姿势和身体活动检测：传感器数量和特征类型的影响。
Posture and Physical Activity Detection: Impact of Number of Sensors and Feature Type.
机构信息
Department of Electrical and Computer Engineering, Northeastern University, Boston, MA.
Bouvé College of Health Sciences, Northeastern University, Boston, MA.
出版信息
Med Sci Sports Exerc. 2020 Aug;52(8):1834-1845. doi: 10.1249/MSS.0000000000002306.
UNLABELLED
Studies using wearable sensors to measure posture, physical activity (PA), and sedentary behavior typically use a single sensor worn on the ankle, thigh, wrist, or hip. Although the use of single sensors may be convenient, using multiple sensors is becoming more practical as sensors miniaturize.
PURPOSE
We evaluated the effect of single-site versus multisite motion sensing at seven body locations (both ankles, wrists, hips, and dominant thigh) on the detection of physical behavior recognition using a machine learning algorithm. We also explored the effect of using orientation versus orientation-invariant features on performance.
METHODS
Performance (F1 score) of PA and posture recognition was evaluated using leave-one-subject-out cross-validation on a 42-participant data set containing 22 physical activities with three postures (lying, sitting, and upright).
RESULTS
Posture and PA recognition models using two sensors had higher F1 scores (posture, 0.89 ± 0.06; PA, 0.53 ± 0.08) than did models using a single sensor (posture, 0.78 ± 0.11; PA, 0.43 ± 0.03). Models using two nonwrist sensors for posture recognition (F1 score, 0.93 ± 0.03) outperformed two-sensor models including one or two wrist sensors (F1 score, 0.85 ± 0.06). However, two-sensor models for PA recognition with at least one wrist sensor (F1 score, 0.60 ± 0.05) outperformed other two-sensor models (F1 score, 0.47 ± 0.02). Both posture and PA recognition F1 scores improved with more sensors (up to seven; 0.99 for posture and 0.70 for PA), but with diminishing performance returns. Models performed best when including orientation-based features.
CONCLUSIONS
Researchers measuring posture should consider multisite sensing using at least two nonwrist sensors, and researchers measuring PA should consider multisite sensing using at least one wrist sensor and one nonwrist sensor. Including orientation-based features improved both posture and PA recognition.
未加标签
使用可穿戴传感器测量姿势、身体活动 (PA) 和久坐行为的研究通常使用单个传感器，这些传感器戴在脚踝、大腿、手腕或臀部上。虽然使用单个传感器可能很方便，但随着传感器的小型化，使用多个传感器变得更加实用。
目的
我们评估了在七个身体部位（两个脚踝、手腕、臀部和优势大腿）使用单点与多点运动感应对使用机器学习算法进行身体行为识别的影响。我们还探讨了使用定向特征与不变向特征对性能的影响。
方法
使用 42 名参与者的数据集中的 22 项身体活动和三种姿势（躺着、坐着和直立）进行的一项单主体外验证，评估 PA 和姿势识别的性能（F1 分数）。
结果
使用两个传感器的姿势和 PA 识别模型的 F1 分数较高（姿势，0.89 ± 0.06；PA，0.53 ± 0.08），而使用单个传感器的模型的 F1 分数较低（姿势，0.78 ± 0.11；PA，0.43 ± 0.03）。用于姿势识别的两个非手腕传感器的模型（F1 分数，0.93 ± 0.03）优于包括一个或两个手腕传感器的两个传感器模型（F1 分数，0.85 ± 0.06）。然而，具有至少一个手腕传感器的两个传感器模型用于 PA 识别（F1 分数，0.60 ± 0.05）优于其他两个传感器模型（F1 分数，0.47 ± 0.02）。随着传感器数量的增加（最多七个；0.99 用于姿势，0.70 用于 PA），姿势和 PA 识别的 F1 分数均有所提高，但性能回报却逐渐减少。当包含基于方向的特征时，模型的性能最佳。
结论
测量姿势的研究人员应考虑使用至少两个非手腕传感器进行多点感应，而测量 PA 的研究人员应考虑使用至少一个手腕传感器和一个非手腕传感器进行多点感应。包含基于方向的特征可提高姿势和 PA 识别的性能。
Zotero 插件