Abinash Tripathy
Abinash Tripathy has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Santanu Kumar Rath
NIT Rourkela
5 shared publications - Ankit Agrawal
School of Science and Engineering, Saint Louis University, USA, St. Louis, Missouri, USA
2 shared publications - Virender Kadyan
University of Petroleum and Energy Studies
2 shared publications Abhishek Anand
National Institute of Technology Rourkela
1 shared publication- Abhishek Anand
Software Engineer, Google India Private limited, Bengaluru, India
1 shared publication Alok Kumar Jena
Gandhi Institute of Education and Technology
1 shared publication
Latest Publications
- Open Access
- 14 November 2026
- Published by Elsevier in AI Thermal Fluids
Surrogate-based analysis of heat transfer in non-newtonian ternary nanofluids for biomedical transport systems
- 14 November 2026
- Published by Elsevier in AI Thermal Fluids
Open AccessSurrogate-based analysis of heat transfer in non-newtonian ternary nanofluids for biomedical transport systems
- 1 November 2025
- Published by Springer Nature
- p. 13-24
Clustering Based Sentiment Analysis for Unlabeled Reviews Using Bi-LSTM for Movie Reviews
- 1 November 2025
- Published by Springer Nature
- p. 13-24
Clustering Based Sentiment Analysis for Unlabeled Reviews Using Bi-LSTM for Movie Reviews
- Open Access
- 19 June 2025
- Published by Springer Nature in Research Square
Fuzzy rule based multi class sentiment analysis using hybrid nature inspired machine learning technique
Due to the increased availability of the Internet and various social media, the sharing of views or comments about any issue has increased. These reviews act as an important resource for understanding the feelings of customers and concerns related to the product and thus, need to be processed properly. Sentiment analysis plays a vital role in processing the reviews and obtaining information that can be used further. Many authors prefer to perform the binary sentiment task by classifying the reviews into either negative or positive classes. The present paper chooses multi-class classification, where the reviews are classified into five different classes. To perform the binary classification task, two sets of hybrid nature-inspired techniques are used i.e., firstly Particle Swarm Optimization (PSO) and Artificial Neural Network (ANN); and secondly, Flower Pollination Algorithm (FPA) and Artificial Neural Network (ANN). PSO and FPA are used for feature selection and ANN then processes the selected features for binary classification. The reviews that are classified correctly go through a Fuzzy rule-based system for multi-class classification. For classification purposes, two movie review datasets namely, IMDb and Polarity dataset are considered.
- 19 June 2025
- Published by Springer Nature in Research Square
Open AccessFuzzy rule based multi class sentiment analysis using hybrid nature inspired machine learning technique
Due to the increased availability of the Internet and various social media, the sharing of views or comments about any issue has increased. These reviews act as an important resource for understanding the feelings of customers and concerns related to the product and thus, need to be processed properly. Sentiment analysis plays a vital role in processing the reviews and obtaining information that can be used further. Many authors prefer to perform the binary sentiment task by classifying the reviews into either negative or positive classes. The present paper chooses multi-class classification, where the reviews are classified into five different classes. To perform the binary classification task, two sets of hybrid nature-inspired techniques are used i.e., firstly Particle Swarm Optimization (PSO) and Artificial Neural Network (ANN); and secondly, Flower Pollination Algorithm (FPA) and Artificial Neural Network (ANN). PSO and FPA are used for feature selection and ANN then processes the selected features for binary classification. The reviews that are classified correctly go through a Fuzzy rule-based system for multi-class classification. For classification purposes, two movie review datasets namely, IMDb and Polarity dataset are considered.
- Open Access
- 2 June 2022
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 9 (1) , 1-23
Developing sequentially trained robust Punjabi speech recognition system under matched and mismatched conditions
Development of a native language robust ASR framework is very challenging as well as an active area of research. Although an urge for investigation of effective front-end as well as back-end approaches are required for tackling environment differences, large training complexity and inter-speaker variability in achieving success of a recognition system. In this paper, four front-end approaches: mel-frequency cepstral coefficients (MFCC), Gammatone frequency cepstral coefficients (GFCC), relative spectral-perceptual linear prediction (RASTA-PLP) and power-normalized cepstral coefficients (PNCC) have been investigated to generate unique and robust feature vectors at different SNR values. Furthermore, to handle the large training data complexity, parameter optimization has been performed with sequence-discriminative training techniques: maximum mutual information (MMI), minimum phone error (MPE), boosted-MMI (bMMI), and state-level minimum Bayes risk (sMBR). It has been demonstrated by selection of an optimal value of parameters using lattice generation, and adjustments of learning rates. In proposed framework, four different systems have been tested by analyzing various feature extraction approaches (with or without speaker normalization through Vocal Tract Length Normalization (VTLN) approach in test set) and classification strategy on with or without artificial extension of train dataset. To compare each system performance, true matched (adult train and test—S1, child train and test—S2) and mismatched (adult train and child test—S3, adult + child train and child test—S4) systems on large adult and very small Punjabi clean speech corpus have been demonstrated. Consequently, gender-based in-domain data augmented is used to moderate acoustic and phonetic variations throughout adult and children’s speech under mismatched conditions. The experiment result shows that an effective framework developed on PNCC + VTLN front-end approach using TDNN-sMBR-based model through parameter optimization technique yields a relative improvement (RI) of 40.18%, 47.51%, and 49.87% in matched, mismatched and gender-based in-domain augmented system under typical clean and noisy conditions, respectively.
