检索结果-内蒙古大学图书馆

2017第二届亚太计算智能与信息技术学术会议 (APCIIT 2017)

作者： Tien-Wen Sung Chia-Jung Lee Pei-Wei Tsai Sheng-Hui Meng Fu-Tian Lin Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Information Science and EngineeringFujian University of Technology Department of Electrical Engineering Tung Fang Design University

The popularity of Internet and growing B2 C electronic commerce nowadays make product or service information easy to be acquired. However,making an optimal choice from the various alternative products becomes a laborious process. In this paper,an ontology-based Decision Support System(DSS) with Analytic Hierarchy Process(AHP) was proposed for the specific application of tour package selection. The system is composed of two subsystems,the product gatherer and the decision maker,which are used to find out right products and make an expected choice respectively. In the product gatherer subsystem,an ontology-based web service architecture with Web Ontology Language(OWL) was established for the semantic content processing of product information. The Simple Object Access Protocol(SOAP) is utilized to establish the communication interface and gather XML-based contents through Remote Procedure Calls(RPC) between the system and the database servers of travel agencies. In the decision maker subsystem,the Analytic Hierarchy Process is utilized to make an optimal decision for satisfying the requirement given by the consumer. The system aims to help consumers to avoid falling into decision-making hesitation and get an expected choice from various and similar products.

关键词： Protocol Internet Ontology-based decision support system with analytic hierarchy process for tour package selection Web

来源：评论

学校读者我要写书评

暂无评论

Recommendation system based on trusted relation transmission

Recommendation system based on trusted relation transmission

引用

International Conference on Intelligent System and knowledge engineering, ISKE

作者： Yixiong Bian Huakang Li Jiangsu Key Lab of Big Data and Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China

With the rapid development of the internet, applications of recommendation systems for online shops and entertainment platforms become more and more popular. In order to improve the effectiveness of recommendation, external information has been incorporated into various algorithms, such as location and social relationship. However, most algorithms only focus on the introduction of external information without depth analysis of the intrinsic mechanism in the external information. This paper proposed a transfer model of social trusted relationship, and optimized the reliability of the transfer model using pruning algorithm based on original trust recommendation. A credible social relationship macro-transfer model based on iterations of new credible relationships is defined by the similarity of social relationships. With a certain interest topic as a source of information, a micro-transfer model achieves the theme of interest and credibility of the expansion using social information dissemination algorithm. To demonstrate the effectiveness of the macro and micro credible transfer models, we used the Mantra search tree pruning algorithm and the optimization algorithm of similar category replacing similar products. The experimental results show that the proposed method based on the macroscopic and microscopic transfer models of the trusted relationship enhances the success rate and stability of the recommended system.

关键词： Collaboration Reliability Social network services Heuristic algorithms Optimization System performance Convergence

来源：评论

学校读者我要写书评

暂无评论

Cross-domain Human Parsing via Adversarial Feature and Label Adaptation

arXiv

引用

arXiv 2018年

作者： Liu, Si Sun, Yao Zhu, Defa Ren, Guanghui Chen, Yu Feng, Jiashi Han, Jizhong Institute of Information Engineering Chinese Academy of Sciences *** Department of Ece National University of Singapore Jiangsu Key Laboratory of Big Data Analysis Technology/B-DAT Nanjing University of Information Science and Technology Collab. Innov. Ctr. of Atmosph. Environ. and Equip. Technol. Nanjing Univ. of Info. Sci. and Technol. Nanjing China

Human parsing has been extensively studied recently (Yamaguchi et al. 2012;Xia et al. 2017) due to its wide applications in many important scenarios. Mainstream fashion parsing models (i.e., parsers) focus on parsing the high-resolution and clean images. However, directly applying the parsers trained on benchmarks of high-quality samples to a particular application scenario in the wild, e.g., a canteen, airport or workplace, often gives non-satisfactory performance due to domain shift. In this paper, we explore a new and challenging cross-domain human parsing problem: Taking the benchmark dataset with extensive pixel-wise labeling as the source domain, how to obtain a satisfactory parser on a new target domain without requiring any additional manual labeling? To this end, we propose a novel and efficient crossdomain human parsing model to bridge the cross-domain differences in terms of visual appearance and environment conditions and fully exploit commonalities across domains. Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences. A discriminative feature adversarial network is introduced to supervise the feature compensation to effectively reduces the discrepancy between feature distributions of two domains. Besides, our proposed model also introduces a structured label adversarial network to guide the parsing results of the target domain to follow the high-order relationships of the structured labels shared across domains. The proposed framework is end-to-end trainable, practical and scalable in real applications. Extensive experiments are conducted where LIP dataset is the source domain and 4 different datasets including surveillance videos, movies and runway shows without any annotations, are evaluated as target domains. The results consistently confirm data efficiency and performance advantages of the proposed method for the challenging cross-domain human parsing problem. Copyright

