RAMNATH M

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Computer Vision and Pattern Recognition, Artificial Intelligence, Computer Science

Scopus Publications

High-precision malware detection in android apps using quantum explainable hierarchical interaction network
Ramnath Muthusamy and Yesubai Rubavathi Charles
Elsevier BV



PREDICTIVE ANALYSIS ON DEMONETIZATION DATA USING SUPPORT VECTOR MACHINE TECHNIQUE




Enhancing AppAuthentix recommender systems using advanced machine learning techniques to identify genuine and counterfeit android applications
Ramnath M. and Yesubai Rubavathi C.
PeerJ
Smartphone app expansion needs strict security measures to avoid fraud and danger. This study overcomes this issue by identifying apps differently. This new solution uses convolutional neural network (CNN), natural language processing (NLP), and the strong AppAuthentix Recommender algorithm to secure app stores and boost customer confidence in the digital marketplace. Since the app ecosystem has grown, counterfeit and harmful applications have risen, threatening consumers and app merchants. These risks need advanced technology that can distinguish malware from legitimate apps. A complex prediction model using CNNs for image analysis, NLP for text feature extraction, and the novel AppAuthentix Recommender algorithm to properly identify legitimate and counterfeit mobile applications is the goal of this research. The whole strategy secures app stores and authenticates apps. The urgent need to safeguard app markets and users against unauthorized and hazardous programs sparked this study. Our cutting-edge solutions make mobile app consumers’ digital lives safer and app marketplaces more trustworthy. CNN, NLP, and AppAuthentix Recommender yielded amazing results in this investigation. Mobile app authenticity may be estimated with 98.25% accuracy. This technology greatly improves app store security and enables mobile app verification. In conclusion, our work offers a novel way to app identification at a time of rapid mobile app development. CNN, NLP, and AppAuthentix Recommender have dramatically enhanced app store security. These new solutions may boost mobile app security and consumer confidence.


Oral Lesion Cell Segmentation and Classification using Convolution Neural Network Technique
J. Amutha, S. Priyadarsini, S. Prasanth, M. R. Senkumar, M. Ramnath, and T. Jasperline
IEEE
Oral Cancer of the mouth kills millions of people, Oral cancer is better treated and more often survived when caught early. Convolutional neural networks (CNNs) have recently shown remarkable promise for cancer diagnosis and other medical image processing applications. In this study, we train deep convolutional neural networks (CNNs) to detect oral cancer early. The suggested approach makes use of a large database of pictures of the mouth and its cavities. Develop and refine a convolutional neural network (CNN) model using the use of radiographs, histology slides, and intraoral images. Oral carcinogenic tumours, both precancerous and malignant, may be identified and classified automatically using this approach. The process begins with picture pre-processing, continues with dataset supplementation for better model generalizability, and culminates in the use of complex neural networks for feature extraction and learning. Transfer learning methods modify previously taught models for this medical imaging task. The system’s performance, sensitivity, and accuracy are evaluated using a set of images that have pre-existing diagnoses. Deep learning CNNs were able to identify oral cancer with an efficiency and accuracy of 93.62%, according to the research. The trained model is a valuable tool for early cancer screening because of its high sensitivity and specificity. By automating the process, oral cancer may be detected and treated more quickly, which improves patient outcomes and decreases the disease burden.


Advancing Brain-Computer Interaction: EEG-based Eye Movement Recognition with AI
Ravi Kumar Saidala, M. Ramnath, Komala C R, N. Gowri Vidhya, Syed Noeman Taqui, and Rajendiran M
IEEE
The integration of Electroencephalography (EEG) and Brain-Computer Interface (BCI) technologies is causing an evolution in healthcare, accessibility, and neuroscience. This multidisciplinary method offers a non-invasive means to communicate and control through intentional eye movements, which is particularly promising for patients suffering from neurological illnesses. In this study, eye movements are identified using EEG data from the EPOC Flex wireless EEG brain device. Using advanced Deep Learning models such as the Deep Belief Network (DBN) and the Deep Residual Network (Deep ResNet), and attempted to distinguish four distinct eye movements: open, close, right, and left. Some of the primary metrics utilized for assessing these models were accuracy, precision, recall, and F1 score. The Deep ResNet model gives better results with an accuracy of 96.25%, recall of 95.85%, precision of 96.66%, and an F1 score of 96.24%. The findings suggest that BCI frameworks can leverage EEG-based eye movement detection to improve rehabilitation procedures and make computers and devices easier to operate. This study's findings open a path for future research into neurotechnological applications and human-computer interaction.


