Shawni Dutta
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
Shawni Dutta has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Samir Kumar Bandyopadhyay
Lincoln University College
19 shared publications Samir Kumar Bandyopadhyay
GLA University, India
6 shared publications- Digvijay Pandey
Department of Technical Education, Government of Uttar Pradesh, India
4 shared publications - Midhunchakkaravarthy Janarthanan
Lincoln University College
3 shared publications - Payal Bose
Department of Computer Science and Engineering, Swami Vivekananda University, Barrackpore, Kolkata, India
3 shared publications - Sabyasachi Pramanik
Haldia Institute of Technology, India
2 shared publications
Latest Publications
- 30 April 2024
- Published by Springer Nature
- p. 655-665
A Predictive Modeling to Assess the Underlying Risks of Stroke
- 30 April 2024
- Published by Springer Nature
- p. 655-665
A Predictive Modeling to Assess the Underlying Risks of Stroke
- 20 September 2023
- Published by Springer Nature
- p. 51-63
An Intelligent Approach for Investigating Water Quality Using Machine Learning Models
- 20 September 2023
- Published by Springer Nature
- p. 51-63
An Intelligent Approach for Investigating Water Quality Using Machine Learning Models
- 30 June 2023
- Published by IGI Global Scientific Publishing
- p. 395-419
Recent Trends of Addressing COVID-19 Disease by AI/ML
A new hype known as the novel coronavirus has consumed many human lives over the past few years. Consequently, the continued pandemic crisis will necessitate the use of an automated system. The computerised system should be able to provide constant monitoring of different domains of the COVID-19 disease. This study has concentrated on heterogeneous fields of COVID-19 including suspected-infected-recovered-deceased count analysis, impact of lockdown, different health habits responsible for this disease, analysis perforation patterns of lungs due to COVID-19, vaccination intake, and progress investigation. The literature included in this study has been investigated in terms of their prediction efficiency and possible improvements. Due to the exhaustive discourse of current COVID-19 based literature, the study is able to provide a comprehensive knowledge of the ongoing research trends. A concrete future perspective regarding each of the aforementioned domains has been included in the conclusion section which can effectively assist in finding the shortcomings of the existing research.
- 30 June 2023
- Published by IGI Global Scientific Publishing
- p. 395-419
Recent Trends of Addressing COVID-19 Disease by AI/ML
A new hype known as the novel coronavirus has consumed many human lives over the past few years. Consequently, the continued pandemic crisis will necessitate the use of an automated system. The computerised system should be able to provide constant monitoring of different domains of the COVID-19 disease. This study has concentrated on heterogeneous fields of COVID-19 including suspected-infected-recovered-deceased count analysis, impact of lockdown, different health habits responsible for this disease, analysis perforation patterns of lungs due to COVID-19, vaccination intake, and progress investigation. The literature included in this study has been investigated in terms of their prediction efficiency and possible improvements. Due to the exhaustive discourse of current COVID-19 based literature, the study is able to provide a comprehensive knowledge of the ongoing research trends. A concrete future perspective regarding each of the aforementioned domains has been included in the conclusion section which can effectively assist in finding the shortcomings of the existing research.
- 18 March 2023
- Published by Springer Nature
- p. 47-57
A Novel SARS-COV-2 Variant Omicron Disseminating Evaluation
- 18 March 2023
- Published by Springer Nature
- p. 47-57
A Novel SARS-COV-2 Variant Omicron Disseminating Evaluation
- 1 January 2021
- Published by IGI Global Scientific Publishing
- p. 146-163
Secure Text Extraction From Complex Degraded Images by Applying Steganography and Deep Learning
This work's primary goal is to secure the transmission of text hidden within the cover image using steganography over a public network of computers. Steganography is a powerful tool for concealing information within a cover image so that the concealed message remains undetectable. As a result, steganography refers to concealed writing. The secure transmission of information over a public network communication channel using steganography occurs in two stages, the first on the sender side and the second on the receiver side. In the first phase, steganography is normally applied to conceal the encrypted information within the image as a cover. The encrypted data is implanted inside the cover image using an improved least significant bit steganography method. The secret key obtained by the embedding algorithm is shared with the message retrieval algorithm on the receiver side to retrieve the message. Finally, the embedded text message is identified using a hybrid convolution regression adaptive integrated neural network (CRAINN) approach.