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Cross-Modulated Amplitudes and Frequencies of Epileptic EEG

引用

Journal of Physics: Conference Series 2019年第3期1302卷

作者： Yujie Cai Jiafei Dai Jin Li Jun Wang Fengzhen Hou Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing 210003 China Nanjing General Hospital of Nanjing Military Command Nanjing China College of Physics and Information Technology Shaanxi Normal University Xi'an China Key Laboratory of Biomedical Functional Materials China Pharmaceutical University Nanjing China

Epilepsy is a neural disorder with the hallmark of recurrent seizures. To characterize the epileptic brain electrical activities, we employed the cross modulation of instantaneous amplitudes and frequencies to separate synchronous and anti-synchronous modulation. Amplitude-amplitude, amplitude-frequency and frequency-frequency cross modulation were adopted to analyse the difference between EEG signal of epileptic patients and that of normal people. By comparing the observed patterns with two groups of EEG signals we demonstrate that the cross-modulation exponentials at the temporal region and the occipital region of right hemisphere are significant different.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Image Encryption Algorithm by Combining Two Chaotic Maps

A New Image Encryption Algorithm by Combining Two Chaotic Ma...

引用

ISCC 2017-the 5th International Conference on Information Science and Cloud Computing

作者： Congxu Zhu Shuai Li School of Information Science and Engineering Central South University Guangxi Colleges and Universities Key Laboratory of Complex System Optimization and Big Data Processing Yulin Normal University

This treatise proposes a new algorithm of encrypting images by combining Sine map with generalized Arnold transformation. The algorithm adds a shift transformation link to the common permutation-diffusion structure. Firstly,the plain-image is permutated in pixel positions by using the generalized Arnold transformation. Secondly,the permutated image is diffused by using the Sine map. Then,the diffused image is performed through the shifting process,which can avoid multiple encryption and shorten the encryption time. The results of analysis and experimental tests for the proposed algorithm have been given in detail,which showed that our new algorithm is highly secure. In conclusion,it has great application potential in Internet-based image secure communication.

关键词： image Arnold A New Image Encryption Algorithm by Combining Two Chaotic Maps

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Chinese Text Automatic Proofreading System

引用

IOP Conference Series: Materials Science and engineering 2018年第1期466卷

作者： Yonggang Gong Junying Fu Xiaoqin Lian Yuying Li Beijing Key Laboratory of Big Data Technology for Food Safety School of Computer and Information Engineering Beijing Technology and Business University Beijing 100048 China.

The news media platform has a huge amount of original news releases every day, it is impractical to use manual review of text typos. This paper designed and implemented a Chinese text automatic proofreading system for large-scale text content and high-speed processing. The proofreading content is first analyzed and classified: typos and sensitive information. Firstly, the system used the n-gram model to statistically analyze the corpus after segmentation to form a 2-gram model library and a contextual context library; secondly, builded a typo confusion set, and then calculated the probability of the target word in the knowledge base to realize automatic error detection and correction of Chinese text. The system has been successfully applied to the error of the content of many government news media platforms, each server can handle one million articles every day. The results show that the recall rate of the article is 78.9% and the accuracy rate is 85.1%. It meets the demand of high speed and accurate processing of massive text error, and has important practical significance and application fields.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating timeline summaries with social media attention

引用

Frontiers of Computer Science 2016年第4期10卷 702-716页

作者： Wayne Xin ZHAO Ji-Rong WEN Xiaoming LI School of Information Renmin University of China Beijing 100872 China Beijing Key Laboratory of Big Data Management and Analysis Methods Renmin University of China Beijing 100872 China School of Electronics Engineering and Computer Science Peking University Beijing 100871 China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data Beijing 100144 China

