Estimation model for lower extremity strength using gait movement measured with inertial sensor considering differences of sex and environment

Shiotani, Maho; Hiyama, Takahiro; Sato, Yoshikuni; Ozawa, Jun; Kobayashi, Yoshio

doi:10.1109/embc44109.2020.9176384

Cited by 2 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the study that collected data of daily TV use by an elderly woman for 10 years suggested a trend of correlation between television usage and social activities [8]. Meanwhile, some researchers used wearable sensors to estimate lower limb muscle strength [9] or evaluated the extent of frailty [10]. In addition, models for detecting danger pose [11] and anomalies of health data [12] were constructed in previous studies.…”

Section: Introductionmentioning

confidence: 99%

Research on an Anomaly Detection Method for Physical Condition Change of Elderly People in Care Facilities

Shiotani

Yamaguchi

2022

ABE

View full text Add to dashboard Cite

Currently, the shortage of care workers for the elderly has become a big problem, and more streamlined care operations are needed. In care facilities, care workers are required to use their subjective experience to detect anomalies in physical condition of care receivers, including serious or insigni cant deterioration or behavioral and psychological symptoms of dementia, which can decrease the work ef ciency. Therefore, we aim to create a model using objective data for detecting anomalies in physical condition. In this study, data from 13 subjects in a care facility were collected, and isolation forest models were constructed for each subject. The subjectʼs anomalies in physical condition were documented in a care record by a nurse and used as reference for model evaluation. Recall and speci city were used to evaluate the model, expressed as the percentage of detection success for abnormal or normal conditions. Data collected for 1 to 60 days were used to train the isolation models, and the relationship between the amount of training data and model performance was simulated. Heart rate, respiratory rate, and time of getting out of bed were collected from a sensor placed on the subjectʼs bed and used as the model features. In addition, dietary intake information was collected from the care record. Analysis of the evaluation results showed recall and speci city of 45.6 ± 46.7% and 83.88 ± 6.06%, respectively, for the model constructed using training data of 60 days. For future studies, we will continue to collect data and increase the number of participants to improve the robustness and accuracy of the proposed anomaly detection system.

show abstract