A. B. Rajendra
A. B. Rajendra has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
N. Rajkumar
Accendere Knowledge Management Service Pvt. Ltd
3 shared publications- C. D. Divya
Vidyavardhaka College of Engineering
1 shared publication C. M. Naveen Kumar
Department of Computer Science and Business System, Malnad College of Engineering, Hassan, India
1 shared publication- Harinahalli Lokesh Gururaj
Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education
1 shared publication India Cse/Jss Academy Of Technical Education/Bengaluru
1 shared publication- J Mohan
ISE/Vidyavardhaka College of Engineering/Mysuru 570002 India
1 shared publication
Latest Publications
- Open Access
- 17 February 2026
- Published by Springer Nature in Discover Applied Sciences
- Vol. 8 (4)
Multi-armed bandit-based federated reinforcement learning for dynamic task offloading in a containerized MEC
The development of mobile applications that are latency-sensitive, immersive, and compute intensive, notably mobile virtual reality (VR), augmented reality (AR), real-time video analytics, and IoT processing, has strained the edges of traditional cloud architectures. To reduce latency and improve responsiveness, mobile edge computing (MEC) has evolved to offload computation near the end users. However, the dynamism and resource constraints of edge environments and diverse task demands make efficient offloading a challenging multi-objective problem. This paper proposes a hybrid task offloading framework that leverages multi-armed bandit (MAB)-based algorithms for lightweight, real-time decision-making at the device layer and federated reinforcement learning (FRL) agents trained collaboratively across edge servers. The MAB component allows for adaptable performance under diverse workloads, whereas the FRL component enables scalable, privacy-conscious policy optimization. The frame work is deployed into a containerized MEC environment that provides both modularization and portability, allowing for better orchestration. Extensive simulations show that the proposed MAB–FRL framework achieves up to 22% higher QoE and 45%–47% reductions in latency and energy consumption compared to conventional local and greedy offloading schemes, while still outperforming centralized DRL by approximately 10% in QoE and 11% in latency and 19% in energy consumption. MAB as part of FRL provides a comprehensive adaptive and intelligent solution for dynamic task scheduling in forthcoming distributed edge ecosystems.
- 17 February 2026
- Published by Springer Nature in Discover Applied Sciences
- Vol. 8 (4)
Open AccessMulti-armed bandit-based federated reinforcement learning for dynamic task offloading in a containerized MEC
The development of mobile applications that are latency-sensitive, immersive, and compute intensive, notably mobile virtual reality (VR), augmented reality (AR), real-time video analytics, and IoT processing, has strained the edges of traditional cloud architectures. To reduce latency and improve responsiveness, mobile edge computing (MEC) has evolved to offload computation near the end users. However, the dynamism and resource constraints of edge environments and diverse task demands make efficient offloading a challenging multi-objective problem. This paper proposes a hybrid task offloading framework that leverages multi-armed bandit (MAB)-based algorithms for lightweight, real-time decision-making at the device layer and federated reinforcement learning (FRL) agents trained collaboratively across edge servers. The MAB component allows for adaptable performance under diverse workloads, whereas the FRL component enables scalable, privacy-conscious policy optimization. The frame work is deployed into a containerized MEC environment that provides both modularization and portability, allowing for better orchestration. Extensive simulations show that the proposed MAB–FRL framework achieves up to 22% higher QoE and 45%–47% reductions in latency and energy consumption compared to conventional local and greedy offloading schemes, while still outperforming centralized DRL by approximately 10% in QoE and 11% in latency and 19% in energy consumption. MAB as part of FRL provides a comprehensive adaptive and intelligent solution for dynamic task scheduling in forthcoming distributed edge ecosystems.
- 17 October 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (16) , 1-17
Efficient hybrid feature selection using intrinsic and metaheuristic optimization algorithm and classification of malware using ensemble learning algorithm
- 17 October 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (16) , 1-17
Efficient hybrid feature selection using intrinsic and metaheuristic optimization algorithm and classification of malware using ensemble learning algorithm
- 2 February 2023
- Published by Springer Nature in SN Computer Science
- Vol. 4 (2) , 1-11
An Improvised Sentiment Analysis Model on Twitter Data Using Stochastic Gradient Descent (SGD) Optimization Algorithm in Stochastic Gate Neural Network (SGNN)
Sentiment analysis is one of the effective techniques for mining the opinion from shapeless data contains text like review of the products, review of the movie. Sentiment analysis is used as a key to gather response from consumers, reviews of brands, marketing analyses, and political campaigns. In the subject of natural processing, performing sentiment analysis using the data obtained from Twitter is considered as a new study in these days. The dataset is gathered using the Twitter API and the Twitter package. The analysis of Twitter data is a process which takes place automatically by text data analysis to determine the view of public on the specified topic. Here, an improvised sentimental analysis model is proposed to identify the polarity of the tweets such as positive, neutral and negative. In this paper, stochastic gradient descent (SGD) algorithm uses stochastic gradient neural network (SGNN) to categorize the sentiment analysis on basis of tweets provided by the Twitter users and the proposed stochastic gradient descent optimization Algorithm based on stochastic gradient neural network (SGDOA-SGNN) provides better performance when compared with the existing Forest–Whale Optimization Algorithm based on deep neural network F-WOA-DNN model.
