Latha Parthiban
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Latha Parthiban has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- P. Santhosh Kumar
SRM Institute of Science and Technology,Chennai,India
4 shared publications V. Jegatheeswari
4 shared publications- Naresh Sammeta
VIT AP Univ, Sch Comp Sci & Engn, Amaravati, India
3 shared publications R. Subramanian
Department of Computer Science, Ramanujan School of Mathematics & Computer Science, Pondicherry University, Kalapet, Puduchery, 605 014, India
3 shared publicationsRangasamy Parthiban
3 shared publications- Sabout Nagaraju
Department of Computer Science, Pondicherry University Community College, Lawspet, Pondicherry-605 008
3 shared publications
Latest Publications
- Open Access
- 1 March 2023
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 29 (3) , 1551-1559
Study and innovation of effective classification of XML documents using an advanced deep learning approach
In the digital world, classifying real sensed data in huge volumes derived from numerical problems is a challenging task due to the computational complexity of the metaheuristic searching process. The deep learning approach includes convolutional neural network (CNN), long short-term memory (LSTM), and Bidirectional (BI)-LSTM, suitable for an optimistic processing time of analyzing XML datasets (i.e., social media, trade center, and surveillance data exchanged in the internet world). However, it faces process deviation when datasets extend their range beyond the expected volume. This paper proposes a novel deep learning formwork referred to as archimed improved numerical optimization deep learning (AINODL) to improve the classification of XML datasets. The proposed AINODL framework first extracts feature from XML documents using the vector space model. Secondly, it classifies the XML data using the inbuilt function of the AINODL framework. The experiments demonstrate that the performance parameters accuracy (90%), sensitivity (93%), and specificity (94%) of the proposed AINODL framework are significantly enhanced compared with the existing approaches CNN, LSTM, and BI-LSTM.
- 1 March 2023
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 29 (3) , 1551-1559
Open AccessStudy and innovation of effective classification of XML documents using an advanced deep learning approach
In the digital world, classifying real sensed data in huge volumes derived from numerical problems is a challenging task due to the computational complexity of the metaheuristic searching process. The deep learning approach includes convolutional neural network (CNN), long short-term memory (LSTM), and Bidirectional (BI)-LSTM, suitable for an optimistic processing time of analyzing XML datasets (i.e., social media, trade center, and surveillance data exchanged in the internet world). However, it faces process deviation when datasets extend their range beyond the expected volume. This paper proposes a novel deep learning formwork referred to as archimed improved numerical optimization deep learning (AINODL) to improve the classification of XML datasets. The proposed AINODL framework first extracts feature from XML documents using the vector space model. Secondly, it classifies the XML data using the inbuilt function of the AINODL framework. The experiments demonstrate that the performance parameters accuracy (90%), sensitivity (93%), and specificity (94%) of the proposed AINODL framework are significantly enhanced compared with the existing approaches CNN, LSTM, and BI-LSTM.
- Open Access
- 20 October 2022
- Published by ENGG Journals Publications in Indian Journal of Computer Science and Engineering
- Vol. 13 (5) , 1716-1732
IDENTIFICATION OF IRRELEVANT FEATURES IN CLINICAL NON-SMALL CELL LUNG CANCER DATA USING REVERSE FEATURE ELIMINATION MODEL
- 20 October 2022
- Published by ENGG Journals Publications in Indian Journal of Computer Science and Engineering
- Vol. 13 (5) , 1716-1732
Open AccessIDENTIFICATION OF IRRELEVANT FEATURES IN CLINICAL NON-SMALL CELL LUNG CANCER DATA USING REVERSE FEATURE ELIMINATION MODEL
- 11 February 2022
- Published by Wiley
- p. 301-320
Effective Methodologies in Pharmacovigilance for Identifying Adverse Drug Reactions Using IoT
- 11 February 2022
- Published by Wiley
- p. 301-320
Effective Methodologies in Pharmacovigilance for Identifying Adverse Drug Reactions Using IoT
- 1 January 2022
- Published by Zarqa University in The International Arab Journal of Information Technology
- Vol. 20 (5) , 702-710
Blockchain-based Scalable and Secure EHR Data Sharing using Proxy Re-Encryption
- 1 January 2022
- Published by Zarqa University in The International Arab Journal of Information Technology
- Vol. 20 (5) , 702-710
