@annamalaiuniversity.ac.in
Assistant Professor / Computer Sci3ence and Engineering / FEAT
Annamalai University
M.C.A., MPhil(CS), PhD(CA)
Deep Learning, Neural Network, Data Mining
Scopus Publications
A. Senthilkumar, J. Ramkumar, M. Lingaraj, D. Jayaraj, and B. Sureshkumar
EverScience Publications
Suresh kumar B and Jayaraj D
Seventh Sense Research Group Journals
D. Jayaraj, J. Ramkumar, M. Lingaraj, and B. Sureshkumar
EverScience Publications
B. Suresh Kumar and D. Jayaraj
IEEE
Cyclone is a prevailing spinning storm which has strong winds and rain. It encompasses several related features like eyes, rainfall intensity, pathway, wind speed, storm surges, etc. Cyclone prediction is a major issue when the cloud intensity images exhibit feature patterns at several stages of growth. The recently developed artificial intelligence (AI) techniques can be utilized for effective classification of images for cyclone prediction. Several challenging issues exist in the cyclone prediction process such as high prediction error, poor image quality, noise, high complexity, etc. Image pre-processing techniques can be applied for improving the image quality and eliminating the noise that exists in it. In this aspect, this study focuses on comprehensive performance analysis of different image filtering techniques for cyclone prediction. To accomplish this, two types of noises such as salt & pepper and Gaussian noise are added to the input images. Besides, three filtering approaches namely Weiner filter (WF), Gabor filter (GF), and Gaussian filtering (GUF) are used. The filtering approaches help to eradicate the noise and thereby improve the image quality. A detailed simulation analysis is performed on various cyclone images and the results are assessed interms of different measures. The comparative results ensured that the WF technique has the ability to achieve better performance over the other GF and GUF techniques.
D. Jayaraj and S. Sathiamoorthy
Springer International Publishing
Lung cancer is a most important deadly disease which results to mortality of people because of the cells growth in unmanageable way. This problem leads to increased significance among physicians as well as academicians to develop efficient diagnosis models. Therefore, a novel method for automated identification of lung nodule becomes essential and it forms the motivation of this study. This paper presents a new deep learning classification model for lung cancer diagnosis. The presented model involves four main steps namely preprocessing, feature extraction, segmentation and classification. A particle swarm optimization (PSO) algorithm is sued for segmentation and deep neural network (DNN) is applied for classification. The presented PSO-DNN model is tested against a set of sample lung images and the results verified the goodness of the projected model on all the applied images.
D. Jayaraj and S. Sathiamoorthy
IEEE
In recent days, lung cancer become a significant reason for the increased mortality rate. But, the identification and medical of the disease can considerably reduce the death rate. The usage of medical imaging especially Computer Tomography (CT) images are applied to diagnose the lung cancer and the physicians find it hard to understand and classify the cancer from the CT scan images. So, computer-based analysis tool has been developed for utilizing image processing approaches. In this paper, a new automated computer aided model has been developed to identify lung cancer on CT images. The presented model operates on four main stages namely pre-processing, segmentation, feature extraction and classification. For simulation processes, a benchmark dataset from Lung Image Database Consortium (LIDC) is applied and the results are investigated under several aspects. The attained experimental outcome clearly depicted that the presented model showed extraordinary classifier results on the applied dataset.
D. Jayaraj and S. Sathiamoorthy
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
Early recognition and classification of pulmonary nodules by the use of computer-aided diagnosis (CAD) tools finds useful to reduce the death rate due to the illness of lung cancer. This paper devises a new CAD tool utilizing a segmentation based classification process for lung CT images. Initially, the input CT images are pre-processed by image enhancement and noise removal process. Then, watershed segmentation model is employed for the segmentation of the pre-processed images. Subsequently, the feature extraction process is carried out using Xecption model and random forest (RF) classifier is used of the identification of lung CT images as normal, benign or malignant. The use of RF model results to effective classification of the applied images. This model undergoes extensive experimentation against a benchmark lung CT image dataset and the results are investigated under several aspects. The obtained outcome pointed out the significant performance of the presented model over the compared methods.
Lung cancer is a serious illness which leads to increased mortality rate globally. The identification of lung cancer at the beginning stage is the probable method of improving the survival rate of the patients. Generally, Computed Tomography (CT) scan is applied for finding the location of the tumor and determines the stage of cancer. Existing works has presented an effective diagnosis classification model for CT lung images. This paper designs an effective diagnosis and classification model for CT lung images. The presented model involves different stages namely pre-processing, segmentation, feature extraction and classification. The initial stage includes an adaptive histogram based equalization (AHE) model for image enhancement and bilateral filtering (BF) model for noise removal. The pre-processed images are fed into the second stage of watershed segmentation model for effectively segment the images. Then, a deep learning based Xception model is applied for prominent feature extraction and the classification takes place by the use of logistic regression (LR) classifier. A comprehensive simulation is carried out to ensure the effective classification of the lung CT images using a benchmark dataset. The outcome implied the outstanding performance of the presented model on the applied test images.