检索结果-南通市图书馆

Analysis and Prediction of Vehicle Exhaust Emission Using ANN 36

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Analysis and Prediction of Vehicle Exhaust Emission Using AN...

第36届中国控制会议

作者： zhenyi xu Yu Kang Wenjun Lv Department of Automation and State Key Laboratory of Fire Science University of Science and Technology of China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences

ISBN: (纸本)9781538629185

This paper focused on the analysis of vehicle emission based on the Hefei remote sensing data during the last three *** we propose a three-layer artificial neural network model for predicting vehicle exhaust emission using remote sensing ***,we take adaptive-lasso algorithm to analyze the various factors from the emission data,and determine the principal ***,after doing principal components analysis and selecting algorithm and architecture,the Back-Propagation neural network model with 7-12-1 architecture was established as the optimal ***,we give the prediction results on the testing data-set and prove the potentiality and validity of the proposed method in the prediction of vehicle exhaust emission.

关键词： Vehicle Exhaust Emission Adaptive-Lasso Artificial Neural Network

High-emitter identification for heavy-duty vehicles by temporal optimization LSTM and an adaptive dynamic threshold

在线全文

cnki会议

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2023年第11期24卷 1633-1646页

作者： zhenyi xu Renjun WANG Yang CAO Yu KANG Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China AHU-IAI AI Joint Laboratory Anhui UniversityHefei 230601China Department of Automation University of Science and Technology of ChinaHefei 230027China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230088China

Heavy-duty diesel vehicles are important sources of urban nitrogen oxides(NOx)in actual applications for environmental compliance,emitting more than 80%of NOx and more than 90%of particulate matter(PM)in total vehicle *** detection and control of heavy-duty diesel emissions are critical for protecting public ***,vehicles on the road must be regularly tested,every six months or once a year,to filter out high-emission mobile sources at vehicle inspection ***,it is difficult to effectively screen high-emission vehicles in time with a long interval between annual inspections,and the fixed threshold cannot adapt to the dynamic changes of vehicle driving *** on-board diagnostic device(OBD)is installed inside the vehicle and can record the vehicle’s emission data in real *** this paper,we propose a temporal optimization long short-term memory(LSTM)and adaptive dynamic threshold approach to identify heavy-duty high-emitters by using OBD data,which can continuously track and record the emission status in real ***,a temporal optimization LSTM emission prediction model is established to solve the attention bias discrepancy problem on time steps that is caused by the large number of OBD data streams in ***,the concentration prediction error sequence is detected and distinguished from the anomalous emission contexts using flexible criteria,calculated by an adaptive dynamic threshold with changing driving ***,a similarity metric strategy for the time series is introduced to correct some pseudo anomalous *** on three real OBD time-series emission datasets demonstrate that our method can achieve high accuracy anomalous emission identification.

关键词： High-emitter identification Temporal optimization On-board diagnostic device(OBD) Dynamic threshold

Effect of annealing temperature on Ti/Al/Ni/Au ohmic contacts on undoped AlN films

在线全文

学校读者我要写书评

暂无评论

Journal of Semiconductors 2017年第11期38卷 109-112页

作者： xuewei Li Jicai Zhang Maosong Sun Binbin Ye Jun Huang zhenyi xu Wenxiu Dong Jianfeng Wang Ke xu Platform for Characterization and Test Suzhou Institute of Nano-Tech and Nano-Bionics Chinese Academy of Sciences Suzhou 215123 China Suzhou Nanowin Science and Technology Co. Ltd Suzhou 215123 China University of Chinese Academy of Sciences Beijing 100049 China

The Ti/Al/Ni/Au metals were deposited on undoped AlN films by electron beam evaporation. The influence of annealing temperature on the properties of contacts was investigated. When the annealing temperatures were between 800 and 950 ℃, the AlN-Ti/Al/Ni/Au contacts became ohmic contacts and the resistance decreased with the increase of annealing temperature. A lowest specific contacts resistance of 0.379 Ω·cm^2 was obtained for the sample annealed at 950 ℃. In this work, we confirmed that the formation mechanism of ohmic contacts on Al N was due to the formation of Al-Au, Au-Ti and Al-Ni alloys, and reduction of the specific contacts resistance could originate from the formation of Au2Ti and AlAu2 alloys. This result provided a possibility for the preparation of Al N-based high-frequency, high-power devices and deep ultraviolet devices.

