Neepa Biswas
Neepa Biswas has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
Suchismita Maiti
Narula Institute of Technology
5 shared publicationsSudarsan Biswas
RCC Institute of Information Technology, India
3 shared publications- Kartick Chandra Mondal
Department of Information Technology, Jadavpur University, Kolkata, India
2 shared publications Sudarsan Biswas Neepa Biswas
RCC Institute of Information Technology, India
2 shared publicationsAnirban Bhar
1 shared publication- Anirban Bhar
Department of Computer Science and Engineering, University of Calcutta, Kolkata, India
1 shared publication
Latest Publications
- 2 July 2026
- Published by Springer Nature
- p. 313-325
Optimizing Credit Card Fraud Detection: A Hybrid Machine Learning Methods Using SMOTE
- 2 July 2026
- Published by Springer Nature
- p. 313-325
Optimizing Credit Card Fraud Detection: A Hybrid Machine Learning Methods Using SMOTE
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 63-86
Intelligent Machine Learning-Based Systems for Sustainable Coral Reef Health Monitoring
Coral reefs, often hailed as the “rainforests of the sea,” are among the most biodiverse and productive ecosystems on Earth. However, these vital habitats are in rapid decline due to escalating anthropogenic pressures, with climate change emerging as the predominant threat, causing coral bleaching. This paper presents a comparative analysis of intelligent machine learning (ML) systems for automated coral health monitoring, focusing on the classification of healthy versus bleached corals. The findings underscore the transformative potential of these models for scalable, real-time reef monitoring, supporting conservation efforts amid accelerating environmental challenges.
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 63-86
Intelligent Machine Learning-Based Systems for Sustainable Coral Reef Health Monitoring
Coral reefs, often hailed as the “rainforests of the sea,” are among the most biodiverse and productive ecosystems on Earth. However, these vital habitats are in rapid decline due to escalating anthropogenic pressures, with climate change emerging as the predominant threat, causing coral bleaching. This paper presents a comparative analysis of intelligent machine learning (ML) systems for automated coral health monitoring, focusing on the classification of healthy versus bleached corals. The findings underscore the transformative potential of these models for scalable, real-time reef monitoring, supporting conservation efforts amid accelerating environmental challenges.
- 3 July 2025
- Published by IGI Global Scientific Publishing
- p. 315-338
Advancing Mental Health Insights Through Machine Learning on EEG Data
Machine learning techniques have shown promise in classifying mental states based on electroencephalography (EEG) data. This has implications for neuroscience, cognitive psychology, and human-computer interaction. The study applied seven machine learning algorithms, including decision tree, random forest, AdaBoost, K Nearest Neighbour, Naïve Bayes, Support Vector Machine, and Artificial Neural Network, on a publicly available EEG dataset. The random forest algorithm had the best accuracy of 96%, followed by decision tree and K Nearest Neighbour at 90%. These techniques hold great potential for improving diagnosis, treatment, and overall well-being.
- 3 July 2025
- Published by IGI Global Scientific Publishing
- p. 315-338
Advancing Mental Health Insights Through Machine Learning on EEG Data
Machine learning techniques have shown promise in classifying mental states based on electroencephalography (EEG) data. This has implications for neuroscience, cognitive psychology, and human-computer interaction. The study applied seven machine learning algorithms, including decision tree, random forest, AdaBoost, K Nearest Neighbour, Naïve Bayes, Support Vector Machine, and Artificial Neural Network, on a publicly available EEG dataset. The random forest algorithm had the best accuracy of 96%, followed by decision tree and K Nearest Neighbour at 90%. These techniques hold great potential for improving diagnosis, treatment, and overall well-being.
- Open Access
- 5 April 2024
- Published by Qeios Ltd
Review of: "Application of Data Mining Combined with K-means Clustering Algorithm in Enterprises' Risk Audit"
* Role of big data is not relevant here. * Novelty of this work is not found. * It is preferred to use the full phrase "data mining." Data mining is not any technology. * Do not use the short form of big data ...... * It is not any figure (Figu...
- 5 April 2024
- Published by Qeios Ltd
Open AccessReview of: "Application of Data Mining Combined with K-means Clustering Algorithm in Enterprises' Risk Audit"
* Role of big data is not relevant here. * Novelty of this work is not found. * It is preferred to use the full phrase "data mining." Data mining is not any technology. * Do not use the short form of big data ...... * It is not any figure (Figu...
- 15 March 2024
- Published by IGI Global Scientific Publishing
- p. 62-81
Analysis of Chatbots
A chatbot is a computer program or software application that is designed to communicate with humans via text or speech-based interfaces. A chatbot's main objective is to mimic human conversation and deliver immediate responses to user inquiries. Chatbots are used in a variety of industries in various cases, including customer support, sales and marketing, appointment scheduling, retrieving information, virtual assistants, and even more. They can be used on websites, chat apps (such as WhatsApp, Facebook Messenger, or Slack), mobile applications, and voice-activated platforms such as Google Assistant, Siri, and Alexa.This chapter offers a thorough investigation of chatbots, chronicling their historical evolution, looking at their numerous applications, and sketching forth a complete classification scheme. This chapter seeks to provide a comprehensive overview of the evolution, significance, and classification of chatbots in the field of human-computer interaction from its genesis to modern uses. Request access from your librarian to read this chapter's full text.
