J. P. Ananth
Research Subjects
J. P. Ananth has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
G Raghuraman
Department of Computer Science and Engineering, SSN College of Engineering, Chennai 603110, India
2 shared publications- Susan Augustine
Sri Krishna College of Engineering and Technology, Coimbatore, India
2 shared publications G. L. Infant Cyril
Department of Information Technology, DMI College of Engineering, Chennai 600123, India
1 shared publicationH. Aswathy
Sri Krishna College of Engineering and Technology, India
1 shared publicationJ. SahayaAru
Anna University, Tirunelveli, India
1 shared publication- K. L. Shunmuganathan
R.M.K Engineering College
1 shared publication
Latest Publications
- 25 September 2023
- Published by IGI Global Scientific Publishing
- p. 227-243
A Review on Major Complications in the Pregnancies of Women Using Deep Learning Algorithms
Deep learning is an innovative technological advancement that has revolutionized the identification and diagnosis of various severe diseases. The complications in pregnant women lead to changes in mother's health, the health of the fetus, or even both. Pregnant women who were in good health before can also be prone to such complications. The authors of this chapter analyse some of the deep learning algorithms like recurrent neural network (RNN), convolution neural networks (CNN), long short-term memory networks (LSTM), and ensemble models to traverse the intricacies of these pregnancy complications. These algorithms aid in the diagnosis of an array of health problems including migraine, thyroid abnormalities, prenatal issues, stillbirth problems, and heart disease. This chapter not only provides a comprehensive explanation of the theoretical and mathematical foundations of these algorithms for disease diagnosis but also explores the model's predictive abilities. The research team rigorously assesses the accuracy of the model's classifications of the data. Request access from your librarian to read this chapter's full text.
- 25 September 2023
- Published by IGI Global Scientific Publishing
- p. 227-243
A Review on Major Complications in the Pregnancies of Women Using Deep Learning Algorithms
Deep learning is an innovative technological advancement that has revolutionized the identification and diagnosis of various severe diseases. The complications in pregnant women lead to changes in mother's health, the health of the fetus, or even both. Pregnant women who were in good health before can also be prone to such complications. The authors of this chapter analyse some of the deep learning algorithms like recurrent neural network (RNN), convolution neural networks (CNN), long short-term memory networks (LSTM), and ensemble models to traverse the intricacies of these pregnancy complications. These algorithms aid in the diagnosis of an array of health problems including migraine, thyroid abnormalities, prenatal issues, stillbirth problems, and heart disease. This chapter not only provides a comprehensive explanation of the theoretical and mathematical foundations of these algorithms for disease diagnosis but also explores the model's predictive abilities. The research team rigorously assesses the accuracy of the model's classifications of the data. Request access from your librarian to read this chapter's full text.
- 1 October 2020
- Published by Springer Nature in Wireless Networks
- Vol. 26 (7) , 5113-5132
Taylor kernel fuzzy C-means clustering algorithm for trust and energy-aware cluster head selection in wireless sensor networks
- 1 October 2020
- Published by Springer Nature in Wireless Networks
- Vol. 26 (7) , 5113-5132
Taylor kernel fuzzy C-means clustering algorithm for trust and energy-aware cluster head selection in wireless sensor networks
- 24 June 2020
- Published by Wiley in International Journal of Numerical Modelling: Electronic Networks, Devices and Fields
- Vol. 33 (6)
A modified rider optimization algorithm for multihop routing in WSN
Wireless Sensor Networks (WSNs) have an important role in establishing the communication between the Internet of things (IoT) devices. Routing is an important research field in the WSN as it helps in finding the suitable paths for the communication. This paper proposes a multipath routing algorithm based on the optimization approach. The proposed routing algorithm has two important phases, namely, Cluster head selection and multipath routing. Initially, the cluster head selection is carried out by the kernel based Fuzzy C Means (kernel FCM) algorithm. Then, the multipath routing is established by the newly developed Rider Salp Swarm Optimization algorithm (RSSA), which is the integration of the Rider Optimization Algorithm (ROA) and Salp Swarm Algorithm (SSA). The fitness function of the proposed RSSA is designed by considering the several factors, such as energy, QoS and trust. The simulation of the proposed work is carried out using different WSN setups, and the results are compared with several comparative techniques. From the results, it can be summarized that the proposed RSSA based multipath routing has better performance with values of 0.2526, 0.0764, 0.5, and 26 for delay, energy, throughput and number of alive nodes, respectively.
- 24 June 2020
- Published by Wiley in International Journal of Numerical Modelling: Electronic Networks, Devices and Fields
- Vol. 33 (6)
A modified rider optimization algorithm for multihop routing in WSN
Wireless Sensor Networks (WSNs) have an important role in establishing the communication between the Internet of things (IoT) devices. Routing is an important research field in the WSN as it helps in finding the suitable paths for the communication. This paper proposes a multipath routing algorithm based on the optimization approach. The proposed routing algorithm has two important phases, namely, Cluster head selection and multipath routing. Initially, the cluster head selection is carried out by the kernel based Fuzzy C Means (kernel FCM) algorithm. Then, the multipath routing is established by the newly developed Rider Salp Swarm Optimization algorithm (RSSA), which is the integration of the Rider Optimization Algorithm (ROA) and Salp Swarm Algorithm (SSA). The fitness function of the proposed RSSA is designed by considering the several factors, such as energy, QoS and trust. The simulation of the proposed work is carried out using different WSN setups, and the results are compared with several comparative techniques. From the results, it can be summarized that the proposed RSSA based multipath routing has better performance with values of 0.2526, 0.0764, 0.5, and 26 for delay, energy, throughput and number of alive nodes, respectively.
