检索结果-内蒙古大学图书馆

2nd international conference on Complex, Intelligent and Software Intensive Systems

作者： Lai Mingche Guo Jianjun Zhang Zhuxi Wang Zhiying Natl Univ Def Technol Sch Comp Changsha Hunan Peoples R China Logist Res Inst Beijing Peoples R China

ISBN: (纸本)9780769531090

This paper presents the exploration and design of a high-efficiency processor element for multimedia application. Based on the cost estimation model to evaluate the area and energy consumption for synchronous data transport architecture, a divide-and-conquer design approach is proposed to generate the optimal processor element in a short time. The computing core exploration begins with the application characteristics analysis, and continues with a heuristic search process for the performance-energy Pareto optimal cores. Then, the trace-driven simulation and analytical method explore the processor elements which are optimal with respect to performance-energy under area constraint. The automated design approach generates the target processor element within 4 hours, and the processor implemented in UMC 0.13um CMOS process can operate at 500MHz while consuming average 223mW power. For multimedia applications, the generated processor has the comparable performance with the state-of-art high performance DSPs.

关键词： computational modeling Mathematical model Registers Computer architecture Multimedia communication Equations Sockets

来源：评论

学校读者我要写书评

暂无评论

Research on Entrepreneurship Multi-dimensional Computer-Assisted Intelligent Evaluation Model Based on Machine Learning

Research on Entrepreneurship Multi-dimensional Computer-Assi...

引用

Electrical, Automation and Computer Engineering (ICEACE), international conference on

作者： Yuefei He School of Management Shanghai University China

ISBN: (数字)9798350368208

ISBN: (纸本)9798350368215

This study constructs a multi-dimensional computer-assisted intelligent evaluation model for entrepreneurship based on machine learning, with the aim of improving the accuracy and efficiency of entrepreneurial project evaluation. This model achieves efficient and multidimensional analysis of entrepreneurial projects by building an intelligent evaluation framework covering important steps such as data preprocessing, feature extraction, and algorithm planning. The model uses data mining technology to extract key indicators from multiple aspects, and then uses machine learning algorithms to classify, predict, and comprehensively evaluate entrepreneurial projects. It is particularly important to point out that algorithms such as random forests and support vector machines are introduced in the model design process, which greatly improves the accuracy and stability of predictions. The simulation experiment confirms the effectiveness of the model, and the results show that the model has achieved excellent results in all evaluation dimensions: the accuracy rate reaches 92.3%, the error rate is controlled within 5%, and the evaluation efficiency is improved by more than 30% compared with traditional methods.

关键词： Support vector machines Analytical models Accuracy Machine learning algorithms computational modeling Evaluation models Entrepreneurship Feature extraction data models data mining

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Activity Recognition from Movement Time Series data

Machine Learning for Activity Recognition from Movement Time...

引用

2017 2nd international conference on computational modeling, simulation and Applied Mathematics（CMSAM 2017)

作者： Young-Nam Kim Jin-Hee Park Gyu-Jin Jang Hye-Yeon Yu Moon-Hyun Kim College of Software Sungkyunkwan University

Activity recognition is the core technology of intelligent video surveillance systems and focuses on the behavior of a single object or a pair of objects. A common approach to activity recognition is to first extract and track the characteristics of moving objects from an image sequence, with the goal of converting pixel-level data into low-level functions appropriate for activity analysis. And in these methods, it is important to successfully extract good features and analyze the spatio-temporal interaction of the type of object moving from the extracted features. In this paper, we propose a three step activity recognition model that takes into account the spatial elements of the trajectory using time series data of moving pedestrian trajectories. Activity recognition modeling used the c4.5 algorithm and performed recognition experiments on the four behaviors defined in the CAVIAR dataset.

关键词： Activity recognition Trajectory Time series data C4.5 algorithm

来源：评论

学校读者我要写书评

暂无评论

computational model for the study of the fractal parameters characteristic for the surface of titanium dental implants

引用

Communications in Computer and Information Science 2008年 13卷 571-580页

作者： Pusca, Stefan Toma, Theodora Politehnica University Department of Physics Bucharest Romania Smart Edu Software Publishing LTD Bucharest Romania

ISBN: (纸本)9783540705987

In order to check if the Fractal theory could be a useful tool for some quantitative descriptions of the fracture parameters, the present work studied diferent theoretical models. The possibility of using different theoretical models (e.g. the Bazant's Size Efect Law (SEL) [1], the Modifed Size Efect Law [2, 3] and the Carpinteri's MultiFractal Scaling Law (MFSL) [4] wich have been already confirmed for the fracture parameters of concrete specimen, and the compatibility of some of the above studied theoretical models relative to the experimental data, using certain recent procedures to study the global and local compatibility have been analysed. The fracture parameters can be considered as main quantities for computational procedures for modeling the fracture of a certain ensemble (a suddenly emerging phenomena). In the next phase, the thermoelastic generation of ultrasonic perturbations in titanium implant material coated with hidroxiapatite was analyzed (using computer simulation) so as to find similarities with material properties as fractal dimensions. The algorithm, the numerical analysis has taken into account three main physical phenomena: the absorption of electromagnetic energy in substance with heat generation;thermal difusion with electromagnetic energy based heat source and elastodynamic wave generation by thermoelastic expansion. © Springer-Verlag Berlin Heidelberg 2008.

