Daniel T. H. Lai

A Survey on Intrabody Communications for Body Area Network Applications

The rapid increase in healthcare demand has seen novel developments in health monitoring technologies, such as the body area networks (BAN) paradigm. BAN technology envisions a network of continuously operating sensors, which measure critical physical and physiological parameters e.g., mobility, heart rate, and glucose levels. Wireless connectivity in BAN technology is key to its success as it grants portability and flexibility to the user. While radio frequency (RF) wireless technology has been successfully deployed in most BAN implementations, they consume a lot of battery power, are susceptible to electromagnetic interference and have security issues. Intrabody communication (IBC) is an alternative wireless communication technology which uses the human body as the signal propagation medium. IBC has characteristics that could naturally address the issues with RF for BAN technology. This survey examines the on-going research in this area and highlights IBC core fundamentals, current mathematical models of the human body, IBC transceiver designs, and the remaining research challenges to be addressed. IBC has exciting prospects for making BAN technologies more practical in the future.

Wavelet-Based Feature Extraction for Support Vector Machines for Screening Balance Impairments in the Elderly

Trip related falls are a prevalent problem in the elderly. Early identification of at-risk gait can help prevent falls and injuries. The main aim of this study was to investigate the effectiveness of a wavelet based multiscale analysis of a gait variable [minimum foot clearance (MFC)] in comparison to MFC histogram plot analysis in extracting features for developing a model using support vector machines (SVMs) for screening of balance impairments in the elderly. MFC during walking on a treadmill was recorded on 13 healthy elderly and 10 elderly with a history of tripping falls. Features extracted from MFC histogram and then multiscale exponents between successive wavelet coefficient levels after wavelet decomposition of MFC series were used as inputs to the SVM to classify two gait patterns. The maximum accuracy of classification was found to be 100% for a SVM using a subset of selected wavelet based features, compared to 86.95% accuracy using statistical features. For estimating the relative risk of falls, the posterior probabilities of SVM outputs were calculated. These results suggest superior performance of SVM in the detection of balance impairments based on wavelet-based features and it could also be useful for evaluating for falls prevention intervention.

Computational Intelligence in Gait Research: A Perspective on Current Applications and Future Challenges

Our mobility is an important daily requirement so much so that any disruption to it severely degrades our perceived quality of life. Studies in gait and human movement sciences, therefore, play a significant role in maintaining the well-being of our mobility. Current gait analysis involves numerous interdependent gait parameters that are difficult to adequately interpret due to the large volume of recorded data and lengthy assessment times in gait laboratories. A proposed solution to these problems is computational intelligence (CI), which is an emerging paradigm in biomedical engineering most notably in pathology detection and prosthesis design. The integration of CI technology in gait systems facilitates studies in disorders caused by lower limb defects, cerebral disorders, and aging effects by learning data relationships through a combination of signal processing and machine learning techniques. Learning paradigms, such as supervised learning, unsupervised learning, and fuzzy and evolutionary algorithms, provide advanced modeling capabilities for biomechanical systems that in the past have relied heavily on statistical analysis. CI offers the ability to investigate nonlinear data relationships, enhance data interpretation, design more efficient diagnostic methods, and extrapolate model functionality. These are envisioned to result in more cost-effective, efficient, and easy-to-use systems, which would address global shortages in medical personnel and rising medical costs. This paper surveys current signal processing and CI methodologies followed by gait applications ranging from normal gait studies and disorder detection to artificial gait simulation. We review recent systems focusing on the existing challenges and issues involved in making them successful. We also examine new research in sensor technologies for gait that could be combined with these intelligent systems to develop more effective healthcare solutions.

Investigation of Galvanic-Coupled Intrabody Communication Using the Human Body Circuit Model

Intrabody Communication (IBC) is a technique that uses the human body as a transmission medium for electrical signals to connect wearable electronic sensors and devices. Understanding the human body as the transmission medium in IBC paves way for practical implementation of IBC in body sensor networks. In this study, we propose a model for galvanic coupling-type IBC based on a simplified equivalent circuit representation of the human upper arm. We propose a new way to calculate the electrode-skin contact impedance. Based on the model and human experimental results, we discuss important characteristics of galvanic coupling-type IBC, namely, the effect of tissues, anthropometry of subjects, and electrode configuration on signal propagation. We found that the dielectric properties of the muscle primarily characterize the received signal when receiver electrodes are located close to transmitter electrodes. When receiver and transmitter electrodes are far apart, the skin dielectric property affects the received signal.

