Enhancing automated lower limb rehabilitation exercise task recognition through multi-sensor data fusion in tele-rehabilitation.

BACKGROUND: Tele-rehabilitation is the provision of physiotherapy services to individuals in their own homes. Activity recognition plays a crucial role in the realm of automatic tele-rehabilitation. By assessing patient movements, identifying exercises, and providing feedback, these platforms can offer insightful information to clinicians, thereby facilitating an improved plan of care. This study introduces a novel deep learning approach aimed at identifying lower limb rehabilitation exercises. This is achieved through the integration of depth data and pressure heatmaps. We hypothesized that combining pressure heatmaps and depth data could improve the model's overall performance. METHODS: In this study, depth videos and body pressure data from an accessible online dataset were used. This dataset comprises data from 30 healthy individuals performing 7 lower limb rehabilitation exercises. To accomplish the classification task, three deep learning models were developed, all based on an established 3D-CNN architecture. The models were designed to classify the depth videos, sequences of pressure data frames, and combination of depth videos and pressure frames. The models' performance was assessed through leave-one-subject-out and leave-multiple-subjects-out cross-validation methods. Performance metrics, including accuracy, precision, recall, and F1 score, were reported for each model. RESULTS: Our findings indicated that the model trained on the fusion of depth and pressure data showed the highest and most stable performance when compared with models using individual modality inputs. This model could effectively identify the exercises with an accuracy of 95.71%, precision of 95.83%, recall of 95.71%, and an F1 score of 95.74%. CONCLUSION: Our results highlight the impact of data fusion for accurately classifying lower limb rehabilitation exercises. We showed that our model could capture different aspects of exercise movements using the visual and weight distribution data from the depth camera and pressure mat, respectively. This integration of data provides a better representation of exercise patterns, leading to higher classification performance. Notably, our results indicate the potential application of this model in automatic tele-rehabilitation platforms.

Joint angle estimation during shoulder abduction exercise using contactless technology.

BACKGROUND: Tele-rehabilitation, also known as tele-rehab, uses communication technologies to provide rehabilitation services from a distance. The COVID-19 pandemic has highlighted the importance of tele-rehab, where the in-person visits declined and the demand for remote healthcare rises. Tele-rehab offers enhanced accessibility, convenience, cost-effectiveness, flexibility, care quality, continuity, and communication. However, the current systems are often not able to perform a comprehensive movement analysis. To address this, we propose and validate a novel approach using depth technology and skeleton tracking algorithms. METHODS: Our data involved 14 participants (8 females, 6 males) performing shoulder abduction exercises. We collected depth videos from an LiDAR camera and motion data from a Motion Capture (Mocap) system as our ground truth. The data were collected at distances of 2 m, 2.5 m, and 3.5 m from the LiDAR sensor for both arms. Our innovative approach integrates LiDAR with the Cubemos and Mediapipe skeleton tracking frameworks, enabling the assessment of 3D joint angles. We validated the system by comparing the estimated joint angles versus Mocap outputs. Personalized calibration was applied using various regression models to enhance the accuracy of the joint angle calculations. RESULTS: The Cubemos skeleton tracking system outperformed Mediapipe in joint angle estimation with higher accuracy and fewer errors. The proposed system showed a strong correlation with Mocap results, although some deviations were present due to noise. Precision decreased as the distance from the camera increased. Calibration significantly improved performance. Linear regression models consistently outperformed nonlinear models, especially at shorter distances. CONCLUSION: This study showcases the potential of a marker-less system, to proficiently track body joints and upper-limb angles. Signals from the proposed system and the Mocap system exhibited robust correlation, with Mean Absolute Errors (MAEs) consistently below [Formula: see text]. LiDAR's depth feature enabled accurate computation of in-depth angles beyond the reach of traditional RGB cameras. Altogether, this emphasizes the depth-based system's potential for precise joint tracking and angle calculation in tele-rehab applications.

A novel in-bed body posture monitoring for decubitus ulcer prevention using body pressure distribution mapping.

