A5001098482- Biometric Identification and Security
- Forensic Fingerprint Detection Methods
- Digital Media Forensic Detection
- Anomaly Detection Techniques and Applications
- Face recognition and analysis
- Smart Grid Energy Management
- Speech and Audio Processing
- User Authentication and Security Systems
- Big Data Technologies and Applications
- Speech Recognition and Synthesis
- Privacy-Preserving Technologies in Data
- Forensic and Genetic Research
- Voice and Speech Disorders
- Integrated Energy Systems Optimization
- Advanced Data Compression Techniques
- Electric Power System Optimization
- Medical Imaging and Analysis
- Power System Optimization and Stability
- Privacy, Security, and Data Protection
- Optimal Power Flow Distribution
- Face and Expression Recognition
- Industrial Vision Systems and Defect Detection
- Big Data and Digital Economy
Clarkson University
2020-2024
Zimmer Biomet (United States)
2023
State University of New York at Potsdam
2018
Jadavpur University
2016
Touch-based fingerprint biometrics is one of the most popular biometric modalities with applications in several fields. Problems associated touch-based techniques such as presence latent fingerprints and hygiene issues due to many people touching same surface motivated community look for non-contact-based solutions. For last few years, contactless systems are on rise demand because ability turn any device a camera into reader. Yet, before we can fully utilize benefit noncontact-based...
Launched in 2013, LivDet-Iris is an international competition series open to academia and industry with the aim assess report advances iris Presentation Attack Detection (PAD). This paper presents results from fourth of series: 2020. year's introduced several novel elements: (a) incorporated new types attacks (samples displayed on a screen, cadaver eyes prosthetic eyes), (b) initiated as on-going effort, testing protocol available now everyone via Biometrics Evaluation Testing (BEAT)*...
Liveness Detection (LivDet)-Face is an international competition series open to academia and industry. The competition's objective assess report state-of-the-art in liveness / Presentation Attack (PAD) for face recognition. Impersonation presentation of false samples the sensors can be classified as attacks ability detect such attempts known PAD. LivDet-Face 2021 * will first edition competition. This serves important benchmark attack detection, offering (a) independent assessment current...
This paper describes the results of 2023 edition "LivDet" series iris presentation attack detection (PAD) competitions. New elements in this fifth competition include (1) GAN-generated images as a category instruments (PAI), and (2) an evaluation human accuracy at detecting PAI reference benchmark. Clarkson University Notre Dame contributed image datasets for competition, composed samples representing seven different categories, well baseline PAD algorithms. Fraunhofer IGD, Beijing Civil...
A crucial component for developing an automated speaker or speech recognition system is voice preprocessing, which filters unwanted noise and detects the part. This study aimed to develop a computerized model remove background improve signal quality future applications. was developed on large longitudinal dataset containing varying real-world validated both public locally collected test in different environments. An overall pre-processing pipeline presented this study, including denoising,...
Fingerprints are widely recognized as one of the most unique and reliable characteristics human identity. Most modern fingerprint authentication systems rely on contact-based fingerprints, which require use scanners or sensors for capturing fingerprints during process. Various types sensors, such optical, capacitive, ultrasonic employ distinct techniques to gather analyze data. This dependency specific hardware creates a barrier challenge broader adoption based biometric systems. limitation...
Liveness Detection (LivDet) is an international competition series open to academia and industry with the objective assess report state-of-the-art in Presentation Attack (PAD). LivDet-2023 Noncontact Fingerprint first edition of noncontact fingerprint-based PAD for algorithms systems. The serves as important benchmark noncontact-based fingerprint PAD, offering (a) independent assessment systems, (b) common evaluation protocol, which includes finger photos a variety Instruments (PAIs) live...
Constant load variation and voltage level change is frequent in power system. It may be controlled by profile improvement congestion management. Congestion management can performed via system current reduction using FACTS devices. In this work, deviation has been allocating STATCOM device. Fitness value comprising of real loss total reduced placing UPFC Total line loading the decreased due to that placement. Differential Evolution (DE) chosen for suitable sizing sitting IEEE 30 bus...
As more types of transactions move online, there is an increasing need to verify someone's identity remotely. Remote verification (RIdV) technologies have emerged fill this need. RIdV solutions typically use a smart device validate document like driver's license by comparing face selfie the photo on document. Recent research has been focused ensuring that biometric systems work fairly across demographic groups. This study assesses five commercial for equity age, gender, race/ethnicity, and...
Biometric recognition is used for a variety of applications including authentication, identity proofing, and border security. One recent focus research development has been methods to ensure fairness across demographic groups metrics evaluate fairness. However, there little work in this area incorporating statistical variation. This important because differences among can be found by chance when no difference present or may due an actual system performance. We extend previous consider...
In this paper, we propose a self-scheduling model of energy and reserve for combined-cycle gas turbines (CCGT). The hybrid CCGT recently proposed by the authors is deployed scheduling operation. addition, practical issue in current market, i.e., provision during transition process, elaborately modeled. formulated as mixed-integer linear programming (MILP) problem solved via state-of-the-art commercial solver. Numerical test results on modified IEEE 118-bus system show effectiveness approach.
Touch-based fingerprint biometrics is one of the most popular biometric modalities with applications in several fields. Problems associated touch-based techniques such as presence latent fingerprints and hygiene issues due to many people touching same surface motivated community look for non-contact-based solutions. For last few years, contactless systems are on rise demand because ability turn any device a camera into reader. Yet, before we can fully utilize benefit noncontact-based...
Liveness Detection (LivDet) is an international competition series open to academia and industry with the objec-tive assess report state-of-the-art in Presentation Attack (PAD). LivDet-2023 Noncontact Fingerprint first edition of noncontact fingerprint-based PAD for algorithms systems. The serves as important benchmark noncontact-based fingerprint PAD, offering (a) independent assessment systems, (b) common evaluation protocol, which includes finger photos a variety Instruments (PAIs) live...
This paper describes the results of 2023 edition ''LivDet'' series iris presentation attack detection (PAD) competitions. New elements in this fifth competition include (1) GAN-generated images as a category instruments (PAI), and (2) an evaluation human accuracy at detecting PAI reference benchmark. Clarkson University Notre Dame contributed image datasets for competition, composed samples representing seven different categories, well baseline PAD algorithms. Fraunhofer IGD, Beijing Civil...
Launched in 2013, LivDet-Iris is an international competition series open to academia and industry with the aim assess report advances iris Presentation Attack Detection (PAD). This paper presents results from fourth of series: 2020. year's introduced several novel elements: (a) incorporated new types attacks (samples displayed on a screen, cadaver eyes prosthetic eyes), (b) initiated as on-going effort, testing protocol available now everyone via Biometrics Evaluation Testing...
Biometric recognition is used across a variety of applications from cyber security to border security. Recent research has focused on ensuring biometric performance (false negatives and false positives) fair demographic groups. While there been significant progress the development metrics, evaluation groups, mitigation any problems, little work incorporating statistical variation. This important because differences among groups can be found by chance when no difference present. In statistics...