Karthiga M

RESEARCH, TEACHING, or OTHER INTERESTS

Multidisciplinary, Computer Engineering, Artificial Intelligence, Computer Vision and Pattern Recognition

Scopus Publications

AI-enabled metaheuristic optimization for predictive management of renewable energy production in smart grids
S. Sankarananth, M. Karthiga, Suganya E., Sountharrajan S., and Durga Prasad Bavirisetti
Elsevier BV



Optimizing high-utility item mining using hybrid dolphin echolocation and Boolean grey wolf optimization
N. Pazhaniraja, S. Sountharrajan, E. Suganya, and M. Karthiga
Springer Science and Business Media LLC



Privacy Enhancement for Wireless Sensor Networks and the Internet of Things Based on Cryptological Techniques
M. Karthiga, A. Indirani, S. Sankarananth, S. S. Sountharrajan, and E. Suganya
Wiley



Blockchain-based incessant, user-friendly, secure, and unlimited patient care services and management
Karthiga M., Dhivya P., Sankarananth S., and Santhi V.
Elsevier



Cervical Cancer Prediction Using Optimized Meta-Learning
P. Dhivya, M. Karthiga, A. Indirani, and T. Nagamani
Springer Nature Singapore



Hybrid optimized convolutional neural network for efficient classification of ECG signals in healthcare monitoring
M. Karthiga, V. Santhi, and S. Sountharrajan
Elsevier BV



A wireless sensor network for remote detection of arrhythmias using convolutional neural network
M. Karthiga and V. Santhi
Springer Science and Business Media LLC



Alzheimer’s Dementia: Diagnosis and Prognosis using Neuro-Imaging Analysis
S. Sountharrajan, M. Karthiga, E. Suganya and Rajan
Siree Journals
Alzheimer’s disease (AD) is the most common type of progressive neurological disorder that leads to the death of brain cells over the time. It causes memory loss and decline in the cognitive skills among the elderly subjects. Early diagnosis of the progressive diseases plays a vital role in the healthcare community. Machine learning (ML) algorithms and various multivariate data exploratory tools are employed in the field of AD research. The main purpose of this work is to analyse the importance of features selection which in turn enhances the classification accuracy of the models. The hyper parameter tuning for Support Vector Machine (SVM) classification and Boruta algorithm for Random Forest (RF) classification are applied for the selection of optimal set of features. In this work, a five-stage ML pipeline with each stage further categorized into different sub-levels is proposed. Initially, the data collected from the Open Access Series of Imaging Studies (OASIS-2) dataset of Magnetic Resonance Imaging (MRI) brain images is explored and pre-processed using the imputation technique. Feature scaling of the pre-processed data is done using the Min-max scaling technique. Then, the classification techniques such as logistic regression, Decision Tree (DT) classification, Random Forest (RF) classification, Support Vector Machine (SVM) classification and AdaBoost Classification are applied to classify the data and finally the performance of the classifiers are compared in terms of accuracy, Area under the curve of the Receiver Operating Characteristic (AUC) curve and recall measures. From the performance analysis, it is concluded that the Random Forest (RF) classifier yields maximum accuracy, recall and AUC values. The hyperparameter tuning and Boruta algorithm added significance to the SVM and RF classification, thereby resulting in a F-score of 91% and 92% respectively.


Similarity Analytics for Semantic Text Using Natural Language Processing
M. Karthiga, S. Sountharrajan, A. Bazila Banu, S. Sankarananth, E. Suganya, and B. Sathish Kumar
Springer International Publishing



Effective Stock Price Prediction using Time Series Forecasting
Kumar Prakhar, Sountharrajan S, Suganya E, Karthiga M, and Sathis Kumar B
IEEE
Common wisdom states that investing in the stock market is highly risky and is not suitable for trade. This sentiment deters many people from investing in the stock market. Using Time Series Analysis on historical stock data, can train multiple forecasting models which can forecast the future trend in the closing prices of the particular stock. These trend charts can be extremely beneficial for both new and existing investors. Here, ARIMA, Facebook Prophet Model and the ETS model are compared to find out which model is best able to predict future stock price trends. Historical National Stock Exchange (India) data obtained using NSEpy python library is used along with the developed models. Results obtained reveal that the Facebook Prophet model works best to predict the stock price trends for a short-term basis.


Real-Time Face Swapping System using OpenCV
Aabir Datta, Om Krishna Yadav, Yukti Singh, Sountharrajan S, Karthiga M, and Suganya E
IEEE
Face swapping has been a thriving genre of work which primarily is associated with the replacement or substitution of one referral face on the face of the other person, be it by means of still images or in real time. This paper exhibits the research on Real-Time Face Swapping algorithm, using the reference image of the user and henceforth considering it as our input image instead of using a data set thereby working on a real time model by the use of the python open-source model of Computer Vision i.e., OpenCV. The input image facial features and attributes are extracted and are replaced to make the final resulting output through our model. The training of the model starts with learning the facial alignments and features to be able to recognize a face and extract its features before swapping it. Now, heading over to the process of image warping by the dissociation and partitioning of the user's face and its background. To increase the precision of the model, in the second part of parsing the face is performed to cancel out other features of the live image, hence the output is obtained. In this research, it was tried to bring accuracy and precision to the model by improving the condition of the image, editing out borders, and training it to a bunch of data for face recognition and correction. On analyzing it delivers the most subtle outputs alongside performing the tasks with the process including the analysis of our image and its output too. The model delivered is to improve the conditions of security, privacy, image capture, and entertainment purposes.