- 1 January 2021
- Published by IGI Global Scientific Publishing
- p. 146-163
Secure Text Extraction From Complex Degraded Images by Applying Steganography and Deep Learning
This work's primary goal is to secure the transmission of text hidden within the cover image using steganography over a public network of computers. Steganography is a powerful tool for concealing information within a cover image so that the concealed message remains undetectable. As a result, steganography refers to concealed writing. The secure transmission of information over a public network communication channel using steganography occurs in two stages, the first on the sender side and the second on the receiver side. In the first phase, steganography is normally applied to conceal the encrypted information within the image as a cover. The encrypted data is implanted inside the cover image using an improved least significant bit steganography method. The secret key obtained by the embedding algorithm is shared with the message retrieval algorithm on the receiver side to retrieve the message. Finally, the embedded text message is identified using a hybrid convolution regression adaptive integrated neural network (CRAINN) approach.
- 1 January 2021
- Published by IGI Global Scientific Publishing
- p. 1-28
Unseen to Seen by Digital Steganography
In this digital era, most of the daily works of users are captured in digital forms like image, audio, video, or even text. These may contain sensitive, confidential, or private information as well. To keep these, there are different techniques exercised over the years like chest, coffer, repository, treasury, etc. Sometimes such ways of hiding information attract unintended users. Therefore, steganography has been applied to digital objects in a new form called digital steganography. This chapter enforces identifying methods in digital steganography. The basic model of any type of digital steganography is composed of three types of objects: cover object, text to be hidden, and stego object. Depending on the type of cover object, different types of digital steganography methods have been defined. Only data hiding in text is discussed. Request access from your librarian to read this chapter's full text.
- 1 January 2021
- Published by IGI Global Scientific Publishing
- p. 1-28
Unseen to Seen by Digital Steganography
In this digital era, most of the daily works of users are captured in digital forms like image, audio, video, or even text. These may contain sensitive, confidential, or private information as well. To keep these, there are different techniques exercised over the years like chest, coffer, repository, treasury, etc. Sometimes such ways of hiding information attract unintended users. Therefore, steganography has been applied to digital objects in a new form called digital steganography. This chapter enforces identifying methods in digital steganography. The basic model of any type of digital steganography is composed of three types of objects: cover object, text to be hidden, and stego object. Depending on the type of cover object, different types of digital steganography methods have been defined. Only data hiding in text is discussed. Request access from your librarian to read this chapter's full text.
- 1 January 2021
- Published by IGI Global Scientific Publishing
- p. 24-44
Techniques of Steganography and Cryptography in Digital Transformation
Digital enterprise transformation is the amalgamation of digital techniques into the scopes of a business enterprise, fundamentally altering how one can employ and furnish ethics to clients. An organization can be authorized to take digital transformation due to several reasons. But the most important reason is that it is the survival issuance for many people. Digital transformation considers dissimilarity in every organization. Generally, it is the amalgamation of digital technology into all quarters of business. That consolidation brings about major alterations in how the business functions and conveys usefulness to its clients. Here, steganography and cryptography are used to facilitate digital transformation in any business.
- 1 January 2021
- Published by IGI Global Scientific Publishing
- p. 24-44
Techniques of Steganography and Cryptography in Digital Transformation
Digital enterprise transformation is the amalgamation of digital techniques into the scopes of a business enterprise, fundamentally altering how one can employ and furnish ethics to clients. An organization can be authorized to take digital transformation due to several reasons. But the most important reason is that it is the survival issuance for many people. Digital transformation considers dissimilarity in every organization. Generally, it is the amalgamation of digital technology into all quarters of business. That consolidation brings about major alterations in how the business functions and conveys usefulness to its clients. Here, steganography and cryptography are used to facilitate digital transformation in any business.
- Open Access
- 1 December 2020
- Published by Walter de Gruyter GmbH in Applied Computer Systems
- Vol. 25 (2) , 163-171
Breast Cancer Prediction Using Stacked GRU-LSTM-BRNN
Breast Cancer diagnosis is one of the most studied problems in the medical domain. Cancer diagnosis has been studied extensively, which instantiates the need for early prediction of cancer disease. To obtain advance prediction, health records are exploited and given as input to an automated system. The paper focuses on constructing an automated system by employing deep learning based recurrent neural network models. A stacked GRU-LSTM-BRNN is proposed in this paper that accepts health records of a patient for determining the possibility of being affected by breast cancer. The proposed model is compared against other baseline classifiers such as stacked simple-RNN model, stacked LSTM-RNN model, stacked GRU-RNN model. Comparative results obtained in this study indicate that the stacked GRU-LSTM-BRNN model yields better classification performance for predictions related to breast cancer disease.
