Laurence Kenney

Activity identification using body-mounted sensors--a review of classification techniques.

With the advent of miniaturized sensing technology, which can be body-worn, it is now possible to collect and store data on different aspects of human movement under the conditions of free living. This technology has the potential to be used in automated activity profiling systems which produce a continuous record of activity patterns over extended periods of time. Such activity profiling systems are dependent on classification algorithms which can effectively interpret body-worn sensor data and identify different activities. This article reviews the different techniques which have been used to classify normal activities and/or identify falls from body-worn sensor data. The review is structured according to the different analytical techniques and illustrates the variety of approaches which have previously been applied in this field. Although significant progress has been made in this important area, there is still significant scope for further work, particularly in the application of advanced classification techniques to problems involving many different activities.

A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data

Driven by the demands on healthcare resulting from the shift toward more sedentary lifestyles, considerable effort has been devoted to the monitoring and classification of human activity. In previous studies, various classification schemes and feature extraction methods have been used to identify different activities from a range of different datasets. In this paper, we present a comparison of 14 methods to extract classification features from accelerometer signals. These are based on the wavelet transform and other well-known time- and frequency-domain signal characteristics. To allow an objective comparison between the different features, we used two datasets of activities collected from 20 subjects. The first set comprised three commonly used activities, namely, level walking, stair ascent, and stair descent, and the second a total of eight activities. Furthermore, we compared the classification accuracy for each feature set across different combinations of three different accelerometer placements. The classification analysis has been performed with robust subject-based cross-validation methods using a nearest-neighbor classifier. The findings show that, although the wavelet transform approach can be used to characterize nonstationary signals, it does not perform as accurately as frequency-based features when classifying dynamic activities performed by healthy subjects. Overall, the best feature sets achieved over 95% intersubject classification accuracy.

Inertial sensor-based knee flexion/extension angle estimation

A new method for estimating knee joint flexion/extension angles from segment acceleration and angular velocity data is described. The approach uses a combination of Kalman filters and biomechanical constraints based on anatomical knowledge. In contrast to many recently published methods, the proposed approach does not make use of the earths magnetic field and hence is insensitive to the complex field distortions commonly found in modern buildings. The method was validated experimentally by calculating knee angle from measurements taken from two IMUs placed on adjacent body segments. In contrast to many previous studies which have validated their approach during relatively slow activities or over short durations, the performance of the algorithm was evaluated during both walking and running over 5 minute periods. Seven healthy subjects were tested at various speeds from 1 to 5 mile/h. Errors were estimated by comparing the results against data obtained simultaneously from a 10 camera motion tracking system (Qualysis). The average measurement error ranged from 0.7 degrees for slow walking (1 mph) to 3.4 degrees for running (5 mph). The joint constraint used in the IMU analysis was derived from the Qualysis data. Limitations of the method, its clinical application and its possible extension are discussed.

Dimensional change in muscle as a control signal for powered upper limb prostheses: a pilot study

The vast majority of externally powered prostheses are controlled from the myoelectric signal, measured at the skin surface using socket-located electrodes. This signal has been well researched and sophisticated signal processing methods developed. Nevertheless, the inherent properties of the signal, such as its broad bandwidth and low voltage amplitude, make its use less than straightforward in the control of low frequency activity such as powered prosthetic hand movement. This paper reports on a pilot study of an alternative, a signal derived from dimensional change in muscle. A new socket-located sensor was designed to measure dimensional change in muscle, the linearised output of which is termed the myokinemetric (MK) signal. This was used in a series of tasks aimed at investigating the potential for its use in upper-limb prosthesis control. Six amputee subjects were tested, of whom one was a regular user of the myoelectric hand, one had some experience, and four had little or no previous experience of controlling devices using their residual limb. Data is presented on the problems of shift in signal range with time and socket donning and doffing and on the ability of subjects to control the amplitude of the signal. The results show that subjects were able to control the magnitude of the MK signal to a significant degree, with typical errors averaging 0.1-0.3 mm, around 10% of the signal range. The principal problem encountered was the shift in signal with time and socket donning and doffing.

Automated Detection of Instantaneous Gait Events Using Time Frequency Analysis and Manifold Embedding

Accelerometry is a widely used sensing modality in human biomechanics due to its portability, non-invasiveness, and accuracy. However, difficulties lie in signal variability and interpretation in relation to biomechanical events. In walking, heel strike and toe off are primary gait events where robust and accurate detection is essential for gait-related applications. This paper describes a novel and generic event detection algorithm applicable to signals from tri-axial accelerometers placed on the foot, ankle, shank or waist. Data from healthy subjects undergoing multiple walking trials on flat and inclined, as well as smooth and tactile paving surfaces is acquired for experimentation. The benchmark timings at which heel strike and toe off occur, are determined using kinematic data recorded from a motion capture system. The algorithm extracts features from each of the acceleration signals using a continuous wavelet transform over a wide range of scales. A locality preserving embedding method is then applied to reduce the high dimensionality caused by the multiple scales while preserving salient features for classification. A simple Gaussian mixture model is then trained to classify each of the time samples into heel strike, toe off or no event categories. Results show good detection and temporal accuracies for different sensor locations and different walking terrains.

Automatic identification of gait events using an instrumented sock

BackgroundTextile-based transducers are an emerging technology in which piezo-resistive properties of materials are used to measure an applied strain. By incorporating these sensors into a sock, this technology offers the potential to detect critical events during the stance phase of the gait cycle. This could prove useful in several applications, such as functional electrical stimulation (FES) systems to assist gait.MethodsWe investigated the output of a knitted resistive strain sensor during walking and sought to determine the degree of similarity between the sensor output and the ankle angle in the sagittal plane. In addition, we investigated whether it would be possible to predict three key gait events, heel strike, heel lift and toe off, with a relatively straight-forward algorithm. This worked by predicting gait events to occur at fixed time offsets from specific peaks in the sensor signal.ResultsOur results showed that, for all subjects, the sensor output exhibited the same general characteristics as the ankle joint angle. However, there were large between-subjects differences in the degree of similarity between the two curves. Despite this variability, it was possible to accurately predict gait events using a simple algorithm. This algorithm displayed high levels of trial-to-trial repeatability.ConclusionsThis study demonstrates the potential of using textile-based transducers in future devices that provide active gait assistance.

