2026-07-26T19:31:00Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:23605 2025-07-07T04:35:09Z ddc:004 open_access

Faster Classification of Time-Series Input Streams (Artifact) Agrawal, Kunal Baruah, Sanjoy Guo, Zhishan Li, Jing Reghenzani, Federico Yang, Kecheng Zhao, Jinhao Classification Deep Learning Sensor data streams IDK classifiers Deep learning–based classifiers are widely used for perception in autonomous Cyber-Physical Systems (CPS’s). However, such classifiers rarely offer guarantees of perfect accuracy while being optimized for efficiency. To support safety-critical perception, ensembles of multiple different classifiers working in concert are typically used. Since CPS’s interact with the physical world continuously, it is not unreasonable to expect dependencies among successive inputs in a stream of sensor data. Prior work introduced a classification technique that leverages these inter-input dependencies to reduce the average time to successful classification using classifier ensembles. In this paper, we propose generalizations to this classification technique, both in the improved generation of classifier cascades and the modeling of temporal dependencies. We demonstrate, through theoretical analysis and numerical evaluation, that our approach achieves further reductions in average classification latency compared to the prior methods. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Kunal Agrawal and Sanjoy Baruah and Zhishan Guo and Jing Li and Federico Reghenzani and Kecheng Yang and Jinhao Zhao 2025 Is Part Of DARTS, Volume 11, Issue 1, Special Issue of the 37th Euromicro Conference on Real-Time Systems (ECRTS 2025) Article Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/DARTS.11.1.4 urn:nbn:de:0030-drops-236057 https://drops.dagstuhl.de/entities/document/10.4230/DARTS.11.1.4 eng https://creativecommons.org/licenses/by/4.0/legalcode