RGRohini Ganapathi

Rohini Ganapathi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Rohini Ganapathi has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Integrating Blockchain for Secure IOT- Based Energy Trading in Smart Grid

    by Manojkumar Palanisamy, Hariharan Subramani, Gowrishankar Chandran, Rohini Ganapathy

  • CRNN-KHO: hybrid deep learning optimization framework for enhancing energy efficiency in IoT-enabled wireless networks

    by Bhimaraya Patil, Kuldeep Singh, Rohini Ganapathi, Deepak Suresh Asudani, Krishan Dutt Sharma, Nidhi Sindhwani, Ekta Singh


  • Open Access

    Machine Learning-Based Credit Card Fraud Detection: A Comparative Study Using Logistic Regression, SVM, and KNN

    by Tukaram K. Gawali, Alice Hepzibah Albert, S. Sivarajeswari, P. Manimekala, G. Rohini, Swati Shirke Deshmuk, E. Pahutharivu

    The increasing threat of credit card fraud in the digital age necessitates robust and intelligent detection systems. This study investigates the application of machine learning algorithms—Logistic Regression, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN)—to identify fraudulent credit card transactions. Using a real-world dataset, the research addresses issues of class imbalance with the SMOTE technique and develops models capable of classifying transactions with high precision and recall. A web-based fraud detection system is also designed to visualize and evaluate model performance. The results highlight the effectiveness of machine learning in real-time fraud detection and present a scalable system framework suitable for deployment in modern financial infrastructures.

  • Autonomous Forecasting of Traffic in Cellular Networks Based on Long-Short Term Memory Recurrent Neural Network

    by Rohini G, Gnana Kousalya C, Nagendra Singh, Vishal Ratansing Patil

    Forecasting of traffic in cellular network is a significant service for management of available resources strategically in an efficient way. Valuable resources such as link bandwidth and energy are increasing exponentially with increase in usage of cellular data. In this paper, we implement the design of Neural Network for identification of recurrent patterns in different metrics that can be then applied in forecasting of traffic in cellular networks. As this Neural Network design is based on memory and custom architecture, it is able to handle task of prediction in a precise and faster mode in real-time applications such as cellular network traffic forecasting. This work involves a Long Short Term Memory design of Recurrent Neural Network for traffic forecasting in cellular networks. It enhances the performance of the cellular network thereby providing a solution for the service providers as the available resources are utilized in an effective way. Same data set is involved for multiple prediction to analyze the performance of the design and found to be robust than the existing algorithms.


  • Intrusion Detection System with an Ensemble Learning and Feature Selection Framework for IoT Networks

    by G. Rohini, C. Gnana Kousalya, J. Bino

    The Internet of Things (IoT) and its applications are currently the most popular research areas. The properties of IoT are easily adapted to real-life applications but they disclose threats. In computer security, the Intrusion Detection System (IDS) plays an essential role in identifying and repealing malicious deeds in computer networks. The main purpose of this work is motivated by IoT security enhancement for IDS development using ensemble learning and proposing suitable methods for classifier performance. Initially, the preprocessing strategy is used for data cleaning, encoding and normalization, which are conducted in the RPL-NIDDS17 dataset. After that, the Synthetic Minority Oversampling Technique (SMOTE) is used to balance the dataset. Secondly, the Convolution Neural Network (CNN) has been used to extract the features from the dataset. From the extracted features, the optimal features are selected by the proposed Arithmetic Optimization Algorithm (AOA). Finally, it is applied to the proposed weighted majority voting classifier. The AOA with the Butterfly Optimization Algorithm (BOA) is utilized to integrate the predictions of different classifiers to select the most vote class. This enhances the chances of perceived RF, kNN, SVM kernel, Bi-LSTM and GRU classifiers. The proposed method experiment is conducted in the MATLAB platform with the RPL-NIDDS17 dataset. The proposed scheme shows better performances in terms of accuracy, error, sensitivity, specificity, FPR, F1_score, Kappa and MCC, which are compared with the existing methods and algorithms.


  • Ring Cross-over Based GA for DFMB Chip Design and Medical Image Compression

    by G. Brindha, G. Rohini

    : Currently, the clinical data stored in the cloud is easily accessible, and the patient’s data can be shared among treatment centers. In such a case, to handle additional data, the cloud data must be of a lesser scale. A process of compression was introduced to minimize the data with no losing data in order to achieve this size reduction. This paper conducts the experiment in two approaches: fast routing operations and compression from the chip in the DMFB approach. To apply this process of compression, the collected data from the chip was transformed into an image, and then compression of the image was performed utilizing a genetic algorithm (GA) based on a ring crossover. Consequently, the biochip of the 8x8 array is integrated into the power and area with the ring cross-module for an effective energy consumption operation. The technique of the process is utilized by the Microfluidic (MF) feature to handle and maintain the droplets. Also, the optimization process is performed by combining related pin actuation segments in parallel and the control pin to prevent pin-actuation conflicts. Through the optimization process, it synchronizes the length. This proposed approach decreases the consumption of the power and area. The outcome of the simulation indicates an increase in dynamic power, static power, and delay. Image compression is performed with the aid of this algorithm. In addition, for better outcomes, this GA compression application was contrasted with wavelet compressions.

  • Ring Cross Over Based Genetic Algorithm For DFMB Chip Design And Medical Image Compression

    by G. Brindha, G. Rohini

    Objective: Recent days, medical data are stored in the cloud for easy access and sharing the data of patients between the health center for treatments. In such a situation, the data stored in the cloud should be of lesser size to accommodate more information. To perform this size reduction a compression process is implemented to reduce the data without loss of information. Methodology/ investigation: This paper performs such an operation in two ways one is to fast routing operation in the DMFB approach and to perform the compression from the chip. To implement this compression process, the data obtained from the chip is converted into image and then Image compression is implemented using ring cross over based Genetic Algorithm. So, First of all 8x8 arrays biochip is implemented with the module of ring cross for efficient process of consumption in power and area. The process of the system is leads to manipulate and manage the droplets as per the function of Micro fluidic (MF). Also, for avoiding pin-actuation conflicts, optimization process is processed with the merging of corresponding pin actuation sequences in parallel process along with the control pins. It synchronized the length by the optimization process. Conclusion: In this study, this suggested technique reduces the consumption of area, and power miserably. The simulation result shows the improvement in the static power, dynamic power and delay. With the help of this algorithm image compression is implemented. And also this genetic algorithm compression application is compared with wavelet compression for better results.