SAMPATH S
@aitckm.in
Professor and Information Science & Engineering Department
Adichunchanagiri Institute of Technology
EDUCATION
Ph.D in Computer Science Engineering
RESEARCH INTERESTS
High Performance Computing, Parallel Computing
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Pasha C. A. Anser and S. Sampath
IEEE
Fake news poses a significant threat to social media and their users. Hybrid models for detection of fake news on social media, analyzing their strengths, weaknesses, and future directions are surveyed in it. We present an overview of fake news detection, discuss the limitations of individual approaches, and emphasis pros of combining them. We then describe various hybrid models categorized by the variety of techniques they integrate, including content analysis, network analysis, and knowledge reasoning. Additionally, we compare different hybrid models using key metrics namely correctness, precision, recall, and F1-score, presenting the results in tables and diagrams. Finally, we discuss open challenges and promising future directions for research in this domain. Additionally, it serves as a roadmap for future research directions, guiding the development of more robust and ethically sound fake news detection systems.
Durga Prasad Palaparthi and S Sampath
IEEE
Outliers are the data points that vary significantly from the primary distribution of data. In data mining, determining outliers is an essential task for establishing the data quality, decision-making, and models’ performance. Outliers generally cause errors during data collection, sensor malfunction, or data entry. By addressing and detecting outliers, the overall reliability and quality of the data can be increased. The clustering approach is utilized in data mining, image identification, and pattern recognition. In this study, the hard and soft efficient outlier detection clustering models that are implemented for data mining are considered. These are namely K-Means, K++, modified K-Means, K-Medoids, Fuzzy C-means (FCM), Adaptive Switching Randomly Perturbed Particle Swarm Optimization (ASRPPSO) based FCM, and Teaching and Learning-based optimization (TLBO). Accuracy, False Positive Rate (FPR), precision, f-measure, f-score, True Positive Rate (TPR), Completeness Score (CS), Purity measure, Silhouette (SC), Entropy measure, Partition entropy, Partition coefficient Rand Index (RI), Adjusted Rand Index (ARI), Weighted Kappa (WK) coefficient, and convergence time are utilized as the parameters in this study respectively.
S Sampath, Mudarakola Lakshmi Prasad, Mohammad Manzoor Hussain, R Parameswari, D Anil Kumar, and Pundru Chandra Shaker Reddy
IEEE
Living in a major metropolitan area has been linked to an increased risk of developing multiple forms of chronic-kidney-disease(CKD). In developed nations, predicting CKDs is a top priority. Predictive analytics for the purpose of predicting CKDs are the primary focus of this work. However, it is getting harder and harder to forecast outcomes for massive samples. While doing so, the MapReduce architecture makes it possible to write predictive algorithms by combining map and reduce operations. Problems with the scalability and effectiveness of anticipative learning approaches are alleviated by the comparatively straightforward programming interface. To efficiently handle small subsets of massive datasets, the authors propose using an iterative weighted mapreduce approach. Ensemble-nonlinear support-vector-machines(ENSVM) and random-forests(RF) are used to design a binary classification issue. As a result, the suggested approach generates nonlinear blends of kernel activations in example prototypes, as opposed to the conventional linear combination of activations. In addition, an ensemble of deep-SVM is utilized to integrate the descriptors, with the product rule being employed to merge the classifiers' likelihood estimates. Prediction accuracy and results interpretability are used to gauge performance.
Sampath S, Sanjay M, Numan Ahmed, Adi Bhagavath, and Nanjesh B R
IEEE
Human dignity demands that personal information be hidden. Currently, due to the dominance of large internet companies/cloud service providers, the control over the identity is not with the identity holder, leading to privacy concerns. The need for decentralization of identity is because it gives back control of identity credentials to identity holders and allows them to control when, how, and with whom to share their credentials. Self-sovereign Identity is an arising concept, which provides a way for digital identification. It enables the entities to control their identity and data flow in the digital world while enhancing privacy and security. Major privacy concerns are because of the numerous attacks and data breaches that can happen when sensitive information like identity credentials is stored on a centralized system used by the existing systems. Therefore, we propose a blockchain based self-sovereign identity platform where the user’s mobile wallet application. The proof of the Identity credentials are kept in a decentralised storage system based on the blockchain. This platform provides a Zero-Knowledge Proof (ZKP) mechanism to verify the information.
