A5114112373- User Authentication and Security Systems
- Machine Learning in Bioinformatics
- Hepatitis C virus research
- Media Influence and Health
- Computational Drug Discovery Methods
- Biometric Identification and Security
- RNA and protein synthesis mechanisms
- Generative Adversarial Networks and Image Synthesis
- Hearing Impairment and Communication
- Hand Gesture Recognition Systems
- Social Media and Politics
- Misinformation and Its Impacts
- Face recognition and analysis
- Advanced Authentication Protocols Security
- Security and Verification in Computing
- SARS-CoV-2 and COVID-19 Research
- Human Pose and Action Recognition
- Media, Gender, and Advertising
- Digital Media Forensic Detection
- Privacy, Security, and Data Protection
- Genomics and Phylogenetic Studies
- Emotion and Mood Recognition
- Advanced Image Processing Techniques
- Access Control and Trust
- Vibration Control and Rheological Fluids
National University of Singapore
2019-2025
Mawlana Bhashani Science and Technology University
2019-2022
University of Rajshahi
2022
Institute of Post Graduate Medical Education and Research
2020-2021
University of Asia Pacific
2017-2019
United International University
2017-2018
Jadavpur University
2015
Abstract Glycation is chemical reaction by which sugar molecule bonds with a protein without the help of enzymes. This often cause to many diseases and therefore knowledge about glycation very important. In this paper, we present iProtGly‐SS, lysine site identification method based on features extracted from sequence secondary structural information. experiments, found best feature groups combination: Amino Acid Composition, Secondary Structure Motifs, Polarity. We used support vector...
Abstract The year 2020 witnessed a heavy death toll due to COVID-19, calling for global emergency. continuous ongoing research and clinical trials paved the way vaccines. But, vaccine efficacy in long run is still questionable mutating coronavirus, which makes drug re-positioning reasonable alternative. COVID-19 has hence fast-paced treatment of its symptoms. This work builds computational models using matrix completion techniques predict drug-virus association re-positioning. aim assist...
Deepfakes of deceased individuals have recently been explored as tools for conveying prosocial messages that promote positive behaviors. This exploratory study examines how nostalgia influences the perceived credibility this particular deepfake genre, focusing on psychological mechanisms narrative persuasion: transportation and character identification. Nostalgia in narratives about can reduce defensive avoidance shape attitudes through these mechanisms. A between-subjects experiment (n =...
Amid growing ethical concerns over the viral spread of deepfakes, existing literature suggests that their sensory richness and enhanced realism evoke complex, sometimes contradictory, audience reactions. This study examines persuasive potential deepfakes by comparing responses to identical resurrection narratives presented in deepfake video format versus text-based storytelling. Participants (N = 813, Mage 37.28, SDage 12.46) were exposed either a or textual narrative featuring historical...
This research applies Uses and Gratifications theory to examine individual motivations for sharing or not deepfakes. After characterizing popular deepfakes in five genres (two examples each), 1035 US participants (42% female; Age: M = 42.8, SD 14.1, Mdn 41, Range 18–93) watched one of the ten completed a questionnaire Prolific. Results show that most would share due lack personal relevance. However, those who did intend them had hedonistic motivations, mostly enjoyment desire entertainment...
Recent advancements in the field of computer vision with help deep neural networks have led us to explore and develop many existing challenges that were once unattended due lack necessary technologies. Hand Sign/Gesture Recognition is one significant areas where network making a substantial impact. In last few years, large number researches has been conducted recognize hand signs gestures, which we aim extend our mother-tongue, Bangla (also known as Bengali). The primary goal work make an...
The recent renaissance in generative models, driven primarily by the advent of diffusion models and iterative improvement GAN methods, has enabled many creative applications. However, each advancement is also accompanied a rise potential for misuse. In arena deepfake generation, this key societal issue. particular, ability to modify segments videos using such techniques creates new paradigm deepfakes which are mostly real altered slightly distort truth. This been under-explored current...
Electroencephalogram (EEG) signals are of very low amplitude and easily contaminated by different types noises like environmental non-cerebral in nature. Thus signal pre-processing is a major challenge while dealing with applications involving EEG signals. The scenario becomes much more complex using commercially available, resolution devices as they have fewer electrodes. In this paper, we applied some the widely used processing techniques to get rid eye blink noise related artifacts from...
In order to provide the additional security required by modern mobile devices, biometric methods and Continuous Authentication(CA) systems are getting popular. Most existing work on CA concerned about achieving higher accuracy or fusing multiple modalities. However, in a environment there more constraints resources available. This is first compare between different modalities based they use. We do this determining Resource Profile Curve (RPC) for each modality. reveals trade-off...
Face recognition is a popular form of biometric authentication and due to its widespread use, attacks have become more common as well.Recent studies show that Recognition Systems are vulnerable can lead erroneous identification faces.Interestingly, most these white-box, or they manipulating facial images in ways not physically realizable.In this paper, we propose an attack scheme where the attacker generate realistic synthesized face with subtle perturbations realize onto his black-box...
VANET (Vehicular Ad-hoc NETwork) is a network architecture designed to provide road safety, improve transport efficiency, and reduce traffic congestion by combining vehicles with high mobility fixed road-side units or without Vehicular Cloud. Connected aided sensors need be authenticated before transmitting message. Two major problems in existing state-of-the-art schemes which are redundant authentication of each RSUs it passes through authenticating message trusted authority large...
With the advancement of Information technologies and applications, a copious amount data is generated, which attracts both research community to utilize this information for extracting knowledge industry developing knowledge-based system. Visualization data, pattern mining from datasets analyzing drift different features are three highly used applications machine learning science fields. A generic web-based tool integrated with such will provide prodigious support preprocessing dataset thus...
Institute, Warsaw, Poland This paper describes the results of IEEE BigData 2023 Keystroke Verification Challenge <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> (KVC), that considers biometric verification performance Dynamics (KD), captured as tweet-long sequences variable transcript text from over 185,000 subjects. The data are obtained two largest public databases KD up to date, Aalto Desktop and Mobile Databases, guaranteeing a...
This paper describes the results of IEEE BigData 2023 Keystroke Verification Challenge (KVC), that considers biometric verification performance Dynamics (KD), captured as tweet-long sequences variable transcript text from over 185,000 subjects. The data are obtained two largest public databases KD up to date, Aalto Desktop and Mobile Databases, guaranteeing a minimum amount per subject, age gender annotations, absence corrupted data, avoiding excessively unbalanced subject distributions with...
This article presents the Keystroke Verification Challenge - onGoing (KVC-onGoing), on which researchers can easily benchmark their systems in a common platform using large-scale public databases, Aalto University and standard experimental protocol. The keystroke data consist of tweet-long sequences variable transcript text from over 185,000 subjects, acquired through desktop mobile keyboards simulating real-life conditions. results evaluation set KVC-onGoing have proved high discriminative...
Face reenactment refers to the process of transferring pose and facial expressions from a reference (driving) video onto static (source) image while maintaining original identity source image. Previous research in this domain has made significant progress by training controllable deep generative models generate faces based on specific identity, expression conditions. However, mechanisms used these methods control often inadvertently introduce information driving video, also causing loss...
This research applies Uses and Gratifications theory to examine individual motivations for sharing or not deepfakes. After characterizing popular deepfakes in five genres (two examples each), 1035 US participants (42% female; Age: M = 42.8, SD 14.1, Mdn 41, Range 18–93) watched one of the ten completed a questionnaire Prolific. Results show that most would share due lack personal relevance. However, those who did intend them had hedonistic motivations, mostly enjoyment desire entertainment...