检索结果-内蒙古大学图书馆

15th CCF Conference on Computer Supported Cooperative Work and Social Computing, Chinese CSCW 2020

作者： Li, Tiancai Wen, Yiping Tan, Zheng Chen, Hong Cao, Buqing School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Key Laboratory of Knowledge Processing and Networked Manufacturing Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)9789811625398

Aiming at the problems of unreasonable distribution routes in the current logistics distribution field, without considering the impact of real-time road conditions, and the inability to reduce the impact on the timeliness of distribution, this paper proposes a dynamic vehicle distribution path optimization method based on the collaboration of cloud, edge and end devices. This method considers the requirements of demand points for the delivery time and considers the changes in road traffic conditions caused by random road traffic incidents. Combining the characteristics of vehicle speed and time penalty cost in the vehicle delivery process establishes a logistics delivery vehicle path optimization model. Solve it and optimize it with the A* algorithm and dynamic schedule. This method collects road condition data in real-time through terminal equipment, evaluates and judges road conditions at the edge, and makes real-time adjustments to the distribution plan made in advance at the cloud data center. Through simulation experiments on application examples, the vehicle path optimization method proposed in this paper that considers real-time road conditions changes and the optimization method that does not consider road conditions are compared and analyzed, verifying the effectiveness of this method. Experimental results show that this method can reduce distribution costs, reduce distribution time, and reduce the impact of changes in road conditions on the distribution results. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Research on Machine Learning Method for Equipment Health Management in Industrial Internet of Things 15th

Research on Machine Learning Method for Equipment Health Man...

引用

15th CCF Conference on Computer Supported Cooperative Work and Social Computing, Chinese CSCW 2020

作者： Tan, Zheng Wen, Yiping School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Key Laboratory of Knowledge Processing and Networked Manufacturing Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)9789811625398

Much industrial equipment integrates multiple types of sensors for data collection and real-time connection with the Industrial Internet of Things (IIoT) at now. With the popularity and application of miniaturized and low-cost sensors, to manage the health of equipment in the IIoT, such as evaluating the current health indicator (HI) of the equipment, and predicting its remaining useful life (RUL), the machine learning-based method reflects a broader application prospect due to its good at data mining and analysis. A RUL prediction method of equipment in this paper is proposed. First, a specific data processing method is proposed according to the characteristics of the data, the outputs of the hidden layer of stacked denoising autoencoder (SDAE) as the features of the data set which are extracted to complete the HI construction. Then, the trajectory pointwise difference and similarity method are proposed to generate predicted equipment RUL. This paper uses the C-MAPSS engine data set for experimental verification. The experimental results show that the method proposed in this paper can effectively use the data of multi-dimensional sensor data to get the degradation progress of the equipment, thereby assessing the health of the equipment and more accurately estimating the RUL. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Online Machine Learning-Based Prediction Strategy for Dynamic Evolutionary Multi-objective Optimization 11th

An Online Machine Learning-Based Prediction Strategy for Dyn...

引用

11th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2021

作者： Liu, Min Chen, Diankun Zhang, Qiongbing Jiang, Lei School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan4111201 China Key Laboratory of Knowledge Processing and Networked Manufacturing College of Hunan Province Xiangtan4111201 China

ISBN: (纸本)9783030720612

Due to the impact of environmental changes, dynamic evolutionary multi-objective optimization algorithms need to track the time-varying Pareto optimal solution set of dynamic multi-objective optimization problems (DMOPs) as soon as possible by effectively mining historical data. Since online machine learning can help algorithms dynamically adapt to new patterns in the data in machine learning community, this paper introduces Passive-Aggressive Regression (PAR, a common online learning technology) into dynamic evolutionary multi-objective optimization research area. Specifically, a PAR-based prediction strategy is proposed to predict the new Pareto optimal solution set of the next environment. Furthermore, we integrate the proposed prediction strategy into the multi-objective evolutionary algorithm based on decomposition with a differential evolution operator (MOEA/D-DE) to handle DMOPs. Finally, the proposed prediction strategy is compared with three state-of-the-art prediction strategies under the same dynamic MOEA/D-DE framework on CEC2018 dynamic optimization competition problems. The experimental results indicate that the PAR-based prediction strategy is promising for dealing with DMOPs. © 2021, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

CA-NCF: A Category Assisted Neural Collaborative Filtering Approach for Personalized Recommendation

CA-NCF: A Category Assisted Neural Collaborative Filtering A...

