Toward Foundation Models for Online Complex Event Detection in CPS-IoT: A Case Study

• URL: http://arxiv.org/abs/2503.12282v2
• Date: Fri, 25 Apr 2025 19:51:34 GMT
• Title: Toward Foundation Models for Online Complex Event Detection in CPS-IoT: A Case Study
• Authors: Liying Han, Gaofeng Dong, Xiaomin Ouyang, Lance Kaplan, Federico Cerutti, Mani Srivastava,
• Abstract summary: Complex events (CEs) play a crucial role in CPS-IoT applications, enabling high-level decision-making.<n>Most existing models on short-span perception tasks, lacking the long-term reasoning required for CE detection.<n>This work explores CE detection as a case study for CPS-IoT foundation models capable of long-term reasoning.
• Score: 3.651233766923452
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 existing models focus on short-span perception tasks, lacking the long-term reasoning required for CE detection. CEs consist of sequences of short-time atomic events (AEs) governed by spatiotemporal dependencies. Detecting them is difficult due to long, noisy sensor data and the challenge of filtering out irrelevant AEs while capturing meaningful patterns. This work explores CE detection as a case study for CPS-IoT foundation models capable of long-term reasoning. We evaluate three approaches: (1) leveraging large language models (LLMs), (2) employing various neural architectures that learn CE rules from data, and (3) adopting a neurosymbolic approach that integrates neural models with symbolic engines embedding human knowledge. Our results show that the state-space model, Mamba, which belongs to the second category, outperforms all methods in accuracy and generalization to longer, unseen sensor traces. These findings suggest that state-space models could be a strong backbone for CPS-IoT foundation models for long-span reasoning tasks.

Related papers

• NARCE: A Mamba-Based Neural Algorithmic Reasoner Framework for Online Complex Event Detection [3.651233766923452]
  Current machine learning models excel in short-span perception tasks but struggle to derive high-level insights from long-term observation.<n>We propose NARCE, a framework that combines Neural Algorithmic Reasoning (NAR) and mapping sensor inputs to these rules via an adapter.<n>Our results show that NARCE outperforms baselines in generalization, to unseen and longer sensor data, and data efficiency.
  arXiv  Detail & Related papers  (2025-02-11T04:34:53Z)
• CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attention [53.539020807256904]
  We introduce a Compact for Representations of Brain Oscillations using alternating attention (CEReBrO)<n>Our tokenization scheme represents EEG signals at a per-channel patch.<n>We propose an alternating attention mechanism that jointly models intra-channel temporal dynamics and inter-channel spatial correlations, achieving 2x speed improvement with 6x less memory required compared to standard self-attention.
  arXiv  Detail & Related papers  (2025-01-18T21:44:38Z)
• A Reliable Framework for Human-in-the-Loop Anomaly Detection in Time Series [17.08674819906415]
  We introduce HILAD, a novel framework designed to foster a dynamic and bidirectional collaboration between humans and AI. Through our visual interface, HILAD empowers domain experts to detect, interpret, and correct unexpected model behaviors at scale.
  arXiv  Detail & Related papers  (2024-05-06T07:44:07Z)
• An Empirical Evaluation of Neural and Neuro-symbolic Approaches to Real-time Multimodal Complex Event Detection [5.803352384948482]
  Traditional end-to-end neural architectures struggle with long-duration events due to limited context sizes and reasoning capabilities. Recent advances in neuro-symbolic methods, which integrate neural and symbolic models leveraging human knowledge, promise improved performance with less data. This study addresses the gap in understanding these approaches' effectiveness in complex event detection (CED) We investigate neural and neuro-symbolic architectures' performance in a multimodal CED task, analyzing IMU and acoustic data streams to recognize CE patterns.
  arXiv  Detail & Related papers  (2024-02-17T23:34:50Z)
• TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling [54.97005925277638]
  The identification of sensory cues associated with potential opportunities and dangers is frequently complicated by unrelated events that separate useful cues by long delays. It remains a challenging task for state-of-the-art spiking neural networks (SNNs) to establish long-term temporal dependency between distant cues. We propose a novel biologically inspired Two-Compartment Leaky Integrate-and-Fire spiking neuron model, dubbed TC-LIF.
  arXiv  Detail & Related papers  (2023-08-25T08:54:41Z)
• Robustness and Generalization Performance of Deep Learning Models on Cyber-Physical Systems: A Comparative Study [71.84852429039881]
  Investigation focuses on the models' ability to handle a range of perturbations, such as sensor faults and noise. We test the generalization and transfer learning capabilities of these models by exposing them to out-of-distribution (OOD) samples.
  arXiv  Detail & Related papers  (2023-06-13T12:43:59Z)
• On a Uniform Causality Model for Industrial Automation [61.303828551910634]
  A Uniform Causality Model for various application areas of industrial automation is proposed. The resulting model describes the behavior of Cyber-Physical Systems mathematically. It is shown that the model can work as a basis for the application of new approaches in industrial automation that focus on machine learning.
  arXiv  Detail & Related papers  (2022-09-20T11:23:51Z)
• Leveraging the structure of dynamical systems for data-driven modeling [111.45324708884813]
  We consider the impact of the training set and its structure on the quality of the long-term prediction. We show how an informed design of the training set, based on invariants of the system and the structure of the underlying attractor, significantly improves the resulting models.
  arXiv  Detail & Related papers  (2021-12-15T20:09:20Z)
• A Comprehensive Study on Temporal Modeling for Online Action Detection [50.558313106389335]
  Online action detection (OAD) is a practical yet challenging task, which has attracted increasing attention in recent years. This paper aims to provide a comprehensive study on temporal modeling for OAD including four meta types of temporal modeling methods. We present several hybrid temporal modeling methods, which outperform the recent state-of-the-art methods with sizable margins on THUMOS-14 and TVSeries.
  arXiv  Detail & Related papers  (2020-01-21T13:12:58Z)
• Cross-scale Attention Model for Acoustic Event Classification [45.15898265162008]
  We propose a cross-scale attention (CSA) model, which explicitly integrates features from different scales to form the final representation. We show that the proposed CSA model can effectively improve the performance of current state-of-the-art deep learning algorithms.
  arXiv  Detail & Related papers  (2019-12-27T07:28:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.