Skip to main content

About this book

These transactions publish research in computer-based methods of computational collective intelligence (CCI) and their applications in a wide range of fields such as the semantic Web, social networks, and multi-agent systems. TCCI strives to cover new methodological, theoretical and practical aspects of CCI understood as the form of intelligence that emerges from the collaboration and competition of many individuals (artificial and/or natural). The application of multiple computational intelligence technologies, such as fuzzy systems, evolutionary computation, neural systems, consensus theory, etc., aims to support human and other collective intelligence and to create new forms of CCI in natural and/or artificial systems. This nineteenth issue contains 11 carefully selected and revised contributions.

Table of Contents


Management and Computer Science Synergies: A Theoretical Framework for Context Sensitive Simulation Environment

In the light of contemporary management trends and on the basis of the theory of “open innovation”, derives the concept of “crossfertilization”. Crossfertilization, i.e. profitable inter-group knowledge exchange facilitates the fusion of input from different disciplinary communities. In such a scenario, the study highlights the opportunities deriving from the cross-fertilization between management and computer science domains, and yields in terms of cognitive synergies results that exceeds by far the individual outputs of the parties involved. The approach we propose is a full mode generation of knowledge starting from the hypothetical assumptions relative to simulation using context data. A general workflow complementary Structural Equation Modeling (SEM) is defining being the most appropriate mathematical technique for testing causal relationships between latent variables with Fuzzy Data Analysis techniques in order to tailor Decision Support System (DSS) to the context of application. The main contribution of our study is the definition of a theoretical framework to address contextual decision making concerning relations between commitment, loyalty and customer satisfaction.
Carmen De Maio, Giuseppe Fenza, Vincenzo Loia, Aurelio Tommasetti, Orlando Troisi, Massimiliano Vesci

Improved Recommendation System Using Friend Relationship in SNS

With the rapid development of the Internet, SNS services and 3G commercial mobile applications there have been tremendous opportunities although the development of SNS is very short in China, and the social web game is in the early stage of development. Because of massive users, the potential commercial value of Chinese SNS is still a great mining space. However, a relatively large defects is the precipitation and accumulation on content. The dynamic of friends will affect our own decisions largely, it is favorable for the activity of SNS to increase the number of friends. We have improved the existing models, and conduct experiments to validate it and compare it with previous methods.
Qing Liao, Bin Wang, Yanxiang Ling, Jingling Zhao, Xinyue Qiu

Bidirectional Analysis Method of Static XSS Defect Detection Technique Based On Database Query Language

Along with the wide use of web application, XSS vulnerability has become one of the most common security problems and caused many serious losses. In this paper, on the basis of database query language technique, we put forward a static analysis method of XSS defect detection of Java web application by analyzing data flow reversely. This method first converts the JSP file to a Servlet file, and then uses the mock test method to generate calls for all Java code automatically for comprehensive analysis. We get the methods where XSS security defect may occur by big data analysis. Originated from the methods where XSS security defect may occur, we analyze the data flow and program semantic reversely to detect XSS defect by judging whether it can be introduced by user input without filter. Moreover, to trace the taint path and to improve the analysis precision, we put forward bidirectional analysis. Originated from the results of the reverse analysis, we analyze the data flow forward to trace the taint path. These two methods have effectively reduced analyzing tasks which are necessary in forward ways. It was proved by experiments on some open source Java web projects, bidirectional and reverse methods not only improved the efficiency of detection, but also improved the detection accuracy for XSS defect.
Baojiang Cui, Tingting Hou, Baolian Long, Lingling Xu

A Multilevel Security Model for Search Engine Over Integrated Data

Data has become a valuable asset. Extensive work has been put on how to make the best use of data. One of the trends is to open and share data, and to integrate multiple data sources for specific usage, such as searching over multiple sources of data. Integrating multiple sources of data incurs the issue of data security, where different sources of data may have different access control policies. This work investigates the issue of access control over multi data sources when they are integrated together in the scenario of searching over these data. We propose a model to integrate multiple security policies while data are integrated to ensure all data access respects the original data’s access control policies. The proposed model allows the merging of policies and also tackles the issue of policy conflicts. Theoretical analysis has been conducted, which suggests that the proposed model is correct in terms of retaining all original the access control policies and ensure the confidentiality of all data.
Gansen Zhao, Kaijun Chen, Haoxiang Tan, Xinming Wang, Meiying You, Jing Xiao, Feng Zhang

