2017国际智能计算与大数据服务安全会议论文集

需积分: 10 181 浏览量更新于2024-07-19 1 收藏 47.67MB PDF 举报

"《智能计算与大数据服务安全：Springer（2018）》一书是2017年国际会议Security with Intelligent Computing and Big-data Services (SICBS'17) 的论文集，该会议旨在为全球的研究人员、工程师、学者以及工业专业人士提供一个交流在信息安全相关领域研究成果和活动的平台。这次会议的成功举办，展示了对加强国际学术合作与交流的重视，并促进了研究思想的碰撞。 SICBS'17是该系列会议的首次，它汇聚了来自世界各地不同领域的研究人员，为他们提供了分享研究进展和创新理念的论坛。会议共收录了34篇论文，涵盖了广泛的议题，包括算法与安全分析、密码分析与检测系统、物联网与电子商务应用、隐私与云计算、信息隐藏与秘密共享、网络安全及应用、数字取证与移动系统、公钥系统与数据处理，以及区块链技术在各领域的应用。该书属于《智能系统与计算进展》系列，由波兰科学院Janusz Kacprzyk博士担任系列编辑。这个系列专注于智能系统和智能计算的理论、应用及设计方法，涵盖了工程、自然科学、计算机科学、信息技术、经济学、商业、电子商务、环境、健康、生命科学等多个领域，反映了现代智能系统和计算的最新发展动态。出版物主要是重要的会议论文集，反映了基础性和实用性的前沿进展。组织一场成功的国际会议是一项艰巨的任务，背后离不开众多专家志愿者的无私奉献。我们对所有在筹备过程中付出努力的顾问委员会、技术程序委员会和组织委员会成员表示感谢，同时也感谢所有提交论文的作者，他们的高质量作品确保了会议的成功。最后， Springer 出版社的出版工作也起到了关键作用。通过这本书，读者可以深入了解当前智能计算与大数据服务安全领域的前沿研究，以及这些技术如何应用于实际场景，推动了网络安全、隐私保护和新兴技术如区块链的发展。对于从事相关研究或希望了解最新趋势的专业人士来说，这是一本不可或缺的参考资料。"

Shamir’s Secret Sharing Scheme in Parallel ...................... 206

Shyong Jian Shyu and Ying Zhen Tsai

Network Security and Applications

A Cognitive Global Clock Synchronization Protocol in WSNs

........ 219

Bilal Ahmad, Ma Shiwei, and Fu Qi

A Generic Web Application Testing and Attack Data

Generation Method

........................................ 232

Hsiao-Yu Shih, Han-Lin Lu, Chao-Chun Yeh, Hsu-Chun Hsiao,

and Shih-Kun Huang

The Study of Improvement and Risk Evaluation for Mobile

Application Security Testing

................................. 248

Huey-Yeh Lin, Hung-Chang Chang, and Yung-Chuan Su

Application of Pattern for New CAPTCHA Generation Idea

......... 257

Thawatwong Lawan

Digital Forensics and Mobile Systems

An Automatic Approach of Building Threat Patterns

in Android

............................................... 267

Chia-Mei Chen, Yu-Hsuan Tsai, and Gu-Hsin Lai

Identifying Temporal Patterns Using ADS in NTFS

for Digital Forensics

........................................ 275

Da-Yu Kao and Yuan-Pei Chan

Ant-Based Botnet C&C Server Traceback

....................... 286

Chia-Mei Chen and Gu-Hsin Lai

Public Key Systems and Data Processing

T-Brain: A Collaboration Platform for Data Scientists

............. 295

Chao-Chun Yeh, Sheng-An Chang, Yi-Chin Chu, Xuan-Yi Lin,

Yichiao Sun, Jiazheng Zhou, and Shih-Kun Huang

Feature Extraction in Security Analytics: Reducing

Data Complexity with Apache Spark

........................... 310

Dimitrios Sisiaridis and Olivier Markowitch

Storage-Saving Bi-dimensional Privacy-Preserving Data

Aggregation in Smart Grids

.................................. 322

Chun-I Fan, Yi-Fan Tseng, Yi-Hui Lin, and Fangguo Zhang

Verifying the Validity of Public Key Certiﬁcates Using

Edge Computing

.......................................... 330

Shogo Kitajima and Masahiro Mambo

Contents xv

A Social Tagging Recommendation Model Based

on Improved

Artiﬁcial

Fish Swarm Algorithm

and Tensor Decomposition

Hao Zhang

1,2

(

✉

)

, Qiong Hong

, Xiaomeng Shi

, and Jie He

School of Transportation, Southeast University, Nanjing 210096, China

andyhao@seu.edu.cn

Faculty of Transportation Engineering, Huaiyin Institute of Technology,

Huai’an 223003, China

Business School, Huai’an Institute of Information Technology, Huai’an 223003, China

Abstract. Folksonomy Tag Application (FTA) has emerged as an important

approach of Internet content organization. However, with the massive increase

in the scale of data, the information overloading problem has been more severe.

