Machine Learning-Based Knock Localization Using Piezoelectric Array Signals for Human-to-Things Interfaces
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study proposes a machine learning-based knock localization system for human-to-thing interfaces employingelastic wave signals captured by a piezoelectric array. Eight sensors were symmetrically arranged on a plastic plate, and the relativearrival-time differences of the elastic waves were extracted as the primary features for classification. Unlike conventional approaches,which rely on prior knowledge of elastic wave propagation speed and assume material homogeneity, the proposed method overcomesthese limitations and enables real-time applicability through a simplified pipeline. Knock data were collected from nine spatial zonesunder both intra-subject and inter-subject conditions. In the intra-subject evaluation, where training and testing were conducted ondata from the same subject, the ensemble classifier achieved perfect performance across all metrics (accuracy, precision, recall, andF1 score = 1). When evaluated on data from three previously unseen subjects, the model maintained high accuracy (accuracy =0.957), demonstrating strong generalization to user variability. These findings confirm the robustness and practicality of the proposedsystem, particularly in application domains where conventional touch sensors are unsuitable, such as in smart windows and automotivepanels.
Abstract
This study proposes a machine learning-based knock localization system for human-to-thing interfaces employingelastic wave signals captured by a piezoelectric array. Eight sensors were symmetrically arranged on a plastic plate, and the relativearrival-time differences of the elastic waves were extracted as the primary features for classification. Unlike conventional approaches,which rely on prior knowledge of elastic wave propagation speed and assume material homogeneity, the proposed method overcomesthese limitations and enables real-time applicability through a simplified pipeline. Knock data were collected from nine spatial zonesunder both intra-subject and inter-subject conditions. In the intra-subject evaluation, where training and testing were conducted ondata from the same subject, the ensemble classifier achieved perfect performance across all metrics (accuracy, precision, recall, andF1 score = 1). When evaluated on data from three previously unseen subjects, the model maintained high accuracy (accuracy =0.957), demonstrating strong generalization to user variability. These findings confirm the robustness and practicality of the proposedsystem, particularly in application domains where conventional touch sensors are unsuitable, such as in smart windows and automotivepanels.