- 15 March 2024
- Published by IGI Global Scientific Publishing
- p. 62-81
Analysis of Chatbots
A chatbot is a computer program or software application that is designed to communicate with humans via text or speech-based interfaces. A chatbot's main objective is to mimic human conversation and deliver immediate responses to user inquiries. Chatbots are used in a variety of industries in various cases, including customer support, sales and marketing, appointment scheduling, retrieving information, virtual assistants, and even more. They can be used on websites, chat apps (such as WhatsApp, Facebook Messenger, or Slack), mobile applications, and voice-activated platforms such as Google Assistant, Siri, and Alexa.This chapter offers a thorough investigation of chatbots, chronicling their historical evolution, looking at their numerous applications, and sketching forth a complete classification scheme. This chapter seeks to provide a comprehensive overview of the evolution, significance, and classification of chatbots in the field of human-computer interaction from its genesis to modern uses. Request access from your librarian to read this chapter's full text.
- 26 January 2024
- Published by IGI Global Scientific Publishing
- p. 140-155
Harnessing the Power of Machine Learning for Parkinson's Disease Detection
Parkinson's disease (PD) is a progressive neurodegenerative disorder affecting millions worldwide. Early detection of PD is crucial for effective treatment and management of the disease. Deep learning (DL) and machine learning (ML) have emerged as promising approaches for detecting PD. In this study, a comparative performance analysis is done for DL and ML applications based on speech signals. DL methods using convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and ML methods employing random forest and the XGBoost model were trained and assessed. Performance of the models are evaluated using a variety of performance metrics, including accuracy, precision, recall, and F1-score. Results showed that the XGBoost model outperformed the DL models in terms of accuracy and F1 score, while the CNN and LSTM models achieved higher precision and recall. These findings suggest that XGBoost can be a useful tool for detecting PD based on speech signals, particularly in scenarios where interpretability and computational efficiency are important.
- 26 January 2024
- Published by IGI Global Scientific Publishing
- p. 140-155
Harnessing the Power of Machine Learning for Parkinson's Disease Detection
Parkinson's disease (PD) is a progressive neurodegenerative disorder affecting millions worldwide. Early detection of PD is crucial for effective treatment and management of the disease. Deep learning (DL) and machine learning (ML) have emerged as promising approaches for detecting PD. In this study, a comparative performance analysis is done for DL and ML applications based on speech signals. DL methods using convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and ML methods employing random forest and the XGBoost model were trained and assessed. Performance of the models are evaluated using a variety of performance metrics, including accuracy, precision, recall, and F1-score. Results showed that the XGBoost model outperformed the DL models in terms of accuracy and F1 score, while the CNN and LSTM models achieved higher precision and recall. These findings suggest that XGBoost can be a useful tool for detecting PD based on speech signals, particularly in scenarios where interpretability and computational efficiency are important.
- 29 December 2023
- Published by IGI Global Scientific Publishing
- p. 348-371
Challenges and Solutions of Real-Time Data Integration Techniques by ETL Application
Business organizations are trying to focus from the traditional extract-transform-load (ETL) system towards real-time implementation of the ETL process. Traditional ETL process upgrades new data to the data warehouse (DW) at predefined time intervals when the DW is in off-line mode. Modern organizations want to capture and respond to business events faster than ever. Accessing fresh data is not possible using traditional ETL. Real-time ETL can reflect fresh data on the warehouse immediately at the occurrence of an event in the operational data store. Therefore, the key tool for business trade lies in real-time enterprise DW enabled with Business Intelligence. This study provides an overview of ETL process and its evolution towards real-time ETL. This chapter will represent the real-time ETL characteristics, its technical challenges, and some popular real-time ETL implementation methods. Finally, some future directions towards real-time ETL technology are explored. Request access from your librarian to read this chapter's full text.
- 29 December 2023
- Published by IGI Global Scientific Publishing
- p. 348-371
Challenges and Solutions of Real-Time Data Integration Techniques by ETL Application
Business organizations are trying to focus from the traditional extract-transform-load (ETL) system towards real-time implementation of the ETL process. Traditional ETL process upgrades new data to the data warehouse (DW) at predefined time intervals when the DW is in off-line mode. Modern organizations want to capture and respond to business events faster than ever. Accessing fresh data is not possible using traditional ETL. Real-time ETL can reflect fresh data on the warehouse immediately at the occurrence of an event in the operational data store. Therefore, the key tool for business trade lies in real-time enterprise DW enabled with Business Intelligence. This study provides an overview of ETL process and its evolution towards real-time ETL. This chapter will represent the real-time ETL characteristics, its technical challenges, and some popular real-time ETL implementation methods. Finally, some future directions towards real-time ETL technology are explored. Request access from your librarian to read this chapter's full text.
- 3 August 2021
- Published by Springer Nature
- p. 172-182
Integration of ETL in Cloud Using Spark for Streaming Data
- 3 August 2021
- Published by Springer Nature
- p. 172-182
Integration of ETL in Cloud Using Spark for Streaming Data