Generative Pretrained Embedding and Hierarchical Irregular Time Series Representation for Daily Living Activity Recognition

TL;DR

This paper introduces a hierarchical Transformer-based architecture with pretrained embeddings and temporal features for improved daily activity recognition in smart homes, outperforming previous state-of-the-art methods.

Contribution

It proposes a novel GPT-inspired hierarchical model utilizing Transformer decoder embeddings and temporal data for ambient sensor-based activity recognition, demonstrating superior performance.

Findings

Transformer decoder embeddings outperform ELMo in classification accuracy

Hierarchical structure enhances recognition of activity dependencies

Temporal embedding improves time-sensitive activity classification

Abstract

Within the evolving landscape of smart homes, the precise recognition of daily living activities using ambient sensor data stands paramount. This paper not only aims to bolster existing algorithms by evaluating two distinct pretrained embeddings suited for ambient sensor activations but also introduces a novel hierarchical architecture. We delve into an architecture anchored on Transformer Decoder-based pre-trained embeddings, reminiscent of the GPT design, and contrast it with the previously established state-of-the-art (SOTA) ELMo embeddings for ambient sensors. Our proposed hierarchical structure leverages the strengths of each pre-trained embedding, enabling the discernment of activity dependencies and sequence order, thereby enhancing classification precision. To further refine recognition, we incorporate into our proposed architecture an hour-of-the-day embedding. Empirical evaluations underscore the preeminence of the Transformer Decoder embedding in classification endeavors. Additionally, our innovative hierarchical design significantly bolsters the efficacy of both pre-trained embeddings, notably in capturing inter-activity nuances. The integration of temporal aspects subtly but distinctively augments classification, especially for time-sensitive activities. In conclusion, our GPT-inspired hierarchical approach, infused with temporal insights, outshines the SOTA ELMo benchmark.