基于SDAE-BP的联合收割机作业故障监测

为了解决联合收割机作业故障的非线性特征信号难以提取的问题,该研究提出了一种基于堆叠去噪自动编码器(Stack Denoising Auto Encoder, SDAE)和BP神经网络(Back Propagation,BP)融合的联合收割机作业故障监测及诊断的方法(SDAE-BP)。以转速传感器采集联合收割机脱粒滚筒转速、籽粒搅龙转速、喂入搅龙转速、杂余搅龙转速、风机转速、输送链耙转速、割刀频率以及逐稿器振动频率,并将采集的数据集作为系统的输入。利用SDAE提取输入信号的深层次特征,并由BP神经网络辨识收割机作业状态,实现联合收割机故障监测。在SDAE-BP模型训练过程中,去噪自动编码器(Denoising Auto Encode, DAE)依次经带有不同分布中心噪声的原始数据进行训练,然后将其堆叠,并通过误差反向传播算法对模型参数进行优化,以提升模型识别故障性能和泛化能力。试验结果表明,对于2018年联合收割机田间试验数据,模型的故障诊断准确率达到99.00%,与SDAE和BP神经网络相比,分别提高了1.5和4.5个百分点。将SDAE-BP故障诊断模型用2019年的试验数据进行更新,并用2018年和2019年试验数据进行测试,结果表明,更新后的模型对2018年试验数据的故障识别准确率为99.25%,对2019年试验数据的故障识别准确率为98.74%,更新后模型在2019试验数据集上的故障识别准确率较未更新模型提高了6.52个百分点。该文所建模型能够准确识别联合收割机的故障类型,且具有较好的鲁棒性,对旋转型机械故障监测及预警具有参考价值。     

Rapid detection of potato late blight using a loop-mediated isothermal amplification assay

Potato late blight caused by Phytophthora infestans is one of the most destructive plant diseases that threaten global food security. Early and effective diagnosis of P. infestans is required before disease management decisions are made. Here, we developed a quick protocol to detect P. infestans based on a loop-mediated isothermal amplification(LAMP) assay. The P. infestans specific multiple copy DNA sequences(PiSMC), a transposon-like element, provides an ideal target for molecular detection of this pathogen. We designed highly specific and sensitive primers allowing effective LAMP detection of the pathogen at 64℃ in 70 min. In the validation assay, all 15 P. infestans isolates collected from China, Europe and South America could be positively detected, but results of the other 9 Phytophthora species infecting different plants, fungal and bacterial plant pathogens tested were negative. The detection limit of this assay is 1 pg P. infestans DNA. Moreover, the LAMP-PiSMC assay is able to detect P. infestans from infected leaves, tubers and soil. Taken together, this study reports the development of a specific and sensitive LAMP-PiSMC assay for early diagnosis of potato late blight.     

基于光声光谱和TCA迁移学习的稻种活力检测

种子活力是决定水稻产量的最重要因素之一，但目前水稻种子活力的近红外和高光谱等无损检测方法易受种子表皮颜色影响，且所建模型难以适应新品种。该研究提出基于光声光谱技术的稻种活力无损检测方法并结合迁移学习进行新品种稻种活力检测。首先，对Y两优、龙粳、南粳、宁粳、武运粳、新两优等具有区域代表性的典型6种水稻品种，进行高温高湿人工老化处理，得到0~7 d老化时间的水稻种子；再通过调制频率获得8种不同深度的光声光谱信息，用主成分分析、竞争性自适应重加权算法对光谱降维得到特征光谱后，对Y两优、龙粳、南粳、宁粳、武运粳分别建立偏最小二乘回归（Partial Least Squares Regression，PLSR）、反向传播神经网络（Back Propagation Neural Network，BP）、广义回归神经网络（Generalized Regression Neural Network，GRNN）、支持向量回归模型（Support Vector Regression，SVR）、深度卷积神经网络（Convolutional Netural Network，CNN）的稻种活力预测模型，并选择最优调制频率；最后，通过迁移学习将建立的模型迁移到新两优稻种进行活力预测。结果表明，光声光谱最佳扫描频率为300 Hz，CNN预测模型精度较高，相关系数和均方根误差分别优于0.990 9、低于0.967 5；且经过迁移学习，仅需通过对源域数据的训练，即可直接对新品种稻种的活力进行精确预测；通过TCA迁移学习后，新两优稻种活力预测的相关系数从0.718 5提高到0.990 3。研究表明，采用光声光谱深度扫描技术对不同种类稻种的活力进行高精度检测是可行的，且经过迁移学习，仅需80粒新品种稻种信息即可实现稻种活力的精确预测。     

Influence of tree crown characteristics on the local PM10 distribution inside an urban street canyon in Antwerp (Belgium): A model and experimental approach

Apart from influencing the amount of leaf-deposited particles, tree crown morphology will influence the local distribution of atmospheric particles. Nevertheless, tree crowns are often represented very rudimentary in three-dimensional air quality models. Therefore, the influence of tree crown representation on the local ambient PM₁₀ concentration and resulting leaf-deposited PM₁₀ mass was evaluated, using the three-dimensional computational fluid dynamics (CFD) model ENVI-met^® and ground-based LiDAR imaging. The modelled leaf-deposited PM₁₀ mass was compared to gravimetric results within three different particle size fractions (0.2–3, 3–10 and >10 μm), obtained at 20 locations within the tree crown. Modelling of the LiDAR-derived tree crown resulted in altered atmospheric PM₁₀ concentrations in the vicinity of the tree crown. Although this model study was limited to a single tree and model configuration, our results demonstrate that improving tree crown characteristics (shape, dimensions and LAD) affects the resulting local PM₁₀ distribution in ENVI-met. An accurate tree crown representation seems, therefore, of great importance when aiming at modelling the local PM distribution.     