Blockchain-based Scalable and Secure EHR Data Sharing using Proxy Re-Encryption
- 1 November 2021
- Published by Wiley
- p. 301-336
IoT‐Based Bias Analysis in Acoustic Feedback Using Time‐Variant Adaptive Algorithm in Hearing Aids
- 1 November 2021
- Published by Wiley
- p. 301-336
IoT‐Based Bias Analysis in Acoustic Feedback Using Time‐Variant Adaptive Algorithm in Hearing Aids
- 1 November 2021
- Published by Wiley
- p. 245-262
Hierarchical Elitism GSO Algorithm For Pattern Recognition
- 1 November 2021
- Published by Wiley
- p. 245-262
Hierarchical Elitism GSO Algorithm For Pattern Recognition
- Open Access
- 9 October 2021
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 8 (1) , 625-640
Hyperledger blockchain enabled secure medical record management with deep learning-based diagnosis model
In recent times, advanced developments in healthcare sector result in the generation of massive amounts of electronic health records (EHRs). EHR system enables the data owner to control his/her data and share it with designated people. The vast volume of data in the healthcare system makes it difficult for data to ensure security and diagnostic processes. To resolve these issues, this paper develops a new hyperledger blockchain enabled secure medical data management with deep learning (DL)-based diagnosis (HBESDM-DLD) model. The presented model involves distinct stages of operations such as encryption, optimal key generation, hyperledger blockchain-based secure data management, and diagnosis. The presented model allows the user to control access to data, permit the hospital authorities to read/write data, and alert emergency contacts. For encryption, SIMON block cipher technique is applied. At the same time, to improve the efficiency of the SIMON technique, a group teaching optimization algorithm (GTOA) is applied for the optimal key generation of the SIMON technique. Moreover, the sharing of medical data takes place using multi-channel hyperledger blockchain that utilizes a blockchain for storing patient visit data and for the medical institutions to record links for the EHRs saved in external databases. Once the data are decrypted at the receiving end, finally, variational autoencoder (VAE)-based diagnostic model is applied to detect the existence of the diseases. The performance validation of the HBESDM-DLD model takes place on benchmark medical dataset and the results are inspected under various performance measures. The experimental results proves that the HBESDM-DLD methodology is superior to state-of-the-art methods.
- 9 October 2021
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 8 (1) , 625-640
Open AccessHyperledger blockchain enabled secure medical record management with deep learning-based diagnosis model
In recent times, advanced developments in healthcare sector result in the generation of massive amounts of electronic health records (EHRs). EHR system enables the data owner to control his/her data and share it with designated people. The vast volume of data in the healthcare system makes it difficult for data to ensure security and diagnostic processes. To resolve these issues, this paper develops a new hyperledger blockchain enabled secure medical data management with deep learning (DL)-based diagnosis (HBESDM-DLD) model. The presented model involves distinct stages of operations such as encryption, optimal key generation, hyperledger blockchain-based secure data management, and diagnosis. The presented model allows the user to control access to data, permit the hospital authorities to read/write data, and alert emergency contacts. For encryption, SIMON block cipher technique is applied. At the same time, to improve the efficiency of the SIMON technique, a group teaching optimization algorithm (GTOA) is applied for the optimal key generation of the SIMON technique. Moreover, the sharing of medical data takes place using multi-channel hyperledger blockchain that utilizes a blockchain for storing patient visit data and for the medical institutions to record links for the EHRs saved in external databases. Once the data are decrypted at the receiving end, finally, variational autoencoder (VAE)-based diagnostic model is applied to detect the existence of the diseases. The performance validation of the HBESDM-DLD model takes place on benchmark medical dataset and the results are inspected under various performance measures. The experimental results proves that the HBESDM-DLD methodology is superior to state-of-the-art methods.
- 20 August 2021
- Published by Wiley
- p. 27-44
Emotion Detection in IoT‐Based E‐Learning Using Convolution Neural Network
- 20 August 2021
- Published by Wiley
- p. 27-44
Emotion Detection in IoT‐Based E‐Learning Using Convolution Neural Network