Sunanda Das - Academia.edu (original) (raw)

Papers by Sunanda Das

2022 5th International Conference on Contemporary Computing and Informatics (IC3I)

2022 Fourth International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT)

2022 25th International Conference on Computer and Information Technology (ICCIT)

2022 11th International Conference on System Modeling & Advancement in Research Trends (SMART)

International Journal of Electrical and Electronics Research

The rise of digital technology has essentially enhanced the overall communication and data manage... more The rise of digital technology has essentially enhanced the overall communication and data management system, facilitating essential medical care services. Considering this aspect, the healthcare system successfully managed patient requirements through online services and facilitated patient experience. However, the lack of adequate data security and increased digital activities during Covid-19 made the healthcare system a soft target for hackers to gain unauthorized access and steal crucial and sensitive information. Countries such as the UK and the US recently received such challenges, highlighting the need for effective data maintenance. IoT emerged as one of the critical solutions for data management systems in terms of addressing data security which certainly can enhance overall data collection, storage, maintenance, prediction of potential data security breaches and taking appropriate measurements. The concerned research considers a secondary data collection process where nece...

International journal of engineering research and technology, Nov 18, 2021

Two side of the one coin'' Gender oppression, domestic violence and resistance both the perceptio... more Two side of the one coin'' Gender oppression, domestic violence and resistance both the perception are allied from social, political, economic institutional, psychological mechanisms and among these three different notions there are one thing common and that is '' fashioning self '' or given primacy over ''I am this body'' (Menon). For social insecurities, existence destitute as of physique or mind those administrative actualities are demonstrating themselves as the utilisations of volcanic expansions overabundant signifiers. These all are essentially known as, lifelong preoccupation with power and human subjectivity, where how authoritative being political living being they are in a relations, that will be determine by their determination which they have persistent despite all kinds of resistance. Foucauldian treatise is generally based on concessions, duties and to find out hidden aspects of power and resistances between philandering and monogamous. Presently, in this contemporary era, for the complexity of hidden, human relations and catalymistic binaries, we are going through the waves ofdiverse glitches or some blame worthy circumstances, which boils downthe fact as 'peace time of violence'. Fundamental points or self-imagery here could be, they are not pleased with the person with whom they are making legitimate intimacy or nourishments (Scheper-Hughes 1997,Scheper-Hughes& Bourgois 2003). Nude flawless rules of patriarchy neverthinks ''rape'' can be harmful for bodily honour of the person, but rather patriarchal rubrics have expressed it's disquiet against family appreciation. Menon has articulated in her book ''seeing like a feminist rape is fate worse than death''. Family which is known as the source of primary socialization, must be like sanctuary, but realism is far away from the ''ideal-type' 'This phenomena can be discussed through the film''Begum Jan'', which discourses the issue sympathetically. Key words; 'ideal-type', human relations, catalymistic binaries, legitimate intimacy or nourishments.

2021 24th International Conference on Computer and Information Technology (ICCIT), 2021

In recent decades, gold has been one of the most sought-after commodities for long-term and short... more In recent decades, gold has been one of the most sought-after commodities for long-term and short-term investments, as investors perceive gold as a hedge against unanticipated market occurrences. Gold can be purchased, stored, and is rarely utilized as a payment method. However, it is pretty simple to convert gold into cash in almost any currency. As gold is essential for maintaining value, investment, and national economic stability, it is undoubtedly vital to forecast the price of gold accurately. In this paper, we proposed a hybrid method for forecasting the price of gold based on the combination of 1D Convolutional Neural Networks (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU). Though CNN-GRU, CNN-LSTM, CNN-RNN based hybrid networks or, the individual CNN, Bi-GRU, and GRU provide satisfactory results, our proposed hybrid approach is more reliable since it outperforms other networks and achieves the MAE, MAPE, MedAE, RMSE, MSE, MSLE of 11.88, 0.67%, 8.41, 15.59, 242.90, 76.08times10−676.08\times 10^{-6}76.08times10−6 respectively and mathrmR2\mathrm{R}^{2}mathrmR2 Score of 93.56%.

2021 2nd International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST), 2021

Bangladesh is a flood-prone country. With limited resources and a major portion of the population... more Bangladesh is a flood-prone country. With limited resources and a major portion of the population living below the poverty line, flood impacts are severe. Deaths, malnutrition, widespread diseases, damage to infrastructure, disruption in the economy are some of the after-effects of this cataclysm. In order to put a flood management system into effect, it is essential to predict flooding events ahead of time. In this work, we applied different correlation coefficients for feature selection and k-nearest neighbors (k-NN) algorithm for the prediction of flood. The detailed result analysis shows that we achieved a high testing accuracy of 94.91%, average precision of 92.00% and an average recall of 91.00% using the k-NN machine learning model.

