检索结果-内蒙古大学图书馆

Multi-Perspective Data Fusion Framework Based on Hierarchical BERT: Provide Visual Predictions of Business Processes

引用

Computers, Materials & Continua 2024年第1期78卷 1227-1252页

作者： Yongwang Yuan Xiangwei Liu Ke Lu School of Mathematics and Big Data Anhui University of Science and TechnologyHuainan232001China School of Economics and Management Anhui University of Science and TechnologyHuainan232001China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji UniversityShanghai201804China

Predictive Business Process Monitoring(PBPM)is a significant research area in Business Process Management(BPM)aimed at accurately forecasting future behavioral *** present,deep learning methods are widely cited in PBPM research,but no method has been effective in fusing data information into the control flow for multi-perspective process ***,this paper proposes a process prediction method based on the hierarchical BERT and multi-perspective data ***,the first layer BERT network learns the correlations between different category attribute ***,the attribute data is integrated into a weighted event-level feature vector and input into the second layer BERT network to learn the impact and priority relationship of each event on future predicted ***,the multi-head attention mechanism within the framework is visualized for analysis,helping to understand the decision-making logic of the framework and providing visual ***,experimental results show that the predictive accuracy of the framework surpasses the current state-of-the-art research methods and significantly enhances the predictive performance of BPM.

关键词： Business process prediction monitoring deep learning attention mechanism BERT multi-perspective

来源：评论

学校读者我要写书评

暂无评论

Adaptive Granulation for Efficient Classification on Noise Labeled Images 9

Adaptive Granulation for Efficient Classification on Noise L...

引用

9th IEEE International Conference on Computational Intelligence and Applications, ICCIA 2024

作者： Cai, Kecan Zhang, Hongyun Miao, Duoqian Tongji University Department of Computer Science and Technology Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

ISBN: (纸本)9798350352214

Current semi-supervised learning-based sample selection methods for noisy label image classification typically utilize all clean and noisy samples for model training. However, not all noisy samples contribute positively to model training. This paper introduces a novel semi-supervised image data granulation method that employs adaptively generated granular noisy sample subsets in place of the original noisy samples to enhance classification efficiency. The granular data generated retain the essential features of the original data, thereby improving efficiency without compromising classification accuracy. The quality of the granular data is assessed using coverage and specificity criteria, standard metrics for evaluating information granules. The proposed method consists of three main components: (i)selecting clean and noisy samples through network co-training, (ii)calculating granular noisy sample subsets by adaptive granulation, and (iii)optimizing the network model using a semi-supervised strategy. Experimental results on benchmark datasets with varying noise rates demonstrate that our method significantly improves the efficiency of noisy label image classification while maintaining accuracy. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

An Initialization Method based on The Core Clusters for Locality-weight Fuzzy C-Means Clustering 4th

An Initialization Method based on The Core Clusters for Loca...

引用

2013 IEEE 4th International Conference on Software Engineering and service Science

作者： Lei Gu The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University School of Computer Science and Technology Nanjing University of Posts and Telecommunication

ISBN: (纸本)9781467349970

The Locality-weight fuzzy c-means clustering method has been presented *** this approach can improve the clustering accuracies,it often gains the unstable clustering results because some random samples are employed for the initial *** this paper,an initialization method based on the core clusters is used for the locality-weight fuzzy c-means *** core clusters can be formed by constructing the σ-neighborhood graph and their centers are regarded as the initial centers of the locality-weight fuzzy c-means *** investigate the effectiveness of our approach,several experiments are done on three *** results show that our proposed method can improve the clustering performance compared to the previous locality-weight fuzzy c-means clustering.

关键词： the initialization clustering methods core clusters locality-weight fuzzy c-means neighborhood graph

来源：评论

学校读者我要写书评

暂无评论

Analysis and Design of Ironless Axial Flux Permanent Magnet Synchronous Motor 10

Analysis and Design of Ironless Axial Flux Permanent Magnet ...

