RAMESHPRABHAKARAN R

@mzu.edu.in

Assistant Professor and Computer Science and Engineering
Mizoram University

RAMESHPRABHAKARAN R


               Download Compact PDF  
https://researchid.co/rameshsamy5

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Vision and Pattern Recognition, Artificial Intelligence, Computer Science Applications, Computer Engineering
7

Scopus Publications

1

Scholar Citations

1

Scholar h-index

Scopus Publications

  • Smart Group Face Recognition System for Class Room Attendance Management
    P. Ramya, R. Jayalakshmi, Soorya, Ramesh Prabhakaran R, Sangeetha K, Karthika K
    2025 17th IEEE International Conference on Computational Intelligence and Communication Networks Cicn 2025, 2025
    Monitoring student attendance is an essential component in schools and colleges, as it serves as a key indicator of academic performance and participation. Traditionally, attendance is recorded manually by teachers, which can become a time-consuming and inefficient task, especially in classrooms with a large number of students. While some institutions have adopted automated systems such as biometric or RFID-based methods, these alternatives often come with limitations including high implementation costs, the possibility of inaccurate or false records, technical failures, and privacy-related issues. To address these challenges, there is a growing need for a smart, reliable, and cost-effective solution that can seamlessly integrate into the academic environment. One promising approach is the use of facial recognition technology, which has gained significant attention for its nonintrusive and user-friendly application. However, many traditional face recognition systems rely on basic feature extraction methods, which may not always provide the required level of accuracy in dynamic classroom conditions. The proposed system seeks to overcome these shortcomings by employing advanced facial modeling techniques to identify students with higher precision. Designed specifically for classroom scenarios, this automated attendance system not only reduces the burden on instructors but also ensures greater accuracy, efficiency, and reliability compared to conventional methods.
  • Artificial Intelligence Based Digital Writing Pen Technology
    Angel Maanu P, Sherine W B, Nithiyasree P, Niranjan G, Guhan Sankar B, Ramesh Prabhakaran R
    Proceedings 2025 2nd International Conference on Networks and Soft Computing Icnsoc 2025, 2025
  • Machine Learning-Based Crop Recommendation System for Mizoram
    V.D. Ambeth Kumar, Ajoy Kumar Khan, Vanlalhruaia, Saithantluanga, Ramesh Prabhakaran R, Zaitinkhuma
    Proceedings of 2025 3rd International Conference on Intelligent Systems Advanced Computing and Communication Isacc 2025, 2025
    Agriculture is an important sector of Mizoram domicile as more than half of its population relies on Agriculture as principle source of income and sustenance. Some farmers rely on the knowledge acquire from their parents through explicit explanation, and by observing and modelling their practices. But most farmer often struggle to understand the method and type of crops to cultivate for better crop yield. Even experienced farmer believed that using more fertilizer result in better crop yield in spite of that it damages the soil properties. To resolve this challenge, this paper presents a Crop Recommendation System using Machine Learning, tailored for Mizoram, enhancing Agriculture practices towards sustainable development. The Crop Recommendation System analyzes historical data, soil properties, weather pattern and crop performance to recommend the best crop for a specific region and its condition. The aim is to provide the Crop Recommendation System with information about the soil and the condition of the region. The study utilizes various Machine Learning Algorithms such as Random Forest, Decision Trees, Support Vector Machine and Logistic Regression to make optimal recommendation. The results indicate that Random Forest provides superior performance of 99% across all the evaluations metrics. Although many prevention measures need to be taken to avoid complications such as overfitting, etc. The overall results suggested that Random Forest achieved the best results as compared to all the other state of the art algorithms utilized with the same preprocessing steps. This approach enhances the crop and soil. After a long and often complicated process of farming method and selection of crop problem the Crop Recommendation System will aid Mizoram farmers to achieve better crops, yield and higher profit.
  • A Hybrid Cloud Storage System Utilizing The ECC Algorithm and Data Fragmentation Approach Utilizing Secure Cryptography
    Ramesh Prabhakaran R, Rohini S, Ramya P, Nithiyasree P, Anush Priya T, Guhan P
    2025 International Conference on Data Science Agents and Artificial Intelligence Icdsaai 2025, 2025
