Activity2Vec: Learning ADL Embeddings from Sensor Data with a Sequence-to-Sequence Model

TL;DR

This paper introduces Activity2Vec, a sequence-to-sequence model that automatically learns universal features from sensor data for activity recognition and fall detection, reducing the need for manual feature engineering.

Contribution

It proposes a novel seq2seq approach for automatic feature extraction applicable across various time series human activity datasets, enhancing semi-supervised learning.

Findings

Learned features improve activity recognition accuracy

Features are applicable across different sensor types

Reduces manual feature engineering effort

Abstract

Recognizing activities of daily living (ADLs) plays an essential role in analyzing human health and behavior. The widespread availability of sensors implanted in homes, smartphones, and smart watches have engendered collection of big datasets that reflect human behavior. To obtain a machine learning model based on these data,researchers have developed multiple feature extraction methods. In this study, we investigate a method for automatically extracting universal and meaningful features that are applicable across similar time series-based learning tasks such as activity recognition and fall detection. We propose creating a sequence-to-sequence (seq2seq) model to perform this feature learning. Beside avoiding feature engineering, the meaningful features learned by the seq2seq model can also be utilized for semi-supervised learning. We evaluate both of these benefits on datasets collected from wearable and ambient sensors.