检索结果-内蒙古大学图书馆

2019 IEEE International Conference on computer science and Educational Informatization, CSEI 2019

作者： Zhang, Xiaojiang Jiang, Ying Wang, Zhijun Yunnan Key Lab of Computer Technology Application Kunming University of Science and Technology Kunming China Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

ISBN: (纸本)9781728123080

At present, there are many researches on automatic code generation methods based on machine learning. However, there is no analysis on automatic code generation tools based on machine learning. According to the role of existing code generation tools based on machine learning in practical development, this paper proposes the content and the method of analysis of automatic code generation tools based on machine learning. Based on the presented method, the corresponding analysis plug-ins API4ACGT are implemented. Finally, three existing automatic code generation tools based on machine learning are used to generate specific codes in two programming environments. The experimental results show that the proposed method and analysis plug-ins API4ACGT are effective. © 2019 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent agent-based modeling of kinesin nanomotor

Intelligent agent-based modeling of kinesin nanomotor

引用

37th Annual Conference of the IEEE Industrial Electronics Society, IECON 2011

作者： Khataee, H.R. Moh Aris, T.N. Sulaiman, M.N. Yousef Ibrahim, M. Department of Computer Science Faculty of Computer Science and Information Technology Universiti Putra Malaysia 43400 UPM Serdang Selangor Malaysia Gippsland Regional Automation Centre School of Applied Science and Engineering Monash University Churchill VIC 3842 Australia

ISBN: (纸本)9781612849720

This paper introduces a new methodology to develop comprehensive structural and behavioral models of kinesin nanomotor within its cell using agent technology. In this work, firstly, kinesin nanomotor is introduced as a physical intelligent agent. Then, we have proposed an agent-based structural model of kinesin nanomotor using composite diagram of Unified Modeling Language (UML). We also introduced its heads and tail as the kinesin's sensors and its motor domain as its actuator. An agent-based behavioral model of kinesin nanomotor was developed using Finite State Machine (FSM) diagram of UML and illustrated the internal intelligent and autonomous decision-making process of the nanomotor. The proposed agent-based behavioral FSM model was verified with its mathematical definitions which developed as Deterministic Finite Automaton (DFA) and its respective grammar. The outputs of the proposed grammar were in agreement with the proposed DFA model and traced the behavior of the nanomotor in nature. Also, the behavioral DFA model of the nanomotor was implemented as its software agent model. The proposed agent-based structural and behavioral models of kinesin nanomotor introduced the nanomotor as bio-nanoagent which was able to sense its cell through its sensors, make decision internally, and perform actions upon the cell through its actuator. © 2011 IEEE.

关键词： Actuators

来源：评论

学校读者我要写书评

暂无评论

Video segmentation based on acoustic analysis

Video segmentation based on acoustic analysis

引用

2010 3rd International Conference on Artificial Intelligence and Education, ICAIE 2010

作者： Zhang, Shilin Wang, Hui Faculty of Computer Science Network and Information Management Center North China University of Technology Beijing China Automation School Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9781424469338

Video segmentation is a key step for the long videos recorded from Television channels to be represented in the hierarchical structure. In this paper, a novel approach based on acoustic cues for automatic segmenting television stream into individual programs is proposed. This presented method is composed of the following steps: Several sets of repetitions in the audio track is detected by using silence detection and robust audio hashing;The found repetitions are treated as advertisements if the range of their length is from 5 seconds to 120 seconds;Programs are segmented from the recorded TV streams using the detected advertisements. Experiments on real-world TV recordings show the effectiveness of the proposed approach. ©2010 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Estimation of the Impact of Dimensionality Reduction of the Feature Space on the Efficiency of Movements Classification Based on Surface Electromyography 5

Estimation of the Impact of Dimensionality Reduction of the ...

