Walking Person Research Articles

Abstracts Presented at the 2nd Annual Advancing Healthcare Innovation Summit: Nov 11, 2022, Cincinnati, OH

Abstracts Presented at the 2nd Annual Advancing Healthcare Innovation Summit: Nov 11, 2022, Cincinnati, OH

Surrogate lower limb design for ankle-foot orthosis mechanical evaluation.

This study designs and provides a pilot evaluation of a novel surrogate lower limb (SLL) that provides anatomically realistic three-dimensional (3D) foot motion, based on a literature consensus of passive lower limb motion. This SLL is intended to replace single axis surrogates currently used in mechanical testing of ankle-foot orthoses (AFO). The SLL design is inspired by the Rizzoli foot model, with shank, hindfoot, midfoot, forefoot, and toe sections. Ball and socket joints were used between hindfoot-midfoot (HM)-forefoot sections. Forefoot-toes used a hinge joint. Three-dimensional printed nylon, thermoplastic polyurethane (TPU) and polylactic acid (PLA), as well as casted silicone rubber were used to re-create foot components. After fabrication, motion capture was performed to measure rotation using fiducial markers. The SLL was then loaded under both static and cyclic loads representing a 100kg person walking for 500,000 cycles. Most joints were within 5° of target angles. The SLL survived static loads representing 1.5 times body weight for both static and cyclical loading. This SLL moved as designed and survived testing loads, warranting further investigation towards enabling essential mechanical testing for AFO currently on the market, and helping to guide device prescription.

Footstep Power Generation Using Piezoelectric Sensor

Abstract: Man has needed and used energy at an increasing rate for the sustenance and well-being since time immemorial. Due to this a lot of energy resources have been exhausted and wasted. Proposal for the utilization of waste energy of foot power with human locomotion is very much relevant and important for highly populated countries like India where the railway station, temples etc., are overcrowded all round the clock. When the flooring is engineered with piezo electric technology, the electrical energy produced by the pressure is captured by floor sensors and converted to an electrical charge by piezo transducers, then stored and used as a power source. And this power source has many applications as in agriculture, home application and street lighting and as energy source for sensors in remote locations. This paper is all about generating electricity when people walk on the Floor. Think about the forces you exert which is wasted when a person walks. The idea is to convert the weight energy to electrical energy The Power generating floor intends to trans- late the kinetic energy to the electrical power. Energy Crisis is the main issue of world these days. The motto of this research work is to face this crisis somehow. Though it won't meet the requirement of electricity but as a matter of fact if we are able to design a power generating floor that can produce 100W on just 12 steps, then for 120 steps we can produce 1000 Watt and if we install such type of 100 floors with this system then it can produce 1MegaWatt. Which itself is an achievement to make it significant. Keywords: Piezoelectric sensor, Footstep, remote location, force and pressure, power generation

Validation of a Platform for the Electrostatic Characterization of Textile

Floor covering samples of different thickness, pile height, pile design, materials, construction methods, and applied finishes were selected for electrostatic characterization with a standard plotter platform and a newly designed digital platform. There is an existing standard ISO 6356 in which the voltage generated by a human walking on the carpet is measured with human involvement under controlled conditions. A walking person performs the original test procedure to generate the electrostatic charge and manually calculates results. In contrast, the newly designed system does not require a person to calculate peaks and valleys for the generated electrostatic charges, which offers advantages in terms of accuracy, consistency, and reproducibility, and eliminates human error. The electronic platform is extended with an automated foot for a fully automated test, called “automatic mode”, that has a fixed capacitive and resistive circuit, in replace of human body resistance, and capacitance that varies from person to person and over time. The procedure includes both the old and new platforms, where the new platform is placed in a “human walking” mode to compare the two and validate the new device. Next, all the floor coverings are tested in automatic mode with the automated foot to compare and validate results. We conclude that the new testing device can fully characterize the electrostatic behavior of textile without the involvement of a human, which offers advantages in terms of accuracy, consistency, and reproducibility.

