James Tung

3D Pose tracking of walker users' lower limb with a structured-light camera on a moving platform

Tracking and understanding human gait is an important step towards improving elderly mobility and safety. Our research team is developing a vision-based tracking system that estimates the 3D pose of a wheeled walker users lower limbs with a depth sensor, Kinect, mounted on the moving walker. Our tracker estimates 3D poses from depth images of the lower limbs in the coronal plane in a dynamic, uncontrolled environment. We employ a probabilistic approach based on particle filtering, with a measurement model that works directly in the 3D space and another measurement model that works in the projected image space. Empirical results show that combining both measurements, assuming independence between them, yields tracking results that are better than with either one alone. Experiments are conducted to evaluate the performance of the tracking system with different users. We demonstrate that the tracker is robust against unfavorable conditions such as partial occlusion, missing observations, and deformable tracking target. Also, our tracker does not require user intervention or manual initialization commonly required in most trackers.

Measuring Life Space in Older Adults with Mild-to-Moderate Alzheimer's Disease Using Mobile Phone GPS

Background: As an indicator of physical and cognitive functioning in community-dwelling older adults, there is increasing interest in measuring life space, defined as the geographical area a person covers in daily life. Typically measured through questionnaires, life space can be challenging to assess in amnestic dementia associated with Alzheimers disease (AD). While global positioning system (GPS) technology has been suggested as a potential solution, there remains a lack of data validating GPS-based methods to measure life space in cognitively impaired populations. Objective: The purpose of the study was to evaluate the construct validity of a GPS system to provide quantitative measurements of global movement for individuals with mild-to-moderate AD. Methods: Nineteen community-dwelling older adults with mild-to-moderate AD (Mini-Mental State Examination score 14-28, age 70.7 ± 2.2 years) and 33 controls (CTL; age 74.0 ± 1.2 years) wore a GPS-enabled mobile phone during the day for 3 days. Measures of geographical territory (area, perimeter, mean distance from home, and time away from home) were calculated from the GPS log. Following a log-transformation to produce symmetrical distributions, group differences were tested using two-sample t tests. Construct validity of the GPS measures was tested by examining the correlation between the GPS measures and indicators of physical function [steps/day, gait velocity, and Disability Assessment for Dementia (DAD)] and affective state (Apathy Evaluation Scale and Geriatric Depression Scale). Multivariate regression was performed to evaluate the relative strength of significantly correlated factors. Results: GPS-derived area (p < 0.01), perimeter (p < 0.01), and mean distance from home (p < 0.05) were smaller in the AD group compared to CTL. The correlation analysis found significant associations of the GPS measures area and perimeter with all measures of physical function (steps/day, DAD, and gait velocity; p < 0.01), symptoms of apathy (p < 0.01), and depression (p < 0.05). Multivariate regression analysis indicated that gait velocity and dependence were the strongest variables associated with GPS measures. Conclusion: This study demonstrated that GPS-derived area and perimeter: (1) distinguished mild-to-moderate AD patients from CTL and (2) were strongly correlated with physical function and affective state. These findings confirm the ability of GPS technology to assess life space behaviour and may be particularly valuable to continuously monitor functional decline associated with neurodegenerative disease, such as AD.

Everyday Patient-Care Technologies for Alzheimer's Disease

The Alzheimers Association has stimulated collaboration and scientific advancement in preventing and treating Alzheimers disease by bringing together leading researchers developing technological approaches offering promise in this area. This year, the Alzheimers Association collaborated with the International Society to Advance Alzheimers Research and Treatment to organize the first Technology & Dementia symposium at the 2013 Alzheimers Association International Conference in Boston. Here, the authors present some of the projects discussed at the symposium, which address early diagnosis, monitoring, treatment, and assistance.

Frontal plane standing balance with an ambulation aid:Upper limb biomechanics

Despite widespread acceptance of clinical benefits, empirical evidence to evaluate the advantages and limitations of ambulation aids for balance control is limited. The current study investigates the upper limb biomechanical contributions to the control of frontal plane stability while using a 4-wheeled walker in quiet standing. We hypothesized that: (1) upper limb stabilizing moments would be significant, and (2) would increase under conditions of increased stability demand. Factors influencing upper limb moment generation were also examined. Specifically, the contributions of upper limb center-of-pressure (COP(hands)), vertical and horizontal loads applied to the assistive device were assessed. The results support a significant mechanical role for the upper limbs, generating 27.1% and 58.8% of overall stabilizing moments under baseline and challenged stability demand conditions, respectively. The increased moment was achieved primarily through the preferential use of phasic upper limb control, reflected by increased COP(hands) (baseline vs. challenged conditions: 0.29 vs. 0.72cm). Vertical, but not horizontal, was the primary force direction contributing to stabilizing moments in quiet standing. The key finding that the upper limbs play an important role in effecting frontal plane balance control has important implications for ambulation aid users (e.g., elderly, stroke, and traumatic brain injury).

