Dr. C Priya Dr.M.G.R. Educational and Research Institute | Dr.M.G.R University (original) (raw)

Papers by Dr. C Priya Dr.M.G.R. Educational and Research Institute

Research paper thumbnail of Passivity based Approach for the Level Control of Spherical Tank Process

International Journal of Engineering Sciences, 2020

The aim of this paper is to obtain the mathematical model and the real time model of the Single I... more The aim of this paper is to obtain the mathematical model and the real time model of the Single Input Single Output (SISO) conical tank system. The experimental model is obtained from the open loop response in real time and the transfer function is obtained using the two point method. For the real time model, two different controllers namely Zeigler Nichols tuned PI controller and passivity based controller are designed and tested in simulation and the performance of both the controllers are tested for servo operation and regulatory operation. The designed controllers are tested in Simulation and the response is recorded. The simulation results shows that the Passivity based Controller works better for the spherical tank process.

Research paper thumbnail of Deep Learning for Quantification of Epicardial and Thoracic Adipose Tissue from Non-Contrast CT

IEEE transactions on medical imaging, Jan 9, 2018

Epicardial adipose tissue (EAT) is a visceral fat deposit related to coronary artery disease. Ful... more Epicardial adipose tissue (EAT) is a visceral fat deposit related to coronary artery disease. Fully automated quantification of EAT volume in clinical routine could be a timesaving and reliable tool for cardiovascular risk assessment. We propose a new fully automated deep learning framework for EAT and thoracic adipose tissue (TAT) quantification from non-contrast coronary artery calcium CT scans. A first multi-task convolutional neural network (ConvNet) is used to determine heart limits and perform segmentation of heart and adipose tissues. A second ConvNet, combined with a statistical shape model (SSM), allows for pericardium detection. EAT and TAT segmentations are then obtained from outputs of both ConvNets. We evaluate the performance of the method on CT datasets from 250 asymptomatic individuals. Strong agreement between automatic and expert manual quantification is obtained for both EAT and TAT with median Dice score coefficients (DSC) of 0.823 (inter-quartile range (IQR): 0....

Research paper thumbnail of Feature Extraction of Metastasis and Acrometastasis Diseases Using the SVM Classifier

Intelligent Computing and Innovation on Data Science, 2020

Metastasis and acrometastasis diseases were presented as the tumor in the tongue and hands of the... more Metastasis and acrometastasis diseases were presented as the tumor in the tongue and hands of the human body. These two diseases may cause cancer to the lungs part of the human body. Metastases have the base in parts of the lung, breast or kidney. In this paper, the lung cancer symptoms can be diagnosed based on the metastases to the tongue images and acrometastases to the hands’ images. The proposed effort composed of feature extraction of tongue and hand images as input by using the Wiener filter processes. A support vector machine in supervised learning models with learning steps can explore the data which can be used for classification and regression scrutiny. The classifier techniques sustain to classify the metastases and acrometastases data. Finally, the classification and regression process can increase accuracy to predict the metastasis and acrometastasis diseases for lungs cancer. The proposed work is implemented using the MATLAB software and classifier increases an accuracy of feature extraction.

Research paper thumbnail of A Review on Anatomical Methods in Plant Systematics

Plant Archives, 2021

The comparative study of plant structure, morphology, and anatomy has always been the backbone of... more The comparative study of plant structure, morphology, and anatomy has always been the backbone of plant systematics. Anatomical characteristics are important evidence when elucidating the relationships among higher plants. Therefore the anatomical information can be taxonomically useful without having obvious evolutionary or phylogenetic interpretation. This review is a comprehensive study of the plant anatomical methods used by various researchers using different plant sources like leaf, petiole, and stem.

Research paper thumbnail of Passivity based Approach for the Level Control of Spherical Tank Process

International Journal of Engineering Sciences, 2020

The aim of this paper is to obtain the mathematical model and the real time model of the Single I... more The aim of this paper is to obtain the mathematical model and the real time model of the Single Input Single Output (SISO) conical tank system. The experimental model is obtained from the open loop response in real time and the transfer function is obtained using the two point method. For the real time model, two different controllers namely Zeigler Nichols tuned PI controller and passivity based controller are designed and tested in simulation and the performance of both the controllers are tested for servo operation and regulatory operation. The designed controllers are tested in Simulation and the response is recorded. The simulation results shows that the Passivity based Controller works better for the spherical tank process.

Research paper thumbnail of Deep Learning for Quantification of Epicardial and Thoracic Adipose Tissue from Non-Contrast CT

IEEE transactions on medical imaging, Jan 9, 2018

Epicardial adipose tissue (EAT) is a visceral fat deposit related to coronary artery disease. Ful... more Epicardial adipose tissue (EAT) is a visceral fat deposit related to coronary artery disease. Fully automated quantification of EAT volume in clinical routine could be a timesaving and reliable tool for cardiovascular risk assessment. We propose a new fully automated deep learning framework for EAT and thoracic adipose tissue (TAT) quantification from non-contrast coronary artery calcium CT scans. A first multi-task convolutional neural network (ConvNet) is used to determine heart limits and perform segmentation of heart and adipose tissues. A second ConvNet, combined with a statistical shape model (SSM), allows for pericardium detection. EAT and TAT segmentations are then obtained from outputs of both ConvNets. We evaluate the performance of the method on CT datasets from 250 asymptomatic individuals. Strong agreement between automatic and expert manual quantification is obtained for both EAT and TAT with median Dice score coefficients (DSC) of 0.823 (inter-quartile range (IQR): 0....

Research paper thumbnail of Feature Extraction of Metastasis and Acrometastasis Diseases Using the SVM Classifier

Intelligent Computing and Innovation on Data Science, 2020

Metastasis and acrometastasis diseases were presented as the tumor in the tongue and hands of the... more Metastasis and acrometastasis diseases were presented as the tumor in the tongue and hands of the human body. These two diseases may cause cancer to the lungs part of the human body. Metastases have the base in parts of the lung, breast or kidney. In this paper, the lung cancer symptoms can be diagnosed based on the metastases to the tongue images and acrometastases to the hands’ images. The proposed effort composed of feature extraction of tongue and hand images as input by using the Wiener filter processes. A support vector machine in supervised learning models with learning steps can explore the data which can be used for classification and regression scrutiny. The classifier techniques sustain to classify the metastases and acrometastases data. Finally, the classification and regression process can increase accuracy to predict the metastasis and acrometastasis diseases for lungs cancer. The proposed work is implemented using the MATLAB software and classifier increases an accuracy of feature extraction.

Research paper thumbnail of A Review on Anatomical Methods in Plant Systematics

Plant Archives, 2021

The comparative study of plant structure, morphology, and anatomy has always been the backbone of... more The comparative study of plant structure, morphology, and anatomy has always been the backbone of plant systematics. Anatomical characteristics are important evidence when elucidating the relationships among higher plants. Therefore the anatomical information can be taxonomically useful without having obvious evolutionary or phylogenetic interpretation. This review is a comprehensive study of the plant anatomical methods used by various researchers using different plant sources like leaf, petiole, and stem.