Leveraging Smartphone Sensors for Detecting Abnormal Gait for Smart Wearable Mobile Technologies

Walking is one of the most common modes of terrestrial locomotion for humans. Walking is essential for humans to perform most kinds of daily activities. When a person walks, there is a pattern in it, and it is known as gait. Gait analysis is used in sports and healthcare. We can analyze this gait in different ways, like using video captured by the surveillance cameras or depth image cameras in the lab environment. It also can be recognized by wearable sensors. e.g., accelerometer, force sensors, gyroscope, flexible goniometer, magneto resistive sensors, electromagnetic tracking system, force sensors, and electromyography (EMG). Analysis through these sensors required a lab condition, or users must wear these sensors. For detecting abnormality in gait action of a human, we need to incorporate the sensors separately. We can know about one's health condition by abnormal human gait after detecting it. Understanding a regular gait vs. abnormal gait may give insights to the health condition of the subject using the smart wearable technologies. Therefore, in this paper, we proposed a way to analyze abnormal human gait through smartphone sensors. Though smart devices like smartphones and smartwatches are used by most of the person nowadays. So, we can track down their gait using sensors of these intelligent wearable devices. In this study, we used twenty-three (N=23) people to record their walking activities. Among them fourteen people have normal gait actions, and nine people were facing difficulties with their walking due to their illness. To do the stratification of the gait of the subjects, we have adopted five machine learning algorithms with addition a deep learning algorithm. The advantages of the traditional classification are analyzed and compared among themselves. After rigorous performance analysis we found support vector machine (SVM) showing 96% accuracy, highest among the tradition classifiers. 70%, 84%, and 95% accuracy is obtained by the logistic regression, Naïve Bayes, and k-Nearest Neighbor (kNN) classifiers, respectively. As per the state-of-the art, deep learning classifiers has been proven to outperform the traditional classifiers in similar binary classification problems. We have considered the scenario and applied the 2D convolutional neural network (2D-CNN) classification algorithm, which outperformed the other algorithms showing accuracy of 98%. The model can be optimized and can be integrated with the other sensors to be utilized in the mobile wearable devices.

Persons with Parkinson's disease show impaired interlimb coordination during backward walking

IntroductionAlthough there is growing literature supporting the implementation of backward walking as a potential rehabilitation tool, moving backwards may precipitate falls for persons with Parkinson's disease. We sought to better understand interlimb coordination during backward walking in comparison to forward walking in persons with Parkinson's disease and healthy controls. MethodsWe assessed coordination using point estimate of relative phase at each participant's preferred walking speed. ResultsPersons with Parkinson's disease demonstrated impaired interlimb coordination between the more affected arm and each leg compared to controls, which worsened during backward walking. ConclusionFor those with Parkinson's disease, inability to output smooth coordinated movement of the more affected shoulder may impair coordination during forward and, especially, backward walking. Our findings provide new information about backward walking that can allow clinicians to make safer, more effective therapeutic recommendations for persons with Parkinson's disease.

Multipurposed Intelligent ID Card for Social Distancing & Safety Emergency alert systems

Abstract: This proposed invention is related with multipurpose device which is intelligent id card provided to the employee will help track and trace by connecting to the respective corporate server network. This server acts as a central intelligence and provides a dashboard that will help set up and get data and insights. These constantly monitor the smart cards and transmit their position to the central system. Many important multi-tasking tasks can be performed using this smart ID card which has the ability to provide real-time location information and also automatically identify if the person is where they should be. Accidents, such as a person walking into a danger zone, can be easily reported. In the event of a fire, you can quickly find the total people count along with the latest positions. The crowding of places such as offices, shops, workplaces, bathrooms, canteens, etc. it can be reported in real-time in order to avoid any infections. The temperature measurement alone is useless if the readings are not associated with the employee and are recorded to analyses trends. The proposed ID card will keep track of the number of times the employee has washed their hands. If not, a social notification will be raised. With real-time monitoring, you can easily provide daily attendance data to HR for payroll calculation and contract work invoice review. The employee's Bluetooth tag will help track time spent within the authorized area and will sound an alarm if the person enters a danger zone, all in real-time. The employee tag will allow the employee to send an SOS signal in case of any danger or panic situation. It will not be necessary to keep an attendance register. The tag will automatically record the time of entry and exit. A body sensor attached to the ID card will detect if the card is moved away from the body and kept aside. Hence, there is no possibility of cheating. The battery inside the card would last 5 to 10 years. IP 65, therefore resistant to water and rain. No maintenance is required. Keywords: Covid-19 study, Safety Device, Health Tracking, Social distancing, smart id.