Automatic Recognition of Gait Patterns Exhibiting Patellofemoral Pain Syndrome Using a Support Vector Machine Approach

Patellofemoral pain syndrome (PFPS) is a common disorder that afflicts people across all age groups, and results in various degrees of knee pain. The diagnosis of PFPS is difficult since the exact biomechanical factors and the extent to which they are affected by the disorder are still unknown. Recent research has reported significant statistical differences in ground reaction forces (GRFs) and foot kinematics, which could be indicative of PFPS, but the interrelationship between many of these measures and the pathology have been absent so far. In this paper, we applied the support vector machines (SVMs) to detect PFPS gait based on 14 GRF and 16 foot kinematic features recorded from 27 subjects (14 healthy and 13 with PFPS). The influence of combined gait parameters on classification performance was investigated through the use of a feature-selection algorithm. The optimal feature set was then compared against the most statistically significant individual features (p < 0.05) found by previous study. Test results indicated that GRF features alone resulted in a higher leave-one-out (LOO) classification accuracy (85.15%) compared to 74.07% using only kinematic features. A hill-climbing feature-selection algorithm was applied to determine the subset of combined kinematic and kinetic features, which provided optimal classifier performance. This subset, which consists of six features (two from GRF and four from foot kinematic features), provided an improved LOO accuracy of 88.89% . The optimal feature set detected by the SVM, which best identified gait characteristics of PFPS, was found to be closely related to inferential statistical analysis with the added distinction that the SVM could potentially be deployed as an automated system for detecting gait changes in patients with PFPS.

Detection of tripping gait patterns in the elderly using autoregressive features and support vector machines

Elderly tripping falls cost billions annually in medical funds and result in high mortality rates often perpetrated by pulmonary embolism (internal bleeding) and infected fractures that do not heal well. In this paper, we propose an intelligent gait detection system (AR-SVM) for screening elderly individuals at risk of suffering tripping falls. The motivation of this system is to provide early detection of elderly gait reminiscent of tripping characteristics so that preventive measures could be administered. Our system is composed of two stages, a predictor model estimated by an autoregressive (AR) process and a support vector machine (SVM) classifier. The system input is a digital signal constructed from consecutive measurements of minimum toe clearance (MTC) representative of steady-state walking. The AR-SVM system was tested on 23 individuals (13 healthy and 10 having suffered at least one tripping fall in the past year) who each completed a minimum of 10 min of walking on a treadmill at a self-selected pace. In the first stage, a fourth order AR model required at least 64 MTC values to correctly detect all fallers and non-fallers. Detection was further improved to less than 1 min of walking when the model coefficients were used as input features to the SVM classifier. The system achieved a detection accuracy of 95.65% with the leave one out method using only 16 MTC samples, but was reduced to 69.57% when eight MTC samples were used. These results demonstrate a fast and efficient system requiring a small number of strides and only MTC measurements for accurate detection of tripping gait characteristics.

Measuring toe clearance using a wireless inertial sensing device

Tripping and slipping falls are serious health concerns for the elderly because they incur high medical costs and can result in life threatening injuries i.e., internal bleeding. Recently there has been an increased interest in the development of portable inertial sensing devices for measuring human movement. These devices employ acceleration and angular data to obtain limb motion such as velocity and displacement through integration of acceleration values. In this paper, we investigate the performance of a wireless inertial sensing device for monitoring vertical toe clearance during walking. It has been demonstrated that variability in minimum toe clearance (MTC) which occurs during the swing phase is a sensitive falls risk predictor. Our device is composed of a tri-axis accelerometer and dual-axis gyroscope wirelessly connected through the use of Crossbow motes. The vertical toe clearance is obtained through double integration of the resultant acceleration in the vertical direction. We have performed zero base, treadmill and intersubject experiments to investigate device performance to environmental variations and compared the calculated toe clearance against measurements made by an Optotrak motion system. It was found that device outputs were approximately independent of small ambient temperature variations, had a reliable range of 20 m indoors and 50 m outdoors and a maximum transmission rate of 20 packets/s. Toe clearance measurements coincided with Optotrak measurement trends but suffered from cumulative integration errors over time. The identification, quantification and reduction of these errors are intricate but important further research issues.

