Dr. T BHARGAVA RAMU

@mlrit.ac.in

Associate Professor, Department of Electrical and Electronics Engineering
MLR Institute Of Technology

Dr. T BHARGAVA RAMU


               Download Compact PDF  
https://researchid.co/mlrit1539

RESEARCH, TEACHING, or OTHER INTERESTS

Electrical and Electronic Engineering
15

Scopus Publications

Scopus Publications

  • Chalcogenide perovskites for next-generation solar cells: Progress, challenges, and future perspectives
    K. Umamaheswari, P. Pattunnarajam, T. Bhargava Ramu, R. Balasubramaniyan, P.S. Gomathi, V. Samuthira Pandi
    Micro and Nanostructures, 2026
  • A Robust Security System Using SHA-512 with Reinforcement Learning in Wireless Sensor Networks
    C. Anuradha, A. V. Mayakkannan, R. Vinodha, K. Narsimha Reddy, B. Annapurna, T. Bhargava Ramu, T. M. Nithya, C. Srinivasan
    Engineering Technology and Applied Science Research, 2025
    Routing in Wireless Sensor Networks (WSNs) is highly vulnerable due to the unreliable wireless medium and limited node resources. Routing attacks can severely degrade network performance. This paper proposes a Robust Security system using Reinforcement Learning (RSRL) and the Secure Hash Algorithm 512 (SHA-512) for secure and efficient routing in WSNs. The primary objective of the RSRL mechanism is to detect malicious nodes and enhance system security. In the RSRL mechanism, the Base Station (BS) performs aggregator verification using SHA-512 to ensure data integrity without burdening low-power sensor nodes. A Reinforcement Learning (RL) agent, executed at the BS, dynamically learns optimal policies to detect malicious sensor nodes based on node Response Time ( ), Consumed Energy ( ), and Loss Ratio ( ). The RSRL system selects reliable nodes for route selection to improve routing efficiency. The proposed RSRL model is implemented in Network Simulator 2.35. Simulation results demonstrate a 26.44% improvement in Packet Forwarding Ratio ( ) and 95% detection accuracy compared to a conventional secure routing mechanism. The results confirm that RSRL effectively mitigates routing attacks while maintaining high network performance.
  • Transformer based models with hierarchical graph representations for enhanced climate forecasting
    T. Bhargava Ramu, Raviteja Kocherla, G. N. V. G. Sirisha, V. Lakshmi Chetana, P. Vidya Sagar, R. Balamurali, Nanditha Boddu
    Scientific Reports, 2025
    Accurate climate predictions are essential for agriculture, urban planning, and disaster management. Traditional forecasting methods often struggle with regional accuracy, computational demands, and scalability. This study proposes a Transformer-based deep learning model for daily temperature forecasting, utilizing historical climate data from Delhi (2013-2017, consisting of 1,500 daily records). The model integrates three key components: Spatial-Temporal Fusion Module (STFM) to capture spatiotemporal dependencies, Hierarchical Graph Representation and Analysis (HGRA) to model structured climate relationships, and Dynamic Temporal Graph Attention Mechanism (DT-GAM) to enhance temporal feature extraction. To improve computational efficiency and feature selection, we introduce a hybrid optimization approach (HWOA-TTA) that combines the Whale Optimization Algorithm (WOA) and Tiki-Taka Algorithm (TTA). Experimental results demonstrate that the proposed model outperforms baseline models (RF-LSTM-XGBoost, cGAN, CNN + LSTM, and MC-LSTM) by achieving 7.8% higher accuracy, 6.3% improvement in recall, and 8.1% enhancement in F1-score. Additionally, training time is reduced by 22.4% compared to conventional deep learning models, demonstrating improved computational efficiency. These findings highlight the effectiveness of hierarchical graph-based deep learning models for scalable and accurate climate forecasting. Future work will focus on validating the model across diverse climatic regions and enhancing real-time deployment feasibility.
  • Enhancing E-commerce recommendations with sentiment analysis using MLA-EDTCNet and collaborative filtering
    E. S. Phalguna Krishna, T. Bhargava Ramu, R. Krishna Chaitanya, M. Sitha Ram, Narasimhula Balayesu, Hari Prasad Gandikota, B. N. Jagadesh
    Scientific Reports, 2025