Prostate cancer prognosis-a comparative approach using machine learning techniques
Sagar.C. Bellad, Ananya Mahapatra, Sahil Dilip Ghule, Satvik Sridhar Shetty, Sountharrajan S, Karthiga M, and Suganya E
IEEE
Recently machine learning have been a field of interest for many researchers. Machine learning holds applications in tremendous sectors like healthcare, e-commerce and so on. It plays a vital role in the field of healthcare by their significant contribution through its ability to read from the historic/ past data especially in the diagnosis/predicting of diseases. Many classification algorithms have been proposed for the prediction process. The problem with classifiers is their vast variety and difficulty in choosing an appropriate method for the particular problem. To overcome the issue of selecting the appropriate method a comprehensive study on various classifiers should be done. This paper focuses on the working of various classifiers for prediction of prostate Cancer in calculating the level of efficiency in prediction and this helps in selecting the best method.


A Deep Learning Approach to classify the Honeybee Species and health Identification
Karthiga M, Sountharrajan S, Nandhini S S, Suganya E, and Sankarananth S
IEEE
Honey bee is one of the charming insect that utilizes a collective behavioral nature to achieve the powerful action. Protecting honey bees is one of the important jobs of every human in the world to preserve the ecological balance. Tracking and determining the several species of the bees over their life span electronically is a tedious work. Automated classification of species is important to preserve the various species of honey bees from danger. The diseases that affect the honey bees during their life span have to be detected autonomously and the spread of the diseases to other healthy honey bees has to be preserved. The proposed technique aims in classifying the several species of honey bees and identifying the diseases that are prone to honey bees. Convolution neural network with two dimensional layers are used as a classifier in the proposed model. Data augmentation using Synthetic Minority Over-sampling Technique (SMOTE) is utilized. More than 5000 images of honey bees with lot of features are used for learning purpose. The proposed methodology attained an accuracy of 86% for subspecies classification and 84% for bee health identification.


Machine learning based diagnosis of alzheimer’s disease
M. Karthiga, S. Sountharrajan, S. S. Nandhini, and B. Sathis Kumar
Springer International Publishing



Sustainable development of an integrated numerous dc-to-dc input converters for non-conventional sources of energy and its applications




Malevolent melanoma diagnosis using deep convolution neural network
M. Karthiga, R.K. Priyadarshini, and A Bazila Banu
A and V Publications



On-the-Go Network Establishment of IoT Devices to Meet the Need of Processing Big Data Using Machine Learning Algorithms
S. Sountharrajan, E. Suganya, M. Karthiga, S. S. Nandhini, B. Vishnupriya, and B. Sathiskumar
Springer International Publishing



Dynamic Recognition of Phishing URLs Using Deep Learning Techniques
S. Sountharrajan, M. Nivashini, Shishir K. Shandilya, E. Suganya, A. Bazila Banu, and M. Karthiga
Springer International Publishing



Lasso and ridge regression for optimized resource allocation in cloud computing




IoT in Agriculture Investigation on Plant Diseases and Nutrient Level Using Image Analysis Techniques
E. Suganya, S. Sountharrajan, Shishir Kumar Shandilya, and M. Karthiga
Elsevier



Mobile cancer prophecy system to assist patients: Big data analysis and design
E. Suganya, S. Sountharrajan, Shishir K. Shandilya, and M. Karthiga
American Scientific Publishers
The growth of cancer in India is growing hastily in recent years. Efficient monitoring and medication procedures are needed in high demand. Recent research states diagnose of cancer during its early break through will prevent mortality. The evolution of smart mobile devices paves its mutual focus in healthcare sectors. In this paper, an Intellectual model of disease diagnosis using the advantage of smart mobile devices has been proposed. This mobile based cancer diagnosis model uses a cloud environment for disease prediction and analysis. The Principal Component Analysis (PCA) technique is utilized to confiscate the superfluous features and choose the most appropriate features. Using the optimized features, cancer disease classification is accomplished using Support Vector Machines with sigmoid kernel function. SVM classifies the patients as normal and abnormal and the evaluated results are conveyed to the patients as well as the respective medical practitioners. The accuracy achieved through proposed model is satisfiable in comparison with other existing methods. Proposed Model incorporates with big data technologies to address the current issues of cancer system.


Secured cryptosystem using blowfish and RSA algorithm for the data in public cloud




Comparative analysis on image retrieval technique using machine learning
S. Sasireka, M. Karthiga, and N. Santhi
IEEE
The recommended system focus on Bag of features (Bof) model in image instance retrieval system. Most of the years, image retrieval is mainly used for browsing and searching for many applications. In recent years large amount of image retrieval shows the importance of semantic image retrieval in both research and industry application. Filter descriptors show an incredible discriminative power in taking care of vision issues like extricating the data about the recordings naturally. The recommended algorithm performs image quantizing of neighborhood descriptors and converts into visual words and further applies an adaptable ordering and recovery process. Every single image is splitted into short casings by outlines. Histograms are calculated based on the visual words dictionary of each picture and an input query are given and the particular images are selected from the database. Histogram is also used for counting the number of occurrences of an image. Key point locations are used to ensure an invariance of image location, scale and rotation. Closer image to the key point scale undergoes the process. Support Vector Machine is to compare the positive and negative occurrence of an image. Support Vector Machines (SVM) is utilized to recover the specific picture from the database and process the yield. Using this process, the images can be retrieved as soon as possible.


A novel battery and super capacitor using IOT to interface renewable energy sources with dual direction and its application
S Sankarananth, M Karthiga, C Karthikeyan, and M. Vinith Kumar
American Scientific Publishers



Automatic glioblastoma multiforme detection using hybrid-SVM with improved particle swarm optimisation
S. Sountharrajan, E. Suganya, M. Karthiga, and C. Rajan
Inderscience Publishers

RECENT SCHOLAR PUBLICATIONS