BACKGROUND: Decubitus ulcers are prevalent among the aging population due to a gradual decline in their overall health, such as nutrition, mental health, and mobility, resulting in injury to the skin and tissue. The most common technique to prevent these ulcers is through frequent repositioning to redistribute body pressures. Therefore, the main goal of this study is to facilitate the timely repositioning of patients through the use of a pressure mat to identify in-bed postures in various sleep environments. Pressure data were collected from 10 healthy participants lying down on a pressure mat in 19 various in-bed postures, correlating to the supine, prone, right-side, and left-side classes. In addition, pressure data were collected from participants sitting at the edge of the bed as well as an empty bed. Each participant was asked to lie in these 19 postures in three distinct testing environments: a hospital bed, a home bed, and a home bed with a foam mattress topper. To categorize each posture into its respective class, the pre-trained 2D ResNet-18 CNN and the pre-trained Inflated 3D CNN algorithms were trained and validated using image and video pressure mapped data, respectively. RESULTS: The ResNet-18 and Inflated 3D CNN algorithms were validated using leave-one-subject-out (LOSO) and leave-one-environment-out (LOEO) cross-validation techniques. LOSO provided an average accuracy of 92.07% ± 5.72% and 82.22% ± 8.50%, for the ResNet-18 and Inflated 3D CNN algorithms, respectively. Contrastingly, LOEO provided a reduced average accuracy of 85.37% ± 14.38% and 77.79% ± 9.76%, for the ResNet-18 and Inflated 3D CNN algorithms, respectively. CONCLUSION: These pilot results indicate that the proposed algorithms can accurately distinguish between in-bed postures, on unseen participant data as well as unseen mattress environment data. The proposed algorithms can establish the basis of a decubitus ulcer prevention platform that can be applied to various sleeping environments. To the best of our knowledge, the impact of mattress stiffness has not been considered in previous studies regarding in-bed posture monitoring.

In-Bed Posture Classification Using Deep Neural Network.

In-bed posture monitoring has become a prevalent area of research to help minimize the risk of pressure sore development and to increase sleep quality. This paper proposed 2D and 3D Convolutional Neural Networks, which are trained on images and videos of an open-access dataset consisting of 13 subjects' body heat maps captured from a pressure mat in 17 positions, respectively. The main goal of this paper is to detect the three main body positions: supine, left, and right. We compare the use of image and video data through 2D and 3D models in our classification. Since the dataset was imbalanced, three strategies were evaluated, i.e., down sampling, over sampling, and class weights. The best 3D model achieved accuracies of 98.90 ± 1.05% and 97.80 ± 2.14% for 5-fold and leave-one-subject-out (LOSO) cross validations, respectively. To compare the 3D model with 2D, four pre-trained 2D models were evaluated, where the best-performing model was the ResNet-18 with accuracies of 99.97 ± 0.03% for 5-fold and 99.62 ± 0.37% for LOSO. The proposed 2D and 3D models provided promising results for in-bed posture recognition and can be used in the future to further distinguish postures into more detailed subclasses. The outcome of this study can be used to remind caregivers at hospitals and long-term care facilitiesto reposition their patients if they do not reposition themselves naturally to prevent pressure ulcers. In addition, the evaluation of body postures and movements during sleep can help caregivers understand sleep quality.

Design and Validation of Vision-Based Exercise Biofeedback for Tele-Rehabilitation.

Tele-rehabilitation has the potential to considerably change the way patients are monitored from their homes during the care process, by providing equitable access without the need to travel to rehab centers or shoulder the high cost of personal in-home services. Developing a tele-rehab platform with the capability of automating exercise guidance is likely to have a significant impact on rehabilitation outcomes. In this paper, a new vision-based biofeedback system is designed and validated to identify the quality of performed exercises. This new system will help patients to refine their movements to get the most out of their plan of care. An open dataset was used, which consisted of data from 30 participants performing nine different exercises. Each exercise was labeled as "Correctly" or "Incorrectly" executed by five clinicians. We used a pre-trained 3D Convolution Neural Network (3D-CNN) to design our biofeedback system. The proposed system achieved average accuracy values of 90.57% ± 9.17% and 83.78% ± 7.63% using 10-Fold and Leave-One-Subject-Out (LOSO) cross validation, respectively. In addition, we obtained average F1-scores of 71.78% ± 5.68% using 10-Fold and 60.64% ± 21.3% using LOSO validation. The proposed 3D-CNN was able to classify the rehabilitation videos and feedback on the quality of exercises to help users modify their movement patterns.