Recommendations of Smartphone Applications According to Customer Reviews and Capabilities
M. Ramnath and C. Yesubai Rubavathi
IEEE
There are a plethora of new Android portable apps available now. As a result, making sure the apps you install on your mobile device are safe is a daunting undertaking for the average user. This study provides a popular and secure mobile App with a recommendation system to streamline the process. The design focus is on making recommendations for mobile apps by gauging their popularity and potential security issues. To index the apps and save the information in a database, a web crawler is employed. The programs are then sorted into groups according to their popularity and ratings. The suggested Android app provides a list of applications from the Google Play Store along with their respective security ratings whenever a query is executed. How popular an app is and what permissions it requires from the user significantly increase the app's potential security risks. This work aims to create such a recommendation system without sacrificing security or user engagement.


Prediction of Breast Cancer Risk Using Microarrays and Deep Learning
R. Madhubala Shanmu, P. Brundha, G. Aravind Swaminathan, R. Tino Merlin, V. Hemamalini, and M. Ramnath
IEEE
More than 1.15 million new instances of breast cancer are identified each year. In the clinic, only a few reliable prognostic and predictive indicators are utilized to make decisions about the treatment of breast cancer patients. The mortality rate of breast cancer patients may be lowered and their survival time extended by early identification. Analysis and processing of Microarray images, the principal test used for screening and early diagnosis, are the keys to improving breast cancer prognosis and are at the heart of this study. The Fuzzy C-means (FCM) approach is used for image segmentation in microarray for the detection of breast cancer. After features are retrieved from the segmented areas and the system is fully trained, the efficient classifier is used to assign microarrays to their respective classes. Techniques such as Multi-level Discrete Wavelet Transform, Principal Component Analysis (PCA), and Gray-level Co-occurrence Matrix (GLCM) are used to extract texture information. Differentiating masses and microarray image calcifications from the surrounding tissue is achieved with the aid of morphological operators and the classification of these features is handled by the Deep Convolution Neural Network (DCNN) algorithm. In a microarray, the tumor’s borders are highlighted and exhibited to the doctor, who may then assess the extent of the growth.


Towards Enhanced Deep CNN for Early and Precise Skin Cancer Diagnosis
S. Malaiarasan, R. Ravi, D.R. Maheswari, C.Yesubai Rubavathi, M. Ramnath, and V. Hemamalini
IEEE
Most people’s first experience with cancer will be with skin cancer, which is also the most prevalent and potentially fatal kind. Determining a skin cancer diagnosis also requires the use of information technologies. This highlights the need of developing and deploying highly effective deep-learning methods for the early and accurate diagnosis and detection of skin cancer. Deep Convolution Neural Network (DCNN) is proposed for automated skin cancer detection in this study. This study’s unique contribution is the use of a deep convolution neural network containing 12 nested processing layers to improve the accuracy of skin cancer diagnosis and detection. As a consequence of this study’s findings, researchers have determined that deep learning techniques are superior to machine learning for spotting skin cancer. As a consequence, pathologists’ precision and competence may be improved by using automated evidence-based detection of skin cancer. To accurately distinguish between benign and malignant skin lesions, we present a deep convolution neural network (DCNN) model in this research that uses a deep learning technique. First, we normalize the input photos and identify characteristics that aid in correct classification, then we apply a filter or Gaussian to eliminate noise and artifacts, and lastly, we supplement the data to increase the number of images, which enhances the accuracy of the classification rate.


