Since the variety and destructiveness of unexpected natural disasters and health emergencies, and the weakness of emergency systems around the world, studies on collaborative emergency management (CEM) are receiving i...
详细信息
Since the variety and destructiveness of unexpected natural disasters and health emergencies, and the weakness of emergency systems around the world, studies on collaborative emergency management (CEM) are receiving increasingly attention recently. The existing literature has proved that with respect to the constraint of limited resources, it's usually unrealistic for CEM practitioners to push forward all influential factors that affect the comprehensive performance of CEM simultaneously. Thus, identifying the most critical success factors (CSFs) is of great significance to promote the effectiveness of CEM practices. To achieve this intention, we proposed a novel multi-granularity extended probabilistic linguistic weighted influence nonlinear gauge system and interpretative structural modeling (WINGS-ISM) approach with a consensus model optimized by the convolutional neural network algorithm. The new technique specializes in addressing the CSFs of episodes involving CEM characterized by the combination of uncertainty and complexity in group decision-making process. To validate its feasibility and robustness, we mainly investigate 10 CSFs to conduct an illustrative CEM case, the result shows that 'Applicable emergency response plan and regulations', 'Government unity of leadership and coordination' and 'Reasonable organizational structure and clear functions' are identified out of 10 influential factors. Besides, the cause-effect and hierarchal relationship digraphs indicate that the CSFs of CEM are interconnected, and this finding can support CEM practitioners to devote more attention to the most important factors, which may yield more improvements in CEM practices. Finally, some research implications are provided for better improving the effectiveness of CEM practices based on the findings of this study.
To date, the authors are not aware of an in-depth investigation about embedded applications of the convolutionalneuralnetwork (CNN) algorithm on small, lightweight, and low-cost hardware (e.g. microcontroller, FPGA,...
详细信息
To date, the authors are not aware of an in-depth investigation about embedded applications of the convolutionalneuralnetwork (CNN) algorithm on small, lightweight, and low-cost hardware (e.g. microcontroller, FPGA, DSP, and Raspberry Pi) applied to detect faults in structural health monitoring (SHM) systems. In this Letter, the authors implement and evaluate both feasibility and performance of an embedded application of the CNN algorithm on the Raspberry Pi 3. The CNN-embedded algorithm quantifies and classifies dissimilarities between the frames representing healthy and damaged structural conditions. In a case study, the CNN-embedded application was experimentally evaluated using three piezoelectric patches glued onto an aluminium plate. The results reveal an impressively effective 100% hit rate. This performance may significantly impact the design and analysis of CNN-based SHM systems where embedded applications are required for identifying structural damage such as those encountered by aerospace structures, rotating machineries, and wind turbines.
Optical colonoscopy is known as a gold standard screening method in detecting and removing cancerous polyps. During this procedure, some polyps may be undetected due to their positions, not being covered by the camera...
详细信息
Optical colonoscopy is known as a gold standard screening method in detecting and removing cancerous polyps. During this procedure, some polyps may be undetected due to their positions, not being covered by the camera or missed by the surgeon. In this Letter, the authors introduce a novel convolutionalneuralnetwork (ConvNet) algorithm to map the internal colon surface to a 2D map (visibility map), which can be used to increase the awareness of clinicians about areas they might miss. This was achieved by leveraging a colonoscopy simulator to generate a dataset consisting of colonoscopy video frames and their corresponding colon centreline (CCL) points in 3D camera coordinates. A pair of video frames were used as input to a ConvNet, whereas the output was a point on the CCL and its direction vector. By knowing CCL for each frame and roughly modelling the colon as a cylinder, frames could be unrolled to build a visibility map. They validated their results using both simulated and real colonoscopy frames. Their results showed that using consecutive simulated frames to learn the CCL can be generalised to real colonoscopy video frames to generate a visibility map.
暂无评论