This paper proposes an automatic fall detector in a wearable device that can reduce risks by detecting falls and promptly alerting caregivers. For this purpose, we propose cluster-analysis-based user-adaptive fall detection using a fusion of heart rate sensor and accelerometer. The objectives of the proposed fall detector are to have high accuracy with a low-complexity model regardless of diverse conditions. To meet the objectives, we propose the best 13-dimensional feature subset by using feature selection. In addition, we verify the performance increment of combining a heart rate sensor with an accelerometer and the effectiveness of the cluster-analysis-based anomaly detection. We also show the effectiveness of the user-adaptive method when using both heart rate and acceleration signals that were hardly covered in other papers. Finally, we prove that the performance of the proposed fall detector achieves is better than that of recent user-adaptive and user-independent approaches. This study is the first attempt to demonstrate the merits of the user-adaptive approach using a combination of heart rate and acceleration signals to detect falls. Moreover, this paper also contributes to fall detection area by providing the data we collected.

Jang YH, et al. J Vet Sci. 2008 Jun;9(2):177-181. https://doi.org/10.4142/jvs.2008.9.2.177

This study proposes a monitoring system to prevent falls from height (FFH) accidents in construction sites. In our previous work, a method was proposed for recognizing the fastening state of the safety hook based on the motion similarity between two Inertial Measurement Unit (IMU) sensors, but its performance was limited to 90.64% Youden's Index (YI). This study introduces a safety hook monitoring system that achieves better performances by utilizing a deep siamese neural network based-model to develop valid feature representations, which enhance performances. Our proposed approach achieves 97.69% YI, surpassing previous works in recognition performances.

관성 측정 장치를 활용한 다양한 동작 인식에서 주요한 역할을 하는 동작 구간 탐지를 위해 다변량 에너지 기반 방법론을 제안한다. 다변량 에너지 기반 방법론의 핵심인 다변량 에너지의 구성을 위해, 기계학습의 특징점 선정 기법을 활용해 최적의 가속도 특징벡터를 선정한다. 기존 문헌에서 사용된 6개 특징의 시계열 데이터에 초점을 맞추어 8차까지 증가시키며 이들을 결합 후, 각 999개와 99,999개의 특징 후보에 대해 동작구간과 비동작구간의 변별력을 4가지 목적 함수로 검증한다. 최종 선정된 2가지 후보에 대해 다층퍼셉트론과 방사형 기저함수를 사용하여 최종 검출 성능을 확인하고, 4가지 기존 방법론과 성능을 비교하여 제안하는 방법의 우수성을 검증한다. 가속도와 가속도의 1차/ 2차 미분의 절대값으로 구성되는 협소한 특징점 공간과 비선형 방사형 기저함수가 결합될 때 가장 훌륭한 성능을 보여준다.