Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

Smart control of the assembly process with a fuzzy control system in the context of Industry 4.0

Assembly line balancing is important for the efficiency of the assembly process, however, a wide range of disruptions can break the current workload balance. Some researchers explored the task assignment plan for the assembly line balancing problem with the assumption that the assembly process is smooth with no disruption. Other researchers considered the impacts of disruptions, but they only explored the task re-assignment solutions for the assembly line re-balancing problem with the assumption that the re-balancing decision has been made already. There is limited literature exploring on-line adjustment solutions (layout adjustment and production rate adjustment) for an assembly line in a dynamic environment. This is because real-time monitoring of an assembly process was impossible in the past, and it is difficult to incorporate uncertainty factors into the balancing process because of the randomness and non-linearity of these factors. However, Industry 4.0 breaks the information barriers between different parts of an assembly line, since smart, connected products, which are enabled by advanced information and communication technology, can intelligently interact and communicate with each other and collect, process and produce information. Smart control of an assembly line becomes possible with the large amounts of real-time production data in the era of Industry 4.0, but there is little literature considering this new context. In this study, a fuzzy control system is developed to analyze the real-time information of an assembly line, with two types of fuzzy controllers in the fuzzy system. Type 1 fuzzy controller is used to determine whether the assembly line should be re-balanced to satisfy the demand, and type 2 fuzzy controller is used to adjust the production rate of each workstation in time to eliminate blockage and starvation, and increase the utilization of machines. Compared with three assembly lines without the proposed fuzzy control system, the assembly line with the fuzzy control system performs better, in terms of blockage ratio, starvation ratio and buffer level. Additionally, with the improvement of information transparency, the performance of an assembly line will be better. The research findings shed light on the smart control of the assembly process, and provide insights into the impacts of Industry 4.0 on assembly line balancing.     

上榆泉煤矿煤泥水多参数在线检测系统应用研究

针对上榆泉煤矿煤泥水性质参数人工检测周期长、误差大、滞后性严重的问题,采用多参数传感器和PLC,开发了煤泥水多参数在线检测系统。经过8 h稳定运行,平均结果显示该厂煤泥水参数为pH值为7.71、浓度9.45%、中值直径(D50)39.56μm、流量2 440 m3/h、水质硬度428.94 mg/L,与人工检测结果相一致。应用结果表明,该检测系统能够实现煤泥水多参数在线监测和数据分析功能,使煤泥水的处理更高效。     

视频侦查中人像智能分析应用及算法优化

人像智能分析指的是对视频或录像中的人像进行结构化和可视化分析,对目标人物进行性别、年龄、发型等特征的智能识别,这项技术在视频侦查中有极高的应用价值。人像识别早期的算法是通过人工提取特征,通过学习低级视觉特征来针对不同属性进行分类学习,这种基于传统方法的模型表现常常不尽如人意。在计算机视觉领域,通过海量图像数据学习的神经网络比传统方法有更丰富的信息量和特征可以被提取。文章尝试通过深度学习技术训练神经网络模型对行人进行检测和识别,对于衣着不同的行人进行智能识别,具有更好的鲁棒性,提升了视频人像识别的准确率,拓展了人工智能技术在身份识别领域的应用。     

Occurrence and diversity of Listeria spp. in seafood processing plant environments

