A5056705041- Biometric Identification and Security
- Face recognition and analysis
- User Authentication and Security Systems
- Face and Expression Recognition
- Advanced Malware Detection Techniques
- Digital Media Forensic Detection
- Anomaly Detection Techniques and Applications
- Emotion and Mood Recognition
- Adversarial Robustness in Machine Learning
- Forensic and Genetic Research
- Network Security and Intrusion Detection
- Generative Adversarial Networks and Image Synthesis
- Advanced Steganography and Watermarking Techniques
- Image and Video Quality Assessment
- Video Surveillance and Tracking Methods
- Forensic Fingerprint Detection Methods
- Speech and Audio Processing
- Advanced Image and Video Retrieval Techniques
- Smart Agriculture and AI
- Brain Tumor Detection and Classification
- Fixed Point Theorems Analysis
- Image Retrieval and Classification Techniques
- Internet Traffic Analysis and Secure E-voting
- Handwritten Text Recognition Techniques
- Advanced Image Fusion Techniques
SUNY Polytechnic Institute
2020-2025
University of Alaska Anchorage
2023-2025
Kansas State University
2024
State University of New York
2020-2023
Institut National de la Recherche Scientifique
2016-2022
University of Memphis
2018-2021
Université du Québec à Montréal
2016-2019
Université du Québec
2018
University of Udine
2014-2017
Cincinnati Children's Hospital Medical Center
2017
In affective computing applications, access to labeled spontaneous data is essential for testing the designed algorithms under naturalistic and challenging conditions. Most databases available today are acted or do not contain audio data. We present a audio-visual face database of mental states. The video clips in obtained by recording subjects from frontal view using stereo camera half-profile mono camera. first shown sequence images short clips, which only meticulously fashioned but also...
Today’s world is highly network interconnected owing to the pervasiveness of small personal devices (e.g., smartphones) as well large computing or services cloud online banking), and thereby each passing minute millions data bytes are being generated, processed, exchanged, shared, utilized yield outcomes in specific applications. Thus, securing data, machines (devices), user’s privacy cyberspace has become an utmost concern for individuals, business organizations, national governments. In...
In this paper, we address the challenge of fingerprint liveness detection by proposing a dual pre-trained model approach that combines VGG16 and ResNet50 architectures. While existing methods often rely on single feature extraction model, they may struggle with generalization across diverse spoofing materials sensor types. To overcome limitation, our leverages high-resolution deep layer architecture to capture more comprehensive range features for improved spoof detection. The proposed...
In recent years, software-based face presentation attack detection (PAD) methods have seen a great progress. However, most existing schemes are not able to generalize well in more realistic conditions. The objective of this competition is evaluate and compare the generalization performances mobile PAD techniques under some real-world variations, including unseen input sensors, instruments (PAI) illumination conditions, on larger scale OULU-NPU dataset using its standard evaluation protocols...
Many consider the KDD Cup 99 data sets to be outdated and inadequate. Therefore, extensive use of these in recent studies evaluate network intrusion detection systems is a matter concern. We contribute literature by addressing concerns.
Multimodal biometric systems are commonly believed to be more robust spoofing attacks than unimodal systems, as they combine information coming from different traits. Recent work has shown that multimodal can misled by an impostor even only one trait. This result was obtained under a 'worst-case' scenario, assuming the distribution of fake scores is identical genuine (i.e. attacker assumed able perfectly replicate trait). assumption also allows evaluate robustness score fusion rules against...
In a spoofing attack, an impostor masquerades as legitimate user by replicating that user's biometrics. Although methods exist to determine whether live person or biometric artifact is in front of sensor, attacks remain problem.
Large Language Models (LLMs), such as the GPT series, LLaMA, and BERT, possess incredible capabilities in human-like text generation understanding across diverse domains, which have revolutionized artificial intelligence applications. However, their operational complexity necessitates a specialized framework known LLMOps (Large Model Operations), refers to practices tools used manage lifecycle processes, including model fine-tuning, deployment, LLMs monitoring. is subcategory of broader...
