Estimation of Muscle Forces About the Ankle During Gait in Healthy and Neurologically Impaired Subjects

This chapter describes a biomechanical model of the forces about the ankle joint applicable to both unimpaired and neurologically impaired subjects. EMGs and joint kinematics are used as inputs and muscle forces are the outputs. A hybrid modeling approach that uses both forward and inverse dynamics is employed and physiological parameters for the model are tuned for each subject using optimization procedures. The forward dynamics part of the model takes muscle activation and uses Hill-type models of muscle contraction dynamics to estimate muscle forces and the corresponding joint moments. Inverse dynamics is used to calibrate the forward dynamics model predictions of joint moments. In this chapter we will describe how to implement an EMG-driven hybrid forward and inverse dynamics model of the ankle that can be used in healthy and neurologically impaired people.

Evolutionary Methods for Analysis of Human Movement

A movement rehabilitation therapist must first diagnose the cause of disability and then prescribe therapies that specifically target the dysfunctional unit of the movement system. Objective diagnosis and prescription are difficult, however, because human movement is the result of complicated interactions among complex and highly nonlinear elements. Treatment based on limited observations may target the wrong element of the movement system. Researchers in central nervous system (CNS) control of human movement and functional electrical stimulation (FES) restoration of movement to paralyzed limbs face similar challenges in objective analysis of the integrated movement system. In this chapter, we will present evolutionary methods as powerful new tools for analysis and rehabilitation of human movement. These methods have been modeled after the same biological processes that have been optimized for the control of human movement in the process of biological evolution. Therefore, it is logical to think that these methods, if applied properly, could help us understand the control of human movement and repair it when it is disabled. A case study demonstrates the potential of evolutionary methods in movement analysis and rehabilitation.

Neural Network Models for Estimation of Balance Control, Detection of Imbalance, and Estimation of Falls Risk

Gait patterns of the elderly are often adjusted to accommodate for reduced function in the balance control system. Recent work has demonstrated the effectiveness of artificial neural network (ANN) modeling in mapping gait measurements onto descriptions of whole body motion during locomotion. Accurate risk assessment is necessary for reducing incidence of falls. Further development of the balance estimation model has been used to test the feasibility of detecting balance impairment using tasks of sample categorization and falls risk estimation. Model design included an ANN and a statistical discrimination method. Sample categorization results reached accuracy of 0.89. Relative risk was frequently assessed at high or very high risk for experiencing falls in a sample of balance impaired older adults. The current model shows potential for detecting balance impairment and estimating falls risk, thereby indicating the need for referral for falls prevention intervention.

Monitoring Human Movement with Body-Fixed Sensors and its Clinical Applications

In this chapter, first we outline the advantage of new technologies based on body-fixed sensors and particularly the possibility to perform field measurement, out of a laboratory and during the actual condition of the subject. The relevance of intelligent computing and its potential to enhance those features hidden in biomechanical signals are reviewed. An emphasis is made to show the results produced by these sensors when used alone and new possibilities offered when the information from different type of body fixed sensors are fused. In the second part, the relevance of body fixed sensors in medicine is presented by providing many clinical applications in orthopedics, Parkinson disease, physiology, pain management, and aging. Finally the chapter ends by emphasizing the potential of synergies between body fixed movement monitoring and other areas such as information technology which lead to the development of wearable body movement monitoring.

Recognition of Gait Patterns Using Support Vector Machines

Automated gait pattern recognition capability has many advantages. For example, it can be used for the detection of at-risk or faulty gait, or for monitoring the progress of treatment effects. In this chapter, we first provide an overview of the major automated techniques for detecting gait patterns. This is followed by a description of a gait pattern recognition technique based on a relatively new machine-learning tool, support vector machines (SVM). Finally, we show how SVM technique can be applied to detect changes in the gait characteristics as a result of the ageing process and discuss their suitability as an automated gait classifier.

Inertial Sensing in Biomechanics

Sensing approaches for ambulatory monitoring of human motion are necessary in order to objectively determine a person’s level of functional ability in independent living. Because this capability is beyond the grasp of the specialized equipment available in most motion analysis laboratories, body-mounted inertial sensing has been receiving increasing interest in the biomedical domain. Crucial to the success of this certainly not new sensing approach will be the capability of wearable inertial sensor networks to accurately recognize the type of activity performed (context awareness) and to determine the person’s current location (personal navigation), eventually in combination with other biomechanical or physiological sensors — key requirements in applications of wearable and mobile computing as well. This chapter reviews sensor configurations and computational techniques that have been implemented or are considered to meet the converging requirements of a wealth of application products, including ambulatory monitors for automatic recognition of activity, quantitative analysis of motor performance, and personal navigation systems.

Computational Modelling in Shoulder Biometrics

The objectives of this chapter are as follows. First, a background in anatomy and biomechanics of the shoulder complex is presented to provide a brief review of the essential functions of the shoulder. Second, important features of practical shoulder models are discussed with reference to capabilities of current computational modelling techniques. Third, techniques in computational modelling of the shoulder complex are compared and contrasted for their effectiveness in representing shoulder biomechanics in situ, with some sample calculations included. Fourth, in vivo and in vitro techniques for verifying computational models will be briefly reviewed. Finally, a summary of emerging trends will indicate the clinical impact that computational modelling can be expected to have in progressing our understanding of shoulder complex movement and its fundamental biomechanics.

Dynamic Pattern Recognition in Sport by Means of Artificial Neural Networks

Behavioural processes like those in sports, motor activities or rehabilitation are often the object of optimization methods. Such processes are often characterized by a complex structure. Measurements considering them may produce a huge amount of data. It is an interesting challenge not only to store these data, but also to transform them into useful information. Artificial Neural Networks turn out to be an appropriate tool to transform abstract numbers into informative patterns that help to understand complex behavioural phenomena. The contribution presents some basic ideas of neural network approaches and several examples of application. The aim is to give an impression of how neural methods can be used, especially in the field of sport.

Control of Man-Machine FES Systems

Movement disabilities due to spinal cord injury (SCI) are usually incomplete, leaving the patients with partially functioning movement system. As a result, functional electrical stimulation (FES) systems for restoration of movement to the paralyzed limbs must operate in parallel with the residual voluntary movements of the patient. In the resulting man-machine system, the central nervous system (CNS) controls the residual voluntary movements while the FES system controls the paralyzed muscles of the same limbs. Clearly, these two control systems must work in synchrony to benefit the patient. In this chapter we will discuss different methods for cooperative control of man-machine FES systems and use a clinical FES system to demonstrate the successful application of these strategies.

Visualisation of Clinical Gait Data Using a Self-Organising Artificial Neural Network

The decision-making performance of gait experts varies depending on their background, training and experience. They have to analyse large quantities of complex gait data and this gives rise to an unbalanced use of the available information. These limitations inevitably lead to a biased interpretation. In this study, self-organising artificial neural networks were used to reduce the complexity of joint kinematic and kinetic data which form part of a typical instrumented gait assessment. Three dimensional joint angles, moments and powers during the gait cycle were projected from the multi-dimensional data space onto a topological neural map which thereby identified gait stem-patterns. Patients were positioned on the map in relation to each other and this enabled them to be compared on the basis of their gait patterns. The visualisation of large amounts of complex data in a two-dimensional map labelled with gait patterns is an enabling step towards more objective analysis protocols which will better inform decision making.