A Comparison of Three Neural Network Approaches for Estimating Joint Angles and Moments from Inertial Measurement Units

The application of artificial intelligence techniques to wearable sensor data may facilitate accurate analysis outside of controlled laboratory settings—the holy grail for gait clinicians and sports scientists looking to bridge the lab to field divide. Using these techniques, parameters that are difficult to directly measure in-the-wild, may be predicted using surrogate lower resolution inputs. One example is the prediction of joint kinematics and kinetics based on inputs from inertial measurement unit (IMU) sensors. Despite increased research, there is a paucity of information examining the most suitable artificial neural network (ANN) for predicting gait kinematics and kinetics from IMUs. This paper compares the performance of three commonly employed ANNs used to predict gait kinematics and kinetics: multilayer perceptron (MLP); long short-term memory (LSTM); and convolutional neural networks (CNN). Overall high correlations between ground truth and predicted kinematic and kinetic data were found across all investigated ANNs. However, the optimal ANN should be based on the prediction task and the intended use-case application. For the prediction of joint angles, CNNs appear favourable, however these ANNs do not show an advantage over an MLP network for the prediction of joint moments. If real-time joint angle and joint moment prediction is desirable an LSTM network should be utilised.

Download Full-text

A Mixed Deep Recurrent Neural Network for MEMS Gyroscope Noise Suppressing

Electronics ◽

10.3390/electronics8020181 ◽

2019 ◽

Vol 8 (2) ◽

pp. 181 ◽

Cited By ~ 12

Author(s):

Changhui Jiang ◽

Yuwei Chen ◽

Shuai Chen ◽

Yuming Bo ◽

Wei Li ◽

...

Keyword(s):

Neural Network ◽

Recurrent Neural Network ◽

Inertial Measurement Unit ◽

Short Term Memory ◽

Inertial Navigation ◽

Measurement Unit ◽

Short Term ◽

Inertial Measurement ◽

Long Short Term Memory ◽

Gated Recurrent Unit

Currently, positioning, navigation, and timing information is becoming more and more vital for both civil and military applications. Integration of the global navigation satellite system and /inertial navigation system is the most popular solution for various carriers or vehicle positioning. As is well-known, the global navigation satellite system positioning accuracy will degrade in signal challenging environments. Under this condition, the integration system will fade to a standalone inertial navigation system outputting navigation solutions. However, without outer aiding, positioning errors of the inertial navigation system diverge quickly due to the noise contained in the raw data of the inertial measurement unit. In particular, the micromechanics system inertial measurement unit experiences more complex errors due to the manufacturing technology. To improve the navigation accuracy of inertial navigation systems, one effective approach is to model the raw signal noise and suppress it. Commonly, an inertial measurement unit is composed of three gyroscopes and three accelerometers, among them, the gyroscopes play an important role in the accuracy of the inertial navigation system’s navigation solutions. Motivated by this problem, in this paper, an advanced deep recurrent neural network was employed and evaluated in noise modeling of a micromechanics system gyroscope. Specifically, a deep long short term memory recurrent neural network and a deep gated recurrent unit–recurrent neural network were combined together to construct a two-layer recurrent neural network for noise modeling. In this method, the gyroscope data were treated as a time series, and a real dataset from a micromechanics system inertial measurement unit was employed in the experiments. The results showed that, compared to the two-layer long short term memory, the three-axis attitude errors of the mixed long short term memory–gated recurrent unit decreased by 7.8%, 20.0%, and 5.1%. When compared with the two-layer gated recurrent unit, the proposed method showed 15.9%, 14.3%, and 10.5% improvement. These results supported a positive conclusion on the performance of designed method, specifically, the mixed deep recurrent neural networks outperformed than the two-layer gated recurrent unit and the two-layer long short term memory recurrent neural networks.

Download Full-text

Simulation of Breathing Patterns and Classification of Sensor Data for the early detection of impending Sudden Infant Death

Current Directions in Biomedical Engineering ◽

10.1515/cdbme-2019-0101 ◽

2019 ◽

Vol 5 (1) ◽

pp. 401-403

Author(s):

Michael Munz ◽

Nicolas Wolf

Keyword(s):

Neural Network ◽

Infant Death ◽

Inertial Measurement Unit ◽

Sudden Infant Death ◽

Sensor Data ◽

Measurement Unit ◽

Sudden Infant ◽

Breathing Patterns ◽

Inertial Measurement

AbstractIn this work, a methodology for the classification of breathing patterns in order to prevent sudden infant death (SID) incidents is presented. The basic idea is to classify breathing patterns which might lead to SID prior to an incident. A thorax sensor is proposed, which is able to simulate breathing patterns given by certain parameters. A sensor combination of conductive strain fabric and an inertial measurement unit is used for data acquisition. The data is then classified using a neural network.