On the other hand, traditional personalized recommendation algorithms based on

the interaction between “user-item” are not easy to extend to the three dimensional

interface of “user-item-tag”. This paper proposes a clustering analysis method for

the initial dataset of the Tag Recommendation System (TRS) based on the

improvement of Artiﬁcial Fish Swarm Algorithm (AFSA). The method is used

for dimension reduction of TRS datasets. To this end, considering the weight of

the elements in TRS and the score that can reveal user preference, a novel

weighted tensor model is established. And in order to complete the personalized

recommendation, the model is solved by the tensor decomposition algorithm with

dynamic incremental updating. Finally, a comparative analysis between the

proposed FTA algorithm and the two classical tag recommendation algorithms is

conducted based on two sets of empirical data. The experimental results show

that the FTA algorithm has better performance in terms of the recall rate and

precision rate.

Keywords: Artiﬁcial ﬁsh swarm algorithm · Clustering analysis

Tensor decomposition · Tag recommendation

1 Introduction

In traditional Personalized Recommendation Systems (PRS), context-based recommen‐

dations are often realized by utilizing the properties of items (e.g. documents, commod‐

ities, services). Alternatively, collaborative ﬁltering recommendations are carried out

through exploiting the similarities among users and items. One of the primary charac‐

teristics of the latter approach is the usage of the two–dimensional (2D) pairwise inter‐

actions between users and items (i.e. user-user, user-item, item-item) to ﬁlter and analyze

the data. Related data analytical techniques include Vector Space Model (VSM), Term

Frequency–Inverse Document Frequency (TF/IDF) and some Natural Language

S.-L. Peng et al. (Eds.): SICBS 2017, AISC 733, pp. 3–13, 2018.

https://doi.org/10.1007/978-3-319-76451-1_1

Processing (NLP) machine learning algorithms etc. [1]. As the advancement of Web

2.0, socialized tag has gradually turned into an important technique to organize the

context of Internet. An application of socialized tag technique namely Folksonomy tag

recommendation has become one of the top popular research topics in personalized

recommendation ﬁeld.

A typical Socialized Tag Recommendation System (STRS) contains three funda‐

mental elements i.e. user, item and tag. And it extends the traditional two-dimensional

relations to three-dimension (3D). Through the modeling and analysis of the higher

dimensional data, richer information is provided to the recommendation system.

However, at the same time, a new issue occurs resulting from the information enrich‐

ment, i.e. traditional algorithms are unable to handle with such data directly. To this end,

some researches regarded the “user-item-tag” relations as a Tripartite Graph, and

decomposed the graph to three Bipartite Graphs while performing recommendation tag

system. Then, conventional recommendation algorithms (e.g. collaborative ﬁltering

algorithm) were integrated to recommend the tag or item [2]. Meanwhile, other scholars

such as Liao et al. (2012) attempted to explore a method to balance the tradeoﬀ between

the maximum retention of 3D relations information and the reduction of complexity in

terms of handling with high dimensional sparse data [3]. And based on the Tripartite

Graph, they proposed a tensor 3D decomposition algorithm and their algorithms were

validated through case studies. The key idea of Tripartite Graph is the conversion of 3D

relations in socialized tag system to 2D relations. Although the complexity of the system

is reduced, the latent information among elements in tag system is missing.

Moreover, the add-on of tag data increases the scale and sparse issues of the recom‐

mendation system. Symeonidis et al. (2009) applied tensor decomposition theory into

tag recommendation system [4]. They adopted tensor decomposition method to predict

the tag so as to reduce the sparse degree of the data. Likewise, to handle with the data

scale and noise issues arising from users’ random label, Sun et al. (2012) and Wang

et al. (2015) clustered the elements in tag system [5, 6]. Moreover, plenty of eﬀective

researches on socialized tag system were conducted through the mining of association

rules, the analysis of link structure and the development of probabilistic models [7].

The novel contributions of this paper is described as follows: Firstly, a new type of

swarm intelligence algorithm – Artiﬁcial Fish Swarm Algorithm (AFSA) is adopted to

cluster the elements in tag system [8]. As such, the dimension of initial input data for

the socialized tag recommendation model is reduced. Then, the tensor decomposition

algorithm with dynamic incremental updating is utilized to model tag recommendation

system. This step can achieve this function of maximize the latent relations among the

elements in tag system while satisfying the performance of recommendation system.

The eﬀorts of this study can contribute on the quality improvement of socialized recom‐

mendation systems as well as providing high-quality recommendation services to users.

4 H. Zhang et al.

剩余376页未读，继续阅读

WindStand

粉丝: 35
资源: 367

2017国际智能计算与大数据服务安全会议论文集

Security in Computing(5th) azw3

VNC-5.2.3-Linux-x64-RPM.tar.gz

IPython-Interactive-Computing-and-Visualization-Cookbook-Over-100-hands-on-recipes-to-sharpen-your-skills-in-high-perfor ....pdf

华为智能汽车解决方案_intelligent-driving-computing-platform-whitepaper.pdf

computing-system-and-program-.zip_computing

Web Microanalysis of Big Image Data-Springer(2018).pdf

fft-computing-sin-cos-FIG..rar_computing_频谱图

Intelligent Systems Technologies and Applications-Springer(2018).pdf

HCIA-Intelligent Computing V1.0 实验手册.pdf

Cloud Computing_Concepts and Practices-Springer(2018).pdf

最新资源