检索结果-南通市图书馆

Student Performance Prediction Based on Behavior Process Similarity

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2020年第6期29卷 1110-1118页

作者： BAO Yunxia lu faming WANG Yanxiao ZENG Qingtian LIU Cong College of Computer Science and Engineering Shandong University of Science and Technology College of Computer Science and Technology Shandong University of Technology

Student performance prediction plays an important role in improving education *** that students,exercise-answering processes exhibit different characteristics according to their different performance levels,this paper aims to mine the performance-related information from students’ exercising logs and to explore the possibility of predicting students’ performance using such process-characteristic information.A formal model of student-shared exercising processes and its discovery method from students’ exercising logs are *** similarity measures between students’ individual exercising behavior and student-shared exercising processes are presented.A prediction method of students’ performance level considering these similarity measures is explored based on classification *** experiment on real-life exercise-answering event logs shows the effectiveness of the proposed prediction method.

关键词： computer aided instruction data mining educational courses real-life exercise-answering event logs similarity measures student-shared process-characteristic information performance-related information performance levels behavior process similarity student performance prediction prediction method Process mining Process similarity Process discovery Student performance prediction

Remaining Time Prediction for Business Processes with Concurrency Based on Log Representation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

China Communications 2021年第11期18卷 76-91页

作者： Rui Cao Weijian Ni Qingtian Zeng faming lu Cong Liu Hua Duan College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao 266510China School of Computer Science and Technology Shandong University of TechnologyZibo 255000China

Remaining time prediction of business processes plays an important role in resource scheduling and plan *** structural features of single process instance and the concurrent running of multiple process instances are the main factors that affect the accuracy of the remaining time *** prediction methods does not take full advantage of these two aspects into *** address this issue,a new prediction method based on trace representation is *** specifically,we first associate the prefix set generated by the event log to different states of the transition system,and encode the structural features of the prefixes in the ***,an annotation containing the feature representation for the prefix and the corresponding remaining time are added to each state to obtain an extended transition ***,states in the extended transition system are partitioned by the different lengths of the states,which considers concurrency among multiple process ***,the long short-term memory(LSTM)deep recurrent neural networks are applied to each partition for predicting the remaining time of new running *** extensive experimental evaluation using synthetic event logs and reallife event logs,we show that the proposed method outperforms existing baseline methods.

关键词： business process monitoring remaining time prediction LSTM feature representation concurrency

Explainable Business Process Remaining Time Prediction Using Reachability Graph

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2023年第3期32卷 625-639页

作者： CAO Rui ZENG Qingtian NI Weijian lu faming LIU Cong DUAN Hua College of Computer Science and Engineering Shandong University of Science and Technology School of Computer Science and Technology Shandong University of Technology

With the recent advances in the field of deep learning, an increasing number of deep neural networks have been applied to business process prediction tasks, remaining time prediction, to obtain more accurate predictive results. However, existing time prediction methods based on deep learning have poor interpretability, an explainable business process remaining time prediction method is proposed using reachability graph,which consists of prediction model construction and visualization. For prediction models, a Petri net is mined and the reachability graph is constructed to obtain the transition occurrence vector. Then, prefixes and corresponding suffixes are generated to cluster into different transition partitions according to transition occurrence vector. Next,the bidirectional recurrent neural network with attention is applied to each transition partition to encode the prefixes, and the deep transfer learning between different transition partitions is performed. For the visualization of prediction models, the evaluation values are added to the sub-processes of a Petri net to realize the visualization of the prediction models. Finally, the proposed method is validated by publicly available event logs.

关键词： Deep learning Training Visualization Recurrent neural networks Petri nets Transfer learning Process control

Constructing low-dimensional perovskite network to assist efficient and stable perovskite solar cells

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第9期96卷 625-632页

作者： Jinwen Gu Xianggang Sun Pok Fung Chan Xinhui lu Peng Zeng Jue Gong faming Li Mingzhen Liu School of Materials and Energy University of Electronic Science and Technology of ChinaChengdu 611731SichuanChina Department of Physics The Chinese University of Hong Kong Shatin999077Hong KongChina Sichuan University-Pittsburgh Institute Sichuan UniversityChengdu 610065China State Key Laboratory Electronic Thin Film and Integrated Devices University of Electronic Science and Technology of ChinaChengdu 611731SichuanChina

