Search

Recently, convolutional neural networks (CNNs) have been widely used in image denoising, and their performance has been enhanced through residual learning. However, previous research mostly focused on optimizing the network architecture of CNNs, ignoring the limitations of the commonly used residual learning. This paper identifies two of its limitations, which are the neglect of image information and the lack of effective consideration of image self-similarity. To solve these limitations, this paper proposes a compositional denoising network (CDN), which contains two sub-paths, the image information path (IIP) and the noise estimation path (NEP), respectively. IIP is trained via an image-to-image method to extract image information. For NEP, it utilizes image self-similarity from the perspective of training. This similarity-based training method constrains NEP to output similar estimated noise distributions for different image patches with a specific kind of noise. Finally, image information and noise distribution information are comprehensively considered for image denoising. Experimental results indicate that CDN outperforms other CNN-based methods in both synthetic and real-world image denoising, achieving state-of-the-art performance. [ABSTRACT FROM AUTHOR]

The paper describes a system and experimental procedure that use integrating passive detectors, such as thermoluminescent dosimeters (TLDs), for the measurement of ultra-low-level ambient dose equivalent rate values at the underground SNOLAB facility located in Sudbury, Ontario, Canada. Because these detectors are passive and can be exposed for relatively long periods of time, they can provide better sensitivity for measuring ultra-low activity levels. The final characterization of ultra-low-level ambient dose around water shielding for ongoing direct dark matter search experiments in Cube Hall at SNOLAB underground laboratory is given. The conclusion is that TLDs provide reliable results in the measurement of the ultra-low-level environmental radiation background. [ABSTRACT FROM AUTHOR]

As Canada's population of older adults rises, the need for aging-in-place solutions is growing due to the declining quality of long-term-care homes and long wait times. While the current standards include questionnaire-based assessments for monitoring activities of daily living (ADLs), there is an urgent need for advanced indoor localization technologies that ensure privacy. This study explores the use of Ultra-Wideband (UWB) technology for activity recognition in a mock condo in the Glenrose Rehabilitation Hospital. UWB systems with built-in Inertial Measurement Unit (IMU) sensors were tested, using anchors set up across the condo and a tag worn by patients. We tested various UWB setups, changed the number of anchors, and varied the tag placement (on the wrist or chest). Wrist-worn tags consistently outperformed chest-worn tags, and the nine-anchor configuration yielded the highest accuracy. Machine learning models were developed to classify activities based on UWB and IMU data. Models that included positional data significantly outperformed those that did not. The Random Forest model with a 4 s data window achieved an accuracy of 94%, compared to 79.2% when positional data were excluded. These findings demonstrate that incorporating positional data with IMU sensors is a promising method for effective remote patient monitoring. [ABSTRACT FROM AUTHOR]

Content Delivery Network (CDN) technology is one of the core technologies for performance optimization of mobile WEB applications, but it often encounters bottlenecks in video storage. In this paper, based on studying the basic technical model of distributed real-time transcoding CDN, we propose an overall technical architecture of a distributed real-time transcoding CDN system, present the business process of distributed real-time transcoding CDN resource negotiation in the model, design a resource storage policy model and algorithm, including the hot storage ratio resource storage value evaluation method and storage resource allocation algorithm. Through simulation experiments, we verify the technical efficiency of the distributed real-time transcoding CDN system by simulation experiments. [ABSTRACT FROM AUTHOR]

A large proportion of chronic stroke survivors still struggle with upper limb (UL) problems in daily activities, typically reaching tasks. During three-dimensional reaching movements, the deXtreme robot offers error enhancement forces. Error enhancement aims to improve the quality of movement. We investigated clinical and patient-reported outcomes and assessed the quality of movement before and after a 5 h error enhancement training with the deXtreme robot. This pilot study had a pre-post intervention design, recruiting 22 patients (mean age: 57 years, mean days post-stroke: 1571, male/female: 12/10) in the chronic phase post-stroke with UL motor impairments. Patients received 1 h robot treatment for five days and were assessed at baseline and after training, collecting (1) clinical, (2) patient-reported, and (3) kinematic (KINARM, BKIN Technologies Ltd., Kingston, ON, Canada) outcome measures. Our analysis revealed significant improvements (median improvement (Q1–Q3)) in (1) UL Fugl–Meyer assessment (1.0 (0.8–3.0), p < 0.001) and action research arm test (2.0 (0.8–2.0), p < 0.001); (2) motor activity log, amount of use (0.1 (0.0–0.3), p < 0.001) and quality of use (0.1 (0.1–0.5), p < 0.001) subscale; (3) KINARM-evaluated position sense (−0.45 (−0.81–0.09), p = 0.030) after training. These findings provide insight into clinical self-reported and kinematic improvements in UL functioning after five hours of error enhancement UL training. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]