R. Nedunchezhian

Ramakrishna Mission Vidyalaya

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

M. Rajalakshmi

Mansoura University

P. Vivekanandan

Sri Eshwar College of Engineering

S. V. Evangelin Sonia

Karunya University

K. Anbumani

Sathyabama Institute of Science and Technology

A. Sakthivel

KPR Institute of Engineering and Technology

V. Vijayakumar

Anna University, Chennai

N. Prakash

PSG INSTITUTE OF TECHNOLOGY AND APPLIED RESEARCH

K. Amshakala

M. Subathra

Bharathiar University

Jasma Balasangameshwara

Dayananda Sagar University

Cooperative Institutions

PSG INSTITUTE OF TECHNOLOGY AND APPLIED RESEARCH

Karunya University

Indian Institute of Science Bangalore

Anna University, Chennai

Bharathiar University

University of Greenwich

Institute of Engineering

KPR Institute of Engineering and Technology

Vellore Institute of Technology University

Kwame Nkrumah University of Science and Technology

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Empowering Artificial Intelligence Through Machine Learning

Apple Academic Press eBooks (2022)

R. Nedunchezhian M. Rajalakshmi Dinesh Goyal S. Balamurugan Muqeem Ahmed

10.1201/9781003055129

Cite

Citations (2)

Cardiac abnormalities from 12‐Lead ECG signals prediction based on deep convolutional neural network optimized with nomadic people optimization algorithm

International Journal of Adaptive Control and Signal Processing (2024)

S. V. Evangelin Sonia R. Nedunchezhian M. Rajalakshmi

Summary Cardiovascular disease (CVD) is a most dangerous disease in the world. Early accurate and automated identification helps the medical professional make a correct diagnosis and administer fast treatment and saving many lives. Several studies have been suggested in this area, but no one yield the expected outcomes owing to data imbalance issue in the medical and healthcare industries. To overcome this problem, a Deep Convolutional Neural Network Optimized with Nomadic People Optimization for Cardiac Abnormalities from 12‐Lead ECG Signals Prediction (CCA‐12L ECG‐DCNN‐NPO) is proposed in this manuscript. At first, the input data is pre‐processed under Morphological filtering and Extended Empirical wavelet transformation (MF‐EEWT) for removing the noise. Then one hot encoding technique is used to improve the predictions and classification accuracy of the method. Afterward, Residual Exemplars Local Binary Pattern (RELBP) based Feature extraction is used to extract the morphological and statistical features. These extracted features are given to DCNN classifier. It contains fully convolutional neural network (FCN) and encoder with decoder framework, which activates pixel‐wise categorization to exactly identify Cardiac abnormalities from 12‐Lead ECG signals. The visual geometry group network (VGGNet) is considered as a backbone of FCN for end‐to‐end training. Generally, DCNN method does not adopt any optimization modes to define the optimum parameters and to assure exact detection. Therefore, Nomadic People Optimization (NPO) is considered to enhance the DCNN weight parameters. The CCA‐12L ECG‐DCNN‐NPO technique is implemented in python and the efficacy is analyzed under performance metrics, such as sensitivity, precision, F‐Score, specificity, accuracy and error rate. From the analysis, the proposed technique attains higher accuracy 27.5%, 10.32%, and 16.65%, higher f‐score 30.93%, 11.14% and 15.3%, lower error rate 36.31%, 15.78%, and 28.08% compared with the existing methods, such as Detecting Cardiac Abnormalities from 12‐lead ECG Signals Under Feature Selection, Feature Extraction, and deep Learning Classification (CCA‐12L ECG‐RFC), Channel self‐attention deep learning framework for multi‐cardiac abnormality diagnosis from varied‐lead ECG signals (CCA‐12L ECG‐CSA‐DNN) and Cardiac disease categorization by electrocardiogram sensing utilizing deep neural network (CCA‐12L ECG‐DNN) respectively.

10.1002/acs.3739

Cite

Citations (4)

IAPI QUAD-FILTER: AN INTERACTIVE AND ADAPTIVE PARTITIONED APPROACH FOR INCREMENTAL FREQUENT PATTERN MINING

R. Nedunchezhian M. Rajalakshmi

Association rule mining has been proposed for market basket analysis and to predict customer purchasing/spending behaviour by analyzing the frequent itemsets in a large pool of transactions. Finding frequent itemsets from a very large and dynamic dataset is a time consuming process. Several sequential algorithms have contributed to frequent pattern generation. Most of them face problems of time and space complexities and do not support incremental mining to accommodate change in customer purchase behaviour. To reduce these complexities researchers propose partitioned and parallel approaches; but they are compromising on anyone of these. An interactive and adaptive partitioned incremental mining algorithm with four level filtering approaches for frequent pattern mining is proposed here. It prepares incremental frequent patterns, without generating local frequent itemsets in less time and space complexities and is efficiently applicable to both sequential and parallel mining.

Affinity analysis

Source

Cite

Citations (2)

A Novel Method for Super Imposed Text Extraction in a Sports Video

International Journal of Computer Applications (2011)

V. Vijayakumar R. Nedunchezhian

Video is one of the sources for presenting the valuable information.It contains sequence of video images, audio and text information.Text data present in video contain useful information for automatic annotation, structuring, mining, indexing and retrieval of video.Nowadays mechanically added (superimposed) text in video sequences provides useful information about their contents.It provides supplemental but important information for video indexing and retrieval.A large number of techniques have been proposed to address this problem.This paper provides a novel method of detecting video text regions containing player information and score in sports videos.It also proposes an improved algorithm for the automatic extraction of super imposed text in sports video.First, we identified key frames from video using the Color Histogram technique to minimize the number of video frames.Then, the key images were converted into gray images for the efficient text detection.Generally, the super imposed text displayed in bottom part of the image in the sports video.So, we cropped the text image regions in the gray image which contains the text information.Then we applied the canny edge detection algorithms for text edge detection.The ESPN cricket video data was taken for our experiment and extracted the super imposed text region in the sports video.Using the OCR tool, the text region image was converted as ASCII text and the result was verified.