引用

10th International Conference on Intelligent Human-Machine systems and Cybernetics, IHMSC 2018

作者： Zhang, Yufeng Liu, Na Guo, Shan Tong, Jun Zhou, Qixun Xi'an University of Science and Technology Xi'an China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9781538658369

In this paper, a single stator twin external rotors ironless AFPMSM for robot applications is studied. The design method of the motor is proposed. The magnetic circuit calculation and the main motor size equations are obtained. To solve the problem of low air-gap flux density in the ironless disk-type PMSM, the armature windings adopts the single-layer concentrated windings, which effectively reduces the air-gap length, increasing the motor power density, and they are initially verified with 3D-FEA. Finally, the mechanical structure of the motor is designed, a prototype is built and experiments are performed. The results show that the back-EMF error is within 2%, the air-gap flux density can reach 0.75T, and the motor has good acceleration performance, which verifies the rationality and feasibility of the design. © 2018 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

General measure of knowledge granularity in incomplete information system

General measure of knowledge granularity in incomplete infor...

引用

GCIS, WRI Global Congress on Intelligent systems

作者： Zhao, Lei Zhao, Mingqing Shandong University of Science and Technology Qingdao China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9780769543048

This essay introduces the concepts of knowledge granularity and information system. On this basis, we propose two new more general knowledge granularities: the combination granularity and polynomial granularity, which include the current common knowledge granularity. And discuss the use of their combination. The results for the establishment of granular computing in the incomplete information system have some theoretical significance and practical values. © 2010 IEEE.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

Particle swarm optimization based on pairwise comparisons 9th

Particle swarm optimization based on pairwise comparisons

引用

9th International Conference on Swarm Intelligence, ICSI 2018

作者： Zhang, JunQi Chen, JianQing Zhu, XiXun Wang, ChunHui Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

ISBN: (纸本)9783319938141

Particle swarm optimization (PSO) is a widely-adopted optimization algorithm which is based on particles’ fitness evaluations and their swarm intelligence. However, it is difficult to obtain the exact fitness evaluation value and is only able to compare particles in a pairwise manner in many real applications such as dose selection, tournament, crowdsourcing and recommendation. Such ordinal preferences from pairwise comparisons instead of exact fitness evaluations lead the traditional PSO to fail. This paper proposes a particle swarm optimization based on pairwise comparisons. Experiments show that the proposed method enables the traditional PSO to work well by using only ordinal preferences from pairwise comparisons. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Incremental sensor node deployment for low cost and highly available WSNs

Incremental sensor node deployment for low cost and highly a...

引用

International Conference on Mobile Ad-hoc and Sensor Networks

作者： Al-Omari, Safwan Shi, Weisong Jordan University of Science and Technology Jordan Key Laboratory of Embedded System and Service Computing Tongji University China Wayne State University United States

ISBN: (纸本)9780769543154

We attack the sensor network deployment problem. We define the deployment problem as the problem of deciding how many sensor nodes should be deployed in the sensor field over how many phases during its lifetime. We target the optimal deployment strategy that meets user-defined availability requirement with minimum total cost taking into consideration node failures and changing field trip to sensor node cost ratio. We model WSN availability and total cost as functions of the deployment plan, then, we formalize the deployment problem as a 2D optimization problem. Our modeling enables us to explore cost-benefit tradeoffs, we believe, this is a solid step toward bringing cost as an explicit dimension in the design space of WSN protocols. We compare the performance of the optimized solution (denoted as pro-active) to more ad-hoc solutions: on-demand) and at-front. The former strategy schedules future deployments only on demand. The latter strategy deploys all nodes at front with no later field trips. Using extensive simulations, we show that proactive outperforms at-front and on-demand in terms of total cost per availability unit in all application scenarios. For example, using pro-active costs $7 compared to $40 and $280 per total uptime in case of on-demand and at-front, respectively. © 2010 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Fuzzy H∞ Filtering for Nonlinear Networked systems with Multiple Stochastic Time-Varying Delays, Packet Dropouts and Sensor Saturation 34

Fuzzy H∞ Filtering for Nonlinear Networked Systems with Mul...

