Ranganathan Vidhyapriya
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ranganathan Vidhyapriya has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- P. T. Vanathi
Dept. of ECE, PSG College of Technology
3 shared publications A.C. Sumathi
Department of Computer Science and Engineering, SNS College of Engineering, Coimbatore, Tamilnadu, India
2 shared publications- Naganathan Archana
PSG Coll Technol, Dept Elect & Elect Engn, Coimbatore 641004, Tamil Nadu, India
2 shared publications R. Rekha
2 shared publications- Seifedine Kadry
Department of Computer Science and Mathematics, Lebanese American University, Beirut, Lebanon
2 shared publications Antony Benedict
Alpha Research and Development, Coimbatore, India
1 shared publication
Latest Publications
- 6 November 2020
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 31 (1) , 59-71
Deeply supervisedU‐Netfor mass segmentation in digital mammograms
Mass detection is a critical process in the examination of mammograms. The shape and texture of the mass are key parameters used in the diagnosis of breast cancer. To recover the shape of the mass, semantic segmentation is found to be more useful rather than mere object detection (or) localization. The main challenges involved in the mass segmentation include: (a) low signal to noise ratio (b) indiscernible mass boundaries, and (c) more false positives. These problems arise due to the significant overlap in the intensities of both the normal parenchymal region and the mass region. To address these challenges, deeply supervised U‐Net model (DS U‐Net) coupled with dense conditional random fields (CRFs) is proposed. Here, the input images are preprocessed using CLAHE and a modified encoder‐decoder‐based deep learning model is used for segmentation. In general, the encoder captures the textual information of various regions in an input image, whereas the decoder recovers the spatial location of the desired region of interest. The encoder‐decoder‐based models lack the ability to recover the non‐conspicuous and spiculated mass boundaries. In the proposed work, deep supervision is integrated with a popular encoder‐decoder model (U‐Net) to improve the attention of the network toward the boundary of the suspicious regions. The final segmentation map is also created as a linear combination of the intermediate feature maps and the output feature map. The dense CRF is then used to fine‐tune the segmentation map for the recovery of definite edges. The DS U‐Net with dense CRF is evaluated on two publicly available benchmark datasets CBIS‐DDSM and INBREAST. It provides a dice score of 82.9% for CBIS‐DDSM and 79% for INBREAST.
- 6 November 2020
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 31 (1) , 59-71
Deeply supervisedU‐Netfor mass segmentation in digital mammograms
Mass detection is a critical process in the examination of mammograms. The shape and texture of the mass are key parameters used in the diagnosis of breast cancer. To recover the shape of the mass, semantic segmentation is found to be more useful rather than mere object detection (or) localization. The main challenges involved in the mass segmentation include: (a) low signal to noise ratio (b) indiscernible mass boundaries, and (c) more false positives. These problems arise due to the significant overlap in the intensities of both the normal parenchymal region and the mass region. To address these challenges, deeply supervised U‐Net model (DS U‐Net) coupled with dense conditional random fields (CRFs) is proposed. Here, the input images are preprocessed using CLAHE and a modified encoder‐decoder‐based deep learning model is used for segmentation. In general, the encoder captures the textual information of various regions in an input image, whereas the decoder recovers the spatial location of the desired region of interest. The encoder‐decoder‐based models lack the ability to recover the non‐conspicuous and spiculated mass boundaries. In the proposed work, deep supervision is integrated with a popular encoder‐decoder model (U‐Net) to improve the attention of the network toward the boundary of the suspicious regions. The final segmentation map is also created as a linear combination of the intermediate feature maps and the output feature map. The dense CRF is then used to fine‐tune the segmentation map for the recovery of definite edges. The DS U‐Net with dense CRF is evaluated on two publicly available benchmark datasets CBIS‐DDSM and INBREAST. It provides a dice score of 82.9% for CBIS‐DDSM and 79% for INBREAST.
