Mps Bhatia

Bio: Mps Bhatia is an academic researcher from Netaji Subhas Institute of Technology. The author has contributed to research in topics: Deep learning & Biometrics. The author has an hindex of 8, co-authored 67 publications receiving 285 citations.

Role of Emotion in Excessive Use of Twitter During COVID-19 Imposed Lockdown in India.

Abstract: The COVID-19 pandemic and the lockdowns to contain it are affecting the daily life of people around the world. People are now using digital technologies, including social media, more than ever before. The objectives of this study were to analyze the social media usage pattern of people during the COVID-19 imposed lockdown and to understand the effects of emotion on the same. We scraped messages posted on Twitter by users from India expressing their emotion or view on the pandemic during the first 40 days of the lockdown. We identified the users who posted frequently and analyzed their usage pattern and their overall emotion during the study period based on their tweets. It was observed that 222 users tweeted frequently during the study period. Out of them, 13.5% were found to be addicted to Twitter and posted 13.67 tweets daily on an average (SD: 4.89), while 3.2% were found to be highly addicted and posted 40.71 tweets daily on an average (SD: 9.90) during the study period. The overall emotion of 40.1% of the users was happiness throughout the study period. However, it was also observed that users who tweeted more frequently were typically angry, disgusted, or sad about the prevailing situation. We concluded that people with a negative sentiment are more susceptible to addictive use of social media.

Skin Lesion Classification: A Transfer Learning Approach Using EfficientNets

Abstract: This paper studies the ability of deep convolutional neural networks (DCNNs) to classify skin lesions belonging to seven different categories Two pre-trained state-of-the-art architectures for computer vision tasks ResNet-50 and Google’s recently proposed, EfficientNet-B0, were fine-tuned for the classification task on the HAM10000 dataset The dataset comprises 10015 dermatoscopic images belonging to seven classes of skin cancer melanocytic nevus, melanoma, benign keratosis, basal cell carcinoma, actinic keratosis, vascular lesions, and dermatofibroma The aim of the study was to establish how well the EfficientNet family of models (which result in up to 84\(\times \) parameter reduction and 16\(\times \) FLOPS reduction) transfers to the skin classification task in comparison with the ResNet architecture Overall, it was found that the EfficientNet-B0 model, with fewer parameters, outperformed the ResNet-50 model EfficientNet-B0 model produced better ROC AUC values for each classification category and also achieved higher macro and micro averaged AUC values for the overall classification, 093 and 097, respectively (in comparison with, 091 and 096 of the ResNet-50 model)

D-BullyRumbler: a safety rumble strip to resolve online denigration bullying using a hybrid filter-wrapper approach

Abstract: Denigration is a specialized form of cyberbullying which describes a recurrent, sustained and intentional attempt to damage the victim’s reputation or ruin the friendships that he or she has by spreading unfounded gossip or rumors online It is the most common bullying tactic involving character assassination of public figures like celebrities and politicians As a comprehensive approach to match to the scale of social media this research put forwards a D-BullyRumbler model for automatic detection and resolution of denigration cyberbullying in online textual content using a hybrid of lexicon-based and machine learning-based techniques The model processes textual, content-based and user-based features to uncover denigration from two perspectives Firstly, a direct explicit content analysis is done to look for denigration markers as features for model training and testing Concurrently, potentially harmful messages, rumors, are identified as candidates and examined for target profile type to reveal the case of denigration An additional OR operation is done to maintain the holistic framework Another novelty of the work includes the use of hybrid filter-wrapper method, Chi-square filter and cuckoo search wrapper algorithm to improve the performance of reputation rumor classification module Experimental results on social media datasets show the superior classification performance The results validate the effectiveness of the proposed model which facilitates timely intervention by buzzing an alarm to the moderators and further forming a rumble safety strip to inhibit the production and dissemination of inappropriate content to protect the victims

Fingerprint Spoofing Detection to Improve Customer Security in Mobile Financial Applications Using Deep Learning

Abstract: Online banking and financial services using mobile applications are seeing a persistent growth among customers, who are using these for their financial transactions. This rise in the use of such applications in smart devices has increased security concerns. There is need for secure mechanisms to prevent fraud and protect personal information. This paper investigates the use of biometric identification in banking and financial services, which leverage the use of smartphones and tablets. While customer engagement and brand loyalty are important concerns, these services are making use of biometric authentication to make customer interactions more secure. However, as technology is growing rapidly, spoofing attacks are becoming common. In this paper, authors have proposed a robust framework to detect spoofing attacks in fingerprint recognition. The process of spoofing detection involves contrast enhancement using histogram equalization and a deep convolutional neural network architecture. Authors have validated the results on various biometric spoofing benchmarks, each one containing real and spoofed samples of user fingerprints. The results indicate that our proposed framework performs better as evaluated against other existing pre-trained CNN models and state-of-the-art methods.

