SEGALL: A Unified Active Learning Framework for Wireless Sensing Data Segmentation
Open Access
- 3 September 2025
- journal article
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 9 (3) , 1-27
Abstract
Wireless sensing has emerged as a promising technology due to its inherently privacy-preserving and contactless characteristics, enabling a wide range of applications. Until now, a major challenge in translating research into real-world applications is achieving accurate data segmentation. This process involves identifying the start and end points of target activities within complex and extended time-series sensing data, forming the foundation for subsequent inference tasks. However, existing segmentation techniques in wireless sensing are often constrained to a specific signal type and exhibit limited performance in distinguishing fine-grained activities, particularly when faced with similar background signals. To address these issues, we present SegALL, a unified segmentation framework capable of processing diverse signals. By leveraging a lightweight, signal-independent deep learning architecture coupled with active learning, SegALL enables accurate segmentation for fine-grained activities, even under interference from activities with similar characteristics. Experimental evaluations on both synthetic and real-world datasets demonstrate that SegALL significantly improves segmentation reliability across various modalities, including IMU, Wi-Fi, and mmWave signals. For example, it achieves a segmentation accuracy of 91.12% for mmWave signals, outperforming previous segmentation solutions that achieved 70.50%. Furthermore, SegALL reduces manual labeling effort by 40.15% and maintains a lightweight computational cost, making it suitable for deployment on edge devices such as the Raspberry Pi.Keywords
Funding Information
- CityU (11206023)
- National Key R&D Program Project (2024YFE0203700)
- CRF (C1045-23G)
- ECS CityU (21216822)
- NSFC (62272317)
- Shenzhen Science and Technology Program (JCYJ20220531103402006)
This publication has 52 references indexed in Scilit:
- Active learning by query by committee with robust divergencesInformation Geometry, 2022
- Fully Convolutional Networks for Panoptic Segmentation2021
- Learning Loss for Active Learning2019
- Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression2019
- Enhancing activity recognition using CPD-based activity segmentationPervasive and Mobile Computing, 2019
- Dynamic Video Segmentation Network2018
- A smart segmentation technique towards improved infrequent non-speech gestural activity recognition modelPervasive and Mobile Computing, 2017
- Dynamic detection of window starting positions and its implementation within an activity recognition frameworkJournal of Biomedical Informatics, 2016
- Fully convolutional networks for semantic segmentation2015
- Multi-Class Active Learning by Uncertainty Sampling with Diversity MaximizationInternational Journal of Computer Vision, 2014