The Application of Machine-Learning on Lower Limb Motion Analysis in Human Exoskeleton System

Background: A variety of shoe modifications have been used to reduce the forces applied on the plantar surface of the foot in those with diabetes. Toe and heel rockers are 2 of the most common types used. The aim of this study is to evaluate the effect of these shoe modifications on the kinematics of both normal and diabetic individuals. Method: Two groups of healthy and diabetic individuals were recruited for this study. The Qualysis motion analysis system was used to record the motions of participants while walking with shoes with toe and a combination of toe and heel rockers (combined). The effects of the type of rockers used and the effect of groups were determined using MANOVA. Results: Results of the study demonstrated no discernible difference between the spatiotemporal and range of motion of the ankle, knee, and hip joints while walking with a toe and combined rockers. There was also no difference between healthy and diabetic individuals in relation to these parameters (P value >.05). Conclusion: Results of this study demonstrated no difference between the spatiotemporal and range of motion of lower-limb joints in healthy and diabetic individuals when walking with toe and combined rockers. Because the use of these rockers did not influence the kinematics of the joints while walking, it is recommended that they be used for this group of individuals if they influence the forces applied on the foot. Levels of Evidence: Level IV

Download Full-text

OS3-4 Motion analysis of a wearable lower-limb robotic exoskeleton in assisting sit-tostand maneuver in individuals with spinal cord injuries(OS3: Rehabilitation Devices I)

The Proceedings of the Asian Pacific Conference on Biomechanics emerging science and technology in biomechanics ◽

10.1299/jsmeapbio.2015.8.83 ◽

2015 ◽

Vol 2015.8 (0) ◽

pp. 83

Author(s):

Tung-Wu Lu ◽

Ting-Ming Wang ◽

Ming-I Lin ◽

Hsing-Po Huang ◽

Hui-Fen Mao ◽

...

Keyword(s):

Spinal Cord ◽

Motion Analysis ◽

Lower Limb ◽

Spinal Cord Injuries ◽

Robotic Exoskeleton ◽

Rehabilitation Devices

Download Full-text

Improving Automatic Control of an Ankle-Foot Prosthesis Using Machine Learning Algorithms

2017 Design of Medical Devices Conference ◽

10.1115/dmd2017-3464 ◽

2017 ◽

Author(s):

Stuart R. Fairhurst ◽

Sara R. Koehler-McNicholas ◽

Billie C. S. Slater ◽

Eric A. Nickel ◽

Karl A. Koester ◽

...

Keyword(s):

Machine Learning ◽

Lower Limb ◽

Learning Algorithms ◽

User Interaction ◽

Standing Position ◽

Machine Learning Algorithms ◽

Measurement Unit ◽

Smartphone App ◽

Automatic Mode ◽

Va Health Care System

Most commercially available lower-limb prostheses are designed for walking, not for standing. The Minneapolis VA Health Care System has developed a bimodal prosthetic ankle-foot system with distinct modes for walking and standing [1]. With this device, a prosthesis user can select standing or walking mode in order to maximize standing stability or walking functionality, depending on the activity and context. Additionally, the prosthesis was designed to allow for an “automatic mode” to switch between standing and walking modes based on readings from an onboard Inertial Measurement Unit (IMU) without requiring user interaction to manually switch modes. A smartphone app was also developed to facilitate changing between walking, standing and automatic modes. The prosthesis described in [1] was used in a pilot study with 18 Veterans with lower-limb amputations to test static, dynamic, and functional postural stability. As part of the study, 17 Veterans were asked for qualitative feedback on the bimodal ankle-foot system (Table 1). The majority of participants (82%) expressed an interest in having an automatic mode. The participants also indicated that the automatic mode would need to reach walking mode on their first step and to lock the ankle quickly once the standing position was achieved. When asked about how they wanted to control the modes of the prosthesis, 82% wanted to use a physical switch and only 12% wanted to use a smartphone app. The results indicated that the following major design changes would be needed: 1) A fast and accurate automatic mode 2) A physical switch for mode changes This paper describes the use of machine learning algorithms to create an improved automatic mode and the use of stakeholder feedback to design a physical switch for the bimodal ankle-foot system.

