AHCI RESEARCH GROUP
Publications
Papers published in international journals,
proceedings of conferences, workshops and books.
OUR RESEARCH
Scientific Publications
How to
Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
2025
Wang, Z.; Aris, A.; Zhang, P.
Mobile-Driven Deep Learning Algorithm for Personalized Clothing Design Using Multi-Feature Attributes Journal Article
In: International Journal of Interactive Mobile Technologies, vol. 19, no. 18, pp. 146–160, 2025, ISSN: 18657923 (ISSN), (Publisher: International Federation of Engineering Education Societies (IFEES)).
Abstract | Links | BibTeX | Tags: Clothing design, Convolutional Neural Networks, Data privacy, Data visualization, Deep learning, E-Learning, Electronic commerce, Fashion design, Feature attributes, Hosiery manufacture, Learning algorithms, Learning platform, Learning systems, Mobile Learning, Mobile learning platform, Mobile-driven deep learning, Multi-feature attribute, multi-feature attributes, Multifeatures, Personalized clothing design, Personalized clothings, StyleFitNet, Textiles, Virtual Reality
@article{wang_mobile-driven_2025,
title = {Mobile-Driven Deep Learning Algorithm for Personalized Clothing Design Using Multi-Feature Attributes},
author = {Z. Wang and A. Aris and P. Zhang},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105017860148&doi=10.3991%2Fijim.v19i18.57239&partnerID=40&md5=de3ca359dd178d8ea59cf8da73a9c486},
doi = {10.3991/ijim.v19i18.57239},
issn = {18657923 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {International Journal of Interactive Mobile Technologies},
volume = {19},
number = {18},
pages = {146–160},
abstract = {Personalized fashion recommendation systems face significant challenges in balancing accurate style prediction, real-time mobile performance, and user privacy compliance. This study presents StyleFitNet, a novel mobile-driven deep learning framework that integrates multiple user feature attributes, including body measurements, fabric preferences, and temporal style evolution, to generate personalized clothing designs. The hybrid convolutional neural networks (CNNs)-recurrent neural networks (RNNs) architecture addresses key limitations of conventional recommendation systems by simultaneously processing spatial features and sequential preference patterns. A comprehensive evaluation demonstrates the system’s superiority in recommendation accuracy, design diversity, and user satisfaction compared to existing approaches. The implementation features GDPR-compliant data handling and a 3D virtual fitting room, significantly reducing return rates while maintaining robust privacy protections. Findings highlight the model’s ability to adapt to evolving fashion trends while preserving individual style preferences, offering both technical and business advantages for e-commerce platforms. The study concludes that StyleFitNet establishes a new standard for artificial intelligence (AI)-driven fashion recommendations, successfully merging advanced personalization with ethical data practices. Key implications include the demonstrated viability of hybrid deep learning models for mobile deployment and the importance of temporal analysis in preference modelling. Future research directions include cross-cultural validation and the integration of generative AI for enhanced visualization. © 2025 Elsevier B.V., All rights reserved.},
note = {Publisher: International Federation of Engineering Education Societies (IFEES)},
keywords = {Clothing design, Convolutional Neural Networks, Data privacy, Data visualization, Deep learning, E-Learning, Electronic commerce, Fashion design, Feature attributes, Hosiery manufacture, Learning algorithms, Learning platform, Learning systems, Mobile Learning, Mobile learning platform, Mobile-driven deep learning, Multi-feature attribute, multi-feature attributes, Multifeatures, Personalized clothing design, Personalized clothings, StyleFitNet, Textiles, Virtual Reality},
pubstate = {published},
tppubtype = {article}
}
Personalized fashion recommendation systems face significant challenges in balancing accurate style prediction, real-time mobile performance, and user privacy compliance. This study presents StyleFitNet, a novel mobile-driven deep learning framework that integrates multiple user feature attributes, including body measurements, fabric preferences, and temporal style evolution, to generate personalized clothing designs. The hybrid convolutional neural networks (CNNs)-recurrent neural networks (RNNs) architecture addresses key limitations of conventional recommendation systems by simultaneously processing spatial features and sequential preference patterns. A comprehensive evaluation demonstrates the system’s superiority in recommendation accuracy, design diversity, and user satisfaction compared to existing approaches. The implementation features GDPR-compliant data handling and a 3D virtual fitting room, significantly reducing return rates while maintaining robust privacy protections. Findings highlight the model’s ability to adapt to evolving fashion trends while preserving individual style preferences, offering both technical and business advantages for e-commerce platforms. The study concludes that StyleFitNet establishes a new standard for artificial intelligence (AI)-driven fashion recommendations, successfully merging advanced personalization with ethical data practices. Key implications include the demonstrated viability of hybrid deep learning models for mobile deployment and the importance of temporal analysis in preference modelling. Future research directions include cross-cultural validation and the integration of generative AI for enhanced visualization. © 2025 Elsevier B.V., All rights reserved.
2024
Bandara, E.; Foytik, P.; Shetty, S.; Hassanzadeh, A.
Generative-AI(with Custom-Trained Meta's Llama2 LLM), Blockchain, NFT, Federated Learning and PBOM Enabled Data Security Architecture for Metaverse on 5G/6G Environment Proceedings Article
In: Proc. - IEEE Int. Conf. Mob. Ad-Hoc Smart Syst., MASS, pp. 118–124, Institute of Electrical and Electronics Engineers Inc., 2024, ISBN: 9798350363999 (ISBN).
