检索结果-内蒙古大学图书馆

6th International Conference on Robotics and Automation engineering, ICRAE 2021

作者： Jin, Xu Xiao, Zhiyun Dong, Alideertu Wang, Yining Nie, Qixin Wang, Lifang Inner Mongolia University of Technology College of Electric Power Hohhot China Inner Mongolia University of Technology Key Laboratory of Electromechanical Control of Inner Mongolia Autonomous Region Hohhot China Inner Mongolia University College of Chemistry and Chemical Engineering Hohhot China Engineering Research Center of Ministry of Education Dairy Product Quality and Safety Control Technology Inner Mongolia University Huohhot010021 China Inner Mongolia Academy of Agriculture and Animal Husbandry Sciences Hohhot China Agric. Prod. Qual. and Safety Risk Assess. Lab. of the Ministry of Agriculture and Rural Affairs Hohhot010031 China

ISBN: (纸本)9781665406970

A hyperspectral inversion modeling method is proposed to predict the fat and protein content in milk by integrating SG, CR and XGBoost to address the drawbacks of traditional chemical methods for detecting fat and protein in milk, which require damage to the emulsion itself, complicated operation and environmental pollution. The method first combines Savitzky-Golay (SG) and Continuum-Removal (CR) to pre-process the hyperspectral data, and then uses Correlation-Analysis (CA) to screen the feature bands. Finally, the screened 10 feature bands are used as inputs to build partial least squares regression (PLSR) and XGBoost models, and the model prediction results are compared. The results show that the SG_CR algorithm is an effective hyperspectral preprocessing method to improve modeling accuracy, and the screening of feature bands can greatly reduce model complexity and improve model efficiency while ensuring model accuracy. Compared with the linear model PLSR, the machine learning integration algorithm XGBoost performed optimally. Its fat and protein models have training set coefficients of determination (R2) of 0.9449 and 0.9980, training set root mean square error (RMSE) of 0.2395 (g/100g) and 0.0409 (g/100g), training set relative analysis error (RPD) of 3.8188 and 22.2079, test set R2 of 0.8653 and 0.9273, test set RMSE were 0.4672 (g/100g), 0.2116 (g/100g), and test set RPD were 2.4625, 3.5998. © 2021 IEEE.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

How the Imperfect E-diagnostics Impacts the Capacity Planning and Pricing Decisions of a Maintenance Service Provider

引用

Procedia CIRP 2019年 83卷 398-403页

作者： Mingyao Sun Feng Wu The School of Management Xi’an Jiaotong University The Key Lab of the Ministry of Education for Process Control & Efficiency Engineering Xi’an 710000 China

Providing online monitoring (E-diagnostics) has become a value-added practice for equipment maintenance service providers to improve the service quality and efficiency. However, the E-diagnostics is always imperfect, whose accuracy depends on how much components of the equipment are monitored (namely, E-diagnostics depth in our research). This research analyzes the optimal capacity planning and pricing problem by taking into account the imperfect E-diagnostics. In addition, we consider the E-diagnostics accelerate effect to the service process and attempt to find how the effect influences the service provider’s decisions. Our results reveal that the optimal pricing and capacity planning decisions are dependent on customers’ failure cost and service provider’s compensation cost. Specifically, if customers’ failure cost is larger than service provider’s compensation, the service provider would improve the price as the E-diagnostics depth increases; otherwise, the price should be lowered as the E-diagnostics depth increases. In addition, we find as the accelerate effect becomes increasingly obvious, customers’ expected waiting time increases but the service price decreases.