Security Analysis of Two Identity Based Proxy Re-encryption Schemes in Multi-user Networks

In proxy re-encryption (\(\mathsf{PRE}\)), a semi-trusted proxy can convert a ciphertext originally intended for Alice into one which can be decrypted by Bob, while the proxy can not know the underlying plaintext. In multi-use \(\mathsf{PRE}\) schemes, the ciphertext can be transformed from Alice to Bob and to Charlie and so on. Due to its ciphertext transformation property, it is difficult to achieve chosen ciphertext security for \(\mathsf{PRE}\), especially for multi-use \(\mathsf{PRE}\). \(\mathsf{IBE}\) is a new kind of public-key encryption where the recipient’s public key is an arbitrary string that represents the recipient’s identity. Identity based proxy re-encryption (\(\textsf {IBPRE}\)) is a primitive combing the feature of \(\mathsf{IBE}\) and \(\mathsf{PRE}\). In 2010 Wang et al. has proposed a multi-use unidirectional CCA-secure identity based proxy re-encryption (\(\textsf {IBPRE}\)) scheme, and in 2011 Luo et al. has proposed an unidirectional identity based proxy re-encryption scheme. Unfortunately, we show these two proposals are not secure and thus can not be applied directly in multi-user networks.
Xu An Wang, Jianfeng Ma, Xiaoyuan Yang, Yuechuan Wei

Enabling Vehicular Data with Distributed Machine Learning

Vehicular Data includes different facts and measurements made over a set of moving vehicles. Most of us use cars or public transportation for our work commute, daily routines and leisure. But, except of our destination, possible time of arrival and what is directly around us, we know very little about the traffic conditions in the city as a whole. Because all roads are connected in a vast network, events in other parts of town can and will directly affect us. The more we know about the traffic inside a city, the better decisions we can make. Vehicular measurements may contain a vast amount of information about the way our cities function. Information that can be used for more than improving our commute, it is indicative of other features of the city like the amount of pollution in different regions. All the information and knowledge we can extract, can be used to directly improve our life.
We live in a world where data is constantly generated and we store it and process it at an ever growing rate. Vehicular Data does not stray from this fact and is rapidly growing in size and complexity, with more and more ways to monitoring traffic, either from inside cars or from sensors placed on the road. Smartphones and in-car-computers are now common and they can produce a vast amount of data: it can identify a cars location, destination, current speed and even driving habits.
Machine learning is the perfect complement for Big Data, as large data sets can be rendered useless without methods to extract knowledge and information from them. Machine learning, currently a popular research topic, has a large number of algorithms design to achieve this task, of knowledge extraction. Most of these techniques and algorithms can be directly applied to Vehicular Data.
In this article we demonstrate how the use of a simple algorithm, k-Nearest Neighbors, can be used to extract valuable information from even a relatively small vehicular data set. Because of the vast size of most of our cities and the number of cars that are on their roads at any time of the day, standard machine learning systems do not manage to process data in a manner that would permit real time use of the extracted information. A solution to this problem is brought by distributed systems and cloud processing. By parallelizing and distributing machine learning algorithms we can use data at its highest potential and with little delay. Here, we show how this can be achieved by distributing the k-Nearest Neighbors machine learning algorithm over MPI. We hope this would motivate the research into other combinations of merging machine learning algorithms with Vehicular Data sets.
Cristian Chilipirea, Andreea Petre, Ciprian Dobre, Florin Pop, Fatos Xhafa

Adapting Distributed Evolutionary Algorithms to Heterogeneous Hardware

Distributed computing environments are nowadays composed of many heterogeneous computers able to work cooperatively. Despite this, the most of the work in parallel metaheuristics assumes a homogeneous hardware as the underlying platform. In this work we provide a methodology that enables a distributed genetic algorithm to be customized for higher efficiency on any available hardware resources with different computing power, all of them collaborating to solve the same problem. We analyze the impact of heterogeneity in the resulting performance of a parallel metaheuristic and also its efficiency in time. Our conclusion is that the solution quality is comparable to that achieved by using a theoretically faster homogeneous platform, the traditional environment to execute this kind of algorithms, but an interesting finding is that those solutions are found with a lower numerical effort and even in lower running times in some cases.
Carolina Salto, Enrique Alba

