Sweta Bhattacharya - Academia.edu (original) (raw)

Papers by Sweta Bhattacharya

India is a country with high educational values and is considered as a country with an asset of t... more India is a country with high educational values and is considered as a country with an asset of technically sound, motivated and hardworking student strength and dedicated faculty members. But at the same time, there exists shortage of such talented faculty members across different Universities and affiliated Institutes in India. The research objective of the paper is to analyse the different factors that guide teaching career decisions among IT engineering graduates and post-graduates and to find the most significant factors which influences such career choices. The statistical analysis presented in the paper is based on a Survey conducted on the Graduate and Post-Graduate students in a private University in India. The factors considered in the study are Motivation, Perception, Interest, Professional and Financial Security, Career Choice based on Knowledge and skill and finally Inclination towards research. The study reveals the effect of Gender on the perception of teaching career...

IEEE Transactions on Green Communications and Networking

— the Pareto principle or most popularly termed as the 80/20 rule is one of the well-known theori... more — the Pareto principle or most popularly termed as the 80/20 rule is one of the well-known theories in the field of economics. This rule of thumb was named after the great economist Vilferdo Pareto. The Pareto principle was proposed by a renowned management consultant Joseph M Juran. The rule states that 80 % of the required work can be completed in 20 % of the time allotted. The idea is to apply this rule of thumb in the Rapid Application Development (RAD) Process model of software engineering. The Rapid application development model integrates end-user in the development using iterative prototyping emphasizing on delivering a series of fully functional prototype to designated user experts. During the application of Pareto Principle the other concepts like the Pareto indifference curve and Pareto efficiency also come into the picture. This enables the development team to invest major amount of time focusing on the major functionalities of the project as per the requirement prioriti...

Background and Objective: In the near future population in the urban areas is going to increase t... more Background and Objective: In the near future population in the urban areas is going to increase to 70% of the total population of the world and hence the future cities are need to be well operated and managed with lots of automation in various spheres of human life. IoT will act as the backbone for these Smart Cities and regular mundane activities like electricity consumption, pollution control, car parking, health monitoring would be handled with the help of IoT based devises Designing a general framework for the smart city is not feasible due to difference in sensor types, total number of sensors, mode of connectivity and its security levels. This paper gives an outline on architecture system in the Smart City and proposes a framework for addressing traffic issues faced in transportation. Materials and Method: The proposed framework caters the traffic issues faced by citizens using a RFID tagging methodology based on ubiquitous network architecture. The approach uses three tier ar...

The management appraisal of the employee's performance irrespective of any industry lacks ind... more The management appraisal of the employee's performance irrespective of any industry lacks industry standards, is not transparent involving excessive variability. Appraisal is ad-hoc and does not have a scientific method for the rating of the employees. A decision support tool if developed will assist software services organization in standardizing and making the appraisal procedure transparent.

ArXiv, 2021

Big data has remarkably evolved over the last few years to realize an enormous volume of data gen... more Big data has remarkably evolved over the last few years to realize an enormous volume of data generated from newly emerging services and applications and a massive number of Internet-of-Things (IoT) devices. The potential of big data can be realized via analytic and learning techniques, in which the data from various sources is transferred to a central cloud for central storage, processing, and training. However, this conventional approach faces critical issues in terms of data privacy as the data may include sensitive data such as personal information, governments, banking accounts. To overcome this challenge, federated learning (FL) appeared to be a promising learning technique. However, a gap exists in the literature that a comprehensive survey on FL for big data services and applications is yet to be conducted. In this article, we present a survey on the use of FL for big data services and applications, aiming to provide general readers with an overview of FL, big data, and the ...

