About the journal

• Home page
• Contact information
• Aims and scope
• Indexing information
• Editorial policies
• ComSIS consortium
• Journal boards
• Managing board

For authors

• Information for contributors
• Paper submission
• Article submission through OJS
• Copyright transfer form
• Download section

For readers

• Forthcoming articles
• Current issue
• Archive

For reviewers

• View and review submissions

News

• Journal's Facebook page
• Calls for special issues
• New issue notification

Guest Editorial: Recent Advances in Information Processing and Systems

In the advent of Big Data, there have been extensive recent research efforts in advanced information processing techniques. Sophisticated algorithms are being developed into practical systems and applied in real-world problems. 2014 2nd International Conference on Systems and Informatics (ICSAI 2014, 15-17 November 2014, Shanghai, China), 2014 7th International Congress on Image and Signal Processing and 2014 7th International Conference on BioMedical Engineering and Informatics (CISP-BMEI 2014, 14-16 October 2014, Dalian, China) attracted numerous researchers and engineers from all over the world to report their recent work in information processing and systems. After rigorous reviews, about 600 papers were selected for inclusion in the conference proceedings. This section contains 8 papers. The 7 papers are extended from some of the best submissions to the conferences and went through another independent review process. Apart from that we invited colleagues from China, Romania and Serbia to prepare one more paper in area of emotional intelligence and emotional agents. This paper also went through independent regular review process.

The first paper brings new insights in the field of emotional, intelligent software agents. The first part is devoted to an overview of the state-of-the-art in emotional intelligence research with emphasis on emotional agents. A wide range of applications in different areas like modeling emotional agents, aspects of learning in emotional environments, interactive emotional systems and so on are presented. Further authors recognize and propose that it is necessary to apply specific methods for dynamic data analysis in order to identify and discover new knowledge from available emotional information and data sets. The last part of the paper discusses research activities for designing an agent-based architecture, in which agents are capable of reasoning about and displaying some kind of emotions based on emotions detected in human behavior.

Huang Wei-Qing, Ding Chang, and Wang Si-Ye design and realize a comprehensive method to implement RFID indoor localization algorithms in a geographic information system. A geographic environment is established using geographic information system in order to combine RFID indoor positioning results with the real environment. The authors use a distributed system architecture to filter useless data, so that indoor targets real-time positioning and visualization can be achieved. System tests show that this approach achieves ideal indoor positioning data display with high precision.

Jinson Zhang et al discuss visual analytics for BigData variety and its behaviours. In particular, the authors have defined and studied “5W dimensions” for different data forms across multiple datasets, i.e., when did the data occur, where did the data come from, what was the data content, how was the data transferred, why did the data occur, and who received the data. The clustering and reordering of the 5Ws parallel axes enables a clearer and better understanding of BigData analysis and visualization. This approach makes BigData pattern discovery much more accurate and easier.

Hong Zhu, Shengli Tian, Genyuan Du, and Meiyi Xie study anonymization on refining partition and demonstrate improved data utility with the same level of privacy. To reduce the correlation loss in anonymization on the initial partition, the authors propose an optimization model to generate a refining partition of the initial partition, and anonymization is then applied on the refining partition. Although anonymization on refining partition can be used on top of any existing partitioning methods to reduce the correlation loss, the authors demonstrate that a new partitioning method tailored for the refining partition can further improve data utility. An experimental evaluation shows that this approach is able to efficiently reduce correlation loss.

Shuo Xiong and Hiroyuki Iida investigate attractiveness of real time strategy (RTS) games. The authors select StarCraft II, one of the most popular RTS games, as a testbed and introduce a concept of strategy tree in order to construct a game tree of a RTS game. They then calculate game refinement values and compare with other type of games. They conclude that StarCraft II has a zone value of game refinement. The paper addresses the challenge of applying the game refinement theory in the domain of RTS games.

Shu-Bo Zhang and Jian-Huang Lai propose an integrated information-based similarity measurement of gene ontology (GO) terms by taking into account multiple common ancestors and aggregating both semantic information and depth information of GO terms. The semantic value of a GO term is established on non-redundant ancestors and the common semantics term share is derived from non-redundant common ancestors. Validation experiments on both gene expression datasets and pathway datasets suggest superiority over existing methods.

Fei Ma et al present a novel approach to computer-aided mass detection in mammography by extracting change information from temporal mammogram pairs and incorporating the temporal change information in the malignant mass classification. In the proposed method, temporal mammograms are registered based on spatial relations between segmented regions of interest and graph matching, which creates correspondences between regions of current mammogram and regions of previous mammogram. Experiments show that, when combining the single classification and temporal classification results linearly or by taking the minimum value of two classification, the overall classification results are improved.

Ondrej Tichy and Vaclav Smidl focus on estimation of input function from dynamic PET brain data using Bayesian blind source separation. The authors show that their method outperforms other methods in proximity of its estimates to the reference ones. More importantly, agreements of this method with manual selection is very encouraging and can potentially replace invasive estimation of the blood curve used as the input function in various applications.

We thank Professor Mirjana Ivanović, Editor-in-Chief of the Computer Science and Information Systems journal, for her support to and comments for this special section. We are grateful to the authors of this special section for contributing their excellent work and to the reviewers for their timely evaluations.

Guest editor
Lipo Wang
(Nanyang Technological University, Singapore)

Guest editor
Yaoli Wang
(Taiyuan University of Technology, Taiyuan, China)