Tekal Subramanyam Babu Sudarshan
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
Tekal Subramanyam Babu Sudarshan has a total of 106 co-authors. Here are the top co-authors by number of shared publications:
Shikha Tripathi
PES University,Faculty of Engineering,Bangalore,India
9 shared publications- Deepa Gupta
Amrita School of Computing, Amrita Vishwa Vidyapeetham
8 shared publications - Radhakrishnan Gopalapillai
Amrita Vishwa Vidyapeetham
8 shared publications - I. Mamatha
Amrita Vishwa Vidyapeetham
7 shared publications - Juhi R. Srivastava
Amrita University
5 shared publications - Nippun Kumaar Arulmani Angamuthu
Department of Computer Science and Engineering, Amrita Vishwa Vidyapeetham-Bengaluru, India and Department of Computer Science and Engineering (AI &ML), Dayananda Sagar University-Bengaluru, India
5 shared publications
Latest Publications
- Open Access
- 19 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 188-196
SABRE: A Compression-Aware BF16 Accelerator for Neuromorphic Attention
- 19 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 188-196
Open AccessSABRE: A Compression-Aware BF16 Accelerator for Neuromorphic Attention
- Open Access
Noise-Resilient Quantum Aggregation on NISQ for Federated ADAS Learning
Advanced Driver Assistance Systems (ADAS) increasingly employ Federated Learning (FL) to collaboratively train models across distributed vehicular nodes while preserving data privacy. Yet, conventional FL aggregation remains susceptible to noise, latency, and security constraints inherent to real-time vehicular networks. This paper introduces Noise-Resilient Quantum Federated Learning (NR-QFL), a hybrid quantum-classical framework that enables secure, low-latency aggregation through variational quantum circuits (VQCs) operating under Noisy Intermediate-Scale Quantum (NISQ) conditions. The framework encodes model parameters as quantum states with adaptive gate reparameterization, ensuring bounded-error convergence and provable resilience under Completely Positive Trace-Preserving (CPTP) dynamics. NR-QFL employs quantum entropy-based client selection and multi-server coordination for fairness and stability. Empirical validation shows consistent convergence with reduced gradient variance, lower communication overhead, and enhanced noise tolerance under constrained edge conditions. The framework establishes a scalable foundation for quantum-enhanced federated learning, enabling secure, efficient, and dynamically stable ADAS intelligence at the vehicular edge.
Open AccessNoise-Resilient Quantum Aggregation on NISQ for Federated ADAS Learning
Advanced Driver Assistance Systems (ADAS) increasingly employ Federated Learning (FL) to collaboratively train models across distributed vehicular nodes while preserving data privacy. Yet, conventional FL aggregation remains susceptible to noise, latency, and security constraints inherent to real-time vehicular networks. This paper introduces Noise-Resilient Quantum Federated Learning (NR-QFL), a hybrid quantum-classical framework that enables secure, low-latency aggregation through variational quantum circuits (VQCs) operating under Noisy Intermediate-Scale Quantum (NISQ) conditions. The framework encodes model parameters as quantum states with adaptive gate reparameterization, ensuring bounded-error convergence and provable resilience under Completely Positive Trace-Preserving (CPTP) dynamics. NR-QFL employs quantum entropy-based client selection and multi-server coordination for fairness and stability. Empirical validation shows consistent convergence with reduced gradient variance, lower communication overhead, and enhanced noise tolerance under constrained edge conditions. The framework establishes a scalable foundation for quantum-enhanced federated learning, enabling secure, efficient, and dynamically stable ADAS intelligence at the vehicular edge.
- Open Access
- 1 February 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 15  (1) , 1079-1088
Optimal task partitioning to minimize failure in heterogeneous computational platform
The increased energy consumption by heterogeneous cloud platforms surges the carbon emissions and reduces system reliability, thus, making workload scheduling an extremely challenging process. The dynamic voltage- frequency scaling (DVFS) technique provides an efficient mechanism in improving the energy efficiency of cloud platform; however, employing DVFS reduces reliability and increases the failure rate of resource scheduling. Most of the current workload scheduling methods have failed to optimize the energy and reliability together under a central processing unit - graphical processing unit (CPU-GPU) heterogeneous computing platform; As a result, reducing energy consumption and task failure are prime issues this work aims to address. This work introduces task failure minimization (TFM) through optimal task partitioning (OTP) for workload scheduling in the CPU-GPU cloud computational platform. The TFM-OTP introduces a task partitioning model for the CPU-GPU pair; then, it provides a DVFS- based energy consumption model. Finally, the energy-load optimization problem is defined, and the optimal resource allocation design is presented. The experiment is conducted on two standard workloads namely SIPHT and CyberShake workload. The result shows that the proposed TFA-OTP model reduces energy consumption by 30.35%, reduces makespan by 70.78% and reduces task failure energy overhead by 83.7% in comparison with energy minimized scheduling (EMS) approach.