关键词： Electromagnetic waves

来源：评论

学校读者我要写书评

暂无评论

Theoretical and Case Study on Multiple Equal Part Linear Regression

Theoretical and Case Study on Multiple Equal Part Linear Reg...

引用

2017 2nd international conference on computational modeling, simulation and Applied Mathematics（CMSAM 2017)

作者： Zu-chang ZHONG Xue-ying CHEN Hui-Ling Yang Gang WANG Wen-Tsao PAN School of Business Guangdong University of Foreign Studies

This paper is to propose a new concept, which is called the Multiple Equal Part Linear Regression, in which the analysis data are divided into several equal parts and then the linear regression model is built up. This way, we will be able to observe the trend of sample data in each equal part. Difference comparison can be made with the general standard linear regression model.

关键词： Extreme value Multiple regression analysis Equal part linear regression GNP

来源：评论

学校读者我要写书评

暂无评论

Technologies Integration With Semantic Web Techniques For Business Valuation: Identifying Equities' Intrinsic Value Without Market Bias

Technologies Integration With Semantic Web Techniques For Bu...

引用

Cyber Resilience (ICCR), international conference on

作者： Alessio Faccia Rania Itani Ahmed Ae Eltweri Leena Wanganoo Leonardo Luigi Pio University of Birmingham Dubai UAE Murdoch University Dubai UAE Applied Science Research Center Applied Science Private University Amman Jordan Liverpool John Moores University UK Universita di Foggia Italy

ISBN: (数字)9798350394962

ISBN: (纸本)9798350394979

This text sets out to present an innovative approach to intrinsic equity value estimation, deploying state-of-the-art mechanisms and new technologies, but in particular, focusing on the integration of Semantic Web techniques. Its focus is on the problem of market sentiment, which commonly causes the value of equities to be far from their real worth. The proposed solution is to use in a mixed way sophisticated computational techniques and the capability of the Semantic Web's structured data handling to keep the valuations free of bias. The methodology employs advanced analytics, machine learning models, and Natural Language Processing (NLP) for the discovery of patterns and insights that may not easily be visible from traditional valuation methodologies. The holistic approach also involves qualitative analysis to enhance the understanding of the company's prospects. This approach integrates these technologies into the framework of the Semantic Web to provide a transparent and replicable way of determining the intrinsic value of equities, with minimum distortion by market sentiment. The paper argues that this method is quite opposite to traditional business valuation models that use a framework that emphasizes upon empirical evidence and methodological rigor. It postulates that, in the future, if these Semantic Web tools can be put into use for the systematic gathering of varied datasets for contextual analysis, the way valuation functions are handled will undergo a revolution. It would mean a shift in business valuation towards one that is more empirical and technology-enabled towards potentially changing investment analysis by methodological stringency and empirical data. CCS CONCEPTS. Computing methodologies ~ modeling and simulation ~ Model development and analysis ~ modeling methodologies

关键词： Semantic Web Analytical models Systematics computational modeling Machine learning Natural language processing Cost accounting

来源：评论

学校读者我要写书评

暂无评论

Research and Application of Cloud Computing Platform Monitoring System Based on Virtual Cluster

Research and Application of Cloud Computing Platform Monitor...

引用

Electrical, Automation and Computer Engineering (ICEACE), international conference on

作者： Yuhan Liu Tingting Yu Jiayi Chen Xinyue Luo Jiajia Jiang Huiling Xue Jingxi Liu Department of Business and Economy University of Hong Kong Hong Kong China Guangdong Baiyun University Guangzhou China Hebei University of Engineering Handan China Liaoning University Shenyang China Jiangxi University of Finance and Economics Nanchang China Jiangxi Normal University Nanchang China Yunnan Normal University School of Economics Kunming China

ISBN: (数字)9798350368208

ISBN: (纸本)9798350368215

This paper proposes a sentiment recognition algorithm for digital market text data based on natural language processing (NLP) technology. The algorithm uses the global vector (GloVe) model to represent words, which can better capture the semantic relationship between words. In the algorithm design, the paper first preprocess the text data, including noise removal, word segmentation and word frequency analysis. Then, the word vector generated by GloVe is used as input to perform sentiment classification through a deep learning model. The simulation results of the model show that the accuracy of the algorithm reaches 87.6% and the F1 value is 85.3% in the user comments and product evaluation data related to the digital market. Compared with traditional sentiment analysis methods, it has higher accuracy and stability. In addition, this paper also conducts detailed data analysis and discussion on the model performance under different parameter settings, further verifying the effectiveness and adaptability of the algorithm. Future research will further optimize the model structure to improve the recognition ability of complex emotional expressions.

