Towards Causally Interpretable Wi-Fi CSI-Based Human Activity Recognition with Discrete Latent Compression and LTL Rule Extraction
Towards Causally Interpretable Wi-Fi CSI-Based Human Activity Recognition with Discrete Latent Compression and LTL Rule Extraction
Title: Towards Causally Interpretable Wi-Fi CSI-Based Human Activity Recognition with Discrete Latent Compression and LTL Rule Extraction 标题： 基于离散潜在压缩与线性时序逻辑（LTL）规则提取的因果可解释 Wi-Fi CSI 人体行为识别
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.
摘要： 我们针对人体行为识别（HAR）任务，利用 Wi-Fi 信道状态信息（CSI），同时满足因果可解释性、符号可控性以及对高维原始信号直接操作的需求。深度神经网络模型在基于 CSI 的行为识别（CHAR）中表现出强大的预测性能，但它们依赖于不透明且难以修改的连续潜在表示；相比之下，纯符号方法则无法处理原始 CSI 数据流。
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.
我们提出了一种全自动且严格解耦的流水线：通过带有 Gumbel-Softmax 潜在变量的分类变分自编码器，在容量受控的目标下对 CSI 幅度窗口进行压缩，从而产生紧凑的离散表示。随后，编码器被冻结并用作到独热（one-hot）潜在轨迹的确定性映射。我们对这些轨迹进行因果发现，以估计类条件下的时间依赖图。
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.
具有统计学支持的滞后依赖关系被转化为线性时序逻辑（LTL）规则，从而构建出一个完全符号化且确定性的分类器。该分类器仅基于规则的评估与聚合，无需任何学习型的判别头。由于规则定义在离散潜在变量之上，原则上可以在符号层面组合特定于天线的规则集，从而在无需重新训练编码器的情况下实现结构化的多天线融合。
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.
CHAR 潜在时序规则提取（CHARL-TRE）的结果表明，该方法在保持明确的时间和因果结构的同时，具备极具竞争力的性能。这证明了基于无监督离散潜在表示的确定性符号分类，是无线 HAR 领域中替代端到端黑盒模型的一种可行方案。