A Pilot Study of the Efficiency of LSTM-Based Motion Classification Algorithms Using a Single Accelerometer

Abstract

Inertial sensors are widely used for classifying the motions of daily activities. Although hierarchical classification algorithms were commonly used for defined motions, deep-learning models have been used recently to classify a greater diversity of motions. In addition, ongoing studies are actively investigating algorithm efficiency (e.g., training time and accuracy). Thus, a deep-learning model was constructed in this study for the classification of a given motion based on the raw data of inertial sensors. Furthermore, the number of epochs (150, 300, 500, 750, and 900) and hidden units (100, 150, and 200) were varied in the model to determine its efficiency based on training time and accuracy, and the optimum accuracy and training time was determined. Using a basic long short-term memory (LSTM), which is a neural network known to be suitable for sequential data, the data classification training was conducted on a common desktop PC with typical specifications. The results show that the accuracy was the highest (99.82%) with 150 hidden units and 300 epochs, while the training time was also relatively short (78.15 min). In addition, the model accuracy did not always increase even when the model complexity was increased (by increasing the number of epochs and hidden units) and the training time increased as a consequence. Hence, through suitable combinations of the two factors that constitute deep-learning models according to the data, the potential development and use of efficient models have been verified. From the perspective of training optimization, this study is significant in having determined the importance of the conditions for hidden units and epochs that are suitable for the given data and the adverse effects of overtraining.

Human Posture Transition-Time Detection Based upon Inertial Measurement Unit and Long Short-Term Memory Neural Networks

“…It has a unique structure that enables it to perform better than general recurrent neural networks, especially in tasks such as autonomous speech recognition [35]. LSTM is not limited to speech-recognition tasks; it can also be applied in other areas, such as predicting human decisions [36], exoskeleton control, and posture-change detection for other equipment [37][38][39]. When the human body performs a posture change (whether it is wearing an exoskeleton or there is human-computer interaction), there is a linkage and correlation between each of the joints of lower limbs, and there is also continuity between and memory of various movements.…”

Whole-Body Teleoperation Control of Dual-Arm Robot Using Sensor Fusion

“…And one of the main difficulties is the precise perception of hand motion [27], which requires a robust and reliable sensing system. Many wearable devices have been extensively validated for their effectiveness in human-computer interfaces, robot control, and exoskeleton intent control research [28][29][30][31]. Wearable data gloves have also been proven to enable continuous control of bionic hands, and numerous related studies have confirmed the stability and reliability of this control method [32,33].…”