- 1 December 2020
- Published by Walter de Gruyter GmbH in Applied Computer Systems
- Vol. 25 (2) , 163-171
Open AccessBreast Cancer Prediction Using Stacked GRU-LSTM-BRNN
Breast Cancer diagnosis is one of the most studied problems in the medical domain. Cancer diagnosis has been studied extensively, which instantiates the need for early prediction of cancer disease. To obtain advance prediction, health records are exploited and given as input to an automated system. The paper focuses on constructing an automated system by employing deep learning based recurrent neural network models. A stacked GRU-LSTM-BRNN is proposed in this paper that accepts health records of a patient for determining the possibility of being affected by breast cancer. The proposed model is compared against other baseline classifiers such as stacked simple-RNN model, stacked LSTM-RNN model, stacked GRU-RNN model. Comparative results obtained in this study indicate that the stacked GRU-LSTM-BRNN model yields better classification performance for predictions related to breast cancer disease.
- Open Access
- 7 October 2020
- Published by Advanced Research Publications in Journal of Advanced Research in Medical Science & Technology
- Vol. 07 (03) , 16-21
Detection of Fraud Transactions Using Recurrent Neural Network during COVID-19
Online transactions are becoming more popular in present situation where the globe is facing an unknown disease COVID-19. Now authorities of several countries have requested people to use cashless transaction as far as possible. Practically, it is not always possible to use it in all transactions. Since number of such cashless transactions has been increasing during lockdown period due to COVID-19, fraudulent transactions are also increasing in a rapid way. Fraud can be analysed by viewing a series of customer transactions data that was done in his/ her previous transactions. Normally banks or other transaction authorities warn their customers about the transaction, if they notice any deviation from available patterns; the authorities consider it as a possibly fraudulent transaction. For detection of fraud during COVID-19, banks and credit card companies are applying various methods such as data mining, decision tree, rule based mining, neural network, fuzzy clustering approach and machine learning methods. The approach tries to find out normal usage pattern of customers based on their former activities. The objective of this paper is to propose a method to detect such fraud transactions during such unmanageable situation of the pandemic. Digital payment schemes are often threatened by fraudulent activities. Detecting fraud transactions during money transfer may save customers from financial loss. Mobile-based money transactions are focused in this paper for fraud detection. A Deep Learning (DL) framework is suggested in the paper that monitors and detects fraudulent activities. Implementing and applying Recurrent Neural Network on PaySim generated synthetic financial dataset, deceptive transactions are identified. The proposed method is capable to detect deceptive transactions with an accuracy of 99.87%, F1-Score of 0.99 and MSE of 0.01.
- 7 October 2020
- Published by Advanced Research Publications in Journal of Advanced Research in Medical Science & Technology
- Vol. 07 (03) , 16-21
Open AccessDetection of Fraud Transactions Using Recurrent Neural Network during COVID-19
Online transactions are becoming more popular in present situation where the globe is facing an unknown disease COVID-19. Now authorities of several countries have requested people to use cashless transaction as far as possible. Practically, it is not always possible to use it in all transactions. Since number of such cashless transactions has been increasing during lockdown period due to COVID-19, fraudulent transactions are also increasing in a rapid way. Fraud can be analysed by viewing a series of customer transactions data that was done in his/ her previous transactions. Normally banks or other transaction authorities warn their customers about the transaction, if they notice any deviation from available patterns; the authorities consider it as a possibly fraudulent transaction. For detection of fraud during COVID-19, banks and credit card companies are applying various methods such as data mining, decision tree, rule based mining, neural network, fuzzy clustering approach and machine learning methods. The approach tries to find out normal usage pattern of customers based on their former activities. The objective of this paper is to propose a method to detect such fraud transactions during such unmanageable situation of the pandemic. Digital payment schemes are often threatened by fraudulent activities. Detecting fraud transactions during money transfer may save customers from financial loss. Mobile-based money transactions are focused in this paper for fraud detection. A Deep Learning (DL) framework is suggested in the paper that monitors and detects fraudulent activities. Implementing and applying Recurrent Neural Network on PaySim generated synthetic financial dataset, deceptive transactions are identified. The proposed method is capable to detect deceptive transactions with an accuracy of 99.87%, F1-Score of 0.99 and MSE of 0.01.