Timeline generation is an important research task which can help users to have a quick understanding of the overall evolution of one given topic. Previous methods simply split the time span into fixed, equal time intervals without studying the role of the evolutionary patterns of the underlying topic in timeline generation. In addition, few of these methods take users＇ collective interests into considerations to generate timelines. We consider utilizing social media attention to address these two problems due to the facts： 1） social media is an important pool of real users＇ collective interests; 2） the information cascades generated in it might be good indicators for boundaries of topic phases. Employing Twitter as a basis, we propose to incorporate topic phases and user＇s collective interests which are learnt from social media into a unified timeline generation algorithm. We construct both one informativeness-oriented and three interestingness-oriented evaluation sets over five topics. We demonstrate that it is very effective to generate both informative and interesting timelines. In addition, our idea naturally leads to a novel presen- tation of timelines, i.e., phase based timelines, which can potentially improve user experience.

关键词： timeline social media attention phase users＇collective interests

来源：评论

学校读者我要写书评

暂无评论

Efficient ontology meta-matching using alignment prescreening approach and gaussian random field model assisted NSGA-II

引用

Journal of Information Hiding and Multimedia Signal Processing 2017年第5期8卷 1062-1068页

作者： Xue, Xingsi Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Information Science and Engineering Fujian University of Technology No.3 Xueyuan Road University Town Minhou FuzhouFujian350118 China

Multi-Objective Evolutionary Algorithm (MOEA) is emerging as a new methodology to tackle the ontology meta-matching problem. However, for dynamic applications, besides the alignment’s quality, runtime and memory consumption in the matching process are also of great importance. In this paper, we propose an efficient NSGA-II based ontology meta-matching technology to improve the efficiency of NSGA-II based ontology meta-matching technology. In particular, our approach can automatically prescreen the less promising ontology alignments to be combined, which can reduce the search space of NSGA-II and improve its runtime, and reduce the number of exact individual evaluations by using Gaussian Random Field Model (GRFM), which can decrease the memory consumption of NSGA-II. The experimental results show that the utilization of alignment prescreening approach and GRFM is able to significantly improve the efficiency without sacrificing the alignment’s quality. © 2017, Ubiquitous International. All rights reserved.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Utility-based anonymisation for dataset with multiple sensitive attributes

Utility-based anonymisation for dataset with multiple sensit...

引用

作者： Wang, Lixia Zhu, Qing Key Laboratory for Data Engineering and Knowledge Engineering MOE School of Information Renmin University of China Beijing100872 China

Privacy-preserving data publication problem has attracted more and more attentions in recent years. A lot of related research works have been done towards dataset with single sensitive attribute. However, usually, original dataset contains more than one sensitive attribute. In this paper, we apply k-anonymity principle to solve the data publication problem for dataset with multiple sensitive attributes. We first cluster sensitive values based on a utility matrix. Then, we use a greedy strategy to partition tuples into equivalence classes. Our method can guarantee that the size of equivalence class is k except the last one, which reduces information loss. Also, we can guarantee the diversity of sensitive value in an equivalence class, which can protect privacy against the homogeneity attack. Experiments on a real dataset show that our method performs well on information loss, which indicates that we can guarantee data utility while protecting personal privacy. Copyright © 2016 Inderscience Enterprises Ltd.

关键词： Equivalence classes

来源：评论

学校读者我要写书评

暂无评论

Using artificial bee colony algorithm for optimizing ontology alignment

引用

Journal of Information Hiding and Multimedia Signal Processing 2017年第4期8卷 766-773页

作者： He, Yao Xue, Xingsi Zhang, Shunmiao College of Information Science and Engineering Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology No.3 Xueyuan Road University Town Minhou Fuzhou City350118 China

Due to the high heterogeneity of ontologies, a combination of many methods is necessary to correctly discover the semantic correspondences between their elements. But how to determine the optimal combination way in order to obtain an ontology alignment with high quality is still a challenge. To this end, in this paper, we propose to use the Artificial Bee Colony Algorithm (ABC) to solve the ontology meta-matching problem. In particular, we construct a new optimal model for the ontology meta-matching problem and design a problem specific ABC to solve it. The benchmark of OAEI 2014 is utilized to test our approach, and the experimental results show that the mean recall and precision of our approach is generally high, and the mean f-measure of the alignments obtained by our approach outperform all other state of the art matching systems. © 2017, Ubiquitous International. All rights reserved.

关键词： Ontology

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：