Listeria contamination in processing plant environments is a major issue for the seafood industry worldwide; faster and more reliable results are therefore desired for early detection and monitoring of environmental Listeria spp. This study aimed to gain a better understanding of the prevalence and diversity of Listeria spp., and to evaluate a rapid detection method, the 3M Molecular Detection Assay (MDA) Listeria, for its ability to detect Listeria spp. in environmental samples from seafood processing plants. Duplicate environmental sponge samples (n = 444) were collected from 152 different sites within three seafood processing plants, and analyzed for Listeria spp. by the MDA method (after 26 and 48 h of enrichment) and the U.S. Food and Drug Administration Bacteriological Analytical Manual method. Overall, detection of Listeria spp. by the two methods did not differ significantly (p > 0.05); 11 (4.9%) and 13 (5.9%) samples were positive for Listeria spp. by the MDA and FDA-BAM method, respectively. The sensitivity of the MDS was 87.0% (95% CI: 77.4–96.6%), specificity was 97.6% (95% CI: 95.5–99.7%), accuracy was 95.3%, and the positive predictive value was 89.4% (95% CI: 80.5–98.2%). Classification of 19 Listeria isolates by partial SigB sequencing analysis identified three allelic types. Twelve of these isolates were ATs 58 and 60 which were classified as Listeria monocytogenes lineage I and serotypes 1/2b, 3b, 4b, 4d, 4e, by multiplex-PCR serotyping. Six Listeria isolates were classified as Listeria innocua (AT31). Our data show that the 3M Molecular Detection Assay Listeria provides rapid and reliable results for detection and monitoring of Listeria spp., which are important for seafood processing plants. Effective Listeria monitoring programs will allow for improved development of Listeria control measures in order to minimize cross-contamination in finished products.     

Preparation of molecularly imprinted fluorescence sensor based on carbon quantum dots via precipitation polymerization for fluorescence detection of tetracycline

A facile and effective method was proposed to prepare the molecularly imprinted fluorescence sensor with carbon quantum dots, which were modified vinyl groups by acrylic acid on the surface. The obtained fluorescence composite material was investigated by transmission electron microscope and Fourier transform infrared spectra. After the experimental conditions were optimized, a linear range of 1.0–60 μmol L⁻¹ was obtained and the detection limit was 0.17 μmol L⁻¹. The novel fluorescence sensor can be successfully used to detect tetracycline in real samples. This study provides a convenient strategy for selective recognition and rapid detection of tetracycline in the complex environment.     

Proton-Detected Solid-State NMR of the Cell-Free Synthesized α-Helical Transmembrane Protein NS4B from Hepatitis C Virus

Proton-detected 100 kHz magic-angle-spinning (MAS) solid-state NMR is an emerging analysis method for proteins with only hundreds of microgram quantities, and thus allows structural investigation of eukaryotic membrane proteins. This is the case for the cell-free synthesized hepatitis C virus (HCV) nonstructural membrane protein 4B (NS4B). We demonstrate NS4B sample optimization using fast reconstitution schemes that enable lipid-environment screening directly by NMR. 2D spectra and relaxation properties guide the choice of the best sample preparation to record 2D ¹H-detected ¹H,¹⁵N and 3D ¹H,¹³C,¹⁵N correlation experiments with linewidths and sensitivity suitable to initiate sequential assignments. Amino-acid-selectively labeled NS4B can be readily obtained using cell-free synthesis, opening the door to combinatorial labeling approaches which should enable structural studies.     

Process monitoring method based on correlation variable classification and vine copula

Chemical processes are becoming increasingly complicated, leading to an increase in process variables and more complex relationships among them. The vine copula has a significant advantage in portraying the dependence of high-dimensional variables. However, as the dimensions increase, the vine copula model incurs a high computational load; such pressure greatly reduces model efficiency. Relationships among variables in the industrial process are complex. Different variables may be strongly or weakly associated or even independent. This paper proposes a process monitoring method based on correlation variable classification and vine copula. The weighted correlation measure is first used to divide variables into a correlated subspace and weakly correlated subspace. Then, two vine structures, C-vine and D-vine, are applied to the correlated and weakly correlated subspaces, respectively. This method takes advantage of C-vine for correlated variables and the flexibility of D-vine for weakly correlated variables. Finally, comprehensive statistics are established based on different subspaces. Monitoring results of the numerical system and the Tennessee Eastman process demonstrate the effectiveness and validity of the proposed method.     

环境中污染源废气检测方法及影响因素分析

对污染源废气监测原理进行了简单分析,阐述了当前我国常用的环境中污染源废气检测方法,并对废气检测影响因素及质量控制进行了深入探究。