scispace - formally typeset
Search or ask a question
Author

Akash Dutta

Bio: Akash Dutta is an academic researcher from VIT University. The author has contributed to research in topics: Credit risk & Digital image. The author has an hindex of 1, co-authored 2 publications receiving 13 citations.

Papers
More filters
Proceedings ArticleDOI
01 Oct 2016
TL;DR: This work has adopted the approach of Logistic Regression and Classification and Regression Trees with techniques such as undersampling, Prior Probabilities, Loss Matrix and Matrix Weighing to deal with imbalanced data.
Abstract: In Machine Learning, we often encounter instances of imbalanced data which occur whenever there is an unequal representation in the classification categories. New found interest in Machine Learning has made its usage ubiquitous. Its applications encompass a wide plethora of scenarios ranging from Business and Banking to Bioinformatics and Psychology. These problems are often characterized by imbalanced data, the presence of which often leads to inaccurate predictive models, since the distribution of testing data may differ from that of training data while learning, leading to misclassification of the response variable. The primary focus of the paper is on Credit Risk which is defined as the probability of defaulting on the loan or credit acquired from a banking or financial institution. The base risk is that of the loss of primary principal and interest, disruption of cash flows and increased collection costs. Loan Default is an uncommon phenomena, henceforth we obtain the imbalanced data. We've adopted the approach of Logistic Regression and Classification and Regression Trees (CART) with techniques such as undersampling, Prior Probabilities, Loss Matrix and Matrix Weighing to deal with imbalanced data.

16 citations

Proceedings ArticleDOI
01 Oct 2016
TL;DR: This work has strived to develop a system which can extract texts from a digital image of a Sudoku puzzle, solve the puzzle, and then provide a solution.
Abstract: An Image is a visual representation of any object, place, person etc. In the field of Computer Science a Digital Image is a numeric representation of a two-dimensional image. Often images may contain texts, which are a sequence of human-readable characters. Our general conundrum is extraction of texts from an image for processing and editing. In an image texts are defined by set of pixels just like any other object and thus cannot be processed or edited. In this work we have strived to develop a system which can extract texts from a digital image of a Sudoku puzzle, solve the puzzle, and then provide a solution. Our approach is specific but its application are varied.

1 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: Methods for determining the health state of the battery are explained in a deeper way, while their corresponding strengths and weaknesses of these methods are analyzed in this paper.

509 citations

Journal ArticleDOI
TL;DR: Results indicate that the rankings generated by the TOPSIS, which combine the results of six evaluation criteria, provide a more reasonable evaluation of imbalanced classifiers over any single performance criterion; and Synthetic Minority Oversampling Technique (SMOTE)-based ensemble techniques outperform other groups of im balanced learning approaches.
Abstract: Various classifiers have been proposed for financial risk prediction. The traditional practice of using a singular performance metric for classifier evaluation is not sufficient for imbalanced classification. This paper proposes a multi-criteria decision making (MCDM)-based approach to evaluate imbalanced classifiers in credit and bankruptcy risk prediction by considering multiple performance metrics simultaneously. An experimental study is designed to provide a comprehensive evaluation of imbalanced classifiers using the proposed evaluation approach over seven financial imbalanced data sets from the UCI Machine Learning Repository. The TOPSIS, a well-known MCDM method, was applied to rank three categories of imbalanced classifiers using six popular evaluation criteria. The rankings results indicate that: 1) the rankings generated by the TOPSIS, which combine the results of six evaluation criteria, provide a more reasonable evaluation of imbalanced classifiers over any single performance criterion; and 2) Synthetic Minority Oversampling Technique (SMOTE)-based ensemble techniques outperform other groups of imbalanced learning approaches. Specifically, SMOTEBoost-C4.5, SMOTE-C4.5, and SMOTE-MLP were ranked as the top three classifiers based on their performances on the six criteria.

40 citations

Journal ArticleDOI
TL;DR: In this paper , a coherent literature review on battery health estimation techniques is presented to assist the research community with helpful information. But, the review does not address the advantages and limitations of those techniques, along with their precision and application complexity.
Abstract: To prevent probable battery failures and ensure safety, battery state of health evaluation is a critical step. This study lays out a coherent literature review on battery health estimation techniques to assist the research community with helpful information. Various techniques are systematically classified into respective groups and subgroups for easier understanding and follow-up. This study addresses the advantages and limitations of those techniques, along with their precision and application complexity. Furthermore, the procedures are briefly discussed on the premise of cost, computational effort, the requirement of sophisticated equipment, and their adaptability to various battery chemistries. Lastly, it draws the reader's attention towards a probable futuristic battery management architecture that may dictate the next decade's research efforts.

