SensorQA: A Question Answering Benchmark for Daily-Life Monitoring

TL;DR

SensorQA introduces a novel human-annotated question-answering dataset for long-term sensor data, enabling better human understanding and interaction with daily-life monitoring systems, and benchmarks current AI model performance.

Contribution

This paper presents the first human-created QA dataset for sensor data, along with benchmarks and evaluations on model performance and efficiency.

Findings

Current models underperform on SensorQA tasks.

Significant gap exists between model capabilities and optimal QA performance.

Benchmark results highlight the need for new model development.

Abstract

With the rapid growth in sensor data, effectively interpreting and interfacing with these data in a human-understandable way has become crucial. While existing research primarily focuses on learning classification models, fewer studies have explored how end users can actively extract useful insights from sensor data, often hindered by the lack of a proper dataset. To address this gap, we introduce SensorQA, the first human-created question-answering (QA) dataset for long-term time-series sensor data for daily life monitoring. SensorQA is created by human workers and includes 5.6K diverse and practical queries that reflect genuine human interests, paired with accurate answers derived from sensor data. We further establish benchmarks for state-of-the-art AI models on this dataset and evaluate their performance on typical edge devices. Our results reveal a gap between current models and optimal QA performance and efficiency, highlighting the need for new contributions. The dataset and code are available at: https://github.com/benjamin-reichman/SensorQA.