Abstract | Links | BibTeX | Tags: 5G, 6G, Adversarial machine learning, Bill of materials, Block-chain, Blockchain, Curricula, Data privacy, Distance education, Federated learning, Generative adversarial networks, Generative-AI, Hardware security, Llama2, LLM, Medium access control, Metaverse, Metaverses, Network Security, Nft, Non-fungible token, Personnel training, Problem oriented languages, Reference architecture, Steganography
@inproceedings{bandara_generative-aicustom-trained_2024,
title = {Generative-AI(with Custom-Trained Meta's Llama2 LLM), Blockchain, NFT, Federated Learning and PBOM Enabled Data Security Architecture for Metaverse on 5G/6G Environment},
author = {E. Bandara and P. Foytik and S. Shetty and A. Hassanzadeh},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85210243120&doi=10.1109%2FMASS62177.2024.00026&partnerID=40&md5=f40a8db565fad44ea6dca76eae709ac2},
doi = {10.1109/MASS62177.2024.00026},
isbn = {9798350363999 (ISBN)},
year = {2024},
date = {2024-01-01},
booktitle = {Proc. - IEEE Int. Conf. Mob. Ad-Hoc Smart Syst., MASS},
pages = {118–124},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The Metaverse is an integrated network of 3D virtual worlds accessible through a virtual reality headset. Its impact on data privacy and security is increasingly recognized as a major concern. There is a growing interest in developing a reference architecture that describes the four core aspects of its data: acquisition, storage, sharing, and interoperability. Establishing a secure data architecture is imperative to manage users' personal data and facilitate trusted AR/VR and AI/ML solutions within the Metaverse. This paper details a reference architecture empowered by Generative-AI, Blockchain, Federated Learning, and Non-Fungible Tokens (NFTs). Within this archi-tecture, various resource providers collaborate via the blockchain network. Handling personal user data and resource provider identities is executed through a Self-Sovereign Identity-enabled privacy-preserving framework. AR/NR devices in the Metaverse are represented as NFT tokens available for user purchase. Software updates and supply-chain verification for these devices are managed using a Software Bill of Materials (SBOM) and a Pipeline Bill of Materials (PBOM) verification system. Moreover, a custom-trained Llama2 LLM from Meta has been integrated to generate PBOMs for AR/NR devices' software updates, thereby preventing malware intrusions and data breaches. This Llama2-13B LLM has been quantized and fine-tuned using Qlora to ensure optimal performance on consumer-grade hardware. The provenance of AI/ML models used in the Metaverse is encapsu-lated as Model Card objects, allowing external parties to audit and verify them, thus mitigating adversarial learning attacks within these models. To the best of our knowledge, this is the very first research effort aimed at standardizing PBOM schemas and integrating Language Model algorithms for the generation of PBOMs. Additionally, a proposed mechanism facilitates different AI/ML providers in training their machine learning models using a privacy-preserving federated learning approach. Authorization of communications among AR/VR devices in the Metaverse is conducted through a Zero-Trust security-enabled rule engine. A system testbed has been implemented within a 5G environment, utilizing Ericsson new Radio with Open5GS 5G core. © 2024 Elsevier B.V., All rights reserved.},
keywords = {5G, 6G, Adversarial machine learning, Bill of materials, Block-chain, Blockchain, Curricula, Data privacy, Distance education, Federated learning, Generative adversarial networks, Generative-AI, Hardware security, Llama2, LLM, Medium access control, Metaverse, Metaverses, Network Security, Nft, Non-fungible token, Personnel training, Problem oriented languages, Reference architecture, Steganography},
pubstate = {published},
tppubtype = {inproceedings}
}
The Metaverse is an integrated network of 3D virtual worlds accessible through a virtual reality headset. Its impact on data privacy and security is increasingly recognized as a major concern. There is a growing interest in developing a reference architecture that describes the four core aspects of its data: acquisition, storage, sharing, and interoperability. Establishing a secure data architecture is imperative to manage users' personal data and facilitate trusted AR/VR and AI/ML solutions within the Metaverse. This paper details a reference architecture empowered by Generative-AI, Blockchain, Federated Learning, and Non-Fungible Tokens (NFTs). Within this archi-tecture, various resource providers collaborate via the blockchain network. Handling personal user data and resource provider identities is executed through a Self-Sovereign Identity-enabled privacy-preserving framework. AR/NR devices in the Metaverse are represented as NFT tokens available for user purchase. Software updates and supply-chain verification for these devices are managed using a Software Bill of Materials (SBOM) and a Pipeline Bill of Materials (PBOM) verification system. Moreover, a custom-trained Llama2 LLM from Meta has been integrated to generate PBOMs for AR/NR devices' software updates, thereby preventing malware intrusions and data breaches. This Llama2-13B LLM has been quantized and fine-tuned using Qlora to ensure optimal performance on consumer-grade hardware. The provenance of AI/ML models used in the Metaverse is encapsu-lated as Model Card objects, allowing external parties to audit and verify them, thus mitigating adversarial learning attacks within these models. To the best of our knowledge, this is the very first research effort aimed at standardizing PBOM schemas and integrating Language Model algorithms for the generation of PBOMs. Additionally, a proposed mechanism facilitates different AI/ML providers in training their machine learning models using a privacy-preserving federated learning approach. Authorization of communications among AR/VR devices in the Metaverse is conducted through a Zero-Trust security-enabled rule engine. A system testbed has been implemented within a 5G environment, utilizing Ericsson new Radio with Open5GS 5G core. © 2024 Elsevier B.V., All rights reserved.