rate.
- 24 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 52654-52679
Open AccessDTDP: Dynamic Traffic Demand Prediction for Energy-Aware Paging in Next-Generation Cellular Network
The exponential growth of mobile connectivity demands adaptive and energy-aware communication frameworks capable of sustaining Quality of Service (QoS) in dynamic 5G environments. Recent reports from the International Telecommunication Union (ITU) and Ericsson Mobility (2024) indicate that global data traffic has risen by over 60%. Such trends intensify paging activity and energy consumption in radio access networks. To address these challenges, this study introduces the Dynamic Traffic Demand Prediction (DTDP) framework, which integrates linear (ARIMA) and non-linear (XGBoost) forecasting models with an adaptive paging mechanism. DTDP predicts user traffic demand and dynamically adjust paging intervals to minimize signaling overhead and power usage. Experimental analysis confirms that DTDP enhances the energy efficiency up to 68.4% while maintaining acceptable QoS in terms of latency, packet delivery ratio, and paging success rate.
- Open Access
- 22 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 188355-188380
E2PCRA: A Fuzzy-Based Energy-Efficient Paging Using Clustering and Routing Algorithm for 5G Wireless Networks
The fast-paced development of mobile communication and the deployment of 5G wireless networks necessitate smart and energy-efficient solutions for network features like paging. Paging is a critical enabler for users to accept incoming calls and messages, but conventional methods commonly experience energy efficiency, scalability, and latency limitations. Such constraints are exacerbated in 5G environments with ultra-low latency, massive connectivity, and high reliability needs. To solve these problems, this paper suggests E2PCRA: Energy-Efficient Two-Phase Clustering and Routing Algorithm using Fuzzy Logic for Paging Monitoring in 5G Wireless Networks. The main goal of E2PCRA is to minimize energy consumption and latency during paging by employing fuzzy logic in a two-phase process. In the initial phase, fuzzy logic is employed to create energy-efficient clusters based on parameters such as residual energy, node density, and signal strength. In the subsequent phase, fuzzy-based routing facilitates efficient routing of paging signals by dynamically choosing the best paths. The adaptive approach improves the responsiveness of the network under varying traffic loads and extends the operation life. The resulting framework is optimally designed to address the increasing needs of high-bandwidth applications and the exponential growth of devices in 5G networks. Simulation results confirm that E2PCRA notably saves energy, minimizes paging delays, and maximizes overall system performance, providing an efficient and scalable solution for future wireless networks.
- 22 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 188355-188380
Open AccessE2PCRA: A Fuzzy-Based Energy-Efficient Paging Using Clustering and Routing Algorithm for 5G Wireless Networks
The fast-paced development of mobile communication and the deployment of 5G wireless networks necessitate smart and energy-efficient solutions for network features like paging. Paging is a critical enabler for users to accept incoming calls and messages, but conventional methods commonly experience energy efficiency, scalability, and latency limitations. Such constraints are exacerbated in 5G environments with ultra-low latency, massive connectivity, and high reliability needs. To solve these problems, this paper suggests E2PCRA: Energy-Efficient Two-Phase Clustering and Routing Algorithm using Fuzzy Logic for Paging Monitoring in 5G Wireless Networks. The main goal of E2PCRA is to minimize energy consumption and latency during paging by employing fuzzy logic in a two-phase process. In the initial phase, fuzzy logic is employed to create energy-efficient clusters based on parameters such as residual energy, node density, and signal strength. In the subsequent phase, fuzzy-based routing facilitates efficient routing of paging signals by dynamically choosing the best paths. The adaptive approach improves the responsiveness of the network under varying traffic loads and extends the operation life. The resulting framework is optimally designed to address the increasing needs of high-bandwidth applications and the exponential growth of devices in 5G networks. Simulation results confirm that E2PCRA notably saves energy, minimizes paging delays, and maximizes overall system performance, providing an efficient and scalable solution for future wireless networks.