- 5 February 2020
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 63 (6) , 900-912
MapReduce and Optimized Deep Network for Rainfall Prediction in Agriculture
Rainfall prediction is the active area of research as it enables the farmers to move with the effective decision-making regarding agriculture in both cultivation and irrigation. The existing prediction models are scary as the prediction of rainfall depended on three major factors including the humidity, rainfall and rainfall recorded in the previous years, which resulted in huge time consumption and leveraged huge computational efforts associated with the analysis. Thus, this paper introduces the rainfall prediction model based on the deep learning network, convolutional long short-term memory (convLSTM) system, which promises a prediction based on the spatial-temporal patterns. The weights of the convLSTM are tuned optimally using the proposed Salp-stochastic gradient descent algorithm (S-SGD), which is the integration of Salp swarm algorithm (SSA) in the stochastic gradient descent (SGD) algorithm in order to facilitate the global optimal tuning of the weights and to assure a better prediction accuracy. On the other hand, the proposed deep learning framework is built in the MapReduce framework that enables the effective handling of the big data. The analysis using the rainfall prediction database reveals that the proposed model acquired the minimal mean square error (MSE) and percentage root mean square difference (PRD) of 0.001 and 0.0021.
- 5 February 2020
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 63 (6) , 900-912
MapReduce and Optimized Deep Network for Rainfall Prediction in Agriculture
Rainfall prediction is the active area of research as it enables the farmers to move with the effective decision-making regarding agriculture in both cultivation and irrigation. The existing prediction models are scary as the prediction of rainfall depended on three major factors including the humidity, rainfall and rainfall recorded in the previous years, which resulted in huge time consumption and leveraged huge computational efforts associated with the analysis. Thus, this paper introduces the rainfall prediction model based on the deep learning network, convolutional long short-term memory (convLSTM) system, which promises a prediction based on the spatial-temporal patterns. The weights of the convLSTM are tuned optimally using the proposed Salp-stochastic gradient descent algorithm (S-SGD), which is the integration of Salp swarm algorithm (SSA) in the stochastic gradient descent (SGD) algorithm in order to facilitate the global optimal tuning of the weights and to assure a better prediction accuracy. On the other hand, the proposed deep learning framework is built in the MapReduce framework that enables the effective handling of the big data. The analysis using the rainfall prediction database reveals that the proposed model acquired the minimal mean square error (MSE) and percentage root mean square difference (PRD) of 0.001 and 0.0021.
- 1 December 2015
- Published by American Scientific Publishers in Journal of Computational and Theoretical Nanoscience
- Vol. 12 (12) , 5891-5894
Enhancement of Segmentation and Zoning to Improve the Accuracy of Handwritten Character Recognition
- 1 December 2015
- Published by American Scientific Publishers in Journal of Computational and Theoretical Nanoscience
- Vol. 12 (12) , 5891-5894
Enhancement of Segmentation and Zoning to Improve the Accuracy of Handwritten Character Recognition
- 1 December 2015
- Published by American Scientific Publishers in Journal of Computational and Theoretical Nanoscience
- Vol. 12 (12) , 5562-5565
Krawtchouk Moment Based Interactive Image Retrieval Algorithm
- 1 December 2015
- Published by American Scientific Publishers in Journal of Computational and Theoretical Nanoscience
- Vol. 12 (12) , 5562-5565
Krawtchouk Moment Based Interactive Image Retrieval Algorithm
- 1 November 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 394-399
Recognizing and estimating rainfall using cloud images
Water is elixir of life. So rainfall becomes the inevitable part of every nation which decides the prosperity and economic scenario of a country. In this fast moving world, estimation of rainfall has become a necessity especially when the global heat levels are soaring. The proposed approach here is to use the digital cloud images to predict rainfall. Considering the cost factors and security issues, it is better to predict rainfall from digital cloud images rather than satellite images. The status of sky is found using wavelet. The status of cloud is found using the Cloud Mask Algorithm. The type of cloud can be evolved using the K-Means Clustering technique. As per previous research works done by the researchers, it is stated the Nimbostratus and Cumulonimbus are the rainfall clouds and other clouds like cumulus will produce rain at some rare chances. The type of rainfall cloud is predicted by analyzing the color and density of the cloud images. The cloud images are stored as JPEG file in the file system. Analysis was done over several images. The result predicts the type of cloud with its information like classification, appearance and altitude and will provide the status of the rainfall. The proposed approach can be utilized by common people to just take the photograph of cloud and can come to conclusion about the status of rainfall and to get the desired detail.
- 1 November 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 394-399
Recognizing and estimating rainfall using cloud images
Water is elixir of life. So rainfall becomes the inevitable part of every nation which decides the prosperity and economic scenario of a country. In this fast moving world, estimation of rainfall has become a necessity especially when the global heat levels are soaring. The proposed approach here is to use the digital cloud images to predict rainfall. Considering the cost factors and security issues, it is better to predict rainfall from digital cloud images rather than satellite images. The status of sky is found using wavelet. The status of cloud is found using the Cloud Mask Algorithm. The type of cloud can be evolved using the K-Means Clustering technique. As per previous research works done by the researchers, it is stated the Nimbostratus and Cumulonimbus are the rainfall clouds and other clouds like cumulus will produce rain at some rare chances. The type of rainfall cloud is predicted by analyzing the color and density of the cloud images. The cloud images are stored as JPEG file in the file system. Analysis was done over several images. The result predicts the type of cloud with its information like classification, appearance and altitude and will provide the status of the rainfall. The proposed approach can be utilized by common people to just take the photograph of cloud and can come to conclusion about the status of rainfall and to get the desired detail.