The use of low-dimensional(LD)perovskite materials is crucial for achieving high-performance perovskite solar cells(PSCs).However,LD perovskite films fabricated by conventional approaches give rise to full coverage of the underlying 3D perovskite films,which inevitably hinders the transport of charge carriers at the interface of ***,we designed and fabricated LD perovskite structure that forms net-like morphology on top of the underlying three-dimensional(3D)perovskite bulk *** net-like LD perovskite not only reduced the surface defects of 3D perovskite film,but also provided channels for the vertical transport of charge carriers,effectively enhancing the interfacial charge transfer at the LD/3D *** net-like morphological design comprising LD perovskite effectively resolves the contradiction between interfacial defect passivation and carrier extraction across the ***,the net-like LD perovskite morphology can enhance the stability of the underlying 3D perovskite film,which is attributed to the hydrophobic nature of LD *** a result,the net-like LD perovskite film morphology assists PSCs in achieving an excellent power conversion efficiency of up to 24.6%with over 1000 h long-term operational stability.

关键词： Low-dimensional perovskite Network Carrier transport Perovskite solar cell Stability

基于序列移动距离的用户行为挖掘与相似度计算

在线全文

学校读者我要写书评

暂无评论

计算机集成制造系统 2017年第5期23卷 1060-1068页

作者：林泽东鲁法明段华山东科技大学信息科学与工程学院山东青岛266590 山东科技大学数学与系统科学学院山东青岛266590

为了对用户的行为进行相似性度量,从用户行为流程产生的行为序列出发计算用户行为的相似度。将推土机距离算法应用到用户行为相似度的计算领域,提出用户行为相似度计算的序列移动距离方法。首先定义了基于最长公共子序列的用户行为序列... 详细信息

为了对用户的行为进行相似性度量,从用户行为流程产生的行为序列出发计算用户行为的相似度。将推土机距离算法应用到用户行为相似度的计算领域,提出用户行为相似度计算的序列移动距离方法。首先定义了基于最长公共子序列的用户行为序列距离度量方法;其次定义了用户行为序列多重集之间距离的度量指标,在此基础上提出用户行为相似度计算的SMD方法;最后提出行为序列多重集之间距离度量应遵循的基本准则。在人工和真实数据集上进行了实验,实验结果表明了所提方法的有效性。

关键词：用户行为挖掘用户行为相似度相似性度量 EMD距离序列移动距离

Radiation injury and gut microbiota-based treatment

在线全文

学校读者我要写书评

暂无评论

Protein & Cell 2024年第2期15卷 83-97页

作者： Weihong Wang Bota Cui Yongzhan Nie Lijuan Sun faming Zhang Department of Microbiota Medicine and Medical Center for Digestive Diseases The Second Affiliated Hospital of Nanjing Medical UniversityNanjing210011China Department of Microbiotherapy Sir Run Run HospitalNanjing Medical UniversityNanjing 211166China State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers and National Clinical Research Center for Digestive Diseases Xijing Hospital of Digestive DiseasesFourth Military Medical UniversityXi'an 710032China National Clinical Research Center for Digestive Diseases Xi'an 710032China Key Laboratory of Resource Biology and Biotechnology in Western China Ministry of EducationSchool of MedicineNorthwest UniversityXi'an 710069China

The exposure to either medical sources or accidental radiation can cause varying degrees of radiation injury(RI).RI is a common disease involving multiple human body parts and organs,yet effective treatments are currently *** evidence suggests gut microbiota are closely associated with the development and prevention of various *** article summarizes 10 common types of RI and their possible *** also highlights the changes and potential microbiota-based treatments for RI,including probiotics,metabolites,and microbiota ***,a 5P-Framework is proposed to provide a comprehensive strategy for managing RI.

