A Novel Locomotion Rule Rmbedding Long Short-Term Memory Network with Attention for Human Locomotor Intent Classification Using Multi-Sensors Signals

作     者：Jiajie Shen Yan Wang Dongxu Zhang 

作者机构：Key Laboratory of Symbol Computation and Knowledge EngineeringMinistry of EducationColleague of Computer Science and TechnologyJilin UniversityChangchun130012China College of Softwareand Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin UniversityChangchun130012China 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2024年第79卷第6期

页      面：4349-4370页

核心收录：

学科分类：080202[工学-机械电子工程] 08[工学] 0802[工学-机械工程] 

基　　金：funded by the National Natural Science Foundation of China(Nos.62072212,62302218) the Development Project of Jilin Province of China(Nos.20220508125RC,20230201065GX,20240101364JC) National Key R&D Program(No.2018YFC2001302) the Jilin Provincial Key Laboratory of Big Data Intelligent Cognition(No.20210504003GH) 

主　　题：Lower-limb prosthetics deep neural networks motion classification 

摘      要：Locomotor intent classification has become a research hotspot due to its importance to the development of assistive robotics and wearable *** work have achieved impressive performance in classifying steady locomotion ***,it remains challenging for these methods to attain high accuracy when facing transitions between steady locomotion *** to the similarities between the information of the transitions and their adjacent steady ***,most of these methods rely solely on data and overlook the objective laws between physical activities,resulting in lower accuracy,particularly when encountering complex locomotion modes such as *** address the existing deficiencies,we propose the locomotion rule embedding long short-term memory(LSTM)network with Attention(LREAL)for human locomotor intent classification,with a particular focus on transitions,using data from fewer sensors(two inertial measurement units and four goniometers).The LREAL network consists of two levels:One responsible for distinguishing between steady states and transitions,and the other for the accurate identification of locomotor *** classifier in these levels is composed of multiple-LSTM layers and an attention *** introduce real-world motion rules and apply constraints to the network,a prior knowledge was added to the network via a rule-modulating *** method was tested on the ENABL3S dataset,which contains continuous locomotion date for seven steady and twelve transitions *** results showed that the LREAL network could recognize locomotor intents with an average accuracy of 99.03%and 96.52%for the steady and transitions states,*** is worth noting that the LREAL network accuracy for transition-state recognition improved by 0.18%compared to other state-of-the-art network,while using data from fewer sensors.