关键词： Imperfect E-diagnostics capacity planning pricing E-diagnostics depth accelerate effect

来源：评论

学校读者我要写书评

暂无评论

Auto data augmentation for testing set 1

引用

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Gao, Wanshun Zhao, Xi School of Electronic and Information Engineering Xi’an Jiaotong University Xi’an710049 China School of Management Xi’an Jiaotong University Xi’an710049 China The Key Lab of the Ministry of Education for Process Control & Efficiency Engineering Xi’an710049 China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

Testing phase augmentation is a fast way to further improve the performance of image classification when CNN (Convolutional Neural Network) is already trained for hours. Limited attempts have been made to find the best augmentation strategy for testing set. We propose a reinforcement learning based augmentation strategy searching method for testing phase augmentation. With the augmentation strategy, we augment each testing image and integrate features of its augmented images into one feature. The reinforcement learning method searches the best parameters in the augmentation strategy which is formed as a matrix in this paper. Using the proposed method, we achieve competitive accuracies on image classification and face verification. © Springer Nature Switzerland AG 2019.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Comparison research on X-ray image quality defects detection algorithm in semiconductor manufacturing

Comparison research on X-ray image quality defects detection...

引用

IEEE International Conference on Smart Manufacturing, Industrial & Logistics engineering (SMILE)

作者： Hongyu Hou Feng Wu The Key Lab of the Ministry of Education for Process Control & Efficiency Engineering The school of management Xi'an Jiaotong University Xi'an China

Detecting product quality defects through image recognition technology is one of the key technologies of intelligent manufacturing, and also an important step for enterprises to construct smart factory. In the capsulation step of the semiconductor enterprise, the internal wire bonding of the chip is easily to receive the interference and to produce the defects. Companies need to pick out defective chips to avoid them going to the market. Traditional way is to use artificial vision visual inspection, which may lead to low efficiency and high lab.r cost. This study intends to use machine vision detection method based on image processing technology to identify the defect of the chip and to replace the workers artificial detection work. This paper proposes two algorithms to solve such above problems. The template matching algorithm (TMA) is to determine whether the chip is defective mainly based on the standard template. The neighborhood comparison algorithm (NCA) mainly calculates similarity of the neighbor chips to judge the target chip's defects. The algorithm is implemented by Halcon software. A German semiconductor company has provided enough samples to support our research. The experimental results show that the two algorithms are effective in defect detection of specific products. The advantage of the TMA lies in its processing speed, but the applicability and accuracy of NCA is more excellent. The algorithm proposed in this study can be used for enterprise by being integrated into the actual detection process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transcriptome analysis of unsaturated fatty acids biosynthesis shows essential genes in sprouting of Acer truncatum Bunge seeds

引用

Food Bioscience 2021年 41卷

作者： Chen, Dong-Ju Luo, Xue-Gang Yan, Li-Hua Si, Chuan-Ling Wang, Nan He, Hong-Peng Zhang, Tong-Cun Key Lab of Industrial Fermentation Microbiology of the Ministry of Education Tianjin Key Lab of Industrial Microbiology College of Biotechnology Tianjin University of Science and Technology Tianjin 300457 China Tianjin Engineering Research Center of Microbial Metabolism and Fermentation Process Control Tianjin 300457 China Tianjin Key Laboratory of Pulp & Paper Tianjin University of Science & Technology Tianjin 300457 China

The seeds of Acer truncatum Bunge (ATB) are rich in unsaturated fatty acids (UFA), especially nervonic acid, an important nutrient for the growth and maintenance of the brain. Therefore, the oil of ATB seeds has been approved as a New Resource Food in China. In the present study, changes of transcriptomic profiling and contents of UFA during the sprouting of ATB seeds were analyzed. The results of RNA-seq-based transcriptome analysis showed that the transcription of genes in various metabolic pathways, including the biosynthesis pathway of UFA, were significantly altered during seed sprouting. The gas chromatography-mass spectrometry assay consistently showed that the content of palmitoleic acid, palmitic acid, stearic acid, gondoic acid, arachidic acid, behenic acid, nervonic acid and lignoceric acid increased 77.9, 20.9, 39.6, 26.3, 95.6, 80.0, 41.7 and 141%, respectively, while the content of oleic acid decreased 49.2%, after sprouting. The whole coding sequence regions of genes involved in the UFA biosynthesis were cloned and sequenced, and the alignment analysis predicted that omega-6 fatty acid desaturase and short-chain type dehydrogenase/reductase might have important roles in the biosynthesis of UFA during the sprouting. The results suggested that nervonic acid could be enriched in ATB seeds via sprouting-stimulation, which had not been previously observed. © 2020

关键词： Acer truncatum Bunge Bioinformatics analysis Cloning Transcriptome sequencing Unsaturated fatty acids Yuanbao maple

来源：评论

学校读者我要写书评

暂无评论

Biological and physical properties of a modification silicone liner 4

Biological and physical properties of a modification silicon...