Research Progress on Rapid Serological Assays for Diagnosis of Japanese Encephalitis B

Japanese encephalitis B (JE) is a zoonosis caused by Japanese encephalitis virus which invades the central nervous system,infected by mosquito.Various animals could be the sower and reservoir of JE including swine,horse,cattle and avian.JE could cause a major public health trouble and a horrible crisis of the farm all in Asia and the Western Pacific region.Therefore,it is necessary to diagnose it rapidly and accurately.This review article made a sketch of approaches for the rapid serological assays of JE,including traditional method,emerging technologies and specific improvements of the assay,so as to provide references for the study of rapid,simple and accurate JE diagnose methods.     

防疲劳驾驶系统的设计

设计一套集疲劳驾驶计时功能、疲劳驾驶检测功能、疲劳驾驶警示灯显示功能、GPS疲劳语音提示功能及GPS定位功能于一体的防疲劳驾驶系统,绘制工作流程图.通过模拟驾驶器模拟实际驾驶,对比分析头部位置检测系统、车道偏离报警系统、转向盘监测系统、驾驶员警示系统及PERCLOS系统检测疲劳驾驶的优缺点,得出了PERCLOS系统为最优疲劳驾驶检测方法.依据人因工程理论,给出了车体外部警示灯的位置和颜色的设计方案.     

Detection of cigarettes and other tobacco products by giant African pouched rats (Cricetomys gambianus)

If the illicit tobacco trade were eliminated, governments could gain at least $31.3 billion a year, and more than 164,000 premature deaths a year could be avoided after 2030 (Joossens, Merriman, Ross, and Raw, 2009). Dogs have been used successfully in tobacco control programs, and there is a good chance that rats could also play an important role. In the present experiment, giant African pouched rats were trained to respond to filters that had been stored together with cigarettes (i.e., soaked) and to not respond to filters that had been soaked with noncigarette items. Generalization to untrained types of tobacco was then tested. The sensitivity of 4 rats trained on filters soaked with 1 of 7 types of cigarettes ranged from 86% to 100% (mean, 95%). There was very little evidence of generalization when the rats were tested on tobacco leaves and snuff but good evidence of generalization when the rats were tested on cigarettes that had been soaked with strong-smelling additives. These findings suggest that rats may be a valuable asset in the global effort to control illicit cigarette trade.     

基于农业物联网的改进型双门限频谱检测算法研究

农业物联网的出现,对信息化与农业现代化融合具有积极推动的作用。在农业物联网中信息传输是一个至关重要的环节,到目前为止,普通的3G和4G通信网络已经不能提供农业物联网中进行信息传递所需要的频谱资源,而认知无线电网络恰恰可以满足农业物联网的需求。它显著的特点就是可以发现未被授权用户利用的频谱,来供给未授权用户使用,提高了频谱资源的利用率。在认知无线电中,最重要的步骤就是进行频谱检测,笔者就是在双门限频谱检测算法的基础上提出一种新型算法。该算法适当地选取条件好的认知用户进行数据融合,并不是采纳所有认知用户的本地检测信息。仿真结果表明:本文提出的算法可有效提高认知无线电系统中频谱感知的性能,降低虚警概率,以更好地为农业物联网提供可用的频谱资源。     

Reconstructing mole tunnels using frequency-domain ground penetrating radar

The European mole (Talpa europaea L.) inhabits an underground tunnel system whereby the density, extent and condition of the subsurface tunnels are indicative of its activity. Currently, no survey method was able to reveal the spatial extent and condition of the mole's tunnel network. Frequency-domain ground penetrating radar (GPR) was evaluated on its potential to image these shallow tunnel systems. This technique allows for a non-invasive, high-resolution mapping of the subsurface. We examined the effectiveness of this GPR system for delineating the mole's tunnel network. The integration of different depth slices allowed a detailed overview of the tunnel system. Automatic feature recognition on these GPR images was proven valuable for the detection and representation of the mole tunnels. The GPR survey proved successful in mapping the mole's tunnel network, which facilitates the interpretation and characterization of the mole's living environment. This can be linked to the occurrence of earthworms, as the principle food source of the moles, which regulate important ecosystem processes within the soil. This offers new perspectives for the understanding of the mole's habitat.     

吴忠市利通区西瓜果斑病的发生及防控措施

详细介绍了利通区西瓜果斑病的发生、危害症状及发生前后宜采取的各种防控措施及预防措施。