8 papers
Towards Causally Interpretable Wi-Fi CSI-Based Human Activity Recognition with Discrete Latent Compression and LTL Rule Extraction
Luca Cotti, Luca Lavazza, Marco Cominelli +10
We address Human Activity Recognition (HAR) utilizing Wi-Fi Channel State Information (CSI) under the joint requirements of causal interpretability, symbolic controllability, and d…
GSRF: Complex-Valued 3D Gaussian Splatting for Efficient Radio-Frequency Data Synthesis
Kang Yang, Gaofeng Dong, Sijie Ji +2
Synthesizing radio-frequency (RF) data given the transmitter and receiver positions, e.g., received signal strength indicator (RSSI), is critical for wireless networking and sensin…
NAROCE: A Neural Algorithmic Reasoner Framework for Online Complex Event Detection
Liying Han, Gaofeng Dong, Xiaomin Ouyang +3
Modern machine learning models excel at detecting individual actions, objects, or scene attributes from short, local observations. However, many real-world tasks, such as in smart…
Can Time-Series Foundation Models Perform Building Energy Management Tasks?
Ozan Baris Mulayim, Pengrui Quan, Liying Han +4
Building energy management (BEM) tasks require processing and learning from a variety of time-series data. Existing solutions rely on bespoke task- and data-specific models to perf…
Toward Foundation Models for Online Complex Event Detection in CPS-IoT: A Case Study
Liying Han, Gaofeng Dong, Xiaomin Ouyang +3
Complex events (CEs) play a crucial role in CPS-IoT applications, enabling high-level decision-making in domains such as smart monitoring and autonomous systems. However, most exis…
AutoLife: Automatic Life Journaling with Smartphones and LLMs
Huatao Xu, Panrong Tong, Mo Li +1
This paper introduces a novel mobile sensing application - life journaling - designed to generate semantic descriptions of users' daily lives. We present AutoLife, an automatic lif…