关键词： microbiome ionizing radiation radiation-induced injury short-chain fatty acids fecal microbiota transplant washed microbiota transplantation war nuclear microbiota medicine

On-surface synthesis and characterization of polyynic carbon chains

在线全文

学校读者我要写书评

暂无评论

National Science Review 2024年第3期11卷 192-199页

作者： Wenze Gao Wei Zheng luye Sun faming Kang Zheng Zhou Wei Xu Interdisciplinary Materials Research Center School of Materials Science and Engineering Tongji University

Carbyne, an elusive sp-hybridized linear carbon allotrope, has fascinated chemists and physicists for decades. Due to its high chemical reactivity and extreme instability, carbyne was much less explored in contrast to the sp2-hybridized carbon allotropes such as graphene. Herein, we report the on-surface synthesis of polyynic carbon chains by demetallization of organometallic polyynes on the Au（111） surface;the longest one observed consists of ～60 alkyne units（120 carbon atoms）. The polyynic structure of carbon chains with alternating triple and single bonds was unambiguously revealed by bond-resolved atomic force microscopy. Moreover, an atomically precise polyyne, C14, was successfully produced via tip-induced dehalogenation and ring-opening of the decachloroanthracene molecule(C14Cl10) on a bilayer NaCl/Au（111） surface at 4.7 K, and a band gap of 5.8 eV was measured by scanning tunnelling spectroscopy,in a good agreement with the theoretical HOMO–luMO gap（5.48 eV）.

关键词： polyyne scanning probe microscopy carbon allotrope on-surface synthesis organometallic polyyne

A Comprehensive Study on the Consequences of Gap-Graded Sands Considering the Loss of Fine Particles

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Earth Science 2024年第2期35卷 597-612页

作者： Weiping Liu Yu Gan Yunwei Cui faming Huang Lina Hu School of Civil Engineering and Architecture Nanchang UniversityNanchang330031China

Water and sand leakage disasters are likely to occur during construction in water-rich sand layer areas,resulting in ground *** stress-strain action characteristics of discontinuous graded sand under different internal erosion degrees,and the evolution mechanism of water and sand leakage disasters caused by the internal erosion need to be further ***,this paper takes the discontinuous graded sand in a water rich sand layer area in Nanchang City of China as the research *** the influence of different fine particle losses(0,10%,20%and 30%)under the internal erosion of sand,the salt solution method is used to realize the specified loss of fine particles in the internal *** stress-strain behavior after the loss of fine particles due to internal erosion is studied by triaxial shear ***,the physical model test and PFC-CFD method are both used to study the evolution rules of water and sand leakage disaster considered the influence of internal erosion *** show that:(1)under the same confining pressure,the peak failure strength of sand samples decreases along with the increase of fine particle loss.(2)In the water and sand leakage test of saturated sand,a natural filter channel is formed above the observed soil *** greater the loss of fine particles,the steeper and wider the collapse settlement area.(3)The relationship between the cumulative amount of water and sand leakage and time is *** total mass loss of sand increases along with the increase of internal erosion degree.(4)After the soil arch is formed around the damaged opening,the sand continues to converge above the soil arch under the action of water flow,resulting in the dense convergence of contact force chains.

关键词： sandy soil internal erosion stress and strain water and sand leakage PFC3D engineering geology

在线全文

学校读者我要写书评

暂无评论

基于同步核的BPMN模型融合

系统工程理论与实践 2016年第3期36卷 795-804页

作者：鲁法明曾庆田段华程久军同济大学嵌入式系统与服务计算教育部重点实验室上海200092 山东科技大学信息科学与工程学院青岛266590 山东科技大学电子通信与物理学院青岛266590 山东科技大学数学与系统科学学院青岛266590

流程融合有利于优化企业内部流程、促进企业间的有效合作.然而,现有流程融合技术在流程行为不变性保持以及融合过程自动化方面存在不足,而且未见BPMN模型的融合方法.为解决上述问题,本文提出了一种基于同步核的任务依赖关系建模机制,给... 详细信息

流程融合有利于优化企业内部流程、促进企业间的有效合作.然而,现有流程融合技术在流程行为不变性保持以及融合过程自动化方面存在不足,而且未见BPMN模型的融合方法.为解决上述问题,本文提出了一种基于同步核的任务依赖关系建模机制,给出了流程的BPMN模型与同步核模型之间的相互转换方法,实现了相应的原型系统,最终基于同步核的融合实现了BPMN模型的融合.

关键词：流程融合流程建模 BPMN