Automated Fluid Intake Detection Using RGB Videos.

Dehydration is a common, serious issue among older adults. It is important to drink fluid to prevent dehydration and the complications that come with it. As many older adults forget to drink regularly, there is a need for an automated approach, tracking intake throughout the day with limited user interaction. The current literature has used vision-based approaches with deep learning models to detect drink events; however, most use static frames (2D networks) in a lab-based setting, only performing eating and drinking. This study proposes a 3D convolutional neural network using video segments to detect drinking events. In this preliminary study, we collected data from 9 participants in a home simulated environment performing daily activities as well as eating and drinking from various containers to create a robust environment and dataset. Using state-of-the-art deep learning models, we trained our CNN using both static images and video segments to compare the results. The 3D model attained higher performance (compared to 2D CNN) with F1 scores of 93.7% and 84.2% using 10-fold and leave-one-subject-out cross-validations, respectively.

Design of a Novel Wearable System for Foot Clearance Estimation.

Trip-related falls are one of the major causes of injury among seniors in Canada and can be attributable to an inadequate Minimum Toe Clearance (MTC). Currently, motion capture systems are the gold standard for measuring MTC; however, they are expensive and have a restricted operating area. In this paper, a novel wearable system is proposed that can estimate different foot clearance parameters accurately using only two Time-of-Flight (ToF) sensors located at the toe and heel of the shoe. A small-scale preliminary study was conducted to investigate the feasibility of foot clearance estimation using the proposed wearable system. We recruited ten young, healthy females to walk at three self-selected speeds (normal, slow, and fast) while wearing the system. Our data analysis showed an average correlation coefficient of 0.94, 0.94, 0.92 for the normal, slow, and fast speed, respectively, when comparing the ToF signals with motion capture. The ANOVA analysis confirmed these results further by revealing no statistically significant differences between the ToF signals and motion capture data for most of the gait parameters after applying the newly proposed foot angle and offset compensation. In addition, the proposed system can measure the MTC with an average Mean Error (ME) of -0.08 ± 3.69 mm, -0.12 ± 4.25 mm, and -0.10 ± 6.57 mm for normal, slow, and fast walking speeds, respectively. The proposed affordable wearable system has the potential to perform real-time MTC estimation and contribute to future work focused on minimizing tripping risks.

Influential Factors in Remote Monitoring of Heart Failure Patients: A Review of the Literature and Direction for Future Research.

With new advances in technology, remote monitoring of heart failure (HF) patients has become increasingly prevalent and has the potential to greatly enhance the outcome of care. Many studies have focused on implementing systems for the management of HF by analyzing physiological signals for the early detection of HF decompensation. This paper reviews recent literature exploring significant physiological variables, compares their reliability in predicting HF-related events, and examines the findings according to the monitored variables used such as body weight, bio-impedance, blood pressure, heart rate, and respiration rate. The reviewed studies identified correlations between the monitored variables and the number of alarms, HF-related events, and/or readmission rates. It was observed that the most promising results came from studies that used a combination of multiple parameters, compared to using an individual variable. The main challenges discussed include inaccurate data collection leading to contradictory outcomes from different studies, compliance with daily monitoring, and consideration of additional factors such as physical activity and diet. The findings demonstrate the need for a shared remote monitoring platform which can lead to a significant reduction of false alarms and help in collecting reliable data from the patients for clinical use especially for the prevention of cardiac events.

Deep Neural Network for Slip Detection on Ice Surface.