Measuring perceived quality of audio-visual signals at the end-user has become an important parameter in many multimedia networks and applications. It plays a crucial role shaping processing, compression, transmission systems, along with their implementation, optimization, testing. Service providers are enacting different service (QoS) solutions to issue best experience (QoE) customers. Thus, devising precise perception-based metrics will greatly help improving services over wired wireless...
Recent works have investigated the robustness to spoofing attacks of multi-modal biometric systems in parallel fusion mode. Contrary a common belief, it has been shown that they can be cracked by only one trait. Robustness evaluation serial mode not yet investigated, instead. Thus, aim this paper is comparatively evaluate systems, and modes, under attacks. In particular, we empirically investigate vulnerability face fingerprint biometrics real Our results show both modes are vulnerable...
Despite new technologies that make face detection and recognition more sophisticated, long-recognized problems in security, privacy, accuracy persist. Refining this technology introducing it into domains will require solving these through focused interdisciplinary efforts among developers, researchers, policymakers.
Interest in affective computing is burgeoning, great part due to its role emerging human-computer interfaces (HCI). To date, the majority of existing research on automated emotion analysis has relied data collected controlled environments. With rise HCI applications mobile devices, however, so-called “in-the-wild” settings have posed a serious threat for recognition systems, particularly those based voice. In this case, environmental factors such as ambient noise and reverberation severely...
In medical practice, the X-ray Computed tomography-based scans expose a high radiation dose and lead to risk of prostate or abdomen cancers. On other hand, low-dose CT scan can reduce exposure patient. But reduced degrades image quality for human perception, adversely affects radiologist's diagnosis prognosis. this paper, we introduce GAN based auto-encoder network de-noise images. Our first maps images low dimensional manifolds then restore from its corresponding manifold representations....
In today's highly intertwined network society, the demand for big data processing frameworks is continuously growing. The widely adopted model to process parallel and distributed computing. This paper documents significant progress achieved in field of computing frameworks, particularly Apache Hama, a top level project under Software Foundation, based on bulk synchronous processing. comparative studies empirical evaluations performed this reveal Hama's potential efficacy applications....
Quality of experience (QoE) assessment occupies a key role in various multimedia networks and applications. Recently, large efforts have been devoted to devise objective QoE metrics that correlate with perceived subjective measurements. Despite recent progress, limited success has attained. In this paper, we provide some insights on why is so difficult by presenting few major issues as well general summary quality/QoE formation conception including human auditory vision systems. Also,...
The revolutionary breakthroughs in Machine Learning (ML) and Artificial Intelligence (AI) are extensively being harnessed across a diverse range of domains, e.g., forensic science, healthcare, virtual assistants, cybersecurity, robotics. On the flip side, they can also be exploited for negative purposes, like producing authentic-looking fake news that propagates misinformation diminishes public trust. Deepfakes pertain to audio or visual multimedia contents have been artificially synthesized...
Wheat is an important source of dietary fiber and protein that negatively impacted by a number risks to its growth. The difficulty identifying classifying wheat diseases discussed with emphasis on loose smut, leaf rust, crown root rot. Addressing conditions like rot, this study introduces innovative approach integrates multi-scale feature extraction advanced image segmentation techniques enhance classification accuracy. proposed method uses neural network models Xception, Inception V3,...
Alzheimers disease is a deadly neurological condition, impairing important memory and brain functions. promotes shrinkage, ultimately leading to dementia. Dementia diagnosis typically takes 2.8 4.4 years after the first clinical indication. Advancements in computing information technology have led many techniques of studying disease. Early identification therapy are crucial for preventing disease, as early-onset dementia hits people before age 65, while late-onset occurs this age. According...
The potato is a widely grown crop in many regions of the world. In recent decades, farming has gained incredible traction Potatoes are susceptible to several illnesses that stunt their development. This plant seems have significant leaf disease. Early Blight and Late two prevalent diseases affect plants. early detection these would be beneficial for enhancing yield this crop. ideal solution use image processing identify analyze disorders. Here, we present an autonomous method based on...
Purpose: The increasing number of cyber-attacks has elevated the importance cybersecurity for organizations. This also increased demand professionals with necessary skills to protect these As a result, many individuals are looking enter field cybersecurity. However, there is lack clear understanding required successful career in this field. In paper, we identify professionals. We determine how cyber relates various roles such as security analyst and architect. Furthermore, programming...