International Journal of Computer Networks and Communications Security

Volume 5, Issue 4, April 2016

 

 

 

Parameters Data Distribution Analysis for Dengue Fever Outbreak in Jember Using Monte Carlo

Pages: 45-48 (4) | [Full Text] PDF (272 KB)
MC Roziqin, A Basuki, T Harsono
Informatic and Computer Engineering, Electrical Engineering Polytechnic Institute of Surabaya, Surabaya, Indonesia
Multimedia Creative Boardcasting, Electrical Engineering Polytechnic Institute of Surabaya, Surabaya, Indonesia
Computer Engineering, Electrical Engineering Polytechnic Institute of Surabaya, Surabaya, Indonesia

Abstract -
Dengue Hemorrhagic Fever (DHF) is one of the most challenging infectious disease worlds issues in public health scope includes in some districts or cities in Indonesia. Based on the data of dengue infection cases from 2009 until 2012 in Jember, DHF spread almost comprehensive with the incidence rate of dengue tend to increase. Therefore we need a way to predict the spread of dengue disease in Jember which would help in making the strategies and plans to forecast any outbreak in future well in advance. Some Factors that influence the spread of dengue disease including, population, population density, rainfall, the number of days of rain, larva-free numbers, house index. The number of missing data on the parameter data make the data are not normally distributed. In this paper, we propose an implementation of monte carlo method to predict any influence factor of the spread of dengue disease using different randomization and compared its to get normal distribution.
 
Index Terms - Rainfall, Rainy Day, Larva-Free Number, House Index, Montecarlo, Jember DHF

Citation - MC Roziqin, A Basuki, T Harsono. "Parameters Data Distribution Analysis for Dengue Fever Outbreak in Jember Using Monte Carlo." International Journal of Computer Science and Software Engineering 5, no. 4 (2016): 45-48.

 

Fuzzy Classification Techniques for Online Advertisement Based on User’s Perception in Social Networks

Pages: 49-57 (9) | [Full Text] PDF (697 KB)
H Ahmed, TA Jilani, S Nand
Department of Computer Science, Sir Syed University of Engineering and Technology, Karachi, Pakistan
University of Nottingham, Nottingham, UK

Abstract -
Previously, the advertisement was done in an entirely different manner. Since technology takes over every field, now even advertisement is done through it with the help of internet. There are several websites which were initially supposed to use as socially but over the years, the advertisement is being started on them. Due to this new trend of online marketing it has become a big industry and marketers or advertisers are eagerly interested in showing ads which are well-targeted. This research presents a brief discussion regarding targeted advertisement in social network. In order to display online advertisement in social networks according to user’s interest a machine learning approach, fuzzy classification analysis will be used. In fuzzy classification of users, a user can belong to more than one group in the same time. Compared to other hard clustering techniques, this method is more appropriate and suitable for user’s classification of social networks.
 
Index Terms - Fuzzy Clustering, Online Advertisement, Social Networks, Fuzzy C-Means, Targeted Advertising

Citation - H Ahmed, TA Jilani, S Nand. "Fuzzy Classification Techniques for Online Advertisement Based on User’s Perception in Social Networks." International Journal of Computer Science and Software Engineering 5, no. 4 (2016): 49-57.

 

Hierarchical Classification with Convolutional Neural Networks for Biomedical Literature

Pages: 58-66 (9) | [Full Text] PDF (639 KB)
Y Yan
Department of Computer Science and Technology, University of Science and Technology Beijing

Abstract -
Multi-label document classification is a challenge task in many real-world applications. Recently, hierarchical classification methods have been widely used in document classification. However, at each layer of the hierarchical architecture, a classifier is trained independently, ignoring the relations between the other layers. In addition, compared with general documents, the biomedical literature only consists of the title and abstract information instead of the whole context. To overcome this problem, in this paper, we propose a novel hierarchical indexing method with Convolutional Neural Networks (CNNs) to tackle with the biomedical abstract document collections. First, we construct a hierarchical CNN indexing architecture which adaptively groups word2vec categories into (coarse) subsets by clustering. Next, a suitable loss function is designed for CNN training, where multi-label classification is actually performed in a coarse-to-fine learning style. Thereafter, a high-dimensional space representation is generated with feature extension by word sequence embedding, which contains more semantic information than bag-of-words. Experimental results show that our CNN model achieves an impressed performance.
 
Index Terms - Hierarchical Classification, Deep Learning, Convolutional Neural Networks, Biomedical Literature, Semantic Indexing

Citation - Y Yan. "Hierarchical Classification with Convolutional Neural Networks for Biomedical Literature." International Journal of Computer Science and Software Engineering 5, no. 4 (2016): 58-66.