Slip-induced falls are among the most common causes of major occupational injuries and economic loss in Canada. Identifying the risk factors associated with slip events is key to developing preventive solutions to reduce falls. One factor is the slip-resistance quality of footwear, which is fundamental to reducing the number of falls. Measuring footwear slip resistance with the recently developed Maximum Achievable Angle (MAA) test requires a trained researcher to identify slip events in a simulated winter environment. The human capacity for information processing is limited and human error is natural, especially in a cold environment. Therefore, to remove conflicts associated with human errors, in this paper a deep three-dimensional convolutional neural network is proposed to detect the slips in real-time. The model has been trained by a new dataset that includes data from 18 different participants with various clothing, footwear, walking directions, inclined angles, and surface types. The model was evaluated on three types of slips: Maxi-slip, midi-slip, and mini-slip. This classification is based on the slip perception and recovery of the participants. The model was evaluated based on both 5-fold and Leave-One-Subject-Out (LOSO) cross validation. The best accuracy of 97% was achieved when identifying the maxi-slips. The minimum accuracy of 77% was achieved when classifying the no-slip and mini-slip trials. The overall slip detection accuracy was 86% with sensitivity and specificity of 81% and 91%, respectively. The overall accuracy dropped by about 2% in LOSO cross validation. The proposed slip detection algorithm is not only beneficial for footwear manufactures to improve their footwear slip resistance quality, but it also has other potential applications, such as improving the slip resistance properties of flooring in healthcare facilities, commercial kitchens, and oil drilling platforms.

A Comprehensive Analysis on Wearable Acceleration Sensors in Human Activity Recognition.

Sensor-based motion recognition integrates the emerging area of wearable sensors with novel machine learning techniques to make sense of low-level sensor data and provide rich contextual information in a real-life application. Although Human Activity Recognition (HAR) problem has been drawing the attention of researchers, it is still a subject of much debate due to the diverse nature of human activities and their tracking methods. Finding the best predictive model in this problem while considering different sources of heterogeneities can be very difficult to analyze theoretically, which stresses the need of an experimental study. Therefore, in this paper, we first create the most complete dataset, focusing on accelerometer sensors, with various sources of heterogeneities. We then conduct an extensive analysis on feature representations and classification techniques (the most comprehensive comparison yet with 293 classifiers) for activity recognition. Principal component analysis is applied to reduce the feature vector dimension while keeping essential information. The average classification accuracy of eight sensor positions is reported to be 96.44% ± 1.62% with 10-fold evaluation, whereas accuracy of 79.92% ± 9.68% is reached in the subject-independent evaluation. This study presents significant evidence that we can build predictive models for HAR problem under more realistic conditions, and still achieve highly accurate results.

Technological advances in lower-limb tele-rehabilitation: A review of literature.

Tele-rehabilitation is a healthcare practice that leverages technology to provide rehabilitation services remotely to individuals in their own homes or other locations. With advancements in remote monitoring and Artificial Intelligence, automatic tele-rehabilitation systems that can measure joint angles, recognize exercises, and provide feedback based on movement analysis are being developed. Such platforms can offer valuable information to clinicians for improved care planning. However, with various methods and sensors being used, understanding their pros, cons, and performance is important. This paper reviews and compares the performance of recent vision-based, wearable, and pressure-sensing technologies used in lower limb tele-rehabilitation systems over the past 10 years (from 2014 to 2023). We selected studies that were published in English and focused on joint angle estimation, activity recognition, and exercise assessment. Vision-based approaches were the most common, accounting for 42% of studies. Wearable technology followed at approximately 37%, and pressure-sensing technology appeared in 21% of studies. Identified gaps include a lack of uniformity in reported performance metrics and evaluation methods, a need for cross-subject validation, inadequate testing with patients and older adults, restricted sets of exercises evaluated, and a scarcity of comprehensive datasets on lower limb exercises, especially those involving movements while lying down.

A novel wearable biofeedback system to prevent trip-related falls.