- Open Access
An Image Encryption Scheme Based on Block Scrambling, Modified Zigzag Transformation and Key Generation Using Enhanced Logistic—Tent Map
Nowadays, the images are transferred through open channels that are subject to potential attacks, so the exchange of image data requires additional security in many fields, such as medical, military, banking, etc. The security factors are essential in preventing the system from brute force and differential attacks. We propose an Enhanced Logistic Map (ELM) while using chaotic maps and simple encryption techniques, such as block scrambling, modified zigzag transformation for encryption phases, including permutation, diffusion, and key stream generation to withstand the attacks. The results of encryption are evaluated while using the histogram, correlation analysis, Number of Pixel Change Rate (NPCR), Unified Average Change Intensity (UACI), Peak-Signal-to-Noise Ratio (PSNR), and entropy. Our results demonstrate the security, reliability, efficiency, and flexibility of the proposed method.
Open AccessAn Image Encryption Scheme Based on Block Scrambling, Modified Zigzag Transformation and Key Generation Using Enhanced Logistic—Tent Map
Nowadays, the images are transferred through open channels that are subject to potential attacks, so the exchange of image data requires additional security in many fields, such as medical, military, banking, etc. The security factors are essential in preventing the system from brute force and differential attacks. We propose an Enhanced Logistic Map (ELM) while using chaotic maps and simple encryption techniques, such as block scrambling, modified zigzag transformation for encryption phases, including permutation, diffusion, and key stream generation to withstand the attacks. The results of encryption are evaluated while using the histogram, correlation analysis, Number of Pixel Change Rate (NPCR), Unified Average Change Intensity (UACI), Peak-Signal-to-Noise Ratio (PSNR), and entropy. Our results demonstrate the security, reliability, efficiency, and flexibility of the proposed method.
- 15 June 2019
- Published by Springer Nature in Journal of Medical Systems
- Vol. 43 (8) , 232
Personal Authentication Mechanism Based on Finger Knuckle Print
For authentication purposes, the identification and verification of a user is done by biometric traits like finger print, face, iris and gait, etc. Among the various traits finger print is mostly used in commercial applications for recognizing user’s identity. The other hand based modalities such as vein, and finger knuckle are gaining importance. This paper proposes a methodology for secure biometrics authentication using Finger Knuckle Print (FKP). The texture patterns from finger knuckle are extracted using Gabor with Exception-Maximization (EM) algorithm and the feature vectors from these texture patterns are acquired using Scale Invariant Feature Transform (SIFT) algorithm. The main focus is to reduce the false rejection rate without increasing the false acceptance rate and to improve the performance over the conventional hand based modalities. The performance is compared with Genuine Acceptance Rate (GAR) and False Rejection Rate (FRR). One of the advantages of FKP authentication is its user friendliness in data collection.
- 15 June 2019
- Published by Springer Nature in Journal of Medical Systems
- Vol. 43 (8) , 232
Personal Authentication Mechanism Based on Finger Knuckle Print
For authentication purposes, the identification and verification of a user is done by biometric traits like finger print, face, iris and gait, etc. Among the various traits finger print is mostly used in commercial applications for recognizing user’s identity. The other hand based modalities such as vein, and finger knuckle are gaining importance. This paper proposes a methodology for secure biometrics authentication using Finger Knuckle Print (FKP). The texture patterns from finger knuckle are extracted using Gabor with Exception-Maximization (EM) algorithm and the feature vectors from these texture patterns are acquired using Scale Invariant Feature Transform (SIFT) algorithm. The main focus is to reduce the false rejection rate without increasing the false acceptance rate and to improve the performance over the conventional hand based modalities. The performance is compared with Genuine Acceptance Rate (GAR) and False Rejection Rate (FRR). One of the advantages of FKP authentication is its user friendliness in data collection.