K. N. Mohan Kumar, S. Sampath, Mohammed Imran, and N. Pradeep
Springer Singapore
K. N. Mohan Kumar, S. Sampath, and Mohammed Imran
Springer International Publishing
Rakesh S. Raj, D.S. Sanjay, M. Kusuma, and S Sampath
IEEE
Several chronic diseases have affected the human health in the recent times. Many diseases are widespread and caused severe damage on the mankind. The technological advances have proved most of the diseases can be cured in this medical era, but certain diseases can only be prevented but not cured, one among them is diabetes. In this paper, we report a medical case by considering electronic health records of diabetic patients from various sources. The analyses are carried out using two data mining classification algorithms such as Naive Bayes and Support Vector Machine. The aim of the analysis is to predict diabetes using health record and compare the accuracy of these two algorithms to find a better algorithm for predicting diabetes.
Veerabasavantha Swamy, S. Sampath, B. R. Nanjesh, and Bharat Bhushan Sagar
Springer India
Sampath S, Nanjesh B R, Bharat Bhushan Sagar, and C K Subbaraya
IEEE
Parallel computing operates on the principle that large problems can often be divided into smaller ones, which are then solved concurrently which results in saving time to solve larger problems and to provide concurrency using desktop PC's. The main aim is to form a cluster based parallel computing architecture for demonstrating PVM based parallel applications which works on the Master-Slave computing paradigm. The master will monitor the progress and be able to report the time taken to solve the problem, taking into account the time spent in breaking the problems into sub-tasks and combining the results along with the communication delay. The slaves are capable of accepting sub problems from the master and finding the solution and sending back to the master. We aim to evaluate these time statistics of parallel execution for solving matrix multiplication problem and find the relation between the number of cores and number of slaves utilized for computation. When the number of nodes required for the computation is fixed by the user, the computation time mainly depends on the number of slaves specified for computation. In our work, we find the optimal number of slaves required for PVM based parallel computation when the number of nodes is fixed by a user. The analysis is made for the computation of different sizes of matrices over the different number of nodes.
S. Sampath, B. B. Sagar, and B. R. Nanjesh
IEEE
Parallel computing operates on the principle that large problems can often be divided into smaller ones, which are then solved concurrently to save time (wall clock time) by taking advantage of non-local resources and overcoming memory constraints. The main aim is to form a common cluster based parallel computing architecture for both MPI and PVM, which demonstrates the performance gain and losses achieved through parallel processing using MPI and PVM as separate cases. This can be realized by implementing the parallel applications like solving matrix multiplication problem, using MPI and PVM separately. The common architecture for MPI and PVM is based on the Master-Slave computing paradigm. The master will monitor the progress and be able to report the time taken to solve the problem, taking into account the time spent in breaking the problem into sub-tasks and combining the results along with the communication delays. The slaves are capable of accepting sub problems from the master and finding the solution and sending back to the master. We aim to evaluate and compare these statistics of both the cases to decide which among MPI and PVM gives faster performance and also compare with the time taken to solve the same problem in serial execution to demonstrate communication overhead involved in parallel computation. The results with runs on different number of nodes are compared to evaluate the efficiency of both MPI and PVM. We also show the performance dependency of parallel and serial computation, on RAM.
RECENT SCHOLAR PUBLICATIONS
MOST CITED SCHOLAR PUBLICATIONS
GRANT DETAILS
VGST, Department of Science & Technology, Govt of Karnataka sanctioned Lakhs, project completed in 2019.
INDUSTRY EXPERIENCE
One Year