Real-time gait monitoring of older adults and gait-impaired individuals while providing real-time biofeedback has the potential to help reduce trip-related falls. A low or unsuccessful Minimum Toe Clearance (MTC) is considered a predictor of tripping risk. Thus, increasing the MTC can be a key component in minimizing the likelihood of tripping. This paper discusses a proof-of-concept wearable system that estimates the MTC in real-time using two Time-of-Flight (ToF) sensors and provides auditory biofeedback to alert users if they have a low MTC during everyday walking activities. Ten healthy female adults were asked to perform two experiments: 1) walk at a predetermined speed to evaluate the proposed real-time MTC detection algorithm, and 2) walk in four conditions: baseline, biofeedback with no distraction, biofeedback with distraction 1 (talking on the phone), and biofeedback with distraction 2 (playing a simple mobile game). The average MTC values were significantly greater during all feedback conditions than the baseline, indicating that the proposed system could successfully warn users to increase their MTC in real-time.

Recent Advances and Applications of Textile Technology in Patient Monitoring.

Sleep monitoring has become a prevalent area of research where body position and physiological data, such as heart rate and respiratory rate, are monitored. Numerous critical health problems are associated with poor sleep, such as pressure sore development, sleep disorders, and low sleep quality, which can lead to an increased risk of falls, cardiovascular diseases, and obesity. Current monitoring systems can be costly, laborious, and taxing on hospital resources. This paper reviews the most recent solutions for contactless textile technology in the form of bed sheets or mats to monitor body positions, vital signs, and sleep, both commercially and in the literature. This paper is organized into four categories: body position and movement monitoring, physiological monitoring, sleep monitoring, and commercial products. A detailed performance evaluation was carried out, considering the detection accuracy as well as the sensor types and algorithms used. The areas that need further research and the challenges for each category are discussed in detail.

Development and Evaluation of BLE-Based Room-Level Localization to Improve Hand Hygiene Performance Estimation.

Hand hygiene is one of the most effective ways to prevent infection transmission. However, current electronic monitoring systems are not able to identify adherence to all hand hygiene (HH) guidelines. Location information can play a major role in enhancing HH monitoring resolution. This paper proposes a BLE-based solution to localize healthcare workers inside the patient room. Localization accuracy was evaluated using one to four beacons in a binary (entrance/proximal patient zone) or multiclass (entrance/sink/right side of the bed/left side of the bed) proximity-based positioning problem. Dynamic fingerprints were collected from nine different subjects performing 30 common nursing activities. Extremely randomized trees algorithm achieved the best accuracies of 81% and 71% in the binary and multiclass classifications, respectively. The proposed method can be further used as a proxy for caregiving activity recognition to improve the risk of infection transmission in healthcare settings.

Monitoring fluid intake by commercially available smart water bottles.

Fluid intake is important to prevent dehydration and reduce recurrent kidney stones. There has been a trend in recent years to develop tools to monitor fluid intake using "smart" products such as smart bottles. Several commercial smart bottles are available, mainly targeting health-conscious adults. To the best of our knowledge, these bottles have not been validated in the literature. This study compares four commercially available smart bottles in terms of both performance and functionality. These bottles are the H2OPal, HidrateSpark Steel, HidrateSpark 3, and Thermos Smart Lid. One hundred intake events for each bottle were recorded and analyzed versus ground truth obtained from a high-resolution weight scale. The H2OPal had the lowest Mean Percent Error (MPE) and was able to balance out errors throughout multiple sips. The HidrateSpark 3 provided the most consistent and reliable results, with the lowest per sip error. The MPE values for HidrateSpark bottles were further improved using linear regression, as they had more consistent individual error values. The Thermos Smart Lid provides the lowest accuracy, as the sensors do not extend through the entire bottle, leading to many missed recordings.

A New Performance Metric to Estimate the Risk of Exposure to Infection in a Health Care Setting: Descriptive Study.