ArXiv, 2020

Big data has generated strong interest in various scientific and engineering domains over the las... more Big data has generated strong interest in various scientific and engineering domains over the last few years. Despite many advantages and applications, there are many challenges in big data to be tackled for better quality of service, e.g., big data analytics, big data management, and big data privacy and security. Blockchain with its decentralization and security nature has the great potential to improve big data services and applications. In this article, we provide a comprehensive survey on blockchain for big data, focusing on up-to-date approaches, opportunities, and future directions. First, we present a brief overview of blockchain and big data as well as the motivation behind their integration. Next, we survey various blockchain services for big data, including blockchain for secure big data acquisition, data storage, data analytics, and data privacy preservation. Then, we review the state-of-the-art studies on the use of blockchain for big data applications in different vert...

Bug tracking tools help stake holders involved in software projects to detect bugs, resolve them ... more Bug tracking tools help stake holders involved in software projects to detect bugs, resolve them and then ensure to have contingency and preventive measures so that detected bugs are not repeated in the future projects. The present generation of software developed, are enormous and extensive in size inorder to meet customer requirements and hence presence of bugs is impossible to avoid. Hence it is very important to know the functionalities and features of different bug trackers namely the open source ones so that compatible and relevant tools can be chosen efficiently for bug tracking purposes. The paper provides description of ten popular bug tracking tools and the major features of these tools are discussed in details yet concise manner. A comparative matrix is presented which helps to compare the tools, analyse them and find a tool which supports majority of the functionalities expected from an ideal bug tracking tool.

International Journal of Scientific & Technology Research, 2020

The key to success in the field of stock trading depends on the ability of buying and selling sto... more The key to success in the field of stock trading depends on the ability of buying and selling stocks at the correct time where decision making skills and predictions play a major role. The objective is to “Sell high and buy low” which sounds easy but is difficult to achieve and errors in assumption can lead to extensive loss of money. Data mining is a popularly used technique which has helped to resolve decision making issues in this field this increasing accuracy in accuracy of predictions in stock trading. In this paper, a comparative analysis of the use of various classification algorithms namely SVM, Naïve Bayes classifier, CART and LAD are explored which have been a popular choice of algorithms in stock exchange data. Finally, a hybrid model is developed considering the pros and cons of Naïve Bayes classifier and SVM algorithm which has been successful in producing enhances accuracy in comparison to the existing approaches.

The rise of blockchain technology within a few years has attracted researchers across the world. ... more The rise of blockchain technology within a few years has attracted researchers across the world. The prime reason for worldwide attention is undoubtedly due to its feature of immutability along with the decentralized approach of data protection. As this technology is progressing, lots of developments in terms of identifying new applications, blockchain-based platforms, consensus mechanisms, etc are taking place. Hence, in this article, an attempt has been made to review the recent advancements in blockchain technology. Furthermore, we have also explored the available blockchain platforms, highlighted and explored future research directions and challenges.

the Pareto principle or most popularly termed as the 80/20 rule is one of the well-known theories... more the Pareto principle or most popularly termed as the 80/20 rule is one of the well-known theories in the field of economics. This rule of thumb was named after the great economist Vilferdo Pareto. The Pareto principle was proposed by a renowned management consultant Joseph M Juran. The rule states that 80% of the required work can be completed in 20% of the time allotted. The idea is to apply this rule of thumb in the Rapid Application Development (RAD) Process model of software engineering. The Rapid application development model integrates end-user in the development using iterative prototyping emphasizing on delivering a series of fully functional prototype to designated user experts. During the application of Pareto Principle the other concepts like the Pareto indifference curve and Pareto efficiency also come into the picture. This enables the development team to invest major amount of time focusing on the major functionalities of the project as per the requirement prioritizati...

The current situation of COVID-19 demands novel solutions to boost healthcare services and econom... more The current situation of COVID-19 demands novel solutions to boost healthcare services and economic growth. A full-fledged solution that can help the government and people retain their normal lifestyle and improve the economy is crucial. By bringing into the picture a unique incentive-based approach, the strain of government and the people can be greatly reduced. By providing incentives for actions such as voluntary testing, isolation, etc., the government can better plan strategies for fighting the situation while people in need can benefit from the incentive offered. This idea of combining strength to battle against the virus can bring out newer possibilities that can give an upper hand in this war. As the unpredictable future develops, sharing and maintaining COVID related data of every user could be the needed trigger to kick start the economy and blockchain paves the way for this solution with decentralization and immutability of data.