引用

5th International Conference on Neural Networks and Neurotechnologies, NeuroNT 2024

作者： Kuznetsov, Ivan V. Ponomarchuk, Yulia V. Far Eastern State Transport University Department of Computer Science and Computer Graphics Khabarovsk Russia Far Eastern State Transport University Faculty of Control Automation and Telecommunications Khabarovsk Russia

ISBN: (纸本)9798350363739

One of the actual tasks of movement classification based on electromyography is the choice of the most informative set of features characterizing the movements. Increasing the number of features may decrease the learning performance of classifiers and reduce the efficiency of gesture classification. This paper is devoted to study the possibilities of improving the movement's classification efficiency by using the feature space dimensionality reduction methods. Classifiers based on Support Vector Machines (SVM)., Decision Trees (DT)., Random Forest (RF) and K-nearest neighbors (KNN) were considered., and Principal Component Analysis method (PCA) was used to dimensionality reduction. 3% improvement in classification performance was achieved using PCA and KNN. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Anomaly Judgment for Nodes Based on Agent under Cloud Environment

Anomaly Judgment for Nodes Based on Agent under Cloud Enviro...

引用

2019 IEEE International Conference on computer science and Educational Informatization, CSEI 2019

作者： Lei, Yang Jiang, Ying Yunnan Key Lab of Computer Technology Application Kunming University of Science and Technology Kunming China Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

ISBN: (纸本)9781728123080

Under cloud computing environment, cloud computing systems often have abnormalities due to the diversity of applications and the dynamic deployment environment. Collecting node performance data is very valuable for anomaly detection. There are many nodes under cloud computing environment. Many related studies only make abnormal judgments based on the status of single node. However, the state of multi-nodes is not judged. In this paper, a method of nodes anomaly judgment (NAJ method) based on agent under cloud environment is proposed. The collected data are analyzed by using agent technology. Firstly, data conversion technology is used for constructing a unified format for data analysis. Secondly, the detection model is trained and the degree of data anomalies is analyzed through unsupervised learning method. Finally, differences between anomalous nodes and other nodes are detected. The experimental results show that the method can judge the anomaly nodes effectively. © 2019 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Software's Quality-in-use Mining for User's Comments

Software's Quality-in-use Mining for User's Comments

引用

2019 IEEE International Conference on computer science and Educational Informatization, CSEI 2019

作者： Jiang, Ying Hu, Tianyuan Yunnan Key Lab of Computer Technology Application Kunming University of Science and Technology Kunming China Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China

ISBN: (纸本)9781728123080

At present, user's comments are important information sources that help users and software developers to evaluate the software's quality-in-use. However, the accumulation of user's comment information is rapid. There are some difficulties while using user's comments to evaluate software's quality-in-use. The research and practical value of mining software's quality-in-use for user's comments are becoming more and more prominent. The systematic and comprehensive review on software's quality-in-use mining for user's comments is trying to present on the basis of related researches in recent years. There are two cores in software's quality-in-use mining for user's comments, including identification of software's quality-in-use information and analysis of software's quality-in-use information. For identification of software's quality-in-use information, it is concluded that application of feature words reflecting quality-in-use, combination with language rules of quality-in-use, extraction of evaluation aspects reflecting quality-in-use and classification based on quality-in-use characteristics. Furthermore, analysis for overall usage of software and analysis for specific usage of software are summarized. Finally, the future work of software's quality-in-use mining for user's comments is discussed. © 2019 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Bio-nanorobotic in nanotechnology: Structure and potential

Bio-nanorobotic in nanotechnology: Structure and potential

引用

IEEE International Symposium on Industrial Electronics

作者： Khataee, H.R. Ibrahim, M.Y. Teh Noranis, M.A. Department of Computer Science Faculty of Computer Science and Information Technology Universiti Putra Malaysia 43400 UPM Serdang Selangor Malaysia Gippsland Regional Automation Centre School of Applied Science and Engineering Monash University Churchill VIC 3842 Australia

ISBN: (纸本)9781424493128

Bio-nanorobotic systems are made from bio-nanocomponents, particularly proteins. An important group of such protein-based bio-nanocomponents are myosin protein nanomotors that are involved in a wide variety of cellular tasks from cellular transports to muscle contractions. Realization of behavior and properties of the myosin protein nanomotors as bio-nanocomponents could form the basis of bottom-up approaches for constructing active bio-nanorobotic systems. This is the long-term goal of the bio-nanorobotic. In this paper we have presented an engineering point of view to the structure and behavior of both categories of myosin nanomotors, muscle and non-muscle. Myosin nanomotors are self-guiding systems. They have evolved to bind to their polymer filaments and are able to recognize the direction of movement by moving only in one direction of the polarized filaments. Myosin nanomotors also convert the chemical energy into mechanical work directly rather than via an intermediate energy. We have also pointed out to the potential applications of this nanomotor. The myosin's perfect structure, small size, smart and high efficiency indicate that myosin nanomotor can be an ideal bio-nanocomponent for bio-nanorobotic systems. © 2011 IEEE.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Identification of emission sources of umbral flashes using phase congruency