引用

Symposium of Image, Signal processing, and Artificial Vision (STSIVA)

作者： Yimin Peng Rong Hu Yiping Wen Hunan University of Science and Technology Xiangtan China Key Laboratory of Knowledge Processing & Networked Manufacturing Xiangtan China

ISBN: (纸本)9781665426565

In the big data environment, the sparsity problem of collaborative filtering recommendation algorithm becomes increasingly serious, which has a great impact on the accuracy of recommendation. In some recent researches, item categories were input into neural networks to enrich the embedded information in the process of training. However, these methods generally simultaneously use item categories and items as embedded information, which may weaken the importance of item categories. Therefore, this paper proposes a neural collaborative filtering method based on category assistance. In this method, the interaction between item category and user is first modeled by Neural Matrix Factorization ((Neu-MF)), which raises the impact of item category in the relationship extraction between items and users. Then, only the items in the trained results of categories are used in an optimized Neural Collaborative Filtering (NCF) framework for item recommendation. Based on the real ecommerce data set from Alibaba, experimental results show that this method obtains better result in the Hit Rate (HR) and the Normalized Discounted Cumulative Gain (NDCG) compared with other baseline methods.

关键词： Training Collaborative filtering Conferences Neural networks Collaboration Big Data Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Exploring Hybrid Genetic Algorithm Based Large-Scale Logistics Distribution for BBG Supermarket

引用

Journal on Artificial Intelligence 2021年第1期3卷 33-43页

作者： Yizhi Liu Rutian Qing Liangran Wu Min Liu Zhuhua Liao Yijiang Zhao Key Laboratory of Knowledge Processing and Networked Manufacturing College of Hunan ProvinceXiangtan411201China School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan411201China

In the large-scale logistics distribution of single logistic center,the method based on traditional genetic algorithm is slow in evolution and easy to fall into the local optimal *** at this issue,we propose a novel approach of exploring hybrid genetic algorithm based large-scale logistic distribution for BBG *** integrate greedy algorithm and hillclimbing algorithm into genetic *** algorithm is applied to initialize the population,and then hill-climbing algorithm is used to optimize individuals in each generation after selection,crossover and *** approach is evaluated on the dataset of BBG Supermarket which is one of the top 10 supermarkets in *** results show that our method outperforms some other methods in the field.

关键词： Large-scale logistics distribution vehicle routing greedy algorithm hill-climbing algorithm hybrid genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A DBN-Based Ensemble Method for Resource Usage Prediction in Clouds

A DBN-Based Ensemble Method for Resource Usage Prediction in...

引用

International Conference on Applications and Techniques in Cyber Intelligence, ATCI 2019

作者： Wang, Yuan Wen, Yiping Zhang, Yu Chen, Jinjun Key Laboratory of Knowledge Processing and Networked Manufacturing Hunan University of Science and Technology Xiangtan China Swinburne Data Science Research Institute Swinburne University of Technology Melbourne Australia

ISBN: (纸本)9783030251277

To accurately predict the dynamic changes on the usage of cloud computing resources so as to improve resource management efficiency, an ensemble method based on deep belief network (EMDBN) is proposed in this paper. Technically, it adopts the autoregressive model (AR) and the grayscale model (GM) as basic predictors. The results of the basic predictors are used together with historical data as training data for the DBN. Real data from the Google Cloud Data Center is used as experimental data. Back-propagation (BP) neural network, support vector regression (SVR), GM, AR and deep belief network (DBN) are chosen to carry out comparative experiments on cloud resource usage forecasting. Experimental results prove that EMDBN method can prominently enhance the precision in light of three current metrics for predict methods, i.e., mean absolute error (MAE), mean square error (MSE) and mean absolute percentage error (MAPE). © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Data-Driven Approach for Predicting Remaining Useful Life of Industrial Equipment 6th

A Hybrid Data-Driven Approach for Predicting Remaining Usefu...