JOURNAL OF CLINICAL AND DIAGNOSTIC RESEARCH, 2020

Intelligent Data Engineering and Automated Learning – IDEAL 2021, 2021

Bitcoin is an electronic or digital currency. However, unlike government-issued currencies, there... more Bitcoin is an electronic or digital currency. However, unlike government-issued currencies, there is no single entity that issues bitcoin or is in charge of processing transactions. That's why bitcoin has become popular in the recent era. As bitcoin's price fluctuates a lot in a short period, it is very challenging to predict the bitcoin price accurately. In this paper, we proposed a method by merging different highestlevel building blocks in deep learning such as Convolutional Neural Networks (CNN), Long Short Term Memory (LSTM), Bi-LSTM, Recurrent Neural Network (RNN), and Bi-RNN to predict bitcoin price as accurately as possible. Though CNN, LSTM, Bi-LSTM, RNN, Bi-RNN or ARIMA independently produce an acceptable result, our proposed hybrid method is fairly reliable compared to individual building block of the network as the proposed method outperforms other individual models and achieves RMSE, MAE, MAPE, MedAE of 2.69%, 1.78%, 2.20%, and 1.23% respectively.

Handbook of Computational Intelligence in Biomedical Engineering and Healthcare, 2021

Abstract The application of microarray gene expression dataset has created a high impact in the f... more Abstract The application of microarray gene expression dataset has created a high impact in the field of medical health. The presence of all genes in microarray data can cause difficulty in cluster analysis for disease prediction as some of these genes are unwanted. All genes applied in clustering algorithm may wrongly partition the samples, which degrade the quality of the clusters, increasing both cost and time of designing clustering algorithms. For that reason, one of the important requirements is to select only important genes before categorizing the samples for identifying diseases. In the chapter, a multiobjective optimization technique based on an improved strength pareto evolutionary algorithm is proposed to select only the few important genes responsible for disease identification. The method explores the whole search space for approximating the pareto-optimal front that provides the optimal solution. Each chromosome in the population is evaluated using three different objective functions considering the external index for cluster validation, gene numbers present in sample and mutual correlation between the objects separately. The experimental results of the proposed method prove the effectiveness and acceptability of the improved strength pareto evolutionary algorithm in the purpose of important genes selection and sample categorization.

2016 Second International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), 2016

Convergence to local minima point is one of the major disadvantages of conventional fuzzy c-means... more Convergence to local minima point is one of the major disadvantages of conventional fuzzy c-means (FCM). Due to this drawback, segmentation result may hamper for not selecting the cluster centroids properly. To overcome this, a modified genetic (MfGA) algorithm is proposed to improve the performance of FCM. The optimized class levels derived from the MfGA are employed as initial input to FCM for finding global optimal solutions in a large search space. An extensive performance comparison of the proposed MfGA inspired conventional FCM and GA based FCM on two multilevel color images establishes the superiority of the proposed approach.

Computational Intelligence in Pattern Recognition, 2020

In the Indian economy, the agriculture sector has a very important role. So, identification and e... more In the Indian economy, the agriculture sector has a very important role. So, identification and early stage detection of diseases of the infected plants in a timely manner are a challenge in the field of data mining. Researchers are always trying to develop an efficient automated disease classification system to identify crop diseases. This paper presents the development of an automated system that will analyze the diseased infected paddy plant images and will provide guidance to the farmers. The main goal of the development of rice disease classification system is that it identifies and classifies the rice diseases automatically. The work is divided mainly in two parts, namely rice disease detection and classification of rice diseases. In disease detection task, at first, features responsible for diseases are extracted from the diseased portion of the rice images using various feature extraction techniques, and then important and relevant features are selected from the extracted features using the proposed method. The proposed method gives a remarkable result which can help in the agricultural field.

Understanding COVID-19: The Role of Computational Intelligence, 2021

In this crisis of COVID19, everyone is staying in touch with the world through social media. This... more In this crisis of COVID19, everyone is staying in touch with the world through social media. This has led to social media becoming a significant source of new information for many people and unfortunately this phenomenon has given birth to a lot of misinformation, chaos and fear in people’s minds. This fear is often due to the inadequate and wrong information. Therefore, there is a important need to understand this crisis. Patterns need to be established between popular tweets and its effect on the public’s sentiments, especially their fear. So, tweets of three different countries namely United States of America, Federative Republic of Brazil and Republic of India. Sentiment analysis reveals that fear of this unknown and mysterious nature of the coronavirus is dominant among the public. Predominant analysis of tweets within past two months will be done and then a model will be built to predict future reaction of the general public based on the crisis level in the country. Machine Learning algorithms such as ‘Logistic Regression (LR)’, ‘Multinomial Naive Bayes’ and ‘Support Vector Machine (SVM)’are used for classification purpose preceded by the pre-processing steps of raw data from each country. 90% of accuracy has been achieved from sentiment classification result. Insights to the fear, sentiments have also been provided. Tweets with negative sentiment and emotion indicates the cases for the pandemic outbreak. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

In this article, we have devised modified genetic algorithm (MfGA) based fuzzy C-means algorithm,... more In this article, we have devised modified genetic algorithm (MfGA) based fuzzy C-means algorithm, which segment magnetic resonance (MR) images. In FCM, local minimum point can be easily derived for not selecting the centroids correctly. The proposed MfGA improves the population initialization and crossover parts of GA and generate the optimized class levels of the multilevel MR images. After that, the derived optimized class levels are applied as the initial input in FCM. An extensive performance comparison of the proposed method with the conventional FCM on two MR images establishes the superiority of the proposed approach.

