ABSTRACT
Purpose: This study evaluates the effect of power wheelchair telemonitoring and battery charging training on user charging behavior and repair measures and assesses the relationship between wheelchair usage and repair measures to support technician-led servicing.Methods: This is a retrospective analysis of two matched cohorts with a total of n=237 users from the NHS service dataset. In the training cohort, a wheelchair usage telemonitoring device monitored the battery usage of n=119 power wheelchair users for 12 months. Users whose battery charging behavior was not optimal were instructed on appropriate charging practices. Wheelchair usage parameters of wheelchair drive and power time every month were used to predict repairs and associated costs.Results: Fifty-four out of 119 users in the training cohort did not charge batteries regularly and were instructed on appropriate charging. Twenty-six of them changed their behavior and charged their batteries every night. This cohort experienced reduced battery repairs by 18%, wheelchair repairs by 11%, and repair costs by £3,092 compared to a matched standard care cohort (n=118). User age and drive time were associated with repair measures. Drive time predicted time-to-failure for wheelchair parts and classified failure risk with the area under the receiver operating characteristic curve as 0.71 (95% CI 0.61 to 0.82; p<.001). Conclusions: By leveraging the significant relationships between wheelchair usage and repairs, wheelchair users at risk of part failures can be identified, and technician-led servicing tools for proactive interventions can be developed. Wheelchair battery health telemonitoring and instructing users on appropriate battery charging reduced repairs and associated costs.
Proactive wheelchair servicing by repair technicians in collaboration with wheelchair users safeguards users against critical part failures and minimises repair-related operating costs for service providers.Providers should leverage wheelchair telemonitoring technologies and related research outputs to improve repair services and support their clients' continued mobility and community participation.It is important that healthcare plans and policies recognise the benefits of proactive wheelchair servicing and use data as a tool to allocate device usage and performance-based reimbursements.
ABSTRACT
Millions of commuters face congestion as a part of their daily routines. Mitigating traffic congestion requires effective transportation planning, design, and management. Accurate traffic data are needed for informed decision making. As such, operating agencies deploy fixed-location and often temporary detectors on public roads to count passing vehicles. This traffic flow measurement is key to estimating demand throughout the network. However, fixed-location detectors are spatially sparse and do not cover the entirety of the road network, and temporary detectors are temporally sparse, providing often only a few days of measurements every few years. Against this backdrop, previous studies proposed that public transit bus fleets could be used as surveillance agents if additional sensors were installed, and the viability and accuracy of this methodology was established by manually processing video imagery recorded by cameras mounted on transit buses. In this paper, we propose to operationalize this traffic surveillance methodology for practical applications, leveraging the perception and localization sensors already deployed on these vehicles. We present an automatic, vision-based vehicle counting method applied to the video imagery recorded by cameras mounted on transit buses. First, a state-of-the-art 2D deep learning model detects objects frame by frame. Then, detected objects are tracked with the commonly used SORT method. The proposed counting logic converts tracking results to vehicle counts and real-world bird's-eye-view trajectories. Using multiple hours of real-world video imagery obtained from in-service transit buses, we demonstrate that the proposed system can detect and track vehicles, distinguish parked vehicles from traffic participants, and count vehicles bidirectionally. Through an exhaustive ablation study and analysis under various weather conditions, it is shown that the proposed method can achieve high-accuracy vehicle counts.
Subject(s)
Motor Vehicles , Transportation , Humans , Research Design , WeatherABSTRACT
Social distancing (SD) is an effective measure to prevent the spread of the infectious Coronavirus Disease 2019 (COVID-19). However, a lack of spatial awareness may cause unintentional violations of this new measure. Against this backdrop, we propose an active surveillance system to slow the spread of COVID-19 by warning individuals in a region-of-interest. Our contribution is twofold. First, we introduce a vision-based real-time system that can detect SD violations and send non-intrusive audio-visual cues using state-of-the-art deep-learning models. Second, we define a novel critical social density value and show that the chance of SD violation occurrence can be held near zero if the pedestrian density is kept under this value. The proposed system is also ethically fair: it does not record data nor target individuals, and no human supervisor is present during the operation. The proposed system was evaluated across real-world datasets.