引用

第三十四届中国控制会议

作者： XU Xiaoli YAN Huaicheng ZHANG Hao SHI Hongbo Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education School of information Science and Engineering East China University of Science and Technology Key Laboratory of Embedded System and Service Computing Ministry of Education

ISBN: (纸本)9781467374439

This paper investigates the problem of H∞ filter design for a class of nonlinear networked system based on T-S fuzzy model. Multiple stochastic time-varying delays and some incomplete information are considered simultaneously. Incomplete information includes randomly occurring sensor saturation and packet dropouts. Stochastic time-varying delays are depicted as a sequence of stochastic and independent variables, which take values on 0 and 1. Two sets of Bernoulli distributed white noises are introduced to describe randomly occurring sensor saturation and packet dropouts. system conservatism is reduced due to introduce an approach of piecewise quadratic Lyapunov function. By solving a set of linear matrix inequalities(LMIs), the filter parameters are obtained. Finally, a simulation example is provided to illustrate the effectiveness of the proposed filter design approach.

关键词： H ∞ filtering,multiple time-varying delays,randomly occurring sensor saturation,packet dropouts,piecewise quadratic Lyapunov function

来源：评论

学校读者我要写书评

暂无评论

Behavioral authentication method for mobile gesture against resilient user posture 3

Behavioral authentication method for mobile gesture against ...

引用

2016 3rd International Conference on systems and Informatics, ICSAI 2016

作者： Liu, Qiang Wang, Mimi Zhao, Peihai Yan, Chungang Ding, Zhijun Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Tongji University Ministry of Education Shanghai China

ISBN: (纸本)9781509055210

The password pattern has become a widely used mobile authentication method. However, there are still some potential security problems since the passwords are easy to be cracked by some malicious software. An important research direction of improving its security is adding behavior pattern into the password pattern. The existing methods mainly used user's gesture behavior data such as the location, pressure and contact area of finger collected by touch screen to build a behavior authentication model, which did not consider the influence of user's posture on user's gesture behavior. This paper aims to propose a gesture authentication construction method that is resilient against the change of user's posture. Firstly, for the posture behavior data collected by mobile's orientation sensor and acceleration sensor, we use K-means algorithm to get user's postures. Secondly, we train a gesture authentication sub-model for each posture based on the data collected by touch screen. Finally, we give a behavior authentication method based on these models. Our experimental result shows that the method achieves an effect of 4.36% False Acceptance Rate (FAR) and 5.03% False Rejection Rate (FRR) © 2016 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Application of SIRUS in credit card fraud detection 1

引用

7th International Conference on Computational Data and Social Networks, CSoNet 2018

作者： Zhang, Yuwei Liu, Guanjun Luan, Wenjing Yan, Chungang Jiang, Changjun Department of Computer Science and Technology Tongji University Shanghai201804 China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China

ISBN: (数字)9783030046484

ISBN: (纸本)9783030046477

Credit card fraud problem is very common in recent years. It not only causes economic loss to people, but also causes trust crisis to enterprises. Due to the imbalance of data, fraud detection has always been tricky. In our previous work, we proposed a method of dealing with the class imbalance problem based on stacking ensemble learning and inverse random undersampling method (SIRUS). First, the inverse random undersampling method is used to generate multiple data subsets from the original data set. Then we use the stacking ensemble learning method for each data subset to train several different learners (also called first-level learners), and then the results generated by each first-level learner are taken as features to train a meta learner. We apply SIRUS to detect the credit card fraud in this paper. Our dataset comes from a financial company in China. A variety of measurements such as recall, precision, accuracy, F-measure, and G-mean to illustrate the effectiveness of our method in fraud detection. © Springer Nature Switzerland AG 2018.

关键词： Learning systems

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：