    The rapid growth of e-commerce has made product recommendation systems essential for enhancing customer experience and driving business success. This research proposes an advanced recommendation framework that integrates sentiment analysis (SA) and collaborative filtering (CF) to improve recommendation accuracy and user satisfaction. The methodology involves feature-level sentiment analysis with a multi-step pipeline: data preprocessing, feature extraction using a log-term frequency-based modified inverse class frequency (LFMI) algorithm, and sentiment classification using a Multi-Layer Attention-based Encoder-Decoder Temporal Convolution Neural Network (MLA-EDTCNet). To address class imbalance issues, a Modified Conditional Generative Adversarial Network (MCGAN) generates balanced oversamples. Furthermore, the Ocotillo Optimization Algorithm (OcOA) fine-tunes the model parameters to ensure optimal performance by balancing exploration and exploitation during training. The integrated system predicts sentiment polarity-positive, negative, or neutral-and combines these insights with CF to provide personalized product recommendations. Extensive experiments conducted on an Amazon product dataset demonstrate that the proposed approach outperforms state-of-the-art models in accuracy, precision, recall, F1-score, and AUC. By leveraging SA and CF, the framework delivers recommendations tailored to user preferences while enhancing engagement and satisfaction. This research highlights the potential of hybrid deep learning techniques to address critical challenges in recommendation systems, including class imbalance and feature extraction, offering a robust solution for modern e-commerce platforms.
  • Study of thermal performance and melting behaviour of a novel paraffin wax-carbon quantum Dots PCMs
    G. Murali, J. Emeema, B. Venkateswara Reddi, P. S. N. Masthan Vali, P. V. Elumalai, M. Murugan, Mamdooh Alwetaishi, T. Bhargava Ramu, S. Prabhakar
    Scientific Reports, 2025
    Thermal energy storage with phase change materials (PCMs) is emerging as a key solution in addressing the global energy crisis, driving innovation in energy storage and management systems. This work numerically investigates the thermal performance and melting behavior of a novel composite PCM composed of paraffin wax (PW) dispersed with different weight percentages of carbon quantum dots (CQDs) in order to validate the experimental results. Latent heat curves for the prepared composite PCMs were generated numerically using computational fluid dynamics (CFD), with the input values provided from experiments and they seem to support the pattern of the experimental curves. The temperature profile and melting properties of the PCMs have also been studied. Melting temperatures of the composites indicated a maximum 5.8% discrepancy between the experimental and numerical analysis. The melting times of composites were longer than those of PW, indicating a delayed yet steady state absorption of heat during melting and improved latent heat.
  • Deep Belief Networks for Multi-Class Brain Tumor Classification with Improved Diagnostic Accuracy
    Ramadevi R., Bhargava Ramu T., Elangovan Guruva Reddy, Padmapriya D., Jehan C., Ganesh Babu T.R.
    Journal of Innovative Image Processing, 2025
    The proposed research work investigates the use of Deep Belief Networks (DBNs) for the multi-class classification of brain tumors to improve diagnostic accuracy in medical imaging. Brain tumors present significant difficulties in identification and classification due to their varied morphologies and overlapping characteristics. DBNs, characterized by their multi-layered structure of restricted Boltzmann machines, are used to automatically extract hierarchical characteristics from magnetic resonance images of brain. The proposed technique consists of a two-phase training process: first, unsupervised network pre-training to extract pertinent features, followed by supervised fine-tuning to enhance classification performance. The DBN model's efficacy is compared to traditional machine learning techniques using an extensive dataset of brain tumor images. The results demonstrate that the DBN technique improves current approaches for accuracy, sensitivity, and specificity across several tumor types, including gliomas, meningiomas, and pituitary tumors. The proposed DBN achieves 97.9% accuracy, outperforming existing machine learning algorithms with a 7–18% enhancement in brain tumour classification, demonstrating greater diagnostic accuracy. The results highlight the efficacy of DBNs as a powerful instrument for automated brain tumor classification, offering significant assistance to radiologists and enhancing diagnostic processes. It supports the increasing evidence for using deep learning methods in clinical practices to improve patient care in oncology.
  • Creating Reliable Electric Vehicle Battery Management Systems Digital Twin Technology: Improving Safety, Energy Efficiency, and the Battery Lifecycle
    C.Praveen Kumar, T Bhargava Ramu, V. Manohari, Khaled Tawfiq Al-Assaf, Sorabh Lakhanpal, R. Balasubramaniyan
    Proceedings IEEE 10th International Conference on Smart Structures and Systems Icsss 2025, 2025
  • Speed control of BLDC motor using PID controller
    Tirunagari Bhargava Ramu, Sreevardhan Cheerla, Ravi Kumar Kallakuta, Kaja Krishna Mohan, Syed Inthiyaz, Nelaturi Nanda Prakash, Bodapati Venkata Rajanna, Cheeli Ashok Kumar
    International Journal of Applied Power Engineering, 2025