- 1 October 2025
- Published by Springer Nature
- p. 221-231
Enhanced Lung Cancer Classification Using SMOTE and Soft Voting Ensemble of Decision Tree, XGBoost, and Logistic Regression
- 1 October 2025
- Published by Springer Nature
- p. 221-231
Enhanced Lung Cancer Classification Using SMOTE and Soft Voting Ensemble of Decision Tree, XGBoost, and Logistic Regression
- 17 April 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (5) , 1-16
Efficient Breast Cancer Classification Using a Hybrid CNN-Attention-Residual Connection (CAR) Model
- 17 April 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (5) , 1-16
Efficient Breast Cancer Classification Using a Hybrid CNN-Attention-Residual Connection (CAR) Model
- 1 February 2025
- Published by Springer Nature in Wireless Personal Communications
- Vol. 140 (3-4) , 1191-1218
MPTCP-DQRL Based Learning Protocol for Finding Various Flows of Optimal Path in MPTCP Scheduling System
- 1 February 2025
- Published by Springer Nature in Wireless Personal Communications
- Vol. 140 (3-4) , 1191-1218
MPTCP-DQRL Based Learning Protocol for Finding Various Flows of Optimal Path in MPTCP Scheduling System
- 4 July 2022
- Published by Taru Publications in Journal of Information and Optimization Sciences
- Vol. 43 (5) , 1081-1088
Music recommender system via deep learning
Music is an integral part of our everyday life. Almost everyone uses various streaming services to listen to music on their mobile phones. These streaming services recommend tailored music to each individual by categorizing music into numerous genres, thus enriching the user experience. The backbone of these streaming services is a music recommender system that recommends the best music to the users. The efficiency of these streaming services ultimately depends on the music recommender systems’ results. The music recommender system suggests music based on the user’s interests. The necessity of these music recommender systems is increasing day by day, but most of the systems do not meet users’ expectations. This paper plans and actualizes a general music recommender system that applies several audio signal features to train several machine learning and deep learning models for categorizing music into ten genres to meet the users’ expectations for music suggestions. The music recommender system consists of a feature extractor, a data preprocessing module, and a classifier. The system classifies the audio signals into blues, classical, country, disco, hip-hop, jazz, metal, pop, reggae, and rock. The classifiers such as support vector machine (SVM), K-nearest neighbors (KNN), random forest, and feedforward neural networks (FNN) are used for the system evaluation. The music classification results from our recommender show that the FNN based system has the highest prediction results than other classifiers. The FNN based music recommender system achieved 80% accuracy on the GTZAN music dataset and validates the impact of the deep learning models for music classification.
- 4 July 2022
- Published by Taru Publications in Journal of Information and Optimization Sciences
- Vol. 43 (5) , 1081-1088
Music recommender system via deep learning
Music is an integral part of our everyday life. Almost everyone uses various streaming services to listen to music on their mobile phones. These streaming services recommend tailored music to each individual by categorizing music into numerous genres, thus enriching the user experience. The backbone of these streaming services is a music recommender system that recommends the best music to the users. The efficiency of these streaming services ultimately depends on the music recommender systems’ results. The music recommender system suggests music based on the user’s interests. The necessity of these music recommender systems is increasing day by day, but most of the systems do not meet users’ expectations. This paper plans and actualizes a general music recommender system that applies several audio signal features to train several machine learning and deep learning models for categorizing music into ten genres to meet the users’ expectations for music suggestions. The music recommender system consists of a feature extractor, a data preprocessing module, and a classifier. The system classifies the audio signals into blues, classical, country, disco, hip-hop, jazz, metal, pop, reggae, and rock. The classifiers such as support vector machine (SVM), K-nearest neighbors (KNN), random forest, and feedforward neural networks (FNN) are used for the system evaluation. The music classification results from our recommender show that the FNN based system has the highest prediction results than other classifiers. The FNN based music recommender system achieved 80% accuracy on the GTZAN music dataset and validates the impact of the deep learning models for music classification.
- 4 July 2022
- Published by Taru Publications in Journal of Information and Optimization Sciences
- Vol. 43 (5) , 933-939
Genetic algorithm based coverage optimization 5G networks
The advancements of smart and intelligent devices have resulted in the exponential growth of data traffic, which has increased the need for higher capacity wireless networks. Naturally, 5G networks must deal with exponentially increasing devices. This poses excessive stress on resource allocation tasks, both in terms of scalability and throughput for network deployment. in this sense, location intelligence can be key to addressing this challenge and complementing legacy methods at a temporal and spatial scale that are not currently given importance. Thus, this paper presents a genetic algorithm (GA) approach and its application in estimating the best location for 5G base stations in terms of coverage and transmission power. Our experimental results exhibit the proposed approach's effectiveness.
- 4 July 2022
- Published by Taru Publications in Journal of Information and Optimization Sciences
- Vol. 43 (5) , 933-939
Genetic algorithm based coverage optimization 5G networks
The advancements of smart and intelligent devices have resulted in the exponential growth of data traffic, which has increased the need for higher capacity wireless networks. Naturally, 5G networks must deal with exponentially increasing devices. This poses excessive stress on resource allocation tasks, both in terms of scalability and throughput for network deployment. in this sense, location intelligence can be key to addressing this challenge and complementing legacy methods at a temporal and spatial scale that are not currently given importance. Thus, this paper presents a genetic algorithm (GA) approach and its application in estimating the best location for 5G base stations in terms of coverage and transmission power. Our experimental results exhibit the proposed approach's effectiveness.
- 3 June 2022
- Published by Springer Nature
- p. 353-358
Performance Analysis of Video Streaming Methods