Now showing 1 - 6 of 6
  • Publication
    Segmentation of shoulder rehabilitation exercises for single and multiple inertial sensor systems
    Introduction:Digital home rehabilitation systems require accurate segmentation methods to provide appropriate feedback on repetition counting and exercise technique. Current segmentation methods are not suitable for clinical use; they are not highly accurate or require multiple sensors, which creates usability problems. We propose a model for accurately segmenting inertial measurement unit data for shoulder rehabilitation exercises. This study aims to use inertial measurement unit data to train and test a machine learning segmentation model for single- and multiple-inertial measurement unit systems and to identify the optimal single-sensor location. Methods:A focus group of specialist physiotherapists selected the exercises, which were performed by participants wearing inertial measurement units on the wrist, arm and scapula. We applied a novel machine learning based segmentation technique involving a convolutional classifier and Finite State Machine to the inertial measurement unit data. An accuracy score was calculated for each possible single- or multiple-sensor system. Results:The wrist inertial measurement unit was chosen as the optimal single-sensor location for future system development (mean overall accuracy 0.871). Flexion and abduction based exercises mostly could be segmented with high accuracy, but scapular movement exercises had poor accuracy. Conclusion:A wrist-worn single inertial measurement unit system can accurately segment shoulder exercise repetitions; however, accuracy varies depending on characteristics of the exercise.
  • Publication
    Rehabilitation Exercise Segmentation for Autonomous Biofeedback Systems with ConvFSM
    Segmenting physical movements is a key step for any accelerometry-based autonomous biofeedback system oriented to rehabilitation and physiotherapy activities. Fundamentally, this can be reduced to the detection of recurrent patterns, also called motion primitives, in longer inertial signals. Most of the solutions developed in the literature require extensive domain knowledge, or are incapable of scaling to complex motion patterns and new exercises. In this paper, we explore the capabilities of inertial measurement units for the segmentation of upper limb rehabilitation exercises. To do so, we introduce a novel segmentation technique based on Convolutional Neural Networks and Finite State Machines, called ConvFSM. ConvFSM is able to isolate motion primitives from raw streaming data, using very little domain knowledge. We also investigate different combinations of sensors, in order to identify the most effective and flexible setup that could fit a home-based rehabilitation feedback system. Experimental results are presented, based on a dataset obtained from a combination of common upper limb and lower limb exercises.
      384Scopus© Citations 5
  • Publication
    Automatic Classification of Knee Rehabilitation Exercises Using a Single Inertial Sensor: a Case Study
    Inertial measurement units have the ability to accurately record the acceleration and angular velocity of human limb segments during discrete joint movements. These movements are commonly used in exercise rehabilitation programmes following orthopaedic surgery such as total knee replacement. This provides the potential for a biofeedback system with data mining technique for patients undertaking exercises at home without physician supervision. We propose to use machine learning techniques to automatically analyse inertial measurement unit data collected during these exercises, and then assess whether each repetition of the exercise was executed correctly or not. Our approach consists of two main phases: signal segmentation, and segment classification. Accurate pre-processing and feature extraction are paramount topics in order for the technique to work. In this paper, we present a classification method for unsupervised rehabilitation exercises, based on a segmentation process that extracts repetitions from a longer signal activity. The results obtained from experimental datasets of both clinical and healthy subjects, for a set of 4 knee exercises commonly used in rehabilitation, are very promising.
      506Scopus© Citations 20
  • Publication
    An interactive exercise biofeedback Android application utilizing a single inertial measurement unit to support joint replacement rehabilitation
    Boomerang Ortho is an Android application developed with the aim to better support patients in their exercise rehabilitation program following total knee replacement. The use of a single inertial measurement unit (IMU) attached to the lower leg allows for classification of exercise technique, real-time biofeedback, and both self and remote monitoring of patient data. The prototype application for demonstration is currently undergoing pilot testing prior to an assessment of impact on clinical outcome.
  • Publication
    Clinician perceptions of a prototype wearable exercise biofeedback system for orthopaedic rehabilitation: a qualitative exploration
    Objectives: This study explores the opinions of orthopaedic healthcare professionals regarding the opportunities and challenges of using wearable technology in rehabilitation. It continues to assess the perceived impact of an exemplar exercise biofeedback system that incorporates wearable sensing, involving the clinician in the user-centred design process, a valuable step in ensuring ease of implementation, sustained engagement and clinical relevance. Design: This is a qualitative study consisting of one-to-one semi-structured interviews, including a demonstration of a prototype wearable exercise biofeedback system. Interviews were audio-recorded and transcribed, with thematic analysis conducted of all transcripts. Setting: The study was conducted in the orthopaedic department of an acute private hospital. Participants Ten clinicians from a multidisciplinary team of healthcare professionals involved in the orthopaedic rehabilitation pathway participated in the study. Results: Participants reported that there is currently a challenge in gathering timely and objective data for the monitoring of patients in orthopaedic rehabilitation. While there are challenges in ensuring reliability and engagement of biofeedback systems, clinicians perceive significant value in the use of wearable biofeedback systems such as the exemplar demonstrated for use following total knee replacement. Conclusions: Clinicians see an opportunity for wearable technology to continuously track data in real-time, and feel that feedback provided to users regarding exercise technique and adherence can further support the patient at home, although there are clear design and implementation challenges relating to ensuring technical accuracy and tailoring rehabilitation to the individual. There was perceived value in the prototype system demonstrated to participants which supports the ongoing development of such exercise biofeedback platforms.
      328Scopus© Citations 15
  • Publication
    Human Activity Recognition with Convolutional Neural Networks
    The problem of automatic identification of physical activities performed by human subjects is referred to as Human Activity Recognition (HAR). There exist several techniques to measure motion characteristics during these physical activities, such as Inertial Measurement Units (IMUs). IMUs have a cornerstone position in this context, and are characterized by usage flexibility, low cost, and reduced privacy impact. With the use of inertial sensors, it is possible to sample some measures such as acceleration and angular velocity of a body, and use them to learn models that are capable of correctly classifying activities to their corresponding classes. In this paper, we propose to use Convolutional Neural Networks (CNNs) to classify human activities. Our models use raw data obtained from a set of inertial sensors. We explore several combinations of activities and sensors, showing how motion signals can be adapted to be fed into CNNs by using different network architectures. We also compare the performance of different groups of sensors, investigating the classification potential of single, double and triple sensor systems. The experimental results obtained on a dataset of 16 lower-limb activities, collected from a group of participants with the use of five different sensors, are very promising.
      322Scopus© Citations 46