xImpact: Intelligent Wireless System for Cost-Effective Rapid Condition Assessment of Bridges under Impacts.

Bridge strikes by over-height vehicles or ships are critical sudden events. Due to their unpredictable nature, many events go unnoticed or unreported, but they can induce structural failures or hidden damage that accelerates the bridge's long-term degradation. Therefore, always-on monitoring is essential for deployed systems to enhance bridge safety through the reliable detection of such events and the rapid assessment of bridge conditions. Traditional bridge monitoring systems using wired sensors are too expensive for widespread implementation, mainly due to their significant installation cost. In this paper, an intelligent wireless monitoring system is developed as a cost-effective solution. It employs ultralow-power, event-triggered wireless sensor prototypes, which enables on-demand, high-fidelity sensing without missing unpredictable impact events. Furthermore, the proposed system adopts a smart artificial intelligence (AI)-based framework for rapid bridge assessment by utilizing artificial neural networks. Specifically, it can identify the impact location and estimate the peak force and impulse of impacts. The obtained impact information is used to provide early estimation of bridge conditions, allowing the bridge engineers to prioritize resource allocation for the timely inspection of the more severe impacts. The performance of the proposed monitoring system is demonstrated through a full-scale field test. The test results show that the developed system can capture the onset of bridge impacts, provide high-quality synchronized data, and offer a rapid damage assessment of bridges under impact events, achieving the error of around 2 m in impact localization, 1 kN for peak force estimation, and 0.01 kN·s for impulse estimation. Long-term deployment is planned in the future to demonstrate its reliability for real-life impact events.

An FPGA Accelerator for High-Speed Moving Objects Detection and Tracking With a Spike Camera.

Ultra-high-speed object detection and tracking are crucial in fields such as fault detection and scientific observation. Existing solutions to this task have deficiencies in processing speeds. To deal with this difficulty, we propose a neural-inspired ultra-high-speed moving object filtering, detection, and tracking scheme, as well as a corresponding accelerator based on a high-speed spike camera. We parallelize the filtering module and divide the detection module to accelerate the algorithm and balance latency among modules for the benefit of the task-level pipeline. To be specific, a block-based parallel computation model is proposed to accelerate the filtering module, and the detection module is accelerated by a parallel connected component labeling algorithm modeling spike sparsity and spatial connectivity of moving objects with a searching tree. The hardware optimizations include processing the LIF layer with a group of multiplexers to reduce ADD operations and replacing expensive exponential operations with multiplications of preprocessed fixed-point values to increase processing speed and minimize resource consumption. We design an accelerator with the above techniques, achieving 19 times acceleration over the serial version after 25-way parallelization. A processing system for the accelerator is also implemented on the Xilinx ZCU-102 board to validate its functionality and performance. Our accelerator can process more than 20,000 spike images with 250 × 400 resolution per second with 1.618 W dynamic power consumption.

[Cost Analysis of Dog Deworming in Echinococcosis Control Program in Daofu，Sichuan Province].

Objective: To estimate the cost of dog deworming in Daofu, Sichuan Province and analyze the factors influencing the cost, in order to provide a scientific basis for the investment for echinococcosis control. Methods: Thirty villages were randomly selected in Daofu, Sichuan Province in November 2015, according to the proportion of agricultural and pastoral areas. Data concerning the cost during each step of dog deworming were collected. The unit cost was estimated, the cost composition in each step, element, and institution were described, and the main cost-influencing factors were analyzed using the linear regression method. Results: The mean cost of dog deworming in the 30 surveyed villages was 3.76 yuan/dog-times, comprising drug cost of 0.38 yuan/dog-times, bait cost of 0.37 yuan/dog-times, drug delivery cost of 0.09 yuan/dog-times, mobilization cost of 0.19 yuan/dog-times, household deworming cost of 2.05 yuan/dog-times, faeces disposal cost of 0.35 yuan/dog-times, training cost of 0.29 yuan/dog-times, and supervision cost of 0.04 yuan/dog-times. Among the deworming steps, household deworming cost occupied the most （2.05 yuan/dog-times）; among the cost elements, labour cost had the highest proportion （2.55 yuan/dog-times）; among the different-leveled institutions, village-level cost was the most important part（2.82 yuan/dog-times）. Linear regression analysis revealed that the type of production and the distance among households were the major influencing factors. The labour price was the most sensitive factor for cost-estimation in the dog deworming activities. Conclusion: The labor cost of dog deworming is very high. Governments should increase investment according to local situations.