Sales promotion: the role of equity sensitivity

PurposeThis paper explores how consumer psychographics impact responses to sales promotions (SPs), and specifically whether equity sensitivity (ES) moderates attitudes towards sales promotion in the retail purchase experience (PE).Design/methodology/approachThe study examines data from a survey of 284 Hong Kong consumers, using a shopping mall-intercept method. Every third person walking past the researchers was asked to participate in the survey. After obtaining their permission, those agreeing to take part in the study were surveyed either inside or outside of the shopping complex. The face-to-face intercept surveying method also increases confidence in sample and response reliability.FindingsThe study finds that ES has a significant positive relationship with evaluations of the retail PE. Consumers identified as “Benevolents” were significantly more positive towards SPs and reported significantly higher satisfaction with the PE. In contrast, consumers identified as “Entitled” were less positive towards SP and less satisfied with the PE. In addition, noncash SPs significantly positively influenced Benevolents' PE.Research limitations/implicationsThe current study extends and expands equity theory and ES research by applying these concepts to consumer SPs. The study is limited to an examination of common consumer purchases, across different product categories and SP types. While this allows us to examine the relationship between SP attitudes, ES and purchase satisfaction, future comparisons between individual sales promotion techniques (SPTs) and specific consumer profiles are recommended.Practical implicationsFrom a retail perspective, it is important to understand individual differences and what influences and motivates the consumers' retail PE. Retail managers are advised to track customer purchases and satisfaction levels linked to SPs as this would allow for the identification of which customers are more likely to fit the Entitled or Benevolent psychological profiles and predict their likely responses to SP offers.Originality/valueTo date, there has been little research on individual psychological differences between consumers when offered SPs at retail stores. The current study contributes to the marketing literature by extending the price fairness equity model to the retail PE, thereby addressing a prominent gap in the literature.

Camera-Based Human Gait Speed Monitoring and Tracking for Performance Assessment of Elderly Patients with Cancer.

This paper presents a camera-based device for monitoring walking gait speed. The walking gait speed data will be used for performance assessment of elderly patients with cancer and calibrating wearable walking gait speed monitoring devices. This standalone device has a Raspberry Pi computer, three cameras (two cameras for finding the trajectory and gait speed of the subject and one camera for tracking the subject), and two stepper motors. The stepper motors turn the camera platform left and right and tilt it up and down by using video footage from the center camera. The left and right cameras are used to record videos of the person walking. The algorithm for operating the proposed system is developed in Python. The measured data and calculated outputs of the system consist of times for frames, distances from the center camera, horizontal angles, distances moved, instantaneous gait speed (frame-by-frame), total distance walked, and average speed. This system covers a large Lab area of 134.3 m2 and has achieved errors of less than 5% for gait speed calculation.Clinical Relevance- This project will help specialists to adjust the chemo dosage for elderly patients with cancer. The results will be used to analyze the human walking movements for estimating frailty and rehabilitation applications, too.

A CNN-Based Wearable Assistive System for Visually Impaired People Walking Outdoors

In this study, we propose an assistive system for helping visually impaired people walk outdoors. This assistive system contains an embedded system—Jetson AGX Xavier (manufacture by Nvidia in Santa Clara, CA, USA) and a binocular depth camera—ZED 2 (manufacture by Stereolabs in San Francisco, CA, USA). Based on the CNN neural network FAST-SCNN and the depth map obtained by the ZED 2, the image of the environment in front of the visually impaired user is split into seven equal divisions. A walkability confidence value for each division is computed, and a voice prompt is played to guide the user toward the most appropriate direction such that the visually impaired user can navigate a safe path on the sidewalk, avoid any obstacles, or walk on the crosswalk safely. Furthermore, the obstacle in front of the user is identified by the network YOLOv5s proposed by Jocher, G. et al. Finally, we provided the proposed assistive system to a visually impaired person and experimented around an MRT station in Taiwan. The visually impaired person indicated that the proposed system indeed helped him feel safer when walking outdoors. The experiment also verified that the system could effectively guide the visually impaired person walking safely on the sidewalk and crosswalks.