- 25 April 2019
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 79 (23-24) , 17081-17099
Securing one-time password generation using elliptic-curve cryptography with self-portrait photograph for mobile commerce application
- 25 April 2019
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 79 (23-24) , 17081-17099
Securing one-time password generation using elliptic-curve cryptography with self-portrait photograph for mobile commerce application
- 1 January 2019
- Published by Inderscience Publishers in International Journal of Biomedical Engineering and Technology
- Vol. 31 (2) , 137-160
Aligning large biomedical ontologies for semantic interoperability using graph partitioning
Ontologies formal specifications of domain knowledge play an imperative role in the semantic web and are developed by several domain experts in the biomedical field. Ontology alignment or mapping is the process of identifying correspondences among the concepts in the ontology to facilitate data integration between heterogeneous data sources. In particular, the proposed ontology mapping system addresses two pivotal issues: 1) to facilitate the automated alignment process by incorporating random forests (RF), an ensemble learning system that is stable for outliers; 2) to improve the execution time by partitioning the ontologies using cluster-walktrap methodology and identify the correspondence between the concepts in parallel. The performance of the system is pragmatically evaluated on benchmark datasets in the anatomy and large biomedical ontology tracks of the OAEI 2013 and 2014. With the aid of the proposed system, quantifiable improvement is noticed to an extent of 4.4% in average precision, recall and F-measure.
- 1 January 2019
- Published by Inderscience Publishers in International Journal of Biomedical Engineering and Technology
- Vol. 31 (2) , 137-160
Aligning large biomedical ontologies for semantic interoperability using graph partitioning
Ontologies formal specifications of domain knowledge play an imperative role in the semantic web and are developed by several domain experts in the biomedical field. Ontology alignment or mapping is the process of identifying correspondences among the concepts in the ontology to facilitate data integration between heterogeneous data sources. In particular, the proposed ontology mapping system addresses two pivotal issues: 1) to facilitate the automated alignment process by incorporating random forests (RF), an ensemble learning system that is stable for outliers; 2) to improve the execution time by partitioning the ontologies using cluster-walktrap methodology and identify the correspondence between the concepts in parallel. The performance of the system is pragmatically evaluated on benchmark datasets in the anatomy and large biomedical ontology tracks of the OAEI 2013 and 2014. With the aid of the proposed system, quantifiable improvement is noticed to an extent of 4.4% in average precision, recall and F-measure.
- Open Access
- 30 June 2018
- Published by Wroclaw Medical University in Advances in Clinical and Experimental Medicine
- Vol. 27 (6) , 727-734
Design of a hybrid model for cardiac arrhythmia classification based on Daubechies wavelet transform
Background. Automation in cardiac arrhythmia classification helps medical professionals make accurate decisions about the patient's health. Objectives. The aim of this work was to design a hybrid classification model to classify cardiac arrhythmias. Material and methods. The design phase of the classification model comprises the following stages: preprocessing of the cardiac signal by eliminating detail coefficients that contain noise, feature extraction through Daubechies wavelet transform, and arrhythmia classification using a collaborative decision from the K nearest neighbor classifier (KNN) and a support vector machine (SVM). The proposed model is able to classify 5 arrhythmia classes as per the ANSI/AAMI EC57: 1998 classification standard. Level 1 of the proposed model involves classification using the KNN and the classifier is trained with examples from all classes. Level 2 involves classification using an SVM and is trained specifically to classify overlapped classes. The final classification of a test heartbeat pertaining to a particular class is done using the proposed KNN/SVM hybrid model. Results. The experimental results demonstrated that the average sensitivity of the proposed model was 92.56%, the average specificity 99.35%, the average positive predictive value 98.13%, the average F-score 94.5%, and the average accuracy 99.78%. Conclusions. The results obtained using the proposed model were compared with the results of discriminant, tree, and KNN classifiers. The proposed model is able to achieve a high classification accuracy.
- 30 June 2018
- Published by Wroclaw Medical University in Advances in Clinical and Experimental Medicine
- Vol. 27 (6) , 727-734
Open AccessDesign of a hybrid model for cardiac arrhythmia classification based on Daubechies wavelet transform
Background. Automation in cardiac arrhythmia classification helps medical professionals make accurate decisions about the patient's health. Objectives. The aim of this work was to design a hybrid classification model to classify cardiac arrhythmias. Material and methods. The design phase of the classification model comprises the following stages: preprocessing of the cardiac signal by eliminating detail coefficients that contain noise, feature extraction through Daubechies wavelet transform, and arrhythmia classification using a collaborative decision from the K nearest neighbor classifier (KNN) and a support vector machine (SVM). The proposed model is able to classify 5 arrhythmia classes as per the ANSI/AAMI EC57: 1998 classification standard. Level 1 of the proposed model involves classification using the KNN and the classifier is trained with examples from all classes. Level 2 involves classification using an SVM and is trained specifically to classify overlapped classes. The final classification of a test heartbeat pertaining to a particular class is done using the proposed KNN/SVM hybrid model. Results. The experimental results demonstrated that the average sensitivity of the proposed model was 92.56%, the average specificity 99.35%, the average positive predictive value 98.13%, the average F-score 94.5%, and the average accuracy 99.78%. Conclusions. The results obtained using the proposed model were compared with the results of discriminant, tree, and KNN classifiers. The proposed model is able to achieve a high classification accuracy.