- 2 February 2023
- Published by Springer Nature in SN Computer Science
- Vol. 4 (2) , 1-11
An Improvised Sentiment Analysis Model on Twitter Data Using Stochastic Gradient Descent (SGD) Optimization Algorithm in Stochastic Gate Neural Network (SGNN)
Sentiment analysis is one of the effective techniques for mining the opinion from shapeless data contains text like review of the products, review of the movie. Sentiment analysis is used as a key to gather response from consumers, reviews of brands, marketing analyses, and political campaigns. In the subject of natural processing, performing sentiment analysis using the data obtained from Twitter is considered as a new study in these days. The dataset is gathered using the Twitter API and the Twitter package. The analysis of Twitter data is a process which takes place automatically by text data analysis to determine the view of public on the specified topic. Here, an improvised sentimental analysis model is proposed to identify the polarity of the tweets such as positive, neutral and negative. In this paper, stochastic gradient descent (SGD) algorithm uses stochastic gradient neural network (SGNN) to categorize the sentiment analysis on basis of tweets provided by the Twitter users and the proposed stochastic gradient descent optimization Algorithm based on stochastic gradient neural network (SGDOA-SGNN) provides better performance when compared with the existing Forest–Whale Optimization Algorithm based on deep neural network F-WOA-DNN model.
- Open Access
- 8 June 2022
- Published by MECS Publisher in International Journal of Wireless and Microwave Technologies
- Vol. 12 (3) , 54-60
Routing in Hybrid Software Defined Networking using Hop-Count Approach
Software-Defined Networking is a network framework that involves in separating a network's control functions from its data forwarding functions, centralizing its intelligence, and abstraction its underlying architecture from applications and services. Hybrid Software-Define Networking is a framework which supports both the legacy protocols and the Software Defined Networking protocols to operate in the same environment. In this paper, we present an efficient technique for finding the shortest path between any two nodes in Hybrid SDN by reducing the complicated network topology to a basic topology while taking hop count into account. In the suggested proposal, a subgraph is generated from a complicated network, and the best path is found using a modified Bellman-Ford method, which saves time. The emulation test bed in Mininet was established for various numbers of nodes, and the results were analysed. The modified Bellman-Ford algorithm selects the optimal path between the two nodes. For networks with different numbers of nodes, the proposed approach offered a significant increase in the TCP throughput when compared with that of Spanning Tree Protocol. The number of packets received by the SDN controller is less with the proposed work. This increases TCP throughput by reducing the broadcast packets.
- 8 June 2022
- Published by MECS Publisher in International Journal of Wireless and Microwave Technologies
- Vol. 12 (3) , 54-60
Open AccessRouting in Hybrid Software Defined Networking using Hop-Count Approach
Software-Defined Networking is a network framework that involves in separating a network's control functions from its data forwarding functions, centralizing its intelligence, and abstraction its underlying architecture from applications and services. Hybrid Software-Define Networking is a framework which supports both the legacy protocols and the Software Defined Networking protocols to operate in the same environment. In this paper, we present an efficient technique for finding the shortest path between any two nodes in Hybrid SDN by reducing the complicated network topology to a basic topology while taking hop count into account. In the suggested proposal, a subgraph is generated from a complicated network, and the best path is found using a modified Bellman-Ford method, which saves time. The emulation test bed in Mininet was established for various numbers of nodes, and the results were analysed. The modified Bellman-Ford algorithm selects the optimal path between the two nodes. For networks with different numbers of nodes, the proposed approach offered a significant increase in the TCP throughput when compared with that of Spanning Tree Protocol. The number of packets received by the SDN controller is less with the proposed work. This increases TCP throughput by reducing the broadcast packets.
- Open Access
- 1 May 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1913 (1) , 012096
Review on the proportional study of segmentation techniques for iris acknowledgment
Biometrics is one of the fields that are emerging now a days, Iris biometrics was found to yield better consequences on account of persistency, accuracy and security. Iris is a thin, annular arrangement that is existing in the eye, which is colored slice of the eye that controls the extent of the pupil. In this paper we are going to review different techniques that are applied to segment the iris region from the eye along with the available databases using which we will be able to fetch the image of the iris from different categories.
- 1 May 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1913 (1) , 012096
Open AccessReview on the proportional study of segmentation techniques for iris acknowledgment
Biometrics is one of the fields that are emerging now a days, Iris biometrics was found to yield better consequences on account of persistency, accuracy and security. Iris is a thin, annular arrangement that is existing in the eye, which is colored slice of the eye that controls the extent of the pupil. In this paper we are going to review different techniques that are applied to segment the iris region from the eye along with the available databases using which we will be able to fetch the image of the iris from different categories.
- 30 June 2020
- Published by Springer Nature
- p. 925-931
Areca Nut Disease Detection Using Image Processing
- 30 June 2020
- Published by Springer Nature
- p. 925-931
Areca Nut Disease Detection Using Image Processing
- 11 February 2020
- Published by Springer Nature
- p. 869-877
Accessibility Evaluation of Private and Public Websites in India
- 11 February 2020
- Published by Springer Nature
- p. 869-877
Accessibility Evaluation of Private and Public Websites in India
- 22 November 2019
- Published by Springer Nature
- p. 595-604
E-Learning Web Accessibility Framework for Deaf/Blind Kannada-Speaking Disabled People
- 22 November 2019
- Published by Springer Nature
- p. 595-604
E-Learning Web Accessibility Framework for Deaf/Blind Kannada-Speaking Disabled People