- Open Access
- 6 October 2020
- Published by ScienceOpen in ScienceOpen Preprints
A crucial Psychological Analysis of Mental Anxieties of Job-seekers and Working Classes in Society
Corona Virus Infectious Disease (COVID-19) appeared on Earth in December, 2019. This life-threatening disease is taking away numerous human lives at an exponential rate throughout the world. The World Health Organization (WHO) declared a presently appeared (epidemiological) situation due to this infectious disease as Pandemic. This disease not only threatens public health but also socio-economic conditions are also negatively affected by the current scenario. The working environment is devastated by the global virus pandemic situation. In this paper, different classes of peoples such as job-seekers, current employees and their current status are to be considered. It presents concentrations to assess different perspectives of mental conditions of a specific class of peoples. During the pandemic situation, job-seekers feel insecure regarding their placement since campus interviews either online or offline have not occurred due to COVID-19. In addition, currently employed workers are also mentally annoyed about their job-loss due to the financial scenario of the industries are not in a stable condition. In these cases, stress, depression and anxiety are quite evident. To carry out the research for both of these aforementioned cases, 500 students and (specify no. of) employees are surveyed for the period from April 2020 to July, 2020. The collected data are focused on peoples of Kolkata, West Bengal, India. This research work uses Machine Learning (ML) algorithm to assess mental well-being of job-seekers as well as currently placed workers. A hybrid model is presented in this paper that detects mental health status of job-seekers and existing employees. The hybrid model has a mixture of Deep Learning (DL) technique with Convolutional Neural Network. It is a predictive model consisting of two major components such as, CNN and Long-Short term memory (LSTM). LSTM is a variant of Recurrent Neural Network (RNN). This model is applied on the collected data for finding the status of mental anxieties of both classes. Experimental results imply that mental well-beings of job-seekers and presently working employees are predicted with an accuracy of 93.22% and 89.69% respectively. It concludes that the working peoples are more affected than those who may be a working class in near future.
- 6 October 2020
- Published by ScienceOpen in ScienceOpen Preprints
Open AccessA crucial Psychological Analysis of Mental Anxieties of Job-seekers and Working Classes in Society
Corona Virus Infectious Disease (COVID-19) appeared on Earth in December, 2019. This life-threatening disease is taking away numerous human lives at an exponential rate throughout the world. The World Health Organization (WHO) declared a presently appeared (epidemiological) situation due to this infectious disease as Pandemic. This disease not only threatens public health but also socio-economic conditions are also negatively affected by the current scenario. The working environment is devastated by the global virus pandemic situation. In this paper, different classes of peoples such as job-seekers, current employees and their current status are to be considered. It presents concentrations to assess different perspectives of mental conditions of a specific class of peoples. During the pandemic situation, job-seekers feel insecure regarding their placement since campus interviews either online or offline have not occurred due to COVID-19. In addition, currently employed workers are also mentally annoyed about their job-loss due to the financial scenario of the industries are not in a stable condition. In these cases, stress, depression and anxiety are quite evident. To carry out the research for both of these aforementioned cases, 500 students and (specify no. of) employees are surveyed for the period from April 2020 to July, 2020. The collected data are focused on peoples of Kolkata, West Bengal, India. This research work uses Machine Learning (ML) algorithm to assess mental well-being of job-seekers as well as currently placed workers. A hybrid model is presented in this paper that detects mental health status of job-seekers and existing employees. The hybrid model has a mixture of Deep Learning (DL) technique with Convolutional Neural Network. It is a predictive model consisting of two major components such as, CNN and Long-Short term memory (LSTM). LSTM is a variant of Recurrent Neural Network (RNN). This model is applied on the collected data for finding the status of mental anxieties of both classes. Experimental results imply that mental well-beings of job-seekers and presently working employees are predicted with an accuracy of 93.22% and 89.69% respectively. It concludes that the working peoples are more affected than those who may be a working class in near future.