- 17 January 2018
- Published by Springer Nature in Cluster Computing
- Vol. 22 (S4) , 8335-8343
Image compression and reconstruction by examplar based inpainting using wavelet transform on textural regions
- 17 January 2018
- Published by Springer Nature in Cluster Computing
- Vol. 22 (S4) , 8335-8343
Image compression and reconstruction by examplar based inpainting using wavelet transform on textural regions
- 1 January 2018
- Published by Inderscience Publishers in International Journal of Biomedical Engineering and Technology
- Vol. 26 (2) , 197
Maximisation of arrhythmia classification accuracy by addressing class overlap and imbalance problem
Automation in arrhythmia classification helps medical professionals to make accurate decisions upon the patient's health. Classification becomes complicated when class overlapping and class imbalance problem occurs together. The aim of this work is to improve the arrhythmia classification accuracy. Proposed methodology consists of fisher discriminant ratio based feature ranking stage and anomaly detection based training sample selection stage followed by classification using probabilistic neural network classifier. As per the recommendations of the Association for the Advancement of Medical Instrumentation, five arrhythmia classes were classified. The proposed method resulted in average sensitivity, positive predictive value and F Score of 95.37%, 98.35% and 96.72%, respectively. The experimental results revealed that: (1) Selected non-overlapping features were able to better discriminate arrhythmia classes, (2) Mixture of Gaussians based anomaly detection method suited well to handle the class imbalance problem and (3) Minority classes with few training samples were also correctly classified using the proposed method.
- 1 January 2018
- Published by Inderscience Publishers in International Journal of Biomedical Engineering and Technology
- Vol. 26 (2) , 197
Maximisation of arrhythmia classification accuracy by addressing class overlap and imbalance problem
Automation in arrhythmia classification helps medical professionals to make accurate decisions upon the patient's health. Classification becomes complicated when class overlapping and class imbalance problem occurs together. The aim of this work is to improve the arrhythmia classification accuracy. Proposed methodology consists of fisher discriminant ratio based feature ranking stage and anomaly detection based training sample selection stage followed by classification using probabilistic neural network classifier. As per the recommendations of the Association for the Advancement of Medical Instrumentation, five arrhythmia classes were classified. The proposed method resulted in average sensitivity, positive predictive value and F Score of 95.37%, 98.35% and 96.72%, respectively. The experimental results revealed that: (1) Selected non-overlapping features were able to better discriminate arrhythmia classes, (2) Mixture of Gaussians based anomaly detection method suited well to handle the class imbalance problem and (3) Minority classes with few training samples were also correctly classified using the proposed method.
- 1 December 2017
- Published by American Scientific Publishers in Journal of Computational and Theoretical Nanoscience
- Vol. 14 (12) , 5756-5760
Kriging Interpolation Technique with Triangulated Irregular Network for Image Compression Using Image Inpainting
- 1 December 2017
- Published by American Scientific Publishers in Journal of Computational and Theoretical Nanoscience
- Vol. 14 (12) , 5756-5760
Kriging Interpolation Technique with Triangulated Irregular Network for Image Compression Using Image Inpainting
- 23 November 2017
- Published by Springer Nature in Cluster Computing
- Vol. 22 (S5) , 11295-11305
Enhancing 4G Co-existence with Wi-Fi/IoT using cognitive radio
- 23 November 2017
- Published by Springer Nature in Cluster Computing
- Vol. 22 (S5) , 11295-11305
Enhancing 4G Co-existence with Wi-Fi/IoT using cognitive radio