Papers by Debajyoty Banik
Fault modeling for external energy or internal cell defect in quantum dot cellular automata
Microprocessors and Microsystems, Oct 31, 2023
Resnet based hybrid convolution LSTM for hyperspectral image classification
Multimedia Tools and Applications, Oct 19, 2023
Robust stochastic gradient descent with momentum based framework for enhanced chest X-ray image diagnosis
Multimedia tools and applications, Jul 10, 2024
Sentiment induced phrase-based machine translation: Robustness analysis of PBSMT with senti-module
Engineering Applications of Artificial Intelligence
ACM Transactions on Asian and Low-Resource Language Information Processing, Aug 30, 2023
Parallel corpus is the primary ingredient of machine translation. It is required to train the sta... more Parallel corpus is the primary ingredient of machine translation. It is required to train the statistical machine translation (SMT) and neural machine translation (NMT) systems. There is a lack of good quality parallel corpus for Hindi to English. Comparable corpora for a given language pair are comparatively easy to ind, but this cannot be used directly in SMT or NMT systems. As a result, we generate a parallel corpus from the comparable corpus. For this purpose, the sentences (which are translations of each other) are mined from the comparable corpus to prepare the parallel corpus. The proposed algorithm uses the length of the sentence and word translation model to align sentence pairs that are translations of each other. Then, the sentence pairs that are poor translations of each other (measured by a similarity score based on IBM model 1 translation probability) are iltered out. We apply this algorithm to comparable corpora, which are crawled from speeches of the President and Vice-President of India, and mined parallel corpora out of them. The prepared parallel corpus contains good quality aligned sentences (with 96.338% f-score). Subsequently, incorrect sentence pairs are iltered out manually to make the corpus in qualitative practical use. Finally, we gather various sentences from diferent sources to prepare the EnIndic corpus, which comprises 1,656,207 English-Hindi sentence pairs (miscellaneous domain). We have deployed this prepared largest English-Hindi parallel corpus
Segmentation in Microscopic Images using Cellular Automata
Two-Phased Dynamic Language Model: Improved LM for Automated Language Translation
Lecture Notes in Computer Science, 2023
Evolutionary Approaches Toward Traditional to Deep Learning-Based Chatbot
Springer proceedings in mathematics & statistics, 2023
Cybersecurity Imminent Threats with Solutions in Higher Education
Advances in intelligent systems and computing, 2023
Resource Augmentation and Performance Improvement in Machine Translation
Advanced weighted hybridized approach for recommendation system
International Journal of Web Information Systems, May 30, 2023
Purpose This paper aims to describe the usage of a hybrid weightage-based recommender system focu... more Purpose This paper aims to describe the usage of a hybrid weightage-based recommender system focused on books and implementing it at an industrial level, using various recommendation approaches. Additionally, it focuses on integrating the model into the most widely used platform application. Design/methodology/approach It is an industrial level implementation of a recommendation system by applying different recommendation approaches. This study describes the usage of a hybrid weightage-based recommender system focused on books and putting a model into the most used platform application. Findings This paper deals with the phases of software engineering from the analysis of the requirements, the actual making of the recommender model to deployment and testing of the application at the user end. Finally, the hybridized system outperforms over other existing recommender system. Originality/value The proposed recommendation system is an industrial level implementation of a recommendation system by applying different recommendation approaches. The recommendation system is centralized to books and its recommendation. In this paper, the authors also describe the usage of a hybrid weightage-based recommender system focused on books and putting a model into the most used platform application. This paper deals with the phases of software engineering from the analysis of the requirements, the actual making of the recommender model to deployment and testing of the application at the user end. Finally, the newly created hybridized system outperforms the Netflix recommendation model as well as the Hybrid book recommendation system model as has been clearly shown in the Results Analysis section of the book. The source-code can be available at https://github.com/debajyoty/recomender-system.git.
Deep Learning Based Approach for Milk Quality Prediction
Wind Speed Prediction using Machine Learning Techniques
The Important Influencing Factors in Machine Translation
Springer proceedings in mathematics & statistics, Nov 10, 2022
Deep Learning Based Approach for Milk Quality Prediction
2023 11th International Conference on Emerging Trends in Engineering & Technology - Signal and Information Processing (ICETET - SIP)
Better Qualitative Searching for Effecting the Performance of Machine Translation
Communications in computer and information science, 2023
Spelling Checking Mechanism Based on Layered Language Model Complied with Google Web
Impact of Metaverse in the Near ‘Future’
2023 4th International Conference on Intelligent Engineering and Management (ICIEM)
ACM Transactions on Asian and Low-Resource Language Information Processing
Data-driven supervised approaches rely on the parallel corpus. Due to lack of data and resources ... more Data-driven supervised approaches rely on the parallel corpus. Due to lack of data and resources availability, it has become more difficult to achieve accurate outputs. In addition, the efficiency of the machine translation system depends on the quality of the used corpora. Hindi still lacks good quality parallel corpora and needs more resources for accurate machine translation. Comparable corpora are easily available compared to parallel corpora, but they cannot be used directly in machine translation. In our present research, we propose an algorithm to mine these comparable corpora from the web, and generate the parallel corpora automatically. Machine translation systems, system combination approach, and IR-based technique join their hands together to choose the set of sentence pairs. Then the sentence pairs having the best score are chosen to prepare the final parallel corpora. The primary modules of this architecture are fuzzy logic-based evaluation metric, information retrieval...
ACM Transactions on Asian and Low-Resource Language Information Processing
Machine translation has shown potential in improving access to medical information and healthcare... more Machine translation has shown potential in improving access to medical information and healthcare services for multilingual patients. This research aims to enhance machine translation accuracy in the medical field, specifically for translating from Hindi to English. The study introduces a new approach that dynamically allocates decoding parameters using regression models, overcoming the limitations of fixed parameters in the decoder. A comprehensive dataset is created to address limited data availability, enabling regression models to predict optimal pruning parameters. The main motivation for the study is the introduction of a regression method for optimizing pruning parameters, which is a novel approach in this context. The proposed approach outperforms existing methods, achieving improved translation accuracy. Standard metrics such as the BLEU score are used to evaluate translations. Ensemble average and pipeline approaches further enhance performance. The improved performance of...
Uploads
Papers by Debajyoty Banik