International journal of engineering research and technology, 2020

Exertions have been ended to recover the performance of social enterprises over and done with man... more Exertions have been ended to recover the performance of social enterprises over and done with many studies on social entrepreneurs and social entrepreneurship. Conversely, previous studies have abstracted social entrepreneurship based on researches on lucrative entrepreneurs. Furthermore, the scale recycled in the examination of social entrepreneurship emphases primarily on interactive aspects. Even though the social and economic morals followed by social enterprises are important qualities for so cial entrepreneurs, research on the value location of social entrepreneurship is inadequate. The quintessence of a social enterprise is generating social value based on monetary sustainability, so the notion of merged worth has been lately highlighted. This study examined the interactions amongst merged assessment alignment, social entrepreneurship, and the presentation of social enterprises. The consequences designate that the combined assessment alignment of social entrepreneurs prejudic...

Informatics in Medicine Unlocked, 2021

Recently, numerous studies have been conducted on Missing Value Imputation (MVI), intending the p... more Recently, numerous studies have been conducted on Missing Value Imputation (MVI), intending the primary solution scheme for the datasets containing one or more missing attribute's values. The incorporation of MVI reinforces the Machine Learning (ML) models' performance and necessitates a systematic review of MVI methodologies employed for different tasks and datasets. It will aid beginners as guidance towards composing an effective ML-based decision-making system in various fields of applications. This article aims to conduct a rigorous review and analysis of the state-of-the-art MVI methods in the literature published in the last decade. Altogether, 191 articles, published from 2010 to August 2021, are selected for review using the well-known Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) technique. We summarize those articles with relevant definitions, theories, and analyses to provide essential information for building a precise decision-making framework. In addition, the evaluation metrics employed for MVI methods and ML-based classification models are also discussed and explored. Remarkably, the trends for the MVI method and its evaluation are also scrutinized from the last twelve years' data. To come up with the conclusion, several MLbased pipelines, where the MVI schemes are incorporated for performance enhancement, are investigated and reviewed for many different datasets. In the end, informative observations and recommendations are addressed for future research directions and trends in related fields of interest.

A quantum counterpart of classical modified genetic algorithm-based FCM is presented in this arti... more A quantum counterpart of classical modified genetic algorithm-based FCM is presented in this article for color MRI image segmentation. Though classical modified GA enhances the global search optimality of conventional GA but to speed up and make it more optimal and cost effective, some quantum computing phenomena like qubit, superposition, entanglement, quantum gate are incorporated here. To achieve the final segmented output, the class levels generated by quantum-inspired modified genetic algorithm are now fed to conventional FCM to overcome the early convergence to local minima problem of FCM. A performance comparison is delineated between quantum-inspired modified GA-based FCM, quantum-inspired GA-based FCM and classical modified GA-based FCM based on two color MRI images.

2021 International Conference on Automation, Control and Mechatronics for Industry 4.0 (ACMI), 2021

Mental well-being issues are progressively getting evident as genuine medical problems in the wor... more Mental well-being issues are progressively getting evident as genuine medical problems in the working environment. Companies must distinguish what perspectives are responsible for the most part related to mental wellbeing to play down these issues among employees. Subsequently, classification strategies are required to figure out whether a representative needs mental wellbeing treatment or not. Based on an open source survey dataset, we applied some pre- processing then used Pearson’s Correlation Coefficient for feature selection. Then we applied some machine learning models to classify the dataset. Lastly, we applied a voting classifier which totals the discoveries of each classifier passed into it and predicts the final output based on the most noteworthy lion's share of voting. Machine learning models namely Gaussian Naïve Bayes, K-Nearest Neighbor, Support Vector Machine, Decision Tree and Random Forest classifiers provided 78.83%, 86.77%, 81.48%, 86.24% and 87.83% of accuracy respectively. Combining the above methods, Voting Classifier gives us a better accuracy of 90.48%.

2021 International Conference on Automation, Control and Mechatronics for Industry 4.0 (ACMI), 2021

Heart disease is a vital cause of mortality in this world. The number of patients with this noxio... more Heart disease is a vital cause of mortality in this world. The number of patients with this noxious disease is rising every day. It is taking millions of lives each year. It is dismaying that there are not many effective ways to detect heart disease gleaned on elementary information. Nowadays, in order to achieve unprecedented results, Machine Learning (ML) has been exclusively used in various fields. So, we have come up with a proposition of a heart disease prediction model using ML techniques in this paper to accomplish an effective result. We have used different ML classifiers such as Gaussian Naïve Bayes, Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and applied Soft Voting on them. The result shows that the Voting methods give us the most effective results with an Accuracy of 92.42%, Precision of 92.50%, Recall of 92.22% and F1-score of 92.34%. Our purpose is to detect this deleterious disease more precisely to enhance the medical field.