Download Full-text

Biomechanical Model Representing Energy Storing Prosthetic Feet

Volume 2: Biomedical and Biotechnology Engineering ◽

10.1115/imece2010-38707 ◽

2010 ◽

Cited By ~ 1

Author(s):

Francy L. Sinatra ◽

Stephanie L. Carey ◽

Rajiv Dubey

Keyword(s):

Motion Analysis ◽

Lower Limb ◽

Biomechanical Model ◽

Body Segment ◽

Prosthetic Foot ◽

Biomechanical Models ◽

Prosthetic Feet ◽

Analysis System ◽

Lower Limb Amputees ◽

Metabolic Information

Previous studies have been conducted to develop a biomechanical model for a human’s lower limb. Amongst them, there have been several studies trying to quantify the kinetics and kinematics of lower-limb amputees through motion analysis [5, 10, 11]. Currently, there are various designs for lower-limb prosthetic feet such as the Solid Ankle Cushion Heel (SACH) from Otto Bock (Minneapolis) or the Flex Foot from Ossur (California). The latter is a prosthetic foot that allows for flexibility while walking and running. Special interest has been placed in recording the capabilities of these energy-storing prosthetic feet. This has been done through the creation of biomechanical models with motion analysis. In these previous studies the foot has been modeled as a single rigid-body segment, creating difficulties when trying to calculate the power dissipated by the foot [5, 20, 21]. This project studies prosthetic feet with energy-storing capabilities. The purpose is to develop an effective way of calculating power by using a biomechanical model. This was accomplished by collecting biomechanical data using an eight camera VICON (Colorado) motion analysis system including two AMTI (BP-400600, Massachusetts) force plates. The marker set that was used, models the foot using several segments, hence mimicking the motion the foot undergoes and potentially leading to greater accuracy. By developing this new marker set, it will be possible to combine the kinematic and kinetic profile gathered from it with previous studies that determined metabolic information. This information will allow for the better quantification and comparison of the energy storage and return (ES AR) feet and perhaps the development of new designs.

Download Full-text

Research on Non-Invasive Wireless Wearable Sensor System Using Virtual and Physical Sensors for Lower Limb Motion Analysis

Proceedings of the 2015 International Symposium on Computers and Informatics ◽

10.2991/isci-15.2015.126 ◽

2015 ◽

Author(s):

Kun Liu ◽

Jianchen Zhao ◽

Xuan Han

Keyword(s):

Motion Analysis ◽

Lower Limb ◽

Sensor System ◽

Wearable Sensor ◽

Non Invasive ◽

Physical Sensors

Download Full-text

Pose estimation by extended Kalman filter using noise covariance matrices based on sensor output

10.21203/rs.3.rs-29523/v2 ◽

2020 ◽

Author(s):

AYUKO SAITO ◽

Satoru Kizawa ◽

Yoshikazu Kobayashi ◽

Kazuto Miyawaki

Keyword(s):

Kalman Filter ◽

Motion Analysis ◽

Extended Kalman Filter ◽

Pose Estimation ◽

Lower Limb ◽

Covariance Matrices ◽

Motion Sensors ◽

Sensor Output ◽

Joint Angles ◽

Noise Covariance

Abstract This paper presents an extended Kalman filter for pose estimation using noise covariance matrices based on sensor output. Compact and lightweight nine-axis motion sensors are used for motion analysis in widely various fields such as medical welfare and sports. A nine-axis motion sensor includes a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer. Information obtained from the three sensors is useful for estimating joint angles using the Kalman filter. The extended Kalman filter is used widely for state estimation because it can estimate the status with a small computational load. However, determining the process and observation noise covariance matrices in the extended Kalman filter is complicated. The noise covariance matrices in the extended Kalman filter were found for this study based on the sensor output. Postural change appears in the gyroscope output because the rotational motion of the joints produces human movement. Therefore, the process noise covariance matrix was determined based on the gyroscope output. An observation noise covariance matrix was determined based on the accelerometer and magnetometer output because the two sensors’ outputs were used as observation values. During a laboratory experiment, the lower limb joint angles of three participants were measured using an optical 3D motion analysis system and nine-axis motion sensors while participants were walking. The lower limb joint angles estimated using the extended Kalman filter with noise covariance matrices based on sensor output were generally consistent with results obtained from the optical 3D motion analysis system. Furthermore, the lower limb joint angles were measured using nine-axis motion sensors while participants were running in place for about 100 seconds. The experiment results demonstrated the effectiveness of the proposed method for human pose estimation.

Download Full-text