关键词： ohmic contacts AlN annealing temperature Ti/Al/Ni/Au

A PCB defect detection method based on multi-task learning mechanism

在线全文

学校读者我要写书评

暂无评论

A PCB defect detection method based on multi-task learning m...

第三十五届中国仿真大会

作者： Mingliang Fang Yu Kang Yang Cao zhenyi xu

PCB(Printed Circuit Board) is used as a carrier for electrical interconnection of electronic components. With the rapid development and wide application of integrated circuits, the volume of electronic equipment is becoming smaller and smaller, and the density and difficulty of circuit wiring are becoming more and more large. In industrial production and manufacturing, hundreds of components are often stuck on a PCB board, which requires high accuracy. This method uses VGG as the encoding backbone network to extract features, and connects two different tasks at the decoder, namely defect area detection task and defect binary classification task, and mutually improves the detection effect through multi-task mechanism. The motivation of this paper is on the one hand to exploit the useful information contained in multiple related tasks to improve segmentation and classification performance, and on the other hand to deal with the problem of small data, since each task can have relatively small datasets. The experiment results show that compared with the single task results, the proposed method improves the defect area detection performance by 5% to 10% in the case of small samples. According to whether there are defects, the final classification accuracy reaches 98%, and the recall rate of defect samples reaches 100%,which meets the needs of actual production.

关键词：

Air Pollution Lidar Signals Classification Based on Machine Learning Methods

在线全文

cnki会议

学校读者我要写书评

暂无评论

Air Pollution Lidar Signals Classification Based on Machine ...

第三十九届中国控制会议

作者： Binkun Liu zhenyi xu Yu Kang Yang Cao Lihong Pei Department of Automation University of Science and Technology of China Institute of Advanced Technology University of Science and Technology of China

With the rapid development of economy,environmental problems caused by various pollutants have become increasingly prominent,and air pollution become a hot topic of social *** the amount of SO and NO in the atmosphere requires a large-scale,rapid response pollution detecting device as well as a real-time signal processing *** this paper,we try to classify lidar signals to calculate the concentrations of nitrogen dioxide and sulfur dioxide by comparing several machine learning methods ***,Logistic Regression(LR),Random Forest(RF),and BP Neural *** the comparison,we can conclude that the original data extraction characteristics to build a data set,run on the above model can get good results while RF in constructing individual data set to achieve good results.

关键词： Air Pollution Random Forest Machine Learning lidar signals

Air pollution lidar echo signals preprocessing and classification

在线全文

cnki会议

学校读者我要写书评

暂无评论

Air pollution lidar echo signals preprocessing and classific...

第三十九届中国控制会议

作者： Lihong Pei zhenyi xu Yu Kang Yang Cao Binkun Liu Department of Automation University of Science and Technology of China Institute of Advanced Technology University of Science and Technology of China

With the development of ship transportation and economic globalization,burning oil on ships causes more and more serious air *** use of lidar to measure ship exhaust pollution has the advantages of large measurement range,non-contact monitoring,real-time measurement and high *** echo acquired by traditional lidar consists of three parts:the on signals,the off signals and the flag signals used only to distinguish between the on and the off *** data volume of flag signal is the same as the sum of on and off signal data,resulting in a large amount of storage waste and affecting the processing efficiency of real-time *** this paper,PCA is used to reduce the stored data dimensions of the on and the off signals,and binary classification methods such as decision tree,SVM and BP neural network are proposed to distinguish between the on and the off signals so as to reduce the storage waste of flag *** the supervised learning binary classification methods,we can get the classification performance with AUC value of 100%,and the original data volume is reduced from 82500*801 to 55000*8,which proves that the machine learning method has an effective application value in the laser radar echo signal processing.