Wrist-based accelerometer cut-points for quantifying moderate-to-vigorous intensity physical activity in Parkinson’s disease

BackgroundPersons with Parkinson’s disease (PD) participate in low levels of physical activity. This has prompted interest in developing interventions targeting physical activity behavior in PD. However, the current cut-points to quantify moderate-to-vigorous physical activity (MVPA) developed for PD have been derived from a single, vertical axis using hip-worn accelerometers, and this cut-point may not be applicable for wrist-worn devices. Wrist-worn devices might improve accessibility and compliance with physical activity monitoring in PD. Research QuestionWhat is the relationship between wrist-based activity counts and energy expenditure during treadmill walking in persons with PD? Do cut-points for quantifying time spent in MVPA differ between persons with PD and controls matched by age and sex? MethodsThe sample included 26 persons with mild-to-moderate PD (Hoehn and Yahr stages 2–3) and 27 age- and sex-matched controls. Participants completed three, 6-minute bouts of walking on a treadmill at three increasing speeds. Vector magnitude was measured using ActiGraph GT3X+ accelerometer worn on the more affected side for persons with PD and the non-dominant side for controls. The rate of oxygen consumption, or energy expenditure, was measured using a portable, open-circuit spirometry system. ResultsOur results indicated a strong association between activity counts and energy expenditure for persons with PD and controls with R2 values of 0.94(0.07) and 0.95(0.06), respectively. Persons with PD had a cut-point of 2883(871) counts·min−1; this was significantly lower than the cut-point of 4389(1844) counts·min−1 for controls. ConclusionWe generated a PD-specific cut-point for wrist-worn ActiGraph accelerometers among persons with PD, and this was lower than controls. This disease-specific cut-point may provide more accurate measurements of time spent in MVPA in PD.

A Fast and Compact Deep Gabor Network for Micro-Doppler Signal Processing and Human Motion Classification

With the advances in radar technology, there is an increasing interest in radar-based applications for automated surveillance, tracking, and recognition. Radars capture the Doppler-induced frequency shifts, which can be utilized to recognize the small motions by vibrating or rotating parts of the target. This paper introduces a fast and compact deep Gabor neural network for human motion classification using backscattered signals from a continuous-wave Doppler radar. The joint time-frequency representation produced by the S-method is employed to depict the micro-Doppler signature of a walking person. We introduce a new Gabor layer as a generic feature extractor for designing compact neural architectures. Each Gabor layer consists of several steerable Gabor filters that can be trained to extract the salient micro-Doppler features and improve computation efficiency. For human motion classification from a distance, the Deep Gabor Network (DGN) is trained in an end-to-end manner to process the local patches in the time-frequency representation of the radar signal. A Bayesian optimization technique is employed to select the optimal network hyperparameters. The experimental results on a real radar dataset show that the proposed method achieves competitive classification rates compared to several existing approaches while having a significantly smaller model size and shorter prediction time.

Biomechanical differences between fixed-speed and self-paced treadmill walking in persons after stroke

Biomechanical differences between fixed-speed and self-paced treadmill walking in persons after stroke

Comparing spatiotemporal gait parameters between overground walking and self-paced treadmill walking in persons after stroke

A 21-year-old male presented to our hospital for life-threatening pelvic fracture, mandating emergent transarterial embolization of the right internal pudendal artery. At five-month post-injury, penile arterial flow was severely impaired, thus penile revascularization surgery were planned, before attempting urethroplasty for a 2-cm gap in the posterior urethra. However, reevaluation angiography results obtained two months later revealed spontaneous recovery of penile arterial flow. Excision and primary anastomosis urethroplasty was successfully performed without signs of bulbar ischemia. This case suggests that the timing of urethroplasty following pelvic injury should be tailored according to recovery of penile arterial flow.