引用

2020 4th International Conference on Material Science and Technology, ICMST 2020

作者： Gu, Huiru Luan, Huiqin Mo, Zhongjun Song, Iang Fan, Yubo Key Laboratory for Biomechanics and Mechanobiology of Ministry of Education School of Biological Science and Medical Engineering Beihang University Beijing100191 China Key Laboratory of Intelligent Control and Rehabilitation Technology of the Ministry of Civil Affairs National Research Center for Rehabilitation Technical Aids Beijing100176 China Beijing Key Laboratory of Rehabilitation Technical Aids for Old-Age Disability Beijing100176 China Key Lab. of Rehab. Tech. Aids Anal. and Identification of the Min. of Civ. Aff. Beijing100176 China

Silicone liners provide comfortability for amputees, meanwhile effectively protecting their skin surface and subcutaneous tissue. Silicone liners used in prosthetics are mainly used for filling, cushioning, and suspending a receiving cavity. At present, biological and mechanical properties of silicone liners in prosthetic cavity remain unclear, and the price is expensive for amputees. We improve the silicone material preparation process to reduce the price as well as to ensure the mechanics and biosafety of the material. Characterization of silicone liner surface, cellular toxicity of silicone liner, bacterial adhesion on the surface of silicone liner, and mechanical properties were evaluated and compared among commercial materials (sample A and B) and our improved silicone liner material (sample C). The water contact, the macroscopic surface and the calculated mechanical parameters have no significant differences among the three types samples. The extract of three types silicone liner have no cytotoxicity reactivity. Samples C markedly reduced the adhesion of E. coli compared with sample A. The improved silicone material preparation process ensured the biological and mechanical properties and reduced the price of these silicone liners, thereby increasing their potential as silicone liners of prosthetics cavity. © 2020 Institute of Physics Publishing. All rights reserved.

关键词： Silicones

来源：评论

学校读者我要写书评

暂无评论

Prediction of tariff package model using ROF-LGB algorithm 2019

Prediction of tariff package model using ROF-LGB algorithm

引用

2nd International Conference on Data Science and Information Technology, DSIT 2019

作者： Zheng, Nai Song Jiang, Xiao Wei Ao, Yibo Zhao, Xi School of Mathematics and Statistics Xi'an Jiaotong University Xi'an710049 China School of Electronic and Information Engineering Xi'an Jiaotong University Xi'an710049 China School of Management Xi'an Jiaotong University Xi'an710049 China Key Lab of the Ministry of Education for Process Control and Efficiency Engineering Xi'an710049 China

ISBN: (纸本)9781450371414

With the slowing growth of the telecommunication market and the intense competition for existing customers, Customer Churn Management has become a crucial task for all mobile network operators. Recommendation models based on customer behaviors are widely used by operators to provide diverse telecom tariff packages for suitable people and thus improve customer satisfaction. To address the low precision rate and data granularity of prior studies, this study combined rotation forest (ROF) and LightGBM and construct a hybrid algorithm (ROF-LGB). Grid search method was used in parameter tuning, and ten-fold cross-validation method was used to prevent overfitting. Using mobile data generated by operators, ROF-LGB method was tested and compared with other five traditional machine learning methods. The results showed that ROF-LGB method achieved better performance with better precision rate and execution efficiency in telecom tariff package recommendation. © 2019 Association for Computing Machinery.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Methods on Optimization Problems of Natural Gas Pipeline Networks

Reinforcement Learning Methods on Optimization Problems of N...