26 citations

Journal ArticleDOI
TL;DR: In this article, an AI-based human-centric decision support framework for predictive maintenance in asset management, which can facilitate prompt and informed decision-making under pandemic environments, is proposed.
Abstract: Pandemic events, particularly the current Covid-19 disease, compel organisations to re-formulate their day-to-day operations for achieving various business goals such as cost reduction. Unfortunately, small and medium enterprises (SMEs) making up more than 95% of all businesses is the hardest hit sector. This has urged SMEs to rethink their operations to survive through pandemic events. One key area is the use of new technologies pertaining to digital transformation for optimizing pandemic preparedness and minimizing business disruptions. This is especially true from the perspective of digitizing asset management methodologies in the era of Industry 4.0 under pandemic environments. Incidentally, human-centric approaches have become increasingly important in predictive maintenance through the exploitation of digital tools, especially when the workforce is increasingly interacting with new technologies such as Artificial Intelligence (AI) and Internet-of-Things devices for condition monitoring in equipment maintenance services. In this research, we propose an AI-based human-centric decision support framework for predictive maintenance in asset management, which can facilitate prompt and informed decision-making under pandemic environments. For predictive maintenance of complex systems, an enhanced trust-based ensemble model is introduced to undertake imbalanced data issues. A human-in-the-loop mechanism is incorporated to exploit the tacit knowledge elucidated from subject matter experts for providing decision support. Evaluations with both benchmark and real-world databases demonstrate the effectiveness of the proposed framework for addressing imbalanced data issues in predictive maintenance tasks. In the real-world case study, an accuracy rate of 82% is achieved, which indicates the potential of the proposed framework in assisting business sustainability pertaining to asset predictive maintenance under pandemic environments.

20 citations

Journal ArticleDOI
30 Jan 2020
TL;DR: This work proposes a machine learning model that can help in improving the process conditions of customer profile analysis, wherein the process models have to be developed for comprehensive analysis and the ones that can make a sustainable solution for the credit system management.
Abstract: Introduction: Increase in computing power and the deeper usage of the robust computing systems in the financial system is propelling the business growth, improving the operational efficiency of the financial institutions, and increasing the effectiveness of the transaction processing solutions used by the organizations. Problem: Despite that the financial institutions are relying on the credit scoring patterns for analyzing the credit worthiness of the clients, still there are many factors that are imminent for improvement in the credit score evaluation patterns. There is need for improving the pattern to enhance the quality of analysis. Objective: Machine learning is offering immense potential in Fintech space and determining a personal credit score. Organizations by applying deep learning and machine learning techniques can tap individuals who are not being serviced by traditional financial institutions. Methodology: One of the major insights into the system is that the traditional models of banking intelligence solutions are predominantly the programmed models that can align with the information and banking systems that are used by the banks. But in the case of the machine-learning models that rely on algorithmic systems require more integral computation which is intrinsic. Hence, it can be advocated that the models usually need to have some decision lines wherein the dynamic calibration model must be streamlined. Such structure demands the dynamic calibration to have a decision tree system to empower with more integrated model changes. Results: The test analysis of the proposed machine learning model indicates effective and enhanced analysis process compared to the non-machine learning solutions. The model in terms of using various classifiers indicate potential ways in which the solution can be significant. Conclusion: If the systems can be developed to align with more pragmatic terms for analysis, it can help in improving the process conditions of customer profile analysis, wherein the process models have to be developed for comprehensive analysis and the ones that can make a sustainable solution for the credit system management. Originality: The proposed solution is effective and the one conceptualized to improve the credit scoring system patterns. If the model can be improved with more effective parameters and learning metrics, it can be sustainable outcome. Limitations: The model is tested in isolation and not in comparison to any of the existing credit scoring patterns. Only the inputs in terms of shortcomings from the existing models are taken in to account and accordingly the proposed solution is developed.

18 citations