Machine-vision fused brain machine interface based on dynamic augmented reality visual stimulation

Objective. Brain–machine interfaces (BMIs) interpret human intent into machine reactions, and the visual stimulation (VS) paradigm is one of the most widely used of these approaches. Although VS-based BMIs have a relatively high information transfer rate (ITR), it is still difficult for BMIs to control machines in dynamic environments (for example, grabbing a dynamic object or targeting a walking person). Approach. In this study, we utilized a BMI based on augmented reality (AR) VS (AR-VS). The proposed VS was dynamically generated based on machine vision, and human intent was interpreted by a dynamic decision time interval approach. A robot based on the coordination of a task and self-motion system was controlled by the proposed paradigm in a fast and flexible state. Methods. Objects in scenes were first recognized by machine vision and tracked by optical flow. AR-VS was generated based on the objects’ parameters. The number and distribution of VS was confirmed by the recognized objects. Electroencephalogram (EEG) features corresponding to VS and human intent were collected by a dry-electrode EEG cap and determined by the filter bank canonical correlation analysis method. Key parameters in the AR-VS, including the effect of VS size, frequency, dynamic object moving speed, ITR and the performance of the BMI-controlled robot, were analyzed. Conclusion and significance. The ITR of the proposed AR-VS paradigm for nine healthy subjects was 36.3 ± 20.1 bits min−1. In the online robot control experiment, brain-controlled hybrid tasks including self-moving and grabbing objects were 64% faster than when using the traditional steady-state visual evoked potential paradigm. The proposed paradigm based on AR-VS could be optimized and adopted in other kinds of VS-based BMIs, such as P300, omitted stimulus potential, and miniature event-related potential paradigms, for better results in dynamic environments.

Mobility-as-a-Service: Simulation of Multi-Modal Operations in Low-Density Cities

In the case of the low-density city, empirical evidence continuously demonstrates that transit investment is not a magic bullet. Desirable outcomes are not guaranteed and are often dependent on development density and other urban characteristics. Mobility-as-a-service (MaaS) presents a new approach: a digital platform providing access to multi-modal travel alternatives and totally comprehensive integrated trip-making, planning, and payment services. Review of the literature highlights shortcomings in traditional transportation planning by examining aspects of multi-modal planning such as adoption, parterships, operations, integration, capacity implications, and impact analyses. To enhance the practice of multi-modal planning, the following experiment evaluates various performance measures and inter-modal interactions on International Drive in Orlando, Florida, U.S., via D- and I-optimal experimental designs in a simulated MaaS network. Alternative scenarios are developed comparing varied modal shares across five travel modes: personal vehicles, transit, ridesourcing (or ride-hailing), micro-mobility, and walking. The modal effects are analyzed to highlight the strengths and weakness of each mode under a variety of congestion conditions. While transit enjoys the lowest impact per person, ridesourcing demonstrates adverse effects across all measures. Based on the novel interactions of transit and ridesourcing with directional demand, strategies are outlined for optimizing ridesourcing-transit integration to reduce route travel time, queuing, and overall network delay. The performance impacts of curbside facilities are also discussed for improved multi-modal integration at the street level. These findings are applied to propose a framework for effective planning and implementation of mobility services in low-density cities, focused on operations, city-level connectivity, and curbside management.

Visual Saliency Estimation through Manifold Learning

Saliency detection has been a desirable way for robotic vision to find the most noticeable objects in a scene. In this paper, a robust manifold-based saliency estimation method has been developed to help capture the most salient objects in front of robotic eyes, namely cameras. In the proposed approach, an image is considered as a manifold of visual signals (stimuli) spreading over a connected grid, and local visual stimuli are compared against the global image variation to model the visual saliency. With this model, manifold learning is then applied to minimize the local variation while keeping the global contrast, and turns the RGB image into a multi-channel image. After the projection through manifold learning, histogram-based contrast is then computed for saliency modeling of all channels of the projected images, and mutual information is introduced to evaluate each single-channel saliency map against prior knowledge to provide cues for the fusion of multiple channels. In the last step, the fusion procedure combines all single-channel saliency maps according to their mutual information score, and generates the final saliency map. In our experiment, the proposed method is evaluated using one of the largest publicly available image datasets. The experimental results demonstrate that our algorithm consistently outperforms the state-of-the-art unsupervised saliency detection methods, yielding higher precision and better recall rates. Furthermore, the proposed method is tested on a video-type test dataset where a moving camera is trying to catch up with the walking person---a salient object in the video sequence. Our experimental results show that the proposed approach can successful accomplish this task, revealing its potential use for similar robotic applications.