Download Full-text

A Deep Neural Network-Based Fault Detection Scheme for Aircraft IMU Sensors

International Journal of Aerospace Engineering ◽

10.1155/2021/3936826 ◽

2021 ◽

Vol 2021 ◽

pp. 1-13

Author(s):

Yiming Zhang ◽

Hang Zhao ◽

Jinyi Ma ◽

Yunmei Zhao ◽

Yiqun Dong ◽

...

Keyword(s):

Neural Network ◽

Fault Detection ◽

Inertial Measurement Unit ◽

Deep Neural Network ◽

Short Term Memory ◽

Measurement Unit ◽

Short Term ◽

Detection Scheme ◽

Inertial Measurement ◽

Long Short Term Memory

A new fault detection scheme for aircraft Inertial Measurement Unit (IMU) sensors is developed in this paper. This scheme adopts a deep neural network with a CNN-LSTM-fusion architecture (CNN: convolution neural network; LSTM: long short-term memory). The fault detection network (FDN) developed in this paper is irrelative to aircraft model or flight condition. Flight data is reformed into a 2D format for FDN input and is mapped via the net to fault cases directly. We simulate different aircrafts with various flight conditions and separate them into training and testing sets. Part of the aircrafts and flight conditions appears only in the testing set to validate robustness and scalability of the FDN. Different architectures of FDN are studied, and an optimized architecture is obtained via ablation studies. An average detecting accuracy of 94.5% on 20 different cases is achieved.

Download Full-text

Validity and sensitivity of an inertial measurement unit-driven biomechanical model of motor variability for gait

10.1101/2021.09.27.461967 ◽

2021 ◽

Author(s):

Christopher Bailey ◽

Thomas Uchida ◽

Julie Nantel ◽

Ryan Graham

Keyword(s):

Inertial Measurement Unit ◽

Intraclass Correlation ◽

Biomechanical Model ◽

Measurement Unit ◽

Local Dynamic ◽

Joint Angles ◽

Motor Variability ◽

Arm Swing ◽

Inertial Measurement ◽

Local Dynamic Stability

Motor variability in gait is frequently linked to fall risk, yet field-based biomechanical joint evaluations are scarce. We evaluated the validity and sensitivity of an inertial measurement unit (IMU)-driven biomechanical model of joint angle variability for gait. Fourteen healthy young adults completed seven-minute trials of treadmill gait at several speeds and arm swing amplitudes. Joint kinematics were estimated by IMU- and optoelectronic-based models using OpenSim. We calculated range of motion (ROM), magnitude of variability (meanSD), local dynamic stability (λmax), persistence of ROM fluctuations (DFAα), and regularity (SaEn) of each angle over 200 continuous strides, and evaluated model accuracy (e.g., RMSD: root mean square difference), consistency (ICC2,1: intraclass correlation), biases, limits of agreement, and sensitivity to within-participant gait responses (effects of Speed and Swing). RMSDs of joint angles were 1.7–7.5° (pooled mean of 4.8°), excluding ankle inversion. ICCs were mostly good–excellent in the primary plane of motion for ROM and in all planes for meanSD and λmax, but were poor–moderate for DFAα and SaEn. Modeled Speed and Swing responses for ROM, meanSD, and λmax were similar. Results suggest that the IMU-driven model is valid and sensitive for field-based assessments of joint angles and several motor variability features.

Download Full-text

An inertial measurement unit tracking system for body movement in comparison with optical tracking

Proceedings of the Institution of Mechanical Engineers Part H Journal of Engineering in Medicine ◽

10.1177/0954411920921695 ◽

2020 ◽

Vol 234 (7) ◽

pp. 728-737

Author(s):

Rui Li ◽

Barclay Jumet ◽

Hongliang Ren ◽

WenZhan Song ◽

Zion Tsz Ho Tse

Keyword(s):

