International Journal of Computer Networks and Communications Security

Volume 5, Issue 5, May 2016

 

 

 

National Cyber Security Strategies: Global Trends in Cyberspace

Pages: 67-81 (15) | [Full Text] PDF (519 KB)
R Sabillon, V Cavaller, J Cano
Network and Information Technologies, Universitat Oberta de Catalunya (UOC), Barcelona, Spain
Information and Communication Studies, Universitat Oberta de Catalunya (UOC), Barcelona, Spain
Law Faculty, Universidad de los Andes (Uniandes)

Abstract -
Nations must define priorities, objectives, goals and scope when formulating a national strategy that covers cyberspace, cybersecurity, stakeholder engagement, capacity building, cyber governance, cybercrime and cyber defense. The goal of this article is to propose a National Cybersecurity Strategy Model (NCSSM) based on key pillars in order to tackle the completion of all the requirements in a national strategy. This approach aims to develop international cybersecurity strategies, alliances and cooperation. Our research is focused on a comparative analysis of ten leading countries and five intergovernmental organizations cybersecurity strategies. It includes eleven cybersecurity frameworks aligned with cyber governance and cyber law.
 
Index Terms - National cybersecurity strategy, cybersecurity, cyber law, cyber governance, international cybersecurity strategy, cyber policy

Citation - R Sabillon, V Cavaller, J Cano. "National Cyber Security Strategies: Global Trends in Cyberspace." International Journal of Computer Science and Software Engineering 5, no. 5 (2016): 67-81.

 

Query Expansion with Word Embeddings for Biomedical Document Retrieval

Pages: 82-88 (7) | [Full Text] PDF (625 KB)
Yan Li
School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, 100083, China

Abstract -
Query expansion aims to find and select new relevant terms to diversify, enrich and reformulate the original query. The conventional techniques for expansion term selection always base on thesaurus or statistical models. However, they cannot keep the semantic relationship between query terms and expansion terms. Hence, some researchers turn to use machine learning to deal with this problem. Recently, word embeddings become very impressive techniques with powerful semantic learning abilities. But, very few research efforts about word embeddings have been conducted in query expansion. In this paper, we focus on a specific case of information retrieval, i.e., biomedical document retrieval, and introduce word embeddings to perform query expansion for effectively searching documents. First, we design a word-embeddings-based query expansion strategy, where word embeddings are used to discover the relevant terms for the query, including the complicated professional biomedical terms. Thereafter, we construct an effective document retrieval system with this query expansion strategy. Finally, we present an experimental study and extensively compare several state-of-the-art strategies for term expansion for biomedical document retrieval. The experimental results demonstrate that it is effective to perform query expansion with deep learning. Specifically, our designed system obtains a very competitive performance on the document retrieval dataset of 2014 CLEF BioASQ Challenge.
 
Index Terms - Query Expansion, Word Embeddings, Biomedical Document Retrieval

Citation - Yan Li. "Query Expansion with Word Embeddings for Biomedical Document Retrieval." International Journal of Computer Science and Software Engineering 5, no. 5 (2016): 82-88.

 

PSO Based Diagnosis Approach for Surface and Components Faults in Railways

Pages: 89-96 (8) | [Full Text] PDF (1.01 MB)
O Yaman, M Karakose, E Akin
Computer Engineering Department, Firat University, Elazig, Turkey

Abstract -
Railway transport is a type of transport which is commonly used today. Rail line must be robust due to the heavy structure of the railway vehicles. Components constituting the rail line are very important to prevent the disruption of transportation. In this study, faults are determined by monitoring the rail and fastening components constituting the railway. Test vehicle was used to get experimental data. The left and right rails were viewed from different angles by four cameras placed on the test vehicle. Status monitoring and fault detection were performed by applying image processing and particle swarm optimization methods to the images taken. Rail surface was determined by taking the right and left images of rail line from the right and left cameras from different angles. Images taken from the right and left cameras were assembled for the detection of faults in the rail surface. Image matching was performed during the detection of fastening components and the rail surface. Matching was performed for each image taken from the camera by taking into account the correlation coefficient. In the determination of rail surface, template image and similarity were measured by taking specific sections on the image respectively. After template image and similarity ratios of all sections taken from the image were calculated, the sectional image with the highest correlation coefficient was determined as the rail surface. Sections were taken randomly from the image during the detection rail component. The correlation coefficient of the template image was calculated with the sections taken. Correlation coefficient was used as the coherence function in the particle swarm optimization, and fastening components were determined. Condition monitoring was performed by combining the detection results obtained.
 
Index Terms - Condition Monitoring, Railway, Image Processing, Rail Component Detection

Citation - O Yaman, M Karakose, E Akin. "PSO Based Diagnosis Approach for Surface and Components Faults in Railways." International Journal of Computer Science and Software Engineering 5, no. 5 (2016): 89-96.