Upper Limb Contributions to Frontal Plane Balance Control in Rollator-Assisted Walking

While assisting with balance is a primary reason for rollator use, few studies have examined how the upper limbs are used for balance. This study examines upper limb contributions to balance control during rollator-assisted walking. We hypothesized that there would be an increased upper limb contribution, measured by mean vertical loading (Fz) and variation in frontal plane center-of-pressure (COPhigh), when walking balance is challenged/impaired. Experiment 1 compared straight-line and beam-walking in young adults (n = 11). As hypothesized, Fz and COPhighincreased in beam-walking compared to baseline (mean Fz: 13.7 vs. 9.1% body weight (BW), p < 0.001, RMS COPhigh: 1.35 vs. 1.07 cm, p < 0.001). Experiment 2 compared older adults who regularly use rollators (RU, n = 10) to older adult controls (CTL, n = 10). The predicted higher upper limb contribution in the RU group was not supported. However, when individuals were grouped by balance impairment, those with the lowest Berg Balance scores (< 45) demonstrated greater speed-adjusted COPhigh than those with higher scores (p = 0.013). Furthermore, greater COPhigh and Fz were correlated to greater reduction in step width, supporting the role of upper limb contributions to frontal plane balance. This work will guide studies assessing reliance on rollators by providing a basis for measurement of upper limb balance contributions.

Use of mobility aids reduces attentional demand in challenging walking conditions

While mobility aids (e.g., four-wheeled walkers) are designed to facilitate walking and prevent falls in individuals with gait and balance impairments, there is evidence indicating that walkers may increase attentional demands during walking. We propose that walkers may reduce attentional demands under conditions that challenge balance control. This study investigated the effect of walker use on walking performance and attentional demand under a challenged walking condition. Young healthy subjects walked along a straight pathway, or a narrow beam. Attentional demand was assessed with a concurrent voice reaction time (RT) task. Slower RTs, reduced gait speed, and increased number of missteps (>92% of all missteps) were observed during beam-walking. However, walker use reduced attentional demand (faster RTs) and was linked to improved walking performance (increased gait speed, reduced missteps). Data from two healthy older adult cases reveal similar trends. In conclusion, mobility aids can be beneficial by reducing attentional demands and increasing gait stability when balance is challenged. This finding has implications on the potential benefit of mobility aids for persons who rely on walkers to address balance impairments.

Combining ambulatory and laboratory assessment of rollator use for balance and mobility in neurologic rehabilitation in-patients.

Abstract Purpose: Despite the common use of rollators (four-wheeled walkers), understanding their effects on gait and balance is limited to laboratory testing rather than everyday use. This study evaluated the utility of an ambulatory assessment approach to examine balance and mobility in everyday conditions compared to a laboratory assessment. Methods: Standing and walking with a rollator was assessed in three neurological rehabilitation in-patients under two conditions: (1) in laboratory (i.e. forceplate, GaitRite), and (2) while performing a natural walking course within and outside of the institution. An instrumented rollator (iWalker) was used to measure variables related to the balance control (e.g. upper limb kinetics), destabilizing events (e.g. stumbling), and environmental context. Results: Two of three patients demonstrated greater reliance on the rollator for standing balance (2.3–5.9 times higher vertical loading, 72–206% increase in COP excursion) and 29–42% faster gait during the walking course compared to the laboratory. Importantly, destabilizing events (collisions, stumbling) were recorded during the walking course. Such events were not observed in the laboratory. Conclusion: This study illustrated a greater reliance on the rollator during challenges in everyday use compared to laboratory assessment and provided evidence of specific circumstances associated with destabilizing events that may precipitate falls in non-laboratory settings. Implications for Rehabilitation The value of combining laboratory and ambulatory assessment approaches to provide a more comprehensive profile of the risks and benefits of rollator use to prevent falling was studied. Patients demonstrated greater reliance on rollator assistive devices for standing balance and exhibited higher gait speeds during ambulatory assessment, compared to standard laboratory protocols. Repeated instances of events that may precipitate falls (e.g. collisions, stumbling, and unloading behaviors) were observed only during the ambulatory assessment. Individual challenges to balance can be used to identify specific training targets, assess suitability for assistive devices, and recommend rehabilitation goals.