    To improve data security, the Hybrid Cloud Storage System combines data fragmentation and safe cryptography. The solution protects data security and integrity by encrypting files before storing them in the cloud, using the Elliptic Curve Cryptography (ECC) technique. Combining public and private cloud environments, the hybrid cloud approach offers increased security, scalability, and flexibility. A data fragmentation strategy is used, in which the files are split up into smaller pieces and dispersed among several cloud sites, to further secure the data. Because each fragment is useless without the entire dataset, this fragmentation reduces the chance of data breaches. This method is perfect for safeguarding sensitive data in distributed cloud environments because it combines data fragmentation and ECC encryption to provide safe, effective, and dependable cloud storage. To optimize the data replica placement has become one of the fundamental problems. To reduce the inter-node traffic and the system overhead of accessing associated data items. Introduce Replication Management method for Optimal Performance and Security. File Fragmentation- Methodology to split the uploaded file into fragments. Replication is to help ease retrieval of data.
  • SHAP-Based Feature Selection and Optuna-Tuned CatBoost for an Accurate Heart Disease Prediction
    Zaitinkhuma Thihlum, M.S. Divya Dharshini, R. Lalduhsaka, P. Ramya, Ramesh Prabhakaran R, C. Lalrinawma, R. Vanlalawmpuia, Vanlalhruaia, R. Chawngsangpuii
    2025 17th IEEE International Conference on Computational Intelligence and Communication Networks Cicn 2025, 2025
    Cardiovascular disease (CVD) remains the leading cause of mortality worldwide, emphasizing the need for accurate and interpretable predictive systems for early detection and timely intervention. In this study, the CatBoost algorithm, a powerful gradient boosting method, is applied to classify heart disease cases. SHapley Additive exPlanations (SHAP) are employed to identify and select the most influential features, enhancing interpretability and reducing computational complexity without compromising accuracy. Using the top nine SHAP-ranked features and Optuna-based hyperparameter tuning, CatBoost achieved 99.03% accuracy, 100% precision, 98.10% recall, and 99.04% F1-score. These results highlight the combined strength of explainable AI (XAI) and ensemble learning in delivering both high-performance predictions and clinical transparency.
  • Navigation On Mobile Computing Devices with A Walking Using Object-Oriented Techniques to Communicate Stick
    Ramesh Prabhakaran R, Guhan P, E George Dharma Prakash Raj, Karthika K, Angel Maanu P
    3rd International Conference on Communication Control and Intelligent Systems Ccis 2024, 2024
    Moving around in their surroundings is challenging for elderly people and people with visual impairments. The majority of functional sticks in use today are not intelligent and lack an innate ability to recognize obstacles. In an effort to address this issue, mobility and orientation specialists who assist the blind by teaching them to move freely and safely using their remaining senses are brought in. They can navigate around obstacles with the aid of guidance dogs as well. These techniques have drawbacks, such as the dogs' inability to comprehend complicated instructions, the high cost of maintaining these trained dogs, and the need to hire an expert. In light of the aforementioned difficulties, the "Smart walking stick" has become a potential answer. The "Mobile based walking stick" is a useful mobility aid with the capacity to call a relative who can help in the event of an accident, detect obstacles above ground level and pits using ultrasonic sensors, recognize when a collision has occurred, and call the user's mobile phone if it has been misplaced to share the location's GPS for use with GSM connectivity and to share with the user's mention contacts. With some visually disabled people as test subjects, a test case was run, and 95% of the time it was successful.
  • AI Based Anomaly Detection for Bank Security Against Theft
    Ramesh Prabhakaran R, Danish Quamar, Guhan P, Angel Maanu P, Sherine W B, Aman Raj
    3rd International Conference on Communication Control and Intelligent Systems Ccis 2024, 2024
    A critical component of video surveillance research and real-world applications is the detection of anomalous events. In order to improve public safety, more and more surveillance cameras are being installed in public spaces like roadways, crosswalks, banks, and shopping centers. Identification of odd occurrences, such as car accidents, crimes, or illicit activity, is a crucial duty in video surveillance. Because anomalous events are less often than normal activities, the goal of an efficient anomaly detection system is to quickly identify departures from the average and identify the abnormality’s temporal span. One way to think of anomaly detection is as an early stage of video analysis that separates abnormalities from normal patterns. Using classification techniques, an anomaly can be further classified into particular activities once it has been discovered. An overview of anomaly detection with an emphasis on banking operations is given in this paper. Many every day and recurring transactions in the banking industry affect a number of stakeholders, including staff members, clients, debtors, and outside parties. Early detection of these anomalies can reduce or even eliminate any potential bad effects. In order to distinguish between normal and abnormal events, this work employs an anomaly detection technique based on machine learning.

