Understanding LSTM Network Behaviour of IMU-Based Locomotion Mode Recognition for Applications in Prostheses and Wearables.
Understanding LSTM Network Behaviour of IMU-Based Locomotion Mode Recognition for Applications in Prostheses and Wearables.
复制标题
DOI：
10.3390/s21041264
复制
发表时间：
2021-02-10
期刊：
影响因子：
--
通讯作者：
Iravani P
中科院分区：
文献类型：
--
作者：
Sherratt F;Plummer A;Iravani P
人体运动模式识别（LMR）有可能用作下肢主动假肢的控制机制。主动假肢可以帮助截肢者恢复更自然的步态，但作为医疗器械，它必须最大限度地减少用户风险，如福尔斯和绊倒。因此，任何控制系统都必须具有高精度和鲁棒性，并对其内部操作有详细的了解。长短期记忆（LSTM）机器学习网络可以以高精度执行LMR。然而，在分类过程中的内部行为是未知的，当面对新用户时，它们很难概括。本文解决的目标问题是理解LMR的LSTM分类行为。收集了22名非截肢受试者的六种机车活动（行走、停止、楼梯和坡道）的数据集，捕获了自然环境中活动之间的稳态和过渡。非截肢者被用作截肢者的替代品，以提供更大的数据集。该数据集用于分析降低复杂度的LSTM网络的内部行为。该分析发现，该模型主要根据早期立场的数据对活动类型进行分类。对看不见的主体的泛化评估揭示了对超参数的低敏感性和对个人步态特征的过度拟合。研究个体受试者之间的差异表明，用户之间的步态变化主要发生在早期的立场，可能解释了穷人的泛化。单靠调整超参数无法解决这个问题，这表明需要对模型进行个性化。本文的主要成就是：（i）更好地理解了LMR的LSTM，（ii）在评估新的用户泛化时，证明了其对学习超参数的低敏感性，以及（iii）证明了需要个性化ML模型以达到可接受的准确性。
Human Locomotion Mode Recognition (LMR) has the potential to be used as a control mechanism for lower-limb active prostheses. Active prostheses can assist and restore a more natural gait for amputees, but as a medical device it must minimize user risks, such as falls and trips. As such, any control system must have high accuracy and robustness, with a detailed understanding of its internal operation. Long Short-Term Memory (LSTM) machine-learning networks can perform LMR with high accuracy levels. However, the internal behavior during classification is unknown, and they struggle to generalize when presented with novel users. The target problem addressed in this paper is understanding the LSTM classification behavior for LMR. A dataset of six locomotive activities (walking, stopped, stairs and ramps) from 22 non-amputee subjects is collected, capturing both steady-state and transitions between activities in natural environments. Non-amputees are used as a substitute for amputees to provide a larger dataset. The dataset is used to analyze the internal behavior of a reduced complexity LSTM network. This analysis identifies that the model primarily classifies activity type based on data around early stance. Evaluation of generalization for unseen subjects reveals low sensitivity to hyper-parameters and over-fitting to individuals’ gait traits. Investigating the differences between individual subjects showed that gait variations between users primarily occur in early stance, potentially explaining the poor generalization. Adjustment of hyper-parameters alone could not solve this, demonstrating the need for individual personalization of models. The main achievements of the paper are (i) the better understanding of LSTM for LMR, (ii) demonstration of its low sensitivity to learning hyper-parameters when evaluating novel user generalization, and (iii) demonstration of the need for personalization of ML models to achieve acceptable accuracy.
登录
查看更多内容
DOI：
10.3390/s17112556
发表时间：
2017-11-06
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Murad A;Pyun JY
通讯作者：
Pyun JY
影响因子：
5.1
作者：
Koller JR;Remy CD;Ferris DP
通讯作者：
Ferris DP
DOI：
10.1098/rspb.2011.1194
发表时间：
2012-02-07
影响因子：
4.7
作者：
Herr, Hugh M.;Grabowski, Alena M.
通讯作者：
Grabowski, Alena M.
影响因子：
3.9
作者：
Ihianle, Isibor Kennedy;Nwajana, Augustine O.;Orisatoki, Mobolaji O.
通讯作者：
Orisatoki, Mobolaji O.
影响因子：
4.6
作者：
Sabatini, AM;Martelloni, C;Cavallo, F
通讯作者：
Cavallo, F