Eroca: A Framework for Efficiently Recovering Outsourced Ciphertexts for Autonomous Vehicles

In the near future, the next generation (5G) telecommunication network with high speed will become a reality. Autonomous vehicle system without drivers are a typical application of 5G network, for it can connect base stations, autonomous vehicles and computing centers such as traffic information clouds in a very flexible, truly mobile and powerful way. To ensure the security and privacy of autonomous vehicle system, a promise way is to encrypt the real time traffic information and upload the ciphertexts to the center cloud for easily sharing road traffic information among the vehicles. To share these real time traffic information without sacrificing privacy, attribute based encryption (ABE) and block ciphers like AES are promising tools for encrypting these large traffic information. But a basic fact for the autonomous vehicle system is that, the vehicles need to continuously update the traffic information for really catching the road’s real time traffic status, and these updates are often little compared with the status a moment ago. In this paper, we consider the problem of how to retrieve and update the data from the early encrypted file in the cloud efficiently. We propose the notion of attribute based encryption with sender recoverable (ABE-SR). Compared with ABE, ABE-SR can easily achieve message recoverable and updatable for the encrypter. We give a concrete ABE-SR scheme, discuss its features compared with the traditional ABE and prove its security. Based on ABE-SR, we propose a new framework for efficiently recovering outsourced ciphertexts for autonomous vehicles: Eroca. Finally, we give the roughly evaluation results, which show our proposal framework is practical.
Xu An Wang, Jianfeng Ma, Yinbin Miao, Kai Zhang

Coarser-Grained Multi-user Searchable Encryption in Hybrid Cloud

The task of searchable encryption schemes in multi-user setting is to handle the problem of dynamical user injection and revocation with consideration of feasibility. Especially, we have to make sure that user revocation will not cause security problem, such as leakage of secret key. Recently, fine-grained access control using trusted third party is proposed to resolve this issue. However, it increases the management complexity for maintaining massive authentication information of users.
We present a new concept of coarse-grained access control for the first time and use it to construct a multi-user searchable encryption model in hybrid cloud. In our construction, there are two typical schemes, one is broadcast encryption (BE) scheme to simplify access control, the other is a single-user searchable encryption scheme, which supports two-phases operation and is secure when untrustful server colludes with the adversary. Moreover, we implement such a practical scheme using an improved searchable symmetric encryption scheme, and security analysis support our scheme.
Zheli Liu, Chuan Fu, Jun Yang, Zhusong Liu, Lingling Xu

Quantum Information Splitting Based on Entangled States

Two quantum information splitting protocols are proposed, that one is based on Bell states and another is based on cluster states. Two protocols provide two different ways to complete the process of quantum information splitting. The measurement results of Alice represent the secret information in the first protocol which is (n,n) protocol. The secret information is encoded into Pauli operations in the second protocol which is (2, 2) protocol. The original secret information is recovered when all participants are honest cooperation according to the principle of quantum information splitting. Two protocols take full advantages of the entanglement properties of Bell states and cluster states in different basis to check eavesdropping, that are secure against the intercept and resend attack and entangled ancilla particles attack. We also analyse the efficiency of these two protocols.
Xiaoqing Tan, Peipei Li, Xiaoqian Zhang, Zhihong Feng

Zero-Tree Wavelet Algorithm Joint with Huffman Encoding for Image Compression

Embedded Zero-tree Wavelet (EZW) is an effective image encoding algorithm. This paper emphasizes on the principles of EZW improved algorithm and the realization process for algorithm that includes zero-tree structure, wavelet coefficient scanning mode, improving embedding EZQ algorithm flow. Finally, Huffman coding was jointed to encoding.
By carefully analyzing EZW algorithm, we set the edge threshold as a significant coefficient and querying it with maximum value to determine whether it’s the zero-tree root or isolated zero. If the maximum is greater than the threshold, then it will be an isolated zero. The improved algorithm will replace the arithmetic coding method with Huffman coding making it more simpler.
Finally, we simulated the improved algorithm in Matlab to validate the result. Our result shows that in comparison with independent EZW algorithm, the improved algorithm not only increases the compression ratio and encoding efficient, but also improves the peak signal to noise ratio of images and make the vision more clear. Hence proved that the improved algorithm is more feasible and effective.
Wei Zhang, Yuejing Zhang, Aiyun Zhan


Additional information

Premium Partner

    Image Credits