ArXiv, 2021

The rapid development of the Internet and smart devices trigger surge in network traffic making i... more The rapid development of the Internet and smart devices trigger surge in network traffic making its infrastructure more complex and heterogeneous. The predominated usage of mobile phones, wearable devices and autonomous vehicles are examples of distributed networks which generate huge amount of data each and every day. The computational power of these devices have also seen steady progression which has created the need to transmit information, store data locally and drive network computations towards edge devices. Intrusion detection systems play a significant role in ensuring security and privacy of such devices. Machine Learning and Deep Learning with Intrusion Detection Systems have gained great momentum due to their achievement of high classification accuracy. However the privacy and security aspects potentially gets jeopardised due to the need of storing and communicating data to centralized server. On the contrary, federated learning (FL) fits in appropriately as a privacy-pre...

2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE)

As technology and digitization grows, there is a huge surge in digital storage of health records.... more As technology and digitization grows, there is a huge surge in digital storage of health records. Machine learning has an important role in uncovering patterns existing in these health records providing interesting insights to medical practitioners for assistance in the diagnosis of various ailments. Due to the sensitivity of the health records, the machine learning algorithms often fail to predict the diseases accurately. In present work, an ensemble based machine learning model comprising of the Machine Learning (ML) Algorithms namely Random Forest classifier, Decision Tree Classifier, Adaboost Classifier, K-Nearest Neighbour classifier, Logistic Regression classifier is experimented on diabetic retinopathy dataset. As a first step, normalization is done on the diabetic retinopathy dataset by min-max normalization method. This normalized dataset is then trained the proposed ensemble model. The performance of the proposed model is finally evaluated against the individual machine learning algorithms. The comparative analysis reveals the fact that the ensemble machine learning model outperforms the individual machine learning algorithms.

International Journal of Ad Hoc and Ubiquitous Computing

Wireless Communications and Mobile Computing

Crime detection is one of the most important research applications in machine learning. Identifyi... more Crime detection is one of the most important research applications in machine learning. Identifying and reducing crime rates is crucial to developing a healthy society. Big Data techniques are applied to collect and analyse data: determine the required features and prime attributes that cause the emergence of crime hotspots. The traditional crime detection and machine learning-based algorithms lack the ability to generate key prime attributes from the crime dataset, hence most often fail to predict crime patterns successfully. This paper is aimed at extracting the prime attributes such as time zones, crime probability, and crime hotspots and performing vulnerability analysis to increase the accuracy of the subject machine learning algorithm. We implemented our proposed methodology using two standard datasets. Results show that the proposed feature generation method increased the performance of machine learning models. The highest accuracy of 97.5% was obtained when the proposed meth...

Journal of Healthcare Engineering

The cry is a loud, high pitched verbal communication of infants. The very high fundamental freque... more The cry is a loud, high pitched verbal communication of infants. The very high fundamental frequency and resonance frequency characterize a neonatal infant cry having certain sudden variations. Furthermore, in a tiny duration solitary utterance, the cry signal also possesses both voiced and unvoiced features. Mostly, infants communicate with their caretakers through cries, and sometimes, it becomes difficult for the caretakers to comprehend the reason behind the newborn infant cry. As a result, this research proposes a novel work for classifying the newborn infant cries under three groups such as hunger, sleep, and discomfort. For each crying frame, twelve features get extracted through acoustic feature engineering, and the variable selection using random forests was used for selecting the highly discriminative features among the twelve time and frequency domain features. Subsequently, the extreme gradient boosting-powered grouped-support-vector network is deployed for neonate cry c...

IEEE Transactions on Green Communications and Networking

ArXiv, 2021

ArXiv, 2020

International Journal of Scientific & Technology Research, 2020

ArXiv, 2021

2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE)

International Journal of Ad Hoc and Ubiquitous Computing

Wireless Communications and Mobile Computing

Journal of Healthcare Engineering