- 1 February 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 15  (1) , 1079-1088
Open AccessOptimal task partitioning to minimize failure in heterogeneous computational platform
The increased energy consumption by heterogeneous cloud platforms surges the carbon emissions and reduces system reliability, thus, making workload scheduling an extremely challenging process. The dynamic voltage- frequency scaling (DVFS) technique provides an efficient mechanism in improving the energy efficiency of cloud platform; however, employing DVFS reduces reliability and increases the failure rate of resource scheduling. Most of the current workload scheduling methods have failed to optimize the energy and reliability together under a central processing unit - graphical processing unit (CPU-GPU) heterogeneous computing platform; As a result, reducing energy consumption and task failure are prime issues this work aims to address. This work introduces task failure minimization (TFM) through optimal task partitioning (OTP) for workload scheduling in the CPU-GPU cloud computational platform. The TFM-OTP introduces a task partitioning model for the CPU-GPU pair; then, it provides a DVFS- based energy consumption model. Finally, the energy-load optimization problem is defined, and the optimal resource allocation design is presented. The experiment is conducted on two standard workloads namely SIPHT and CyberShake workload. The result shows that the proposed TFA-OTP model reduces energy consumption by 30.35%, reduces makespan by 70.78% and reduces task failure energy overhead by 83.7% in comparison with energy minimized scheduling (EMS) approach.
- 21 June 2024
- Published by Springer Nature
- p. 618-629
Energy Aware Workload Scheduling Metrics for Execution of Parallel Application in Heterogeneous Cloud Computing Platform
- 21 June 2024
- Published by Springer Nature
- p. 618-629
Energy Aware Workload Scheduling Metrics for Execution of Parallel Application in Heterogeneous Cloud Computing Platform
- Open Access
- 28 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 1250-1265
Capturing the Concept Projection in Metaphorical Memes for Downstream Learning Tasks
Metaphorical memes, where a source concept is projected into a target concept, are an essential construct in figurative language. In this article, we present a novel approach for downstream learning tasks on metaphorical multimodal memes. Our proposed framework replaces traditional methods using metaphor annotations with a metaphor-capturing mechanism. Besides using the significant zero-shot learning capability of state-of-the-art pretrained encoders, this work introduces an alternative external knowledge enhancement strategy based on ChatGPT (chatbot generative pretrained transformer), demonstrating its effectiveness in bridging the intermodal semantic gap. We propose a new concept projection process consisting of three distinct components to capture the intramodal knowledge and intermodal concept gap in the forms of text modality embedding, visual modality embedding, and concept projection embedding. This approach leverages the attention mechanism of the Graph Attention Network for fusing the common aspects of external knowledge related to the knowledge in the text and image modality to implement the concept projection process. Our experimental results demonstrate the superiority of our proposed approach compared to existing methods.
- 28 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 1250-1265
Open AccessCapturing the Concept Projection in Metaphorical Memes for Downstream Learning Tasks
Metaphorical memes, where a source concept is projected into a target concept, are an essential construct in figurative language. In this article, we present a novel approach for downstream learning tasks on metaphorical multimodal memes. Our proposed framework replaces traditional methods using metaphor annotations with a metaphor-capturing mechanism. Besides using the significant zero-shot learning capability of state-of-the-art pretrained encoders, this work introduces an alternative external knowledge enhancement strategy based on ChatGPT (chatbot generative pretrained transformer), demonstrating its effectiveness in bridging the intermodal semantic gap. We propose a new concept projection process consisting of three distinct components to capture the intramodal knowledge and intermodal concept gap in the forms of text modality embedding, visual modality embedding, and concept projection embedding. This approach leverages the attention mechanism of the Graph Attention Network for fusing the common aspects of external knowledge related to the knowledge in the text and image modality to implement the concept projection process. Our experimental results demonstrate the superiority of our proposed approach compared to existing methods.
- 27 October 2023
- Published by Springer Nature
- p. 409-425
Performance of Artificial Intelligence Applications on Embedded Parallel Platforms Using Python as the Language Tool
- 27 October 2023
- Published by Springer Nature
- p. 409-425
Performance of Artificial Intelligence Applications on Embedded Parallel Platforms Using Python as the Language Tool
- 23 July 2023
- Published by Springer Nature
- p. 161-177
Optimal KAZE and AKAZE Features for Facial Similarity Matching
- 23 July 2023
- Published by Springer Nature
- p. 161-177
Optimal KAZE and AKAZE Features for Facial Similarity Matching
- 2 February 2022
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 41  (7) , 3903-3930
Hybrid Architecture for Sinusoidal and Non-sinusoidal Transforms
- 2 February 2022
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 41  (7) , 3903-3930
Hybrid Architecture for Sinusoidal and Non-sinusoidal Transforms
- 26 March 2021
- Published by Springer Nature
- p. 186-200
Digital Borders: Design of an Animal Intrusion Detection System Based on Deep Learning
- 26 March 2021
- Published by Springer Nature
- p. 186-200
Digital Borders: Design of an Animal Intrusion Detection System Based on Deep Learning