Anomaly Detection in Multiplex Networks

Abstract: Detecting anomalies in social is a vital task, with numerous high impacted social networks such as WWW, Facebook, Twitter and so on. There are multiple of techniques have been developed for detecting outliers and anomalies in graph data. More recently, the area of multiplex networks has extended a considerable attention among researchers for more concrete results. A Multiplex network is a network, which contains multiple systems of the same set of nodes and there exists various types of the relationship among nodes. In this paper, we discover the anomalies across numerous multiplex networks. By anomalies or outliers means nodes, which behave abnormal or suspicious in the system. Compared to single layer networks, the outliers’ nodes may found into many layers of the multiplex network and find anomalies in the multiplex network is still untouched. From this study, we propose a new metric called cross-layer anomaly detection (CAD). The CAD is a measure, which detects the anomalies in the multiplex network. For experiments, we make use of two real-world multiplex networks. We compare the results of our proposed metric with other similar methods, and we get encouraging and similar results.

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Detection and Resolution of Rumours in Social Media: A Survey

Abstract: Despite the increasing use of social media platforms for information and news gathering, its unmoderated nature often leads to the emergence and spread of rumours, i.e., items of information that are unverified at the time of posting. At the same time, the openness of social media platforms provides opportunities to study how users share and discuss rumours, and to explore how to automatically assess their veracity, using natural language processing and data mining techniques. In this article, we introduce and discuss two types of rumours that circulate on social media: long-standing rumours that circulate for long periods of time, and newly emerging rumours spawned during fast-paced events such as breaking news, where reports are released piecemeal and often with an unverified status in their early stages. We provide an overview of research into social media rumours with the ultimate goal of developing a rumour classification system that consists of four components: rumour detection, rumour tracking, rumour stance classification, and rumour veracity classification. We delve into the approaches presented in the scientific literature for the development of each of these four components. We summarise the efforts and achievements so far toward the development of rumour classification systems and conclude with suggestions for avenues for future research in social media mining for the detection and resolution of rumours.

Opinion of students on online education during the COVID-19 pandemic

Abstract: Abstract The COVID-19 pandemic forced universities around the world to shut down their campuses indefinitely and move their educational activities onto online platforms The universities were not prepared for such a transition and their online teaching-learning process evolved gradually We conducted a survey in which we asked undergraduate students in an Indian university about their opinion on different aspects of online education during the ongoing pandemic We received responses from 358 students The students felt that they learn better in physical classrooms (65 9%) and by attending MOOCs (39 9%) than through online education The students, however, felt that the professors have improved their online teaching skills since the beginning of the pandemic (68 1%) and online education is useful right now (77 9%) The students appreciated the software and online study materials being used to support online education However, the students felt that online education is stressful and affecting their health and social life This pandemic has led to a widespread adoption of online education and the lessons we learn now will be helpful in the future

Detection and Resolution of Rumours in Social Media: A Survey

Abstract: Despite the increasing use of social media platforms for information and news gathering, its unmoderated nature often leads to the emergence and spread of rumours, i.e. pieces of information that are unverified at the time of posting. At the same time, the openness of social media platforms provides opportunities to study how users share and discuss rumours, and to explore how natural language processing and data mining techniques may be used to find ways of determining their veracity. In this survey we introduce and discuss two types of rumours that circulate on social media; long-standing rumours that circulate for long periods of time, and newly-emerging rumours spawned during fast-paced events such as breaking news, where reports are released piecemeal and often with an unverified status in their early stages. We provide an overview of research into social media rumours with the ultimate goal of developing a rumour classification system that consists of four components: rumour detection, rumour tracking, rumour stance classification and rumour veracity classification. We delve into the approaches presented in the scientific literature for the development of each of these four components. We summarise the efforts and achievements so far towards the development of rumour classification systems and conclude with suggestions for avenues for future research in social media mining for detection and resolution of rumours.