Deep learning-based classification with improved time resolution for physical activities of children.
Deep learning-based classification with improved time resolution for physical activities of children.
复制标题
作者：
Jang Y;Kim S;Kim K;Lee D
超重和肥胖人口比例在短时间内大幅增加，最终导致全球肥胖趋势达到流行病的程度。超重和肥胖是严重的问题，尤其是对于儿童而言。这是因为，与非肥胖儿童相比，肥胖儿童的肥胖风险是成人的两倍。如今，有许多维持热量平衡的方法。然而，这些方法并不适用于儿童。在这项研究中，提出了一种使用卷积神经网络（CNN）帮助儿童监控其活动的新方法，适用于需要高精度的实时场景。共有 136 名参与者（86 名男孩和 50 名女孩），年龄在 8.5 岁至 12.5 岁之间（平均 10.5，标准差 1.1）参加了这项研究。参与者在腰间佩戴定制的三轴加速计模块时进行各种运动。加速度计模块获取的数据经过分成小组（2.8 秒内 128 个采样点）进行预处理。所开发的 CNN 使用大约 183,600 个数据样本来学习对十种身体活动进行分类：慢走、快走、慢跑、快跑、走上楼梯、走下楼梯、跳绳、站起来、坐下和保持静止。开发的 CNN 对这 10 种活动进行分类，总体准确率为 81.2%。当类似的活动被合并，导致七个合并活动时，CNN 对活动进行分类的总体准确率为 91.1%。活动合并还提高了性能指标，最大情况下召回率为 66.4%，准确率为 48.5%，f1 得分为 57.4%。将开发的 CNN 分类器与支持向量机、决策树和 k 最近邻算法等传统机器学习算法进行比较，提出的 CNN 分类器表现最好：CNN (81.2%) > SVM (64.8%) > DT (63.9%) > kNN (55.4%)（十项活动）； CNN (91.1%) > SVM (74.4%) > DT (73.2%) > kNN (65.3%)（对于合并的七项活动）。开发的算法使用儿童进行的身体活动中的短时加速度信号来区分具有改进的时间分辨率的身体活动。这项研究涉及算法开发、参与者招募、IRB 批准、数据采集模块的定制设计和数据收集。自选的步行和跑步移动速度（慢和快）以及楼梯的结构降低了算法的性能。但类似的活动合并后，速度自选带来的影响就减少了。实验结果表明，所提算法的性能优于传统算法。由于其简单性，所提出的算法可以应用于实时应用。
The proportion of overweight and obese people has increased tremendously in a short period, culminating in a worldwide trend of obesity that is reaching epidemic proportions. Overweight and obesity are serious issues, especially with regard to children. This is because obese children have twice the risk of becoming obese as adults, as compared to non-obese children. Nowadays, many methods for maintaining a caloric balance exist; however, these methods are not applicable to children. In this study, a new approach for helping children monitor their activities using a convolutional neural network (CNN) is proposed, which is applicable for real-time scenarios requiring high accuracy. A total of 136 participants (86 boys and 50 girls), aged between 8.5 years and 12.5 years (mean 10.5, standard deviation 1.1), took part in this study. The participants performed various movement while wearing custom-made three-axis accelerometer modules around their waists. The data acquired by the accelerometer module was preprocessed by dividing them into small sets (128 sample points for 2.8 s). Approximately 183,600 data samples were used by the developed CNN for learning to classify ten physical activities : slow walking, fast walking, slow running, fast running, walking up the stairs, walking down the stairs, jumping rope, standing up, sitting down, and remaining still. The developed CNN classified the ten activities with an overall accuracy of 81.2%. When similar activities were merged, leading to seven merged activities, the CNN classified activities with an overall accuracy of 91.1%. Activity merging also improved performance indicators, for the maximum case of 66.4% in recall, 48.5% in precision, and 57.4% in f1 score . The developed CNN classifier was compared to conventional machine learning algorithms such as the support vector machine, decision tree, and k-nearest neighbor algorithms, and the proposed CNN classifier performed the best: CNN (81.2%) > SVM (64.8%) > DT (63.9%) > kNN (55.4%) (for ten activities); CNN (91.1%) > SVM (74.4%) > DT (73.2%) > kNN (65.3%) (for the merged seven activities). The developed algorithm distinguished physical activities with improved time resolution using short-time acceleration signals from the physical activities performed by children. This study involved algorithm development, participant recruitment, IRB approval, custom-design of a data acquisition module, and data collection. The self-selected moving speeds for walking and running (slow and fast) and the structure of staircase degraded the performance of the algorithm. However, after similar activities were merged, the effects caused by the self-selection of speed were reduced. The experimental results show that the proposed algorithm performed better than conventional algorithms. Owing to its simplicity, the proposed algorithm could be applied to real-time applicaitons.
登录
查看更多内容
DOI：
10.1109/titb.2005.856864
发表时间：
2006-01-01
影响因子：
--
作者：
Karantonis, DM;Narayanan, MR;Celler, BG
通讯作者：
Celler, BG
DOI：
10.3390/s141222500
发表时间：
2014-11-27
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Garcia-Ceja E;Brena RF;Carrasco-Jimenez JC;Garrido L
通讯作者：
Garrido L
影响因子：
2.2
作者：
Gao, Lei;Bourke, A. K.;Nelson, John
通讯作者：
Nelson, John
影响因子：
3.2
作者：
Mathie, MJ;Celler, BG;Coster, ACF
通讯作者：
Coster, ACF
DOI：
10.3390/s100201154
发表时间：
2010
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Mannini A;Sabatini AM
通讯作者：
Sabatini AM