Automated Calibration of RSS Fingerprinting Based Systems Using a Mobile Robot and Machine Learning.

This paper describes an automated method for the calibration of RSS-fingerprinting-based positioning systems. The method assumes using a robotic platform to gather fingerprints in the system environment and using them for training machine learning models. The obtained models are used for positioning purposes during the system operation. The presented calibration method covers all steps of the system calibration, from mapping the system environment using a GraphSLAM based algorithm to training models for radio map calibration. The study analyses four different models: fitting a log-distance path loss model, Gaussian Process Regression, Artificial Neural Network and Random Forest Regression. The proposed method was tested in a BLE-based indoor localisation system set up in a fully furnished apartment. The results have shown that the tested models allow for localisation with accuracy comparable to those reported in the literature. In the case of the Neural Network regression, the median error of robot positioning was 0.87 m. The median of trajectory error in a walking person localisation scenario was 0.4 m.

Reliability and validity of the modified Walking and Remembering Test in persons with multiple sclerosis.

Cognitive dysfunction can adversely impact the walking ability of people with multiple sclerosis. However, valid and reliable standardized clinical tools to measure cognitive-motor interference or dual-tasking in people with multiple sclerosis remain lacking. This study evaluated the validity and reliability of the modified Walking and Remembering Test (mWART) in people with multiple sclerosis. Eleven adults (mean ± SD age, 51.1 ± 13.4 years) with multiple sclerosis (Expanded Disability Status Score, 2.0-6.0) and six adults (mean ± SD age, 41.5 ± 17.2 years) without multiple sclerosis were administered the mWART twice over a 2-week period. Participants were tested on gait and digit span length under single-task and dual-task conditions according to the mWART procedures over a 10-m walkway. intraclass correlation coefficient2,k were 0.961 for single-task gait velocity (P < 0.001), 0.968 for dual-task gait velocity (P < 0.001), 0.829 for single-task digit span (P = 0.004), and 0.439 for dual-task digit span (P = 0.154). Single-task gait velocity (P = 0.001) and dual-task gait velocity (P = 0.002) were able to discriminate between groups but dual-task costs were similar between participants with and without multiple sclerosis. Those with severe disability demonstrated the greater dual-task cost of gait velocity (P = 0.030). This study provides preliminary evidence of the mWART's validity and reliability in measuring dual-task performance in patients with multiple sclerosis with mild to severe disability. More research is required in more heterogeneous samples of persons with multiple sclerosis.

Association of Machine Learning-Based Predictions of Medial Knee Contact Force With Cartilage Loss Over 2.5 Years in Knee Osteoarthritis.

The relationship between in vivo knee load predictions and longitudinal cartilage changes has not been investigated. We undertook this study to develop an equation to predict the medial tibiofemoral contact force (MCF) peak during walking in persons with instrumented knee implants, and to apply this equation to determine the relationship between the predicted MCF peak and cartilage loss in patients with knee osteoarthritis (OA). In adults with knee OA (39 women, 8 men; mean ± SD age 61.1 ± 6.8 years), baseline biomechanical gait analyses were performed, and annualized change in medial tibial cartilage volume (mm3 /year) over 2.5 years was determined using magnetic resonance imaging. In a separate sample of patients with force-measuring tibial prostheses (3 women, 6 men; mean ± SD age 70.3 ± 5.2 years), gait data plus in vivo knee loads were used to develop an equation to predict the MCF peak using machine learning. This equation was then applied to the knee OA group, and the relationship between the predicted MCF peak and annualized cartilage volume change was determined. The MCF peak was best predicted using gait speed, the knee adduction moment peak, and the vertical knee reaction force peak (root mean square error 132.88N; R2 = 0.81, P < 0.001). In participants with knee OA, the predicted MCF peak was related to cartilage volume change (R2 = 0.35, β = -0.119, P < 0.001). Machine learning was used to develop a novel equation for predicting the MCF peak from external biomechanical parameters. The predicted MCF peak was positively related to medial tibial cartilage volume loss in patients with knee OA.