The Sensitivity and Selectivity of an Implantable Two-Channel Peroneal Nerve Stimulator System for Restoration of Dropped Foot

The objective of this study was to evaluate the stimulation responses on each channel of an implantable two‐channel stimulator that stimulates the peroneal nerve branches innervating the muscles for dorsiflexion and eversion movements. Currently five Dutch patients and five English patients have been implanted with this system. Isometric ankle torque measurements were carried out in the patient with the longest follow‐up period (1 y). A force sensor measured the three components of moment generated at the ankle joint. Stimulation intensity can be adjusted with great accuracy. Dorsiflexion moments are almost entirely determined by the setting of channel 1. Eversion moments are determined mainly by channel 2 and to a lesser extent by channel 1. Both channels determined abduction/adduction moments. We conclude that stimulation responses in both dorsiflexion and eversion direction can be set individually and with great accuracy and are reproducible over a prolonged period.

The effects of prosthetic ankle stiffness on ankle and knee kinematics, prosthetic limb loading, and net metabolic cost of trans-tibial amputee gait

BACKGROUND Previous studies of commercially-available trans-tibial prosthetic components have been unable to provide clear insight into the relationships between prosthetic mechanical properties and user performance (i.e., gait quality and energy expenditure), the understanding of which is key to improving prosthesis design and prescription. Many of these studies have been limited by not characterising the mechanical properties of the tested prostheses and/or only considered level walking at self-selected speeds. The aim of this study was to conduct a systematic investigation of the effects of ankle rotational stiffness on trans-tibial amputee gait during various walking conditions reflective of those encountered during daily ambulation. METHODS Ankle and knee kinematics, prosthetic limb normal ground reaction forces, and net metabolic cost were measured in five traumatic unilateral trans-tibial amputees during treadmill walking on the level, a 5% incline and a 5% decline whilst using an experimental articulated prosthetic foot with four different rotational stiffness setups and without changes in alignment between conditions. FINDINGS Overall, lower dorsiflexion stiffness resulted in greater prosthetic side dorsiflexion motion and sound side knee flexion, reduced normal ground reaction force during the loading phase of prosthetic stance and reduced net metabolic cost. INTERPRETATION Few differences were observed with changes in plantarflexion stiffness, most likely due to the foot achieving early foot flat. Low dorsiflexion stiffness generally improved gait performance seemingly due to easier tibial progression during stance. However, observed differences were small, suggesting that a wider range of walking and stiffness conditions would be useful to fully explore these effects in future studies.

Amputee independent prosthesis properties - a new model for description and measurement

A model is presented for describing the Amputee Independent Prosthesis Properties (AIPP) of complete assemblies of trans-tibial prosthetic components distal to the socket. This new AIPP model includes features of both lumped parameter and roll-over models and describes prosthesis properties that are of importance in stance phase, including prosthetic foot geometry, normal stiffness, shear stiffness, and damping (energy dissipation). Methods are described for measuring the parameters of the AIPP model using a custom test-rig, commercial load-cell, and a motion capture system. Example data are presented for five pylon angles reflecting the shank angles seen in normal gait. Through the inclusion of measured AIPP in future in-vivo studies comparing different prostheses more generic information, as opposed to product specific claims, will become more widely available to inform future designs, prescription, and alignment procedures.

Visuomotor behaviours when using a myoelectric prosthesis.

BackgroundA recent study showed that the gaze patterns of amputee users of myoelectric prostheses differ markedly from those seen in anatomically intact subjects. Gaze behaviour is a promising outcome measures for prosthesis designers, as it appears to reflect the strategies adopted by amputees to compensate for the absence of proprioceptive feedback and uncertainty/delays in the control system, factors believed to be central to the difficulty in using prostheses. The primary aim of our study was to characterise visuomotor behaviours over learning to use a trans-radial myoelectric prosthesis. Secondly, as there are logistical advantages to using anatomically intact subjects in prosthesis evaluation studies, we investigated similarities in visuomotor behaviours between anatomically intact users of a trans-radial prosthesis simulator and experienced trans-radial myoelectric prosthesis users.MethodsIn part 1 of the study, we investigated visuomotor behaviours during performance of a functional task (reaching, grasping and manipulating a carton) in a group of seven anatomically intact subjects over learning to use a trans-radial myoelectric prosthesis simulator (Dataset 1). Secondly, we compared their patterns of visuomotor behaviour with those of four experienced trans-radial myoelectric prosthesis users (Dataset 2). We recorded task movement time, performance on the SHAP test of hand function and gaze behaviour.ResultsDataset 1 showed that while reaching and grasping the object, anatomically intact subjects using the prosthesis simulator devoted around 90% of their visual attention to either the hand or the area of the object to be grasped. This pattern of behaviour did not change with training, and similar patterns were seen in Dataset 2. Anatomically intact subjects exhibited significant increases in task duration at their first attempts to use the prosthesis simulator. At the end of training, the values had decreased and were similar to those seen in Dataset 2.ConclusionsThe study provides the first functional description of the gaze behaviours seen during use of a myoelectric prosthesis. Gaze behaviours were found to be relatively insensitive to practice. In addition, encouraging similarities were seen between the amputee group and the prosthesis simulator group.