Can we use accelerometry to monitor balance exercise performance in older adults

While home-based balance exercises are recommended to reduce the risk of falling and fractures in older adults, adherence to exercise remains suboptimal. The long-term objective of this research is to advance body-worn sensor techniques to measure at-home exercise performance and promote adherence. In this study, a method of distinguishing 5 types of walking using hip- and ankle-worn accelerometers was developed and evaluated in a target clinical population. A secondary objective was to evaluate the methods sensitivity to sensor placement. Eighteen community-dwelling, older females (≥50 years) with low bone mass wore triaxial accelerometers at the left hip and each ankle while performing 5 walking tasks at home: 4 walking balance exercises (figure 8, heel-toe, sidestep, backwards) and straight-line walking. Sensor data were separated into low (0.5-2 Hz) and high (2-10 Hz) frequency bands, and root-mean-square values (energy) were computed for each sensor, axis, and band. These 18 energy estimates were used as inputs to a neural network classifier with 5 outputs, corresponding to each task. Using a leave-one-out cross-validation protocol, the neural network correctly classified 82/90 test instances (91% accuracy). Compared to random selection accuracy of 20% (i.e., 1 in 5), the results indicated excellent separation between tasks. Reducing the sensor set to one hip and one ankle resulted in 6.7-8.9% reduction in accuracy. Our findings can be used in the development of tools used to deliver exercise performance metrics (e.g., % completed) or recognize walking and balance exercise activities using body-worn accelerometers.

Detection of compensatory balance responses using wearable electromyography sensors for fall-risk assessment

Loss of balance is prevalent in older adults and populations with gait and balance impairments. The present paper aims to develop a method to automatically distinguish compensatory balance responses (CBRs) from normal gait, based on activity patterns of muscles involved in maintaining balance. In this study, subjects were perturbed by lateral pushes while walking and surface electromyography (sEMG) signals were recorded from four muscles in their right leg. To extract sEMG time domain features, several filtering characteristics and segmentation approaches are examined. The performance of three classification methods, i.e., k-nearest neighbor, support vector machines, and random forests, were investigated for accurate detection of CBRs. Our results show that features extracted in the 50-200Hz band, segmented using peak sEMG amplitudes, and a random forest classifier detected CBRs with an accuracy of 92.35%. Moreover, our results support the important role of biceps femoris and rectus femoris muscles in stabilization and consequently discerning CBRs. This study contributes towards the development of wearable sensor systems to accurately and reliably monitor gait and balance control behavior in at-home settings (unsupervised conditions), over long periods of time, towards personalized fall risk assessment tools.Loss of balance is prevalent in older adults and populations with gait and balance impairments. The present paper aims to develop a method to automatically distinguish compensatory balance responses (CBRs) from normal gait, based on activity patterns of muscles involved in maintaining balance. In this study, subjects were perturbed by lateral pushes while walking and surface electromyography (sEMG) signals were recorded from four muscles in their right leg. To extract sEMG time domain features, several filtering characteristics and segmentation approaches are examined. The performance of three classification methods, i.e., k-nearest neighbor, support vector machines, and random forests, were investigated for accurate detection of CBRs. Our results show that features extracted in the 50-200Hz band, segmented using peak sEMG amplitudes, and a random forest classifier detected CBRs with an accuracy of 92.35%. Moreover, our results support the important role of biceps femoris and rectus femoris muscles in stabilization and consequently discerning CBRs. This study contributes towards the development of wearable sensor systems to accurately and reliably monitor gait and balance control behavior in at-home settings (unsupervised conditions), over long periods of time, towards personalized fall risk assessment tools.

Radon-Gabor barcodes for medical image retrieval

In recent years, with the explosion of digital images on the Web, content-based retrieval has emerged as a significant research area. Shapes, textures, edges and segments may play a key role in describing the content of an image. Radon and Gabor transforms are both powerful techniques that have been widely studied to extract shape-texture-based information. The combined Radon-Gabor features may be more robust against scale/rotation variations, presence of noise, and illumination changes. The objective of this paper is to harness the potentials of both Gabor and Radon transforms in order to introduce expressive binary features, called barcodes, for image annotation/tagging tasks. We propose two different techniques: Gabor-of-Radon-Image Barcodes (GRIBCs), and Guided-Radon-of-Gabor Barcodes (GRGBCs). For validation, we employ the IRMA x-ray dataset with 193 classes, containing 12,677 training images and 1,733 test images. A total error score as low as 322 and 330 were achieved for GRGBCs and GRIBCs, respectively. This corresponds to ≈ 81% retrieval accuracy for the first hit.