引用

Research in Astronomy and Astrophysics 2014年第8期14卷 1001-1010页

作者： Song Feng Lan Yu Yun-Fei Yang Kai-Fan Ji Yunnan Key Laboratory of Computer Technology Application/Faculty of Information Engineering and Automation Kunming University of Science and Technology Key Laboratory of Solar Activity National Astronomical ObservatoriesChinese Academy of Sciences Department of Information Engineering Yunnan Land and Resources Vocational College

The emission sources of umbral flashes （UFs） are believed to be closely related to running umbral and penumbral waves, and are concluded to be associated with umbral dots in the solar photosphere. Accurate identification of emission sources of UFs is crucial for investigating these physical phenomena and their inherent relationships. A relatively novel model of shape perception, namely phase congruency （PC）, uses phase information in the Fourier domain to identify the geometrical shape of the region of interest in different intensity levels, rather than intensity or gradient. Previous studies indicate that the model is suitable for identifying features with low contrast and low luminance. In the present paper, we applied the PC model to identify the emission sources of UFs and to locate their positions. For illustrating the high performance of our proposed method, two time sequences of Ca n H images derived from the Hinode/SOT on 2010 August 10 and 2013 August 20 were used. Furthermore, we also compared these results with the analysis results that are identified by the traditional/classical identification methods, including the gray-scale adjusted technique and the running difference technique. The result of our analysis demonstrates that our proposed method is more accurate and effective than the traditional identification methods when applied to identifying the emission sources of UFs and to locating their positions.

关键词： techniques image processing -- Sun chromosphere -- Sun photo- sphere -- sunspots -- convection

来源：评论

学校读者我要写书评

暂无评论

Cluster Approach to Model Reduction: Petrov-Galerkin Method, Hypergraphs, Metagraphs 3

Cluster Approach to Model Reduction: Petrov-Galerkin Method,...

引用

3rd International Conference on Control Systems, Mathematical Modeling, automation and Energy Efficiency, SUMMA 2021

作者： Blyumin, Semen Galkin, Alexander Oreshina, Maria Lipetsk State Technical University Department of Applied Mathematics Lipetsk Russia Lipetsk State Technical University Faculty of Automation and Computer Science Lipetsk Russia

ISBN: (纸本)9781665439817

A clustering-based model reduction approach is presented. It combines the Galerkin-Petrov method with graph clustering. A reduced order model of a large-scale system can be constructed using a characteristic clustering matrix of the graph. It is shown that the use of the concepts of hypergraph and metagraph is more natural and correct than the use of the concept of an ordinary graph;thus, the characteristic graph clustering matrix is actually the incidence matrix of a suitable hypergraph. A simple example is presented. © 2021 IEEE.

关键词： Large scale systems

来源：评论

学校读者我要写书评

暂无评论

Dedicated computer programs visualizing some graph theory problems as learning enhancement 16

Dedicated computer programs visualizing some graph theory pr...

引用

16th Conference on Applied Mathematics, APLIMAT 2017

作者： Zawiślak, Stanislaw Kopeć, Jerzy Faculty of Mechanical Engineering and Computer Science Department of Informatics and Automation University of Bielsko-Biala 2 Willowa Street Bielsko-Biala43-309 Poland

ISBN: (纸本)9788022746502

In the present paper, some computer programs are roughly described which are used in didactics of the subjects related to graph theory. The programs are dedicated to the following problems: searching-DFS and BFS, bi-criteria TSP, drawing self-complementary graphs as well as checking their isomorphism. The advanatge consists in visualisation of particular problems. Standard packages for graph drawing were also been utilized.

关键词： Trees (mathematics)

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：