HyperDetect: A Real-Time Hyperdimensional Solution For Intrusion Detection in IoT Networks
Network-based security has emerged as an increasingly critical challenge in the domain of
the Internet of Things (IoT). A number of network intrusion detection systems (NIDS), typically …
the Internet of Things (IoT). A number of network intrusion detection systems (NIDS), typically …
DOMINO: Domain-invariant Hyperdimensional classification for multi-sensor time series data
With the rapid evolution of the Internet of Things, many real-world applications utilize
heterogeneously connected sensors to capture time-series information. Edge-based …
heterogeneously connected sensors to capture time-series information. Edge-based …
Robust and scalable Hyperdimensional computing with brain-like neural adaptations
J Wang, MAA Faruque - arXiv preprint arXiv:2311.07705, 2023 - arxiv.org
The Internet of Things (IoT) has facilitated many applications utilizing edge-based machine
learning (ML) methods to analyze locally collected data. Unfortunately, popular ML …
learning (ML) methods to analyze locally collected data. Unfortunately, popular ML …
SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classification
J Wang, M Al Faruque - Proceedings of the 61st ACM/IEEE Design …, 2024 - dl.acm.org
Many real-world applications of the Internet of Things (IoT) employ machine learning (ML)
algorithms to analyze time series information collected by interconnected sensors. However …
algorithms to analyze time series information collected by interconnected sensors. However …
DEBUG-HD: Debugging TinyML models on-device using Hyper-Dimensional computing
NP Ghanathe, SJE Wilton - arXiv preprint arXiv:2411.10692, 2024 - arxiv.org
TinyML models often operate in remote, dynamic environments without cloud connectivity,
making them prone to failures. Ensuring reliability in such scenarios requires not only …
making them prone to failures. Ensuring reliability in such scenarios requires not only …
Enhanced Detection of Transdermal Alcohol Levels Using Hyperdimensional Computing on Embedded Devices
Alcohol consumption has a significant impact on individuals' health, with even more
pronounced consequences when consumption becomes excessive. One approach to …
pronounced consequences when consumption becomes excessive. One approach to …
Transformer-Based Contrastive Meta-Learning For Low-Resource Generalizable Activity Recognition
J Wang, MAA Faruque - arXiv preprint arXiv:2412.20290, 2024 - arxiv.org
Deep learning has been widely adopted for human activity recognition (HAR) while
generalizing a trained model across diverse users and scenarios remains challenging due …
generalizing a trained model across diverse users and scenarios remains challenging due …