引用

IEEE International Conference on Smart Grid and Smart Cities (ICSGSC)

作者： Dong Yang Siyun Yan Dengji Zhou Tiemin Shao Lin Zhang Tongsheng Xing The key Lab. of power machinery and engineering of education ministry Shanghai Jiao Tong University Shanghai China PetroChina Beijing Oil & Gas Pipeline Control Center Beijing China

ISBN: (数字)9781728194042

ISBN: (纸本)9781728194059

Traditional optimization methods of transport and distribution of natural gas pipeline networks have been widely used up to now with some problems in efficiency, cost, and flexibility, which are hard to be solved in the framework of traditional methods. In order to find the optimal solution in the constraints of each target of this optimization problem, this paper establishes a simulation model based on a part of a natural gas pipeline networks, and utilizes the reinforcement learning (RL) algorithm to analyze the model. The challenge of sparse rewards will also be dealt with. Then the optimal strategy of transport and distribution of gas in this model is obtained with different demands and initial conditions. The parameters of the operation of the strategy can be displayed in the simulation model and its advantages can also be fully reflected. Therefore, the scheme proposed in this paper can be directly or indirectly applied to the practical natural gas transport process.

关键词： Training Analytical models Smart cities Pipelines Reinforcement learning Smart grids Natural gas

来源：评论

学校读者我要写书评

暂无评论

A cost-effective data replica placement strategy based on hybrid genetic algorithm for cloud services 12th

A cost-effective data replica placement strategy based on hy...

引用

12th IFIP WG 8.9 Working Conference on Research and Practical Issues of Enterprise Information Systems, CONFENIS 2018 Held at the 24th IFIP World Computer Congress, WCC 2018

作者： Huang, Xin Wu, Feng School of Management The Key Lab of the Ministry of Education for Process Control and Efficiency Engineering Xi’an Jiaotong University Xi’an710049 China

ISBN: (纸本)9783319990392

Cloud computing provide an efficient big data processing platform for many small and medium scale enterprises, how to replicate and allocate data in clouds is a critical problem influencing cost consumption for small and medium scale enterprises. Cloud data management systems mainly serve two kinds of workloads, one is read-intensive analytical workloads (e.g. OLAP), the other is write-intensive transactional workloads (e.g. OLTP). It is essential to minimize data management costs like storage, communication bandwidth, update and power with guaranteeing the service level agreements. Toward two workloads, a cost-effective data replica placement approach for minimizing data management costs on cloud computing centers is proposed. The definition of different data management costs is identified first, then we construct the cost optimization model of the data replica placement problem. The paper proposes a hybrid genetic algorithm and a data support-based initialization method that addresses the problem. Experiments show that the approach result in significant reduction in total data management cost and the algorithm is with good performance. © IFIP International Federation for Information processing 2018.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Exploring the prediction of variety-seeking behavior 2019

Exploring the prediction of variety-seeking behavior

引用

2nd International Conference on Data Science and Information Technology, DSIT 2019

作者： Li, Jiazhao Zhao, Jiuxia Mao, Minjia Zhao, Xi Zou, Jianhua School of Electronic and Information Engineering Xi'an Jiaotong University Xi'an710049 China School of Mathematics and Statistics Xi'an Jiaotong University Xi'an710049 China School of Management Xi'an Jiaotong University Xi'an ShaanXi China Key Lab of the Ministry of Education for Process Control and Efficiency Egineering Xi'an710049 China

ISBN: (纸本)9781450371414

As a common choice strategy for consumers, variety-seeking has a direct impact on the business performance of enterprises, and has been studied for decades in management science and marketing research. Existing research tends to find factors which influence variety-seeking by means of questionnaires and lab.ratory experiments. Based on the important factors, marketers develop marketing plans which are tailored to consumers. However, due to personal motivation, the results of questionnaires and lab.ratory experiments may not fully reflect internal states of participants. Thus, we propose a data-driven framework, using ensemble learning for predicting variety-seeking behavior based on real student consumption data. Experiments demonstrate that our model outperforms separate machine learning algorithms and can effectively predict variety-seeking behavior. We further analyze the contribution of each feature towards the prediction, achieving some useful conclusions for the study of variety-seeking intervention mechanism. © 2019 Association for Computing Machinery.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：