引用

6th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2020

作者： Tan, Zheng Wen, Yiping Li, TianCai School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Key Laboratory of Knowledge Processing & Networked Manufacturing Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)9789811579837

Guaranteeing the safety of equipment is extremely important in industry. To improve reliability and availability of equipment, various methods for prognostics and health management (PHM) have been proposed. Predicting remaining useful life (RUL) of industrial equipment is a key aspect of PHM and it is always one of the most challenging issues. With the rapid development of industrial equipment and sensing technology, an increasing amount of data on the health level of equipment can be obtained for RUL prediction. This paper proposes a hybrid data-driven approach based on stacked denoising autoencode (SDAE) and similarity theory for estimating remaining useful life of industrial equipment, which is named RULESS. Our work is making the most of stacked SDAE and similarity theory to improve the accuracy of RUL prediction. The effectiveness of the proposed approach was evaluated by using aircraft engine health data simulated by commercial modular Aero-Propulsion system simulation (C-MAPSS). © 2020, Springer Nature Singapore Pte Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Utilizing Tags for Scientific Workflow Recommendation

Utilizing Tags for Scientific Workflow Recommendation

引用

International Conference on Applications and Techniques in Cyber Intelligence, ATCI 2019

作者： Hou, Junjie Wen, Yiping School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Key Laboratory of Knowledge Processing and Networked Manufacturing Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)9783030251277

Scientific workflow recommendation is playing increasingly important role, as an increasing number of reusable scientific workflow are published and shared on the Web. This paper proposes a scientific workflow recommendation method to promote the reuse of workflow. We utilize tags for recommending workflows. The similarity of workflows is obtained by tags besides the workflow descriptions, structures, and hierarchies. Based on the similarities of workflows, the workflows are clustered and recommended. The experimental results show that our method is effective and accurate for recommending workflows. © 2020, Springer Nature Switzerland AG.

关键词： SNN Tags Workflow recommendation

来源：评论

学校读者我要写书评

暂无评论

Extracting Campus’Road Network from Walking GPS Trajectories

引用

Journal of Cyber Security 2020年第3期2卷 131-140页

作者： Yizhi Liu Rutian Qing Jianxun Liu Zhuhua Liao Yijiang Zhao Hong Ouyang Key Laboratory of Knowledge Processing and Networked Manufacturing in Hunan Province Hunan University of Science and TechnologyXiangtan411201China

Road network extraction is vital to both vehicle navigation and road *** approaches focus on mining urban trunk roads from GPS trajectories of floating ***,path extraction,which plays an important role in earthquake relief and village tour,is always *** this issue,we propose a novel approach of extracting campus’road network from walking GPS *** consists of data preprocessing and road centerline *** patrolling GPS trajectories,collected at Hunan University of Science and Technology,were used as the experimental *** experimental evaluation results show that our approach is able to effectively and accurately extract both campus’trunk roads and *** coverage rate is 96.21%while the error rate is 3.26%.

关键词： Trajectory data mining Location-Based Services(LBS) road network extraction path extraction walking GPS trajectories

来源：评论

学校读者我要写书评

暂无评论

Stacking Ensemble Learning-based Gender Identification for User Profiling in Smart Education

Stacking Ensemble Learning-based Gender Identification for U...

引用

IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)

作者： Qiang Fu Yiping Wen Zheng Tan Qi Fu School of Computer Science and Engineering Hunan University of Science & Technology Xiang Tan China Key Laboratory of Knowledge Processing & Networked Manufacturing Hunan University of Science & Technology XiangTan China

ISBN: (纸本)9781665436885

To improve company profit, user profiling has become an important research topic in understanding customers and improving products or services, in which identifying users' gender is a fundamental problem. However, little research work was carried out on user profiling for improving learning in the domain of Smart Education. By analyzing Chinese microblog data, this paper proposes a stacking ensemble learning-based gender identification method for user profiling. It extracts gender features according to user published microblog messages and uses the base learner to extract stacking features, which are used as input to the meta-learner to obtain gender identification results. Its effectiveness is verified by comparison experiments with existing algorithms such as Logistic Regression and Random Forest for social media user gender identification.

关键词： Social networking (online) Stacking Blogs Education Text categorization Companies Feature extraction

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：