Cronobacter spp. are opportunistic pathogens that can cause serious diseases in neonates and infants via consumption of contaminated milk powder. To determine Cronobacter spp. contamination status, 632 samples, including 15 evaporated milk, 45 intermediate powder, 150 finished products, and 422 manufacturing environment samples, were collected from 3 goat milk powder factories in Shaanxi province, China, from July 2013 to April 2014. The recovered Cronobacter isolates were subtyped using pulsed-field gel electrophoresis to trace the potential dissemination routes during the whole production processing. Sixty-seven Cronobacter spp. isolates were recovered. The prevalence rates in manufacturing environment, intermediate powder, and finished products were 92.5, 6.0, and 1.5%, respectively. The predominant species were Cronobacter sakazakii (88.1%); no Cronobacter turicensis, Cronobacter condimenti, or Cronobacter dublinensis were detected. Sixty-seven Cronobacter isolates were grouped in 26 clusters by pulsed-field gel electrophoresis, and substantial genetic similarity was observed among isolates from different sampling sites in the same factory. Isolates in the main clusters were commonly recovered from intermediate powder, floor powder, and shoes. These data indicated that air, powder, and personnel movement were potential routes for Cronobacter dissemination, and manufacturing environment is the key control point for Cronobacter contamination.

Obstacle detection and target tracking are two major issues for intelligent autonomous vehicles. This paper proposes a new scheme to achieve target tracking and real-time obstacle detection of obstacles based on computer vision. ResNet-18 deep learning neural network is utilized for obstacle detection and Yolo-v3 deep learning neural network is employed for real-time target tracking. These two trained models can be deployed on an autonomous vehicle equipped with an NVIDIA Jetson Nano motherboard. The autonomous vehicle moves to avoid obstacles and follow tracked targets by camera. Adjusting the steering and movement of the autonomous vehicle according to the PID algorithm during the movement, therefore, will help the proposed vehicle achieve stable and precise tracking.

Chaos-based dynamics system is typical of the properties of randomness, determinacy and sensitivity to the initial parameters, which makes it suitable for the application of image encryption. In this paper, a wavelet domain color image encryption algorithm based on chaos is proposed. The color plain image is firstly decomposed into R, G, B components. Then an improved 3D chaotic cat map is proposed to confuse the wavelet coefficients of R, G, B components to make these three components affect each other and mixed randomly. The coupled map lattice model is employed to the diffusion process in the spatial domain to improve the performance of the cryptosystem. The effectiveness and capability of the proposed method are tested by a series of simulations and the results show that it is validity for color image and robustness to various attacks.

No abstract