Towards Causally Interpretable Wi-Fi CSI-Based Human Activity Recognition with Discrete Latent Compression and LTL Rule Extraction

2026-04-24

AI Summary

This work addresses the limitations of existing Wi-Fi channel state information (CSI)-based human activity recognition (HAR) approaches—namely, their lack of causal interpretability, limited symbolic controllability, and difficulty in handling high-dimensional raw signals—by proposing the CHARL-TRE method. CHARL-TRE first compresses CSI into discrete latent representations using a capacity-controlled categorical variational autoencoder integrated with Gumbel-Softmax, then constructs a purely symbolic, deterministic classifier through causal discovery and linear temporal logic (LTL) rule extraction. This approach uniquely combines unsupervised discrete representation learning with LTL-based reasoning, eliminating the need for end-to-end training while enabling antenna-level rule fusion and structured multi-antenna integration. The method achieves competitive recognition performance while preserving explicit temporal dynamics and causal structures, thereby demonstrating the efficacy of symbolic classification in wireless HAR.

Technology Category

• Cognitive Modeling & Cognitive Systems: Symbolic Representations
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Models for Web evolution

Abstract

We address Human Activity Recognition (HAR) utilizing Wi-Fi Channel State Information (CSI) under the joint requirements of causal interpretability, symbolic controllability, and direct operation on high-dimensional raw signals. Deep neural models achieve strong predictive performance on CSI-based HAR (CHAR), yet rely on continuous latent representations that are opaque and difficult to modify; purely symbolic approaches, in contrast, cannot process raw CSI streams. We propose a fully automatic and strictly decoupled pipeline in which CSI magnitude windows are compressed by a categorical variational autoencoder with Gumbel-Softmax latent variables under a capacity-controlled objective, yielding a compact discrete representation. The encoder is then frozen and used as a deterministic mapping to one-hot latent trajectories. Causal discovery is performed on these trajectories to estimate class-conditional temporal dependency graphs. Statistically supported lagged dependencies are translated into Linear Temporal Logic (LTL) rules, producing a fully symbolic and deterministic classifier based solely on rule evaluation and aggregation, without any learned discriminative head. Because rules are defined over discrete latent variables, antenna-specific rule sets can in principle be combined at the symbolic level, enabling structured multi-antenna fusion without retraining the encoder. Results from CHAR Latent Temporal Rule Extraction (CHARL-TRE) indicate competitive performance while preserving explicit temporal and causal structure, showing that deterministic symbolic classification grounded in unsupervised discrete latent representations constitutes a viable alternative to end-to-end black-box models for wireless HAR.

Problem

• Human Activity Recognition
• Wi-Fi CSI
• Causal Interpretability
• Symbolic Controllability
• High-dimensional Raw Signals

Innovation

• discrete latent compression
• causal interpretability
• Linear Temporal Logic (LTL)
• symbolic classification
• Wi-Fi CSI-based HAR