Feature Adaptive Developmental Mechanisms for Mobile Apps Recommendations System using the Nearest Centroid Classification Algorithm
G. Twinkle Geojini, M. Ramnath, and C. Yesubai Rubavathi
IEEE
Reviews and ratings play an important part in modern technology since they provide insights that may be used to enhance the functionality and performance of apps. Some customers give app reviews that don't provide developers with useful feedback for improving the app. Developers can't fix bugs or release new versions of their software if they don't catch them as soon as possible. With this method, we extract the most helpful user comments from existing app evaluations and compare them to the apps' overall star ratings. We present a Nearest Centroid Classification (NCC) approach based on supervised machine learning with the goal of spotting new app problems via review analysis. To successfully illustrate resilience to the extreme values that are beyond the range, the suggested framework contains mean vectors of k to evaluate both distance closeness and geographical extent of k-neighbors in each class. After a long time of waiting, developers may at last quickly correct bugs and fine-tune the app's features to enhance the user experience.


App assessment with three phase evidence system using sentiment analysis
M. Ramnath and C. Yesubai Rubavathi
IEEE
The rapid increase in mobile industry results in large number of mobile apps arising in the market which can be downloaded by either paying or free of cost. The selection of an app for a category will be based on rating, review and ranking by the user. The current system to detect the app’s genuineness is based on any one of the parameter that takes time as it doesn’t consider the other two which fail to correlate the results. If app’s evaluation on any one of the parameter gives good results, then there is no need for other kinds of parameters. For this reason, a novel method is proposed to collect, review, rate, and rank an app which will be evaluated independently. In case of review, each review of an app undergoes sentiment analysis using Word2Vec model that predicts words closer to the target word and classify them as either positive or negative. The rating of an app is considered by setting a threshold value for evaluation. The ranking pattern of an app is analyzed which classified under rising, recession and maintenance phase. The results of the above three parameters are aggregated which gives the evidence to determine whether the app is trustworthy or not.

RECENT SCHOLAR PUBLICATIONS

PREDICTIVE ANALYSIS ON DEMONETIZATION DATA USING SUPPORT VECTOR MACHINE TECHNIQUE
VS KALIAPPAN M, MARIAPPAN E, RAMNATH M, KARPAGAVALLI C, ANGEL HEPZIBAH R
https://www.jatit.org/volumes/Vol103No1/27Vol103No1.pdf 2025



ISL Sign Language Recognition Using LSTM-Driven Deep Learning Model
ST Guruprakash B, Nagarajan Gurusamy, RamnathM, Sumathi S, Mariappan E
https://journal.esrgroups.org/jes/article/view/7496/5149 2024



Maximizing Solar Energy Efficiency Through Grasshopper Algorithm-Based Site Selection
AHR Anna Lakshmi A, Ramaswamy S, Mariappan E, Kaliappan M, Ramnath M
https://journal.esrgroups.org/jes/article/view/7132/4909 2024



Machine Learning in Healthcare: Prognosis Heart Disease Prediction
M Ramnath, B Revathi, S Selva Birunda, C Usharani, R Ramana, ...
2024 4th International Conference on Advancement in Electronics 2024



Enhancing AppAuthentix recommender systems using advanced machine learning techniques to identify genuine and counterfeit android applications
M Ramnath
PeerJ Computer Science 10, e2515 2024



LDPC CODE BASED AUTOENCODER OF AWSN USING DEEP NEURAL NETWORKS MODEL FOR WIRELESS COMMUNICATION CHANNEL
DME VAISSNAVE V, AMUTHACHENTHIRU K, DURGA DEVI G, Dr. ANNA LAKSHMI A, Dr ...
https://tianjindaxuexuebao.com/details.php?id=DOI:10.5281/zenodo.14043365 2024



Dragonfly Algorithm-Based Approach for Solar Power Plant Optimization in IEEE 69-Bus Network
KC Angel Hepzibah R., Anna Lakshmi A., Mariappan E., Kaliappan M., Sugel ...
https://www.thelearner-ijsmtl-cgrn.org/cgrn/issue-details.php?pid=474 2024



Heart Disease Prediction: A Machine Learning Model for Evaluation and Hyperparameter Tuning
RMDAALKCSTLVBTTGGD Mariappan E+
https://africanjournalofbiomedicalresearch.com/index.php/AJBR/article/view/2891 2024



Enhanced Solar Plant Positioning Using Moth-Flame Optimization Technique
DEMMDADTJDPEDAJDMKMMRMRA Hepzibah+
https://africanjournalofbiomedicalresearch.com/index.php/AJBR/article/view/2845 2024