关键词： Shipping emissions data preprocessing PCA BP neural network lidar signals classification

在线全文

cnki会议

学校读者我要写书评

暂无评论

美国扣留放行令的贸易影响及中国应对

国际商务研究 2024年第5期45卷 55-66页

作者：徐振毅北京师范大学北京100875

扣留放行令作为美国打击强迫劳动产品的贸易执行工具,因其对强迫劳动的模糊认定以及证据出示的低透明度,导致其在实施过程中存在泛化适用以遏制竞争对手经济发展的现实风险。扣留放行令对中国企业的泛化实施不仅造成了中国产品出口量下... 详细信息

扣留放行令作为美国打击强迫劳动产品的贸易执行工具,因其对强迫劳动的模糊认定以及证据出示的低透明度,导致其在实施过程中存在泛化适用以遏制竞争对手经济发展的现实风险。扣留放行令对中国企业的泛化实施不仅造成了中国产品出口量下降、企业声誉受损等消极影响,同时还破坏了国际供应链体系的稳定。为应对美国可能实施的强迫劳动制裁,中国政府应加强对强迫劳动制裁的风险监控;在受到美国制裁时,中国应进行适当的反制与谈判,同时拓宽受制裁产品的出口渠道,以消解美国制裁的不利影响。此外,企业宜加强产业供应链中的合规审查以降低受制裁的风险;在受到美国制裁时,企业宜通过行政层面的撤销申请以及司法层面的诉讼程序维护自身的合法权益。

关键词：扣留放行令强迫劳动经济制裁

维普期刊数据库博看期刊

大黄对人表皮黑素细胞的增殖及对酪氨酸酶的双向调节作用

在线全文

学校读者我要写书评

暂无评论

中华皮肤科杂志 1997年第6期30卷 404-405页

作者：许振毅张庆红天津市长征医院 300021

为了研究大黄对人表皮黑素细胞增殖的影响及对酪氨酸酶的双向调节作用，我们采用体外黑素细胞培养的方法，观察了大黄三种不同有效成分对表皮黑素细胞、酪氨酸酶的调节作用，现将结果报道如下。一、试验材料（一）细胞来源：４～６个月... 详细信息

为了研究大黄对人表皮黑素细胞增殖的影响及对酪氨酸酶的双向调节作用，我们采用体外黑素细胞培养的方法，观察了大黄三种不同有效成分对表皮黑素细胞、酪氨酸酶的调节作用，现将结果报道如下。一、试验材料（一）细胞来源：４～６个月的胎儿表皮。（二）培养基：角朊细胞...

关键词：大黄表皮黑素细胞细胞增殖酪氨酸酶

多组学数据分析中关联网络融合ANF算法及应用研究

在线全文

学校读者我要写书评

暂无评论

中国卫生统计 2020年第6期37卷 822-827页

作者：徐臻旖王策侯艳李康哈尔滨医科大学卫生统计学教研室 150081

目的引入关联网络融合(affinity network fusion,ANF)方法对多组学数据进行整合分析,并应用于肿瘤分子分型研究。方法模拟产生两组学数据,改变总体差异大小等情况比较多种多组学整合方法的效果。实例分析中目标人群选择TCGA数据库中对... 详细信息

目的引入关联网络融合(affinity network fusion,ANF)方法对多组学数据进行整合分析,并应用于肿瘤分子分型研究。方法模拟产生两组学数据,改变总体差异大小等情况比较多种多组学整合方法的效果。实例分析中目标人群选择TCGA数据库中对铂类药物敏感并拥有mRNA和甲基化两个组学的卵巢癌患者,目标基因是TCGA数据库和ImmPort数据库中共有基因,目标甲基化位点是目标基因对应的所有甲基化位点。使用ANF、SNF、K-means、系统聚类和iCluster五种方法比较聚类效果。结果模拟实验提示存在总体差异的两亚型间差异较小时ANF方法的效果明显优于其他方法。实例分析结果表明,通过ANF方法进行多组学数据整合得到的分子分型较单组学得到的分子分型有更好的生物学意义且多组学聚类效果优于其他方法。结论ANF方法可以应用于多组学数据整合分析,具有实际应用意义。

关键词： ANF方法多组学数据整合免疫分型