9 papers
Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signals
Tomoyoshi Kimura, Denizhan Kara, Jinyang Li +6
Internet of Things (IoT) systems continuously collect heterogeneous sensing signals from ubiquitous sensors to support intelligent applications such as human activity analysis, emo…
Tracking without Seeing: Geospatial Inference using Encrypted Traffic from Distributed Nodes
Sadik Yagiz Yetim, Gaofeng Dong, Isaac-Neil Zanoria +5
Accurate observation of dynamic environments traditionally relies on synthesizing raw, signal-level information from multiple distributed sensors. This work investigates an alterna…
Understanding the Theoretical Foundations of Deep Neural Networks through Differential Equations
Hongjue Zhao, Yizhuo Chen, Yuchen Wang +4
Deep neural networks (DNNs) have achieved remarkable empirical success, yet the absence of a principled theoretical foundation continues to hinder their systematic development. In…
CSRAP: Enhanced Canvas Attention Scheduling for Real-Time Mission Critical Perception
Md Iftekharul Islam Sakib, Yigong Hu, Tarek Abdelzaher
Real-time perception on edge platforms faces a core challenge: executing high-resolution object detection under stringent latency constraints on limited computing resources. Canvas…
PASS: Private Attributes Protection with Stochastic Data Substitution
Yizhuo Chen, Chun-Fu, Chen +3
The growing Machine Learning (ML) services require extensive collections of user data, which may inadvertently include people's private information irrelevant to the services. Vari…
SPAR: Self-supervised Placement-Aware Representation Learning for Distributed Sensing
Yizhuo Chen, Tianchen Wang, You Lyu +7
We present SPAR, a framework for self-supervised placement-aware representation learning in distributed sensing. Distributed sensing spans applications where multiple spatially dis…
InfoMAE: Pair-Efficient Cross-Modal Alignment for Multimodal Time-Series Sensing Signals
Tomoyoshi Kimura, Xinlin Li, Osama Hanna +10
Standard multimodal self-supervised learning (SSL) algorithms regard cross-modal synchronization as implicit supervisory labels during pretraining, thus posing high requirements on…
MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective
Yizhuo Chen, Chun-Fu Chen, Hsiang Hsu +3
The growing richness of large-scale datasets has been crucial in driving the rapid advancement and wide adoption of machine learning technologies. The massive collection and usage…
On the Efficiency and Robustness of Vibration-based Foundation Models for IoT Sensing: A Case Study
Tomoyoshi Kimura, Jinyang Li, Tianshi Wang +9
This paper demonstrates the potential of vibration-based Foundation Models (FMs), pre-trained with unlabeled sensing data, to improve the robustness of run-time inference in (a cla…