    The current state of science, technology, and industrial revolutions did not occur overnight. Many years of empirical study attempts by human intelligence have led to the world's current status. As a result, new technologies and innovations would constantly propel human civilization forward. Another outstanding invention of the present day is the brushless DC (BLDC) motor. This paper outlines the design of a BLDC motor control system utilizing MATLAB/Simulink software. The main aim of this project is to control the speed and to obtain time domain specifications of PID controller. The application of speed control of motor is vast and also required to maintain the work efficient without any disturbance, the power consumption, and any other fuel to run. On the basis of this the brushless DC motor as application is selected because of reduction in losses and also the power. The PID control system is built to control the speed of the motor and gives the precise output. The universal bridge is used to amplify the current in the output of the application. PID controller reduces the error and increases the stability of the system.
  • Incorporating Incremental Conductance MPPT Techniques into Solar Power Extraction
    Pankaj Sonia, Aravinda K, Atul Singla, Y. Jeevan Nagendra Kumar, Manoj Kumar Vishkarma, Hanaa Addai Ali, T. Bhargava Ramu
    E3s Web of Conferences, 2024
    Research into alternative, green energy sources such as solar power has been driven by concerns about environmental sustainability, escalating petroleum costs, and surging energy demand. Solar energy can power the entire world sustainably, since it is abundant and easy to access. Solar radiation, cell temperature, and load impedance all play a part in improving the efficiency of solar energy utilization. In order to maximize solar energy utilization, Maximum Power Point Tracking (MPPT) techniques are used. In order to address factors such as solar effectiveness, dynamic response, convergence speed, complexity, cost, and sensor requirements, different MPPT techniques have been developed. Using Incremental Conductance (INC) as an example, this paper provides a comprehensive overview of MPPT techniques. P&O’s drawback of oscillations around the Maximum Power Point (MPP) is overcome by INC, which minimizes them. The MPP voltage is maintained until the incremental conductance equals zero by comparing the instantaneous conductance of the panel with the incremental conductance. In addition to being easy to implement, INC-based methods offer rapid tracking and efficiency gains. Results from simulations demonstrate INC MPPT’s effectiveness in maximizing power extraction from photovoltaic systems, especially when environmental conditions change rapidly.
  • Solar Energy Forecasting using Optimized Attention-based Bidirectional Long Short-Term Memory
    Rajesh Prasad, T. Jarin, Hiren Mewada, Jithin K Jose, M. Arthi, T Bhargava Ramu
    2024 6th International Symposium on Advanced Electrical and Communication Technologies Isaect 2024, 2024
    Solar energy is abundantly available in the environment and is beneficial for preserving the environment, since they are regenerative and hold significant promise for the future. Forecasting accurate solar energy plays a major part in enhancing the determination of solar power plants, while also decreasing reliance on fossil fuels for economic and social progress. In the domain of deep learning (DL), the prediction of solar resources has transitioned from traditional statistical methods to the implementation of advanced DL models. This work introduces a model of "optimized attention-bidirectional long short-term memory" (OA-Bi-LSTM) for predicting solar energy. Here, the hyper-parameters of the BiLSTM are optimized by the manta ray optimization (MRO). The proposed model predicts solar energy in an efficient manner with respect to the different measures and achieves better MAE (0.15) and RMSE (0.21) values respectively.
  • Optimizing Inter-Cell Resource Partitioning in Network Slicing: A Game-Theoretic Approach
    A. Jaya Mabel Rani, S Lakshmisridevi, Sangeetha J, M. Aswinrani, T Bhargava Ramu, Mariammal R
    2024 5th IEEE Global Conference for Advancement in Technology Gcat 2024, 2024
  • Flexible AC transmission system using TSR
    T. Bhargava Ramu, Aluka Nikhitha, Sriram Ramya, Gavalla Naveen
    Aip Conference Proceedings, 2023
  • Closed loop control of a brushless DC motor to run at the required speed
    T. Bhargava Ramu, V. Soumya, B. Kavyanjali, B. Vani, B. Bhargav Reddy
    Aip Conference Proceedings, 2023
  • Evaluating Topological Insulator-Based FETs in Circuit-Level Performance with Advanced Device Simulations
    A Karthik, Asha V, T Bhargava Ramu, Rupa Rani Sharma, Ginni Nijhawan, Zahraa Salem Mohsen
    2023 International Conference on Power Energy Environment and Intelligent Control Peeic 2023, 2023
  • Mitigating voltage sag in secondary distribution line using DVR with single DC source
    International Journal of Scientific and Technology Research, 2020