关键词： Deep learning Adaptation models Analytical models Accuracy Text recognition computational modeling simulation Vectors data models Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

analysis of Atmospheric Temperature and Humidity Combining MWHTS and GNOS on Qinghai-Tibetan Plateau

Analysis of Atmospheric Temperature and Humidity Combining M...

引用

2017 2nd international conference on computational modeling, simulation and Applied Mathematics（CMSAM 2017)

作者： Jie-ying HE Sheng-wei ZHANG Key Laboratory of Microwave Remote Sensing National Space Science CenterChinese Academy of Sciences

The performance and characteristics of FY-3C MWHTS in orbit are presented in this paper. Then it uses surface and profile reanalysis non-rainy data from NCEP and ECMWF in Qinghai-Tibet Plateau from Jan, 2014 to May, 2015 and takes advantage of Mono RTM model to simulate brightness temperatures according to the MWHTS channel assignment, and validate by MWHTS measured data. Furthermore, a temperature and humidity retrieving mode is established to retrieve global atmospheric profiles and verified by two WMO stations located in mainland and over ocean. Finally, it utilizes FY-3C MWHTS brightness temperature data observed in orbit from JAN to DEC of 2014 to realize and analyze the space-time distribution of atmospheric temperature and humidity profiles on the Qinghai-Tibetan Plateau, especially for them in different pressure level in Oct, 2014.

关键词： FY-3C MWHTS Atmospheric temperature and humidity profile Qinghai-Tibetan Plateau

来源：评论

学校读者我要写书评

暂无评论

Storage and Processing System of Meter data Based on Hadoop

Storage and Processing System of Meter Data Based on Hadoop

引用

2017 2nd international conference on computational modeling, simulation and Applied Mathematics（CMSAM 2017)

作者： Sai LIU Jian GUO Yuan FENG Ocean University of China

The traditional meter data storage and processing system generally uses the expensive large server and relational database to ensure the normal operation of the system. When dealing with a large amount of meter data, this kind of system is difficult to expand, data processing is not in time and the efficiency of data retrieval is low, which led to the fault response cycle is prolonged, even cause a fatal impact on the enterprise. This thesis designed and implemented a storage and processing system for electric meter data based on Hadoop Technology which can realize the distributed storage and processing of the electric meter data. After analyzed the result of System benchmark I/O test, and compared data storage and processing capabilities with the traditional solution, it is proved that the new system has the advantages of efficient storage and processing under the condition of mass data, and is suitable for storage of mass meter data. The new system can significantly improve the efficiency and accuracy of data analysis, reduce labor management costs, has extensive practical value for improving the efficiency and the competitive power of the electric meter.

关键词： Hadoop HBase HDFS MapReduce Meter data

来源：评论

学校读者我要写书评

暂无评论

An Empirical Investigation into Machine Learning Approaches for Breast Cancer Classification

An Empirical Investigation into Machine Learning Approaches ...

引用

Recent Advances in Information Technology for Sustainable Development (ICRAIS), international conference on

作者： Anoushka Duggal Samya Muhuri Department of Computer Science & Engineering Thapar Institute of Engineering and Technology Patiala India

ISBN: (数字)9798350354461

ISBN: (纸本)9798350354522

Breast cancer was diagnosed in 2.3 million individuals worldwide in 2022, and was the cause of 670,000 deaths. It ranks as the second most common cancer overall and the most frequently diagnosed cancer in women. Since survival is highly dependent on early detection, the development of computational models for diagnosis is crucial. Among the various models available, we have chosen to focus on three supervised machine learning models in this study: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Feed-forward Neural Networks (FFNN). Their roles in breast cancer detection are investigated. We have pre-processed the data using normalization and feature selection to enhance these models’ performances. They are trained on real-life documented patient data to predict breast cancer. It is determined that the FFNN is more accurate than both SVM and KNN. This paper provides a comprehensive analysis of the various machine learning models, highlighting their positive and negative aspects in diagnosing breast cancer. The results underscore the potential of advanced neural networks in medical diagnostics and pave the way for further research and development in this domain.

关键词： Support vector machines computational modeling Machine learning Nearest neighbor methods Breast cancer Vectors Medical diagnosis Sustainable development Information technology Research and development

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：