Inertial Measurement Unit ◽

Tracking System ◽

Low Cost ◽

Optical Tracking ◽

Measurement Unit ◽

Joint Movement ◽

Joint Angles ◽

Optical Tracking System ◽

Microelectromechanical System ◽

Inertial Measurement

The recent advancement of motion tracking technology offers better treatment tools for conditions, such as movement disorders, as the outcome of the rehabilitation could be quantitatively defined. The accurate and fast angular information output of the inertial measurement unit tracking systems enables the collection of accurate kinematic data for clinical assessment. This article presents a study of a low-cost microelectromechanical system inertial measurement unit-based tracking system in comparison with the conventional optical tracking system. The system consists of seven microelectromechanical system inertial measurement units, which could be mounted on the lower limbs of the subjects. For the feasibility test, 10 human participants were instructed to perform three different motions: walking, running, and fencing lunges when wearing specially designed sleeves. The subjects’ lower body movements were tracked using our inertial measurement unit-based system and compared with the gold standard—the NDI Polaris Vega optical tracking system. The results of the angular comparison between the inertial measurement unit and the NDI Polaris Vega optical tracking system were as follows: the average cross-correlation value was 0.85, the mean difference of joint angles was 2.00°, and the standard deviation of joint angles was ± 2.65°. The developed microelectromechanical system–based tracking system provides an alternative low-cost solution to track joint movement. Moreover, it is able to operate on an Android platform and could potentially be used to assist outdoor or home-based rehabilitation.

Download Full-text

Gait Phase Recognition Using Deep Convolutional Neural Network with Inertial Measurement Units

Biosensors ◽

10.3390/bios10090109 ◽

2020 ◽

Vol 10 (9) ◽

pp. 109

Author(s):

Binbin Su ◽

Christian Smith ◽

Elena Gutierrez Farewik

Keyword(s):

Wearable Sensors ◽

Sensor Data ◽

Measurement Unit ◽

Deep Convolutional Neural Networks ◽

Inertial Measurement ◽

Measurement Units ◽

Gait Phase ◽

Robotic Devices ◽

Phase Recognition ◽

Five Phases

Gait phase recognition is of great importance in the development of assistance-as-needed robotic devices, such as exoskeletons. In order for a powered exoskeleton with phase-based control to determine and provide proper assistance to the wearer during gait, the user’s current gait phase must first be identified accurately. Gait phase recognition can potentially be achieved through input from wearable sensors. Deep convolutional neural networks (DCNN) is a machine learning approach that is widely used in image recognition. User kinematics, measured from inertial measurement unit (IMU) output, can be considered as an ‘image’ since it exhibits some local ‘spatial’ pattern when the sensor data is arranged in sequence. We propose a specialized DCNN to distinguish five phases in a gait cycle, based on IMU data and classified with foot switch information. The DCNN showed approximately 97% accuracy during an offline evaluation of gait phase recognition. Accuracy was highest in the swing phase and lowest in terminal stance.

Download Full-text

Long short-term memory neural network for traffic speed prediction using remote microwave sensor data

Transportation Research Part C Emerging Technologies ◽

10.1016/j.trc.2015.03.014 ◽

2015 ◽

Vol 54 ◽

pp. 187-197 ◽

Cited By ~ 583

Author(s):

Xiaolei Ma ◽

Zhimin Tao ◽

Yinhai Wang ◽

Haiyang Yu ◽

Yunpeng Wang

Keyword(s):

Neural Network ◽

Short Term Memory ◽

Sensor Data ◽

Short Term ◽

Term Memory ◽

Microwave Sensor ◽

Speed Prediction ◽

Long Short Term Memory ◽

Traffic Speed

Download Full-text

Fall detection system based on BiLSTM neural network

Transactions on Machine Learning and Artificial Intelligence ◽

10.14738/tmlai.75.6318 ◽

2019 ◽

Vol 7 (5) ◽

pp. 01-12

Author(s):

Biao YE ◽

Lasheng Yu

Keyword(s):

Neural Network ◽

Short Term Memory ◽

Detection System ◽

Input Sequence ◽

Fall Detection ◽

Detection Algorithm ◽

Training Data ◽

Sensor Data ◽

Data Set ◽

Sequence Modeling

The purpose of this article is to analyze the characteristics of human fall behavior to design a fall detection system. The existing fall detection algorithms have problems such as poor adaptability, single function and difficulty in processing large data and strong randomness. Therefore, a long-term and short-term memory recurrent neural network is used to improve the effect of falling behavior detection by exploring the internal correlation between sensor data. Firstly, the serialization representation method of sensor data, training data and detection input data is designed. The BiLSTM network has the characteristics of strong ability to sequence modeling and it is used to reduce the dimension of the data required by the fall detection model. then, the BiLSTM training algorithm for fall detection and the BiLSTM-based fall detection algorithm convert the fall detection into the classification problem of the input sequence; finally, the BiLSTM-based fall detection system was implemented on the TensorFlow platform. The detection and analysis of system were carried out using a bionic experiment data set which mimics a fall. The experimental results verify that the system can effectively improve the accuracy of fall detection to 90.47%. At the same time, it can effectively detect the behavior of Near-falling, and help to take corresponding protective measures.

Download Full-text