Prediction of foot clearance parameters as a precursor to forecasting the risk of tripping and falling.

Tripping and falling is a serious health problem for older citizens due to the high medical costs incurred and the high mortality rates precipitated mostly by hip fractures that do not heal well. Current falls prevention technology encompasses a broad range of interventions; both passive (e.g., safer environments, hip protectors) and active (e.g., sensor-based fall detectors) which attempt to reduce the effects of tripping and falling. However the majority of these interventions minimizes the impact of falls and do not directly reduce the risk of falling. This paper investigates the prediction of gait parameters related to foot-to-ground clearance height during the leg swing phase which have been physically associated with tripping and falling risk in the elderly. The objective is to predict parameters of foot trajectory several walking cycles in advance so that anticipated low foot clearance could be addressed early with more volitional countermeasures, e.g., slowing down or stopping. In this primer study, foot kinematics was recorded with a highly accurate motion capture system for 10 healthy adults (25-32 years) and 11 older adults (65-82 years) with a history of falls who each performed treadmill walking for at least 10 min. Vertical foot displacement during the swing phase has three characteristic inflection points and we used these peak values and their normalized time as the target prediction values. These target variables were paired with features extracted from the corresponding foot acceleration signal (obtained through double differentiation). A generalized regression neural network (GRNN) was used to independently predict the gait variables over a prediction horizon (number of gait cycles ahead) of 1-10 gait cycles. It was found that the GRNN attained 0.32-1.10 cm prediction errors in the peak variables and 2-8% errors in the prediction of normalized peak times, with slightly better accuracies in the healthy group compared to elderly fallers. Prediction accuracy decreased linearly (best fit) at a slow rate with increasing prediction horizon ranging from 0.03 to 0.11 cm per step for peak displacement variables and 0.34 × 10(-3) - 1.81 × 10(-3)% per step for normalized peak time variables. Further time series analysis of the target gait variable revealed high autocorrelations in the faller group indicating the presence of cyclic patterns in elderly walking strategies compared to almost random walking patterns in the healthy group. The results are promising because the technique can be extended to portable sensor-based devices which measure foot accelerations to predict the onset of risky foot clearance, thus leading to a more effective falls prevention technology.

The application of support vector machines for detecting recovery from knee replacement surgery using spatio-temporal gait parameters

Knee osteoarthritis (OA) is one of the leading causes of disability among the elderly which, depending on severity, may require surgical intervention. Knee replacement surgery provides pain relief and improves physical function including gait. However gait dysfunction such as altered spatio-temporal measures may persist after the surgery. In this paper, we investigated the application of support vector machines (SVM) to classify gait patterns indicative of knee OA before surgery based on 12 spatio-temporal gait parameters and investigated whether SVMs could be used to predict gait improvement 2 and 12 months following knee replacement surgery. Test results for the pre-operative data indicated that the SVM could successfully identify individuals with OA gait from the healthy using all of the spatio-temporal parameters with a maximum leave one out accuracy of 100% for the training set and 88.89% for the test set. Findings indicated that three patients still had altered gait patterns 2 months post-knee replacement surgery, but all individuals showed improvement in gait 12 months following surgery. Consequently, the SVM detected improvement in gait function due to surgical intervention at 2 and 12 months following knee replacement which coincided with clinical assessment of the knee. This suggests that spatio-temporal parameters contain important discriminative information which may be used for the identification of pathological gait using an SVM classifier.

A Division Algebraic Framework for Multidimensional Support Vector Regression

In this paper, division algebras are proposed as an elegant basis upon which to extend support vector regression (SVR) to multidimensional targets. Using this framework, a multitarget SVR called ¿Z-SVR is proposed based on an ¿-insensitive loss function that is independent of the coordinate system or basis used. This is developed to dual form in a manner that is analogous to the standard ¿-SVR. The ¿H-SVR is compared and contrasted with the least-square SVR (LS-SVR), the Clifford SVR (C-SVR), and the multidimensional SVR (M-SVR). Three practical applications are considered: namely, 1) approximation of a complex-valued function; 2) chaotic time-series prediction in 3-D; and 3) communication channel equalization. Results show that the ¿H-SVR performs significantly better than the C-SVR, the LS-SVR, and the M-SVR in terms of mean-squared error, outlier sensitivity, and support vector sparsity.