Neural computing for walking gait pattern identification based on multi-sensor data fusion of lower limb muscles

Triloka, Joko; Senanayake, S. M. N. Arosha; Lai, Daphne Teck Ching

doi:10.1007/s00521-016-2312-x

Cited by 18 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of a single load cell is one of the unique features of this robot, considering that the other robots use several load cells, such as in [ 37 ]. The load cell measures the force exerted by the user when flexing their foot up and down, which is translated to the user’s intention to move the bat up and down in the game.…”

Section: Discussionmentioning

confidence: 99%

Gamification and Control of Nitinol Based Ankle Rehabilitation Robot

et al. 2021

View full text Add to dashboard Cite

Conventional ankle rehabilitation exercises can be monotonous and repetitive. The use of robots and games can complement the existing practices, provide an engaging environment for the patient and alleviate the physiotherapist’s workload. This paper presents an ankle rehabilitation robot that uses two nitinol wire actuators and a Pong game to provide foot plantarflexion and dorsiflexion exercises. Nitinol is a type of smart material that has high volumetric mechanical energy density and can produce translational motion. A two-state discrete antagonistic control is proposed to manipulate the actuators. The system was tested on healthy participants and stroke patients. The results showed that the robot was safe and compliant. The robot did not forcefully plantarflex or dorsiflex the foot when the participant exerted opposing force. The actuators worked antagonistically to flex to the foot as intended, in sync with the up and down motions of the player’s bat in the game. These behaviors demonstrated the feasibility of a nitinol-based ankle rehabilitation robot and a simple and yet intuitive game in providing interactive rehabilitation exercise. The robot is expected to enhance the patient’s experience, participation and compliance to the rehabilitation routine and to quantitatively monitor the patient’s recovery progress.

show abstract

Section: Discussionmentioning

confidence: 99%

Gamification and Control of Nitinol Based Ankle Rehabilitation Robot

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, few successful applications use IoT technology to bring health services to families, to individuals and to provide personalized health services. Health IoT is an important branch of IoT application, and the change of health service model it brings will not only benefit most users but also promote the development of the health service industry [9][10]. Currently, there are some representative applications of IoT in the medical industry, health monitoring, sports promotion, and spiritual comfort.…”

Section: Introductionmentioning

confidence: 99%

Optimization of IoT-Based Artificial Intelligence Assisted Telemedicine Health Analysis System

Heng

Zhou

2021

IEEE Access

View full text Add to dashboard Cite

This paper presents an in-depth study and exploration of the health IoT architecture and related implementation technologies from both theoretical and practical aspects, with important theoretical significance and practical application value. The research includes cloud fusion health IoT architecture, multimodal information acquisition in health IoT perception layer, multi-level service quality assurance of health IoT based on human LAN, and emotional perception and emotional interaction in health IoT. In terms of health IoT architecture, the cloud convergence health IoT architecture is proposed to deeply integrate the health cloud platform and perception layer by integrating multiple communication technologies to optimize the user experience and make health IoT applications more closely connected with people. This paper describes the basic concepts and main components of multimodal sensing information collection, the design and implementation of a health monitoring cloud robotics platform, robotics-based multimodal data sensing and aggregation, and high comfort sustainable physiological signal collection based on smart clothes. The feasibility and performance of the QoS framework proposed in this paper are verified by computer simulations. In this paper, migration learning is used to implement emotion data labeling, continuous conditional random fields to identify emotions based on data collected from smartphones and smart clothes, respectively, and finally decision layer fusion for emotion classification prediction.INDEX TERMS Internet of things, artificial intelligence, telemedicine, health monitoring, data analysis.

show abstract

“…Regarding the data capture and monitoring, different technological solutions have been proposed [5]. The most popular ones are wearable devices, which have to be attached to specific places of the lower-limb of the patient, and typically capture motion data using Inertial Measurement Units (IMUs) [6]- [10] or biomedical signals such as EMG [11], [12]. A number of commercial devices exist on the market, such as XSens [13], BioStampRC [14], Tracmor [15]), FlexiForce [16], BioCapture [12]).…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Approach to Perform Physical Activity Classification Using a Sensorized Crutch Tip

et al. 2020

View full text Add to dashboard Cite

In recent years, interest in monitoring Physical Activity (PA) has increased due to its positive effect on health. New technological devices have been proposed for this purpose, mainly focused on sports, which include Machine Learning algorithms to identify the type of PA being performed. However, PA monitoring can also provide data useful for assessing the recovery process of people with impaired lower-limbs. In this work, a Machine-Learning based Physical Activity classifier design procedure is proposed, which makes use of the data provided by a Sensorized Tip that can be adapted to different Assistive Devices for Walking (ADW) such as canes or crutches. The procedure is based on three main stages: 1) defining a wide set of potential features to perform the classification; 2) optimizing the number of features by a Random-Forest approach, detecting the most relevant ones to classify five relevant activities (walking at a normal pace, walking fast, standing still, going up stairs and going down stairs); 3) training the MLbased classifiers considering the optimized feature set. A comparative analysis is carried out to evaluate the proposed procedure, using three ML-based classifier (Support Vector Machines, K-Nearest Neighbour and Artificial Neural Networks), demonstrating that the proposed approach can provide very high success rates if proper feature selection is carried out. This work presents four relevant contributions to the PA monitoring area: 1) the approach is focused on people that require ADW, which are not considered in other approaches; 2) an analysis of the features to characterize gait in people that require ADW is carried out; 3) a design procedure to optimize the number of features using a Random-Forest approach is used, avoiding a typical "brute force" procedure; and 4) a comparative analysis is carried out to demonstrate the validity of the approach.

show abstract

Neural computing for walking gait pattern identification based on multi-sensor data fusion of lower limb muscles

Cited by 18 publications

References 14 publications

Gamification and Control of Nitinol Based Ankle Rehabilitation Robot

Gamification and Control of Nitinol Based Ankle Rehabilitation Robot

Optimization of IoT-Based Artificial Intelligence Assisted Telemedicine Health Analysis System

A Machine Learning Approach to Perform Physical Activity Classification Using a Sensorized Crutch Tip

Contact Info

Product

Resources

About