RECENT SCHOLAR PUBLICATIONS

  • A Reliable and Effective Approach for Computerized Skin Disease Classification Using MobileNetV3 and LSTM
    A Vasudevan, C Jackulin, H Khalingarajah, N Raja, R Prabhakaran
    2025
  • IoT sensors for smart cities and business transactions to daily tasks for data analytics algorithms
    RR Prabhakaran, K Subramani, L Jabsheela, S Magesh, SH Charan
    AIP Conference Proceedings 3257 (1), 020161 , 2025
    2025
  • Educational games utilizing augmented reality (AR) and virtual reality (VR)
    RR Prabhakaran, M Rajendiran, K Charulatha, P Ramya
    AIP Conference Proceedings 3257 (1), 020003 , 2025
    2025
  • Artificial Intelligence Based Digital Writing Pen Technology
    WB Sherine, P Nithiyasree, G Niranjan, B Guhan Sankar, ...
    2025 Second International Conference on Networks and Soft Computing (ICNSoC … , 2025
    2025
  • An Advanced Forest Environment Using Augmented Reality and Virtual Reality Technology
    A Vasudevan, SIS Mohammad, N Raja, SD Mayanglambam, PK Singh, ...
    Journal of Posthumanism 5 (1), 1461–1474-1461–1474 , 2025
    2025
    Citations: 1
  • A Hybrid Cloud Storage System Utilizing The ECC Algorithm and Data Fragmentation Approach Utilizing Secure Cryptography
    S Rohini, P Ramya, P Nithiyasree, T Anush Priya, P Guhan
    2025 International Conference on Data Science, Agents & Artificial … , 2025
    2025
  • A survey on the lane detection and assistance system
    NPS Gnanasekar, P Rajendran, V Muralidharan, RP Rengasamy
    AIP Conference Proceedings 3175 (1), 020020 , 2025
    2025
  • Machine Learning-Based Crop Recommendation System for Mizoram
    VDA Kumar, AK Khan
    2025 3rd International Conference on Intelligent Systems, Advanced Computing … , 2025
    2025
  • Augmented Reality (AR) And Virtual Reality (VR) Based on Educational Game for Mode of Quadratic Reflectance Distribution
    SI Mohammad, R Ramesh Prabhakaran, N Raja, H Jadallah, B Al Oraini, ...
    Appl. Math 19 (6), 1263-1272 , 2025
    2025
  • AI Based Anomaly Detection for Bank Security Against Theft
    D Quamar, P Guhan, WB Sherine, A Raj
    2024 International Conference on Communication, Control, and Intelligent … , 2024
    2024
  • Empowering Mizoram State Museum Applying Virtual Reality on Linked Data and Smart Objects
    VDA Kumar, R Ramasamy, G Ramakrishna, RR Prabhakaran
    Science & Technology Journal 12 (2) , 2024
    2024

MOST CITED SCHOLAR PUBLICATIONS

  • An Advanced Forest Environment Using Augmented Reality and Virtual Reality Technology
    A Vasudevan, SIS Mohammad, N Raja, SD Mayanglambam, PK Singh, ...
    Journal of Posthumanism 5 (1), 1461–1474-1461–1474 , 2025
    2025
    Citations: 1
  • A Reliable and Effective Approach for Computerized Skin Disease Classification Using MobileNetV3 and LSTM
    A Vasudevan, C Jackulin, H Khalingarajah, N Raja, R Prabhakaran
    2025
  • IoT sensors for smart cities and business transactions to daily tasks for data analytics algorithms
    RR Prabhakaran, K Subramani, L Jabsheela, S Magesh, SH Charan
    AIP Conference Proceedings 3257 (1), 020161 , 2025
    2025
  • Educational games utilizing augmented reality (AR) and virtual reality (VR)
    RR Prabhakaran, M Rajendiran, K Charulatha, P Ramya
    AIP Conference Proceedings 3257 (1), 020003 , 2025
    2025
  • Artificial Intelligence Based Digital Writing Pen Technology
    WB Sherine, P Nithiyasree, G Niranjan, B Guhan Sankar, ...
    2025 Second International Conference on Networks and Soft Computing (ICNSoC … , 2025
    2025
  • A Hybrid Cloud Storage System Utilizing The ECC Algorithm and Data Fragmentation Approach Utilizing Secure Cryptography
    S Rohini, P Ramya, P Nithiyasree, T Anush Priya, P Guhan
    2025 International Conference on Data Science, Agents & Artificial … , 2025
    2025
  • A survey on the lane detection and assistance system
    NPS Gnanasekar, P Rajendran, V Muralidharan, RP Rengasamy
    AIP Conference Proceedings 3175 (1), 020020 , 2025
    2025
  • Machine Learning-Based Crop Recommendation System for Mizoram
    VDA Kumar, AK Khan
    2025 3rd International Conference on Intelligent Systems, Advanced Computing … , 2025
    2025
  • Augmented Reality (AR) And Virtual Reality (VR) Based on Educational Game for Mode of Quadratic Reflectance Distribution
    SI Mohammad, R Ramesh Prabhakaran, N Raja, H Jadallah, B Al Oraini, ...
    Appl. Math 19 (6), 1263-1272 , 2025
    2025
  • AI Based Anomaly Detection for Bank Security Against Theft
    D Quamar, P Guhan, WB Sherine, A Raj
    2024 International Conference on Communication, Control, and Intelligent … , 2024
    2024
  • Empowering Mizoram State Museum Applying Virtual Reality on Linked Data and Smart Objects
    VDA Kumar, R Ramasamy, G Ramakrishna, RR Prabhakaran
    Science & Technology Journal 12 (2) , 2024
    2024