لطفا منتظر بمانید ...
0% Complete
صفحه اصلی
/
یازدهمین کنفرانس بین المللی کنترل ، ابزار دقیق و اتوماسیون
Explainable Machine Learning for Gait-based Authentication in Metaverse Environment
نویسندگان :
Smit Shah
1
Jay Doshi
2
Janam Patel
3
Rajesh Gupta
4
Sudeep Tanwar
5
Hossein Shahinzadeh
6
Mahtab Bagheri
7
1- Nirma University
2- Nirma University
3- Nirma University
4- Nirma University
5- Nirma University
6- Dept. of Electrical Engineering, Amirkabir University of Technology (Tehran Polytechnic)
7- Islamic Azad University Najafabad Branch
کلمات کلیدی :
Machine Learning،Metaverse
چکیده :
The rise of the metaverse, a fully immersive, interactive, and persistent virtual environment, has posed new challenges for securing user identity. Traditional authentication methods like passwords and tokens are ineffective or insecure in contexts where users interact via avatars and motion-based interfaces. This paper proposes a novel multilayered gait-based authentication system tailored for metaverse environments. It leverages unique natural gait patterns, captured non-intrusively through VR/AR interfaces, as a behavioral biometric for continuous, contactless identity verification. The proposed architecture comprises four layers: the Metaverse Layer (data generation), User Layer (gait acquisition and preprocessing), AI Layer (classification using XGBoost), and Explainable AI Layer (transparency via SHAP and LIME). Experiments on the Metaverse Gait Authentication Dataset, with 5,000 gait samples and 16 derived features, demonstrate XGBoost’s 98% accuracy, 98% precision, and 99% recall. Integrating high-performance machine learning with explainable AI, the system ensures accurate, transparent, and scalable authentication for next-generation virtual communities.
لیست مقالات
لیست مقالات بایگانی شده
Environment Recognition for Controlling Lower-Limb Exoskeletons, by Computer Vision and Deep Learning Algorithm
Marzie Khalili - Sadjaad Ozgoli
Trajectory Planning and Simulation of Palletizing Robot Using MATLAB and Unity
Mohammad Sheibani - Amin Mojarrad Bahre - Armin Nasrollahi - Ali Rajabi
Fault Detection in Induction Motors Using Thermal Images and Interpretable Machine Learning: An Approach Based on EfficientNet and Advanced Simulation Algorithms
ُSeyed Reza Hashemi Dogahe - Behzad Moshiri
Resilient Robust Power System Stabilizer Design via LMI Pole Placement for Cyber-Physical Power Systems
Hossein Shahinzadeh - Hamed Nafisi - Amirafshin Zamani - Mahtab Bagheri - Farshad Ebrahimi - Saiedeh Mehrabani-Najafabadi
H∞ Robust Control Design for Three-Element Industrial Boiler Supervisory System
Narges Ahooghalandari - Reza Shadi - Ahmad Fakharian
A Comparative Study of 4G and 5G Impact on the Performance of Networked Control Systems
Ehsan Badfar - Babak Tavassoli
A Novel Cyber-Secure Algorithm in Cooperative Vehicles Platoon
Abolfazl Saadati Moghadam - Mohammad Haeri
تشخیص و جداسازی عیبها در سیستم سیال با دو مخزن با استفاده از فیلتر تشخیص عیب برد (BFDF)
حسین مصفا - حمید خالوزاده
بررسی تکنیک های کنترل امن به منظور شناسایی حملات سایبری در سیستم های فیزیکی سایبری
مریم عمادی - لادن صادقی خرمی - علی اکبر صفوی
A New Fuzzy Logic Based Learning Rate Scheduling Method for Crop Classification With Convolutional Neural Network
Mohammad Hoseinzadeh - Javad Khoramdel - Yasamin Borhani - Esmaeil Najafi
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.9.5