BACKGROUND: Despite several measures to monitor and improve hand hygiene (HH) in health care settings, health care-acquired infections (HAIs) remain prevalent. The measures used to calculate HH performance are not able to fully benefit from the high-resolution data collected using electronic monitoring systems. OBJECTIVE: This study proposes a novel parameter for quantifying the HAI exposure risk of individual patients by considering temporal and spatial features of health care workers' HH adherence. METHODS: Patient exposure risk is calculated as a function of the number of consecutive missed HH opportunities, the number of unique rooms visited by the health care professional, and the time duration that the health care professional spends inside and outside the patient's room without performing HH. The patient exposure risk is compared to the entrance compliance rate (ECR) defined as the ratio of the number of HH actions performed at a room entrance to the total number of entrances into the room. The compliance rate is conventionally used to measure HH performance. The ECR and the patient exposure risk are analyzed using the data collected from an inpatient nursing unit for 12 weeks. RESULTS: The analysis of data collected from 59 nurses and more than 25,600 records at a musculoskeletal rehabilitation unit at the Toronto Rehabilitation Institute, KITE, showed that there is no strong linear relation between the ECR and patient exposure risk (r=0.7, P<.001). Since the ECR is calculated based on the number of missed HH actions upon room entrance, this parameter is already included in the patient exposure risk. Therefore, there might be scenarios that these 2 parameters are correlated; however, in several cases, the ECR contrasted with the reported patient exposure risk. Generally, the patients in rooms with a significantly high ECR can be potentially exposed to a considerable risk of infection. By contrast, small ECRs do not necessarily result in a high patient exposure risk. The results clearly explained the important role of the factors incorporated in patient exposure risk for quantifying the risk of infection for the patients. CONCLUSIONS: Patient exposure risk might provide a more reliable estimation of the risk of developing HAIs compared to ECR by considering both the temporal and spatial aspects of HH records.

Evidence and User Considerations of Home Health Monitoring for Older Adults: Scoping Review.

BACKGROUND: Home health monitoring shows promise in improving health outcomes; however, navigating the literature remains challenging given the breadth of evidence. There is a need to summarize the effectiveness of monitoring across health domains and identify gaps in the literature. In addition, ethical and user-centered frameworks are important to maximize the acceptability of health monitoring technologies. OBJECTIVE: This review aimed to summarize the clinical evidence on home-based health monitoring through a scoping review and outline ethical and user concerns and discuss the challenges of the current user-oriented conceptual frameworks. METHODS: A total of 2 literature reviews were conducted. We conducted a scoping review of systematic reviews in Scopus, MEDLINE, Embase, and CINAHL in July 2021. We included reviews examining the effectiveness of home-based health monitoring in older adults. The exclusion criteria included reviews with no clinical outcomes and lack of monitoring interventions (mobile health, telephone, video interventions, virtual reality, and robots). We conducted a quality assessment using the Assessment of Multiple Systematic Reviews (AMSTAR-2). We organized the outcomes by disease and summarized the type of outcomes as positive, inconclusive, or negative. Second, we conducted a literature review including both systematic reviews and original articles to identify ethical concerns and user-centered frameworks for smart home technology. The search was halted after saturation of the basic themes presented. RESULTS: The scoping review found 822 systematic reviews, of which 94 (11%) were included and of those, 23 (24%) were of medium or high quality. Of these 23 studies, monitoring for heart failure or chronic obstructive pulmonary disease reduced exacerbations (4/7, 57%) and hospitalizations (5/6, 83%); improved hemoglobin A1c (1/2, 50%); improved safety for older adults at home and detected changing cognitive status (2/3, 66%) reviews; and improved physical activity, motor control in stroke, and pain in arthritis in (3/3, 100%) rehabilitation studies. The second literature review on ethics and user-centered frameworks found 19 papers focused on ethical concerns, with privacy (12/19, 63%), autonomy (12/19, 63%), and control (10/19, 53%) being the most common. An additional 7 user-centered frameworks were studied. CONCLUSIONS: Home health monitoring can improve health outcomes in heart failure, chronic obstructive pulmonary disease, and diabetes and increase physical activity, although review quality and consistency were limited. Long-term generalized monitoring has the least amount of evidence and requires further study. The concept of trade-offs between technology usefulness and acceptability is critical to consider, as older adults have a hierarchy of concerns. Implementing user-oriented frameworks can allow long-term and larger studies to be conducted to improve the evidence base for monitoring and increase the receptiveness of clinicians, policy makers, and end users.