- 2 June 2022
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 9 (1) , 1-23
Open AccessDeveloping sequentially trained robust Punjabi speech recognition system under matched and mismatched conditions
Development of a native language robust ASR framework is very challenging as well as an active area of research. Although an urge for investigation of effective front-end as well as back-end approaches are required for tackling environment differences, large training complexity and inter-speaker variability in achieving success of a recognition system. In this paper, four front-end approaches: mel-frequency cepstral coefficients (MFCC), Gammatone frequency cepstral coefficients (GFCC), relative spectral-perceptual linear prediction (RASTA-PLP) and power-normalized cepstral coefficients (PNCC) have been investigated to generate unique and robust feature vectors at different SNR values. Furthermore, to handle the large training data complexity, parameter optimization has been performed with sequence-discriminative training techniques: maximum mutual information (MMI), minimum phone error (MPE), boosted-MMI (bMMI), and state-level minimum Bayes risk (sMBR). It has been demonstrated by selection of an optimal value of parameters using lattice generation, and adjustments of learning rates. In proposed framework, four different systems have been tested by analyzing various feature extraction approaches (with or without speaker normalization through Vocal Tract Length Normalization (VTLN) approach in test set) and classification strategy on with or without artificial extension of train dataset. To compare each system performance, true matched (adult train and test—S1, child train and test—S2) and mismatched (adult train and child test—S3, adult + child train and child test—S4) systems on large adult and very small Punjabi clean speech corpus have been demonstrated. Consequently, gender-based in-domain data augmented is used to moderate acoustic and phonetic variations throughout adult and children’s speech under mismatched conditions. The experiment result shows that an effective framework developed on PNCC + VTLN front-end approach using TDNN-sMBR-based model through parameter optimization technique yields a relative improvement (RI) of 40.18%, 47.51%, and 49.87% in matched, mismatched and gender-based in-domain augmented system under typical clean and noisy conditions, respectively.
- 29 April 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (6) , 7991-8011
Sentiment classification of movie reviews using GA and NeuroGA
- 29 April 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (6) , 7991-8011
Sentiment classification of movie reviews using GA and NeuroGA
- 20 April 2021
- Published by Springer Nature
- p. 317-327
Sentiment Analysis Using Semi Supervised Machine Learning Technique
- 20 April 2021
- Published by Springer Nature
- p. 317-327
Sentiment Analysis Using Semi Supervised Machine Learning Technique
- 10 May 2017
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 53 (3) , 805-831
Document-level sentiment classification using hybrid machine learning approach
- 10 May 2017
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 53 (3) , 805-831
Document-level sentiment classification using hybrid machine learning approach
- Top Cited Papers
- 1 September 2016
- Published by Elsevier in Expert Systems with Applications
- Vol. 57, 117-126
Classification of sentiment reviews using n-gram machine learning approach
- 1 September 2016
- Published by Elsevier in Expert Systems with Applications
- Vol. 57, 117-126
Top Cited PapersClassification of sentiment reviews using n-gram machine learning approach
- Open Access
Object Oriented Analysis using Natural Language Processing concepts: A Review
The Software Development Life Cycle (SDLC) starts with eliciting requirements of the customers in the form of Software Requirement Specification (SRS). SRS document needed for software development is mostly written in Natural Language(NL) convenient for the client. From the SRS document only, the class name, its attributes and the functions incorporated in the body of the class are traced based on pre-knowledge of analyst. The paper intends to present a review on Object Oriented (OO) analysis using Natural Language Processing (NLP) techniques. This analysis can be manual where domain expert helps to generate the required diagram or automated system, where the system generates the required diagram, from the input in the form of SRS.
Open AccessObject Oriented Analysis using Natural Language Processing concepts: A Review
The Software Development Life Cycle (SDLC) starts with eliciting requirements of the customers in the form of Software Requirement Specification (SRS). SRS document needed for software development is mostly written in Natural Language(NL) convenient for the client. From the SRS document only, the class name, its attributes and the functions incorporated in the body of the class are traced based on pre-knowledge of analyst. The paper intends to present a review on Object Oriented (OO) analysis using Natural Language Processing (NLP) techniques. This analysis can be manual where domain expert helps to generate the required diagram or automated system, where the system generates the required diagram, from the input in the form of SRS.