10.5120/1915-2553

Cite

Citations (11)

Rapid Privacy Preserving Algorithm for Large Databases

IGI Global eBooks (2009)

K. Anbumani R. Nedunchezhian

Data mining techniques have been widely used for extracting non-trivial information from massive amounts of data. They help in strategic decision- making as well as many more applications. However, data mining also has a few demerits apart from its usefulness. Sensitive information contained in the database may be brought out by the data mining tools. Different approaches are being utilized to hide the sensitive information. The proposed work in this article applies a novel method to access the generating transactions with minimum effort from the transactional database. It helps in reducing the time complexity of any hiding algorithm. The theoretical and empirical analysis of the algorithm shows that hiding of data using this proposed work performs association rule hiding quicker than other algorithms.

10.4018/978-1-60566-058-5.ch061

Cite

Citations (0)

Mining data streams with concept drifts using genetic algorithm

Artificial Intelligence Review (2011)

P. Vivekanandan R. Nedunchezhian

10.1007/s10462-011-9209-y

Cite

Citations (23)

Analyzing the Point Multiplication Operation of Elliptic Curve Cryptosystem over Prime Field for Parallel Processing

The International Arab Journal of Information Technology (2014)

A. Sakthivel R. Nedunchezhian

The Elliptic Curve Cryptosystem shortly called as (ECC) is one of the asymmetric key cryptosystems, which provides a high security for wireless applications compared to other asymmetric key cryptosystem. The implementation of this algorithm over prime field Z p has a set of point operations, which are point addition, point subtraction, point multiplication, point division, point inversion, and point doubling. In these operations, the time complexity of the point multiplication is higher than any other time complexity of ECC point operations. So, it is necessary to find out an alternative implementation for point multiplication to take minimum amount of clock cycles, to reduce power consumption, and to support the software scheduling for parallel processing on arithmetic operations during execution. Considering this, the proposed implementation is very useful to perform encryption or decryption on texts, and also for analysing the strength of encryption or decryption computation.

Scalar multiplication

Subtraction

Curve25519

Source

Cite

Citations (7)

A Fast Boosting Based Incremental Genetic Algorithm for Mining Classification Rules in Large Datasets

IGI Global eBooks (2013)

P. Vivekanandan R. Nedunchezhian

Genetic algorithm is a search technique purely based on natural evolution process. It is widely used by the data mining community for classification rule discovery in complex domains. During the learning process it makes several passes over the data set for determining the accuracy of the potential rules. Due to this characteristic it becomes an extremely I/O intensive slow process. It is particularly difficult to apply GA when the training data set becomes too large and not fully available. An incremental Genetic algorithm based on boosting phenomenon is proposed in this paper which constructs a weak ensemble of classifiers in a fast incremental manner and thus tries to reduce the learning cost considerably.

Boosting

Incremental Learning

10.4018/978-1-4666-3628-6.ch004

Cite

Citations (0)

An empirical evaluation of benchmark machine learning classifiers for risk prediction of cardiovascular disease in diabetic males

International Journal of Healthcare Management (2023)

S. V. Evangelin Sonia R. Nedunchezhian S. Ramakrishnan K. E. Kannammal

Coronary artery disease is common in diabetics. 65% of diabetics are at risk of developing coronary artery disease or stroke, according to data from the National Heart Association from 2012. Here, classification techniques were analogized for their ability to foretell the future presence of patients with Cardiovascular Disease (CVD) in the next 10 years. For selecting important features, effective feature selection techniques like Recursive Feature Elimination (RFE) were utilized; also, for analyzing the classifiers' performance, Machine Learning (ML) classifiers were wielded. The methods like Decision Trees (DTs), K–Nearest Neighbor (KNN), Logistic Regression (LR), Artificial Neural Networks (ANNs), along with Random Forest (RF) were tested, and their outcomes were compared. To solve the classification issues, common classifiers like LR classifiers, neural networks, KNNs, RFs, and DTs are combined into a unified model. LR was predicted with the best accuracy among the predicted analysis. The study found that the LR attained the lowest rate of error with the highest accuracy (84.4%). Thus, LR is the optimal method for classification in this data set. By early prediction of coronary illness, this strategy will reduce the outstanding burden on people.

Benchmark (surveying)

Feature (linguistics)

10.1080/20479700.2023.2170006

Cite

Citations (2)

A FAST GENETIC ALGORITHM FOR MINING CLASSIFICATION RULES IN LARGE DATASETS

R. Nedunchezhian

Nowadays data repositories are huge and are extremely large. Building a rule based classification model for these huge data sets using Genetic Algorithm becomes an extremely complex process. This is because during the learning process several passes are made over the training data set by the Genetic Algorithm and this makes it extensively I/O intensive and unsuitable. One way to solve this problem is to build the model incrementally. This paper proposes an incremental Genetic Algorithm that builds the rule based classification model in a fine granular manner by independently evolving tiny components based on the evolution of the data set which reduces the learning cost and thus making it scalable to large data sets.

Data set

Classification rule

Source

Cite

Citations (3)