AN EXAMINING CLUSTER BEHAVIOUR ANALYTICALLY USING KMEANS, EM, AND K* MEANS ALGORITHM
RM Dr. MARRIAPPAN E, Dr. ANNA LAKSHMI A, AMALA PRINCETON X, VETRIVEL P, Dr ...
https://tianjindaxuexuebao.com/details.php?id=DOI:10.5281/zenodo.14038149 2024



Oral Lesion Cell Segmentation and Classification using Convolution Neural Network Technique
J Amutha, S Priyadarsini, S Prasanth, MR Senkumar, M Ramnath, ...
2024 IEEE 3rd World Conference on Applied Intelligence and Computing (AIC 2024



Advancing Brain-Computer Interaction: EEG-based Eye Movement Recognition with AI
RK Saidala, M Ramnath, CR Komala, NG Vidhya, SN Taqui, ...
2024 International Conference on Inventive Computation Technologies (ICICT 2024



7th International Conference onInventive Computation Technologies (ICICT 2024) 24–26 April, 2024
NSS Reddy, VVA Rohith, PS Abhiram, MD Siva, R Saran, S Rebecca, ...
Artificial Intelligence 18, 5 2024



Benign and Malignant Cancer Prediction Using Deep Learning and Generating Pathologist Diagnostic Report
K Madasamy, V Shanmuganathan, Nithish, Vishakan, Vijayabhaskar, ...
International Conference on IoT and Health, 73-87 2023



Recommendations of Smartphone Applications According to Customer Reviews and Capabilities
M Ramnath, CY Rubavathi
2023 Second International Conference on Augmented Intelligence and 2023



Feature Adaptive Developmental Mechanisms for Mobile Apps Recommendations System using the Nearest Centroid Classification Algorithm
GT Geojini, M Ramnath, CY Rubavathi
2023 7th International Conference on Trends in Electronics and Informatics 2023



Prediction of Breast Cancer Risk Using Microarrays and Deep Learning
RM Shanmu, P Brundha, GA Swaminathan, RT Merlin, V Hemamalini, ...
2023 International Conference on Networking and Communications (ICNWC), 1-6 2023



Towards Enhanced Deep CNN For Early And Precise Skin Cancer Diagnosis
S Malaiarasan, R Ravi, DR Maheswari, CY Rubavathi, M Ramnath, ...
2023 International Conference on Networking and Communications (ICNWC), 1-7 2023



App Assessment with Three Phase Evidence System using Sentiment Analysis
M Ramnath, CY Rubavathi
2021 Third International Conference on Intelligent Communication 2021



Dynamic analysis of agent network in self organization using service level agreement technique
DK Jesintha, JP Anandh, M Ramnath
Int. J. of Eng. Sci. Invent 4 (3), 44-49 2015

MOST CITED SCHOLAR PUBLICATIONS

Towards Enhanced Deep CNN For Early And Precise Skin Cancer Diagnosis
S Malaiarasan, R Ravi, DR Maheswari, CY Rubavathi, M Ramnath, ...
2023 International Conference on Networking and Communications (ICNWC), 1-7 2023
Citations: 7



App Assessment with Three Phase Evidence System using Sentiment Analysis
M Ramnath, CY Rubavathi
2021 Third International Conference on Intelligent Communication 2021
Citations: 4



Dynamic analysis of agent network in self organization using service level agreement technique
DK Jesintha, JP Anandh, M Ramnath
Int. J. of Eng. Sci. Invent 4 (3), 44-49 2015
Citations: 3



Recommendations of Smartphone Applications According to Customer Reviews and Capabilities
M Ramnath, CY Rubavathi
2023 Second International Conference on Augmented Intelligence and 2023
Citations: 1



Feature Adaptive Developmental Mechanisms for Mobile Apps Recommendations System using the Nearest Centroid Classification Algorithm
GT Geojini, M Ramnath, CY Rubavathi
2023 7th International Conference on Trends in Electronics and Informatics 2023
Citations: 1



Prediction of Breast Cancer Risk Using Microarrays and Deep Learning
RM Shanmu, P Brundha, GA Swaminathan, RT Merlin, V Hemamalini, ...
2023 International Conference on Networking and Communications (ICNWC), 1-6 2023
Citations: 1