Fluid Intake Monitoring Systems for the Elderly: A Review of the Literature.

Fluid intake monitoring is an essential component in preventing dehydration and overhydration, especially for the senior population. Numerous critical health problems are associated with poor or excessive drinking such as swelling of the brain and heart failure. Real-time systems for monitoring fluid intake will not only measure the exact amount consumed by the users, but could also motivate people to maintain a healthy lifestyle by providing feedback to encourage them to hydrate regularly throughout the day. This paper reviews the most recent solutions to automatic fluid intake monitoring both commercially and in the literature. The available technologies are divided into four categories: wearables, surfaces with embedded sensors, vision- and environmental-based solutions, and smart containers. A detailed performance evaluation was carried out considering detection accuracy, usability and availability. It was observed that the most promising results came from studies that used data fusion from multiple technologies, compared to using an individual technology. The areas that need further research and the challenges for each category are discussed in detail.

Evaluation of Winter Footwear: Comparison of Test Methods to Determine Footwear Slip Resistance on Ice Surfaces.

The use of slip-resistant winter footwear is crucial for the prevention of slips and falls on ice and snow. The main objective of this paper is to evaluate a mechanical testing method to determine footwear slip resistance on wet and dry ice surfaces and to compare it with the human-centred test method introduced by researchers at KITE (Knowledge, Innovation, Talent, Everywhere)-Toronto Rehabilitation Institute-University Health Network. Phase 1 of this study assessed the repeatability and reproducibility of the mechanical method by evaluating ten different occupational winter boots using two SATRA Slip resistance testers (STM 603, SATRA Technology Centre, Kettering, UK). One tester is located in Toronto and one in Montreal. These boots were chosen based on the needs of the IRSST (Institut de Recherche Robert-Sauvé en Santé et en Sécurité du Travail, Montréal, Quebec, Canada), who were primarily interested in providing safe winter footwear for police, firefighters and municipal workers. In Phase 2, the results of the human-centred test approach were compared with the mechanical results. In Phase 3, two of these boots with conflicting results from the previous phases were tested using a second human-centred method. In Phase 1, the mechanical testing results obtained in the two labs showed a high linear correlation (>0.94) and good agreement on both ice surfaces; however, they revealed a bias (~0.06) between the two labs on the dry ice condition. The mechanical and human-centred tests (phase 2) were found to be better correlated in the wet ice condition (R = 0.95) compared to the dry ice condition (R = 0.34). Finally, the rating of the footwear slip resistance based on the number of slips counted in phase 3 was consistent with the rating by the human-centred test method (phase 2), but not the mechanical method (phase 1). The findings of this study provide a better understanding of the limitations of the SATRA ice tray for measuring footwear slip resistance and demonstrate that the mechanical method must be further refined to make it more comparable to the human-centred methods to achieve better agreement with real-world performance.

A Vision-Based Approach for Sidewalk and Walkway Trip Hazards Assessment.

Tripping hazards on the sidewalk cause many falls annually, and the inspection and repair of these hazards cost cities millions of dollars. Currently, there is not an efficient and cost-effective method to monitor the sidewalk to identify any possible tripping hazards. In this paper, a new portable device is proposed using an Intel RealSense D415 RGB-D camera to monitor the sidewalks, detect the hazards, and extract relevant features of the hazards. This paper first analyzes the effects of environmental factors contributing to the device's error and compares different regression techniques to calibrate the camera. The Gaussian Process Regression models yielded the most accurate predictions with less than 0.09 mm Mean Absolute Errors (MAEs). In the second phase, a novel segmentation algorithm is proposed that combines the edge detection and region-growing techniques to detect the true tripping hazards. Different examples are provided to visualize the output results of the proposed method.