Convolutional long short-term memory model for recognizing construction workers' postures from wearable inertial measurement units. (October 2020)

• Record Type: Journal Article
• Authors: Zhao, Junqi; Obonyo, Esther
• Is Part Of: Advanced engineering informatics. Volume 46(2020)
• Publication Date: 2020-10
• Subjects: Posture recognition -- Wearable sensing -- Deep neural networks -- Construction worker -- Injury prevention -- Ergonomics; BT Bending Posture -- CLN Convolutional LSTM model -- CNN Convolutional Neural Networks -- CV Computer Vision -- DL Deep Learning -- DNN Deep Neural Networks -- DT C4.5 Decision Tree -- EEG Electroencephalography -- IMUs Inertial Measurement Units -- KN Kneeling Posture -- KNN K-Nearest Neighbor -- LB Literal bending Posture -- LSTM Long Short-Term Memory -- ML Machine Learning -- MSDs Musculoskeletal Disorders -- NB Naive Bayes -- NON Transitional Posture -- OW Overhead Working Posture -- OWAS Ovako Working Posture Analyzing System -- RF Random Forest -- RFE Recursive Feature Elimination -- RNN Recurrent Neural Networks -- SGD Stochastic Gradient Descend -- SQ Squatting Posture -- SRS Stratified Random Shuffle -- ST Standing Posture -- SVM Support Vector Machine -- VS Vision-based Sensing -- WS Wearable Sensing; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2020.101177
• Languages: English
• ISSNs: 1474-0346

Abstract

Graphical abstract: Highlights: Recognizing awkward postures helps preventing injuries in construction. Wearable Inertial Measurement Units (IMUs) can be used for workers' motion sensing. Convolutional Long Short-Term Memory (CLN) recognition model can work with IMUs. CLN model leverages automated feature and pattern learning from IMUs output. CLN improves the recognition performance of conventional Machine Learning models. Abstract: This paper proposes using Deep Neural Networks (DNN) models for recognizing construction workers' postures from motion data captured by wearable Inertial Measurement Units (IMUs) sensors. The recognized awkward postures can be linked to known risks of Musculoskeletal Disorders among workers. Applying conventional Machine Learning (ML)-based models has shown promising results in recognizing workers' postures. ML models are limited – they reply on heuristic feature engineering when constructing discriminative features for characterizing postures. This makes further improving the model performance regarding recognition accuracy challenging. In this paper, the authors investigate the feasibility of addressing this problem using a DNN model that, through integrating Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) layers, automates feature engineering and sequential pattern detection. The model's recognition performance was evaluated using datasets collected from four workers on construction sites. The DNN model integrating one convolutional and two LSTM layers resulted in the best performance (measured by F1 Score). The proposed model outperformed baseline CNN and LSTM models suggesting that it leveraged the advantages of the two baseline models for effective feature learning. It improved benchmark ML models' recognition performance by an average of 11% under personalized modelling. The recognition performance was also improved by 3% when the proposed model was applied to 8 types of postures across three subjects. These results support that the proposed DNN model has a high potential in addressing challenges for improving the recognition performance that was observed when using ML models.