Volume 5, Issue 1, January 2013

Application of DSmT-ICM with Adaptive decision rule to supervised classification in multisource remote sensing

A. Elhassouny, S. Idbraim, A. Bekkari, D. Mammass and D. Ducrot

In this paper, we introduce a new procedure called DSmT-ICM with adaptive decision rule, which is an alternative and extension of Multisource Classification Using ICM (Iterated conditional mode) and DempsterShafer theory (DST). This work confirmed the ability of the Dezert-Smarandache Theory (DSmT) used for the modeling of the classes sets of themes to significantly improve the quality of ICM classification algorithm with constraints by the fusion of the multidates images. The proposed approach uses a fusion process based on hybrid DSmT model finalized by a new adaptive decision rule (ADR) that allows to take in account the parcellary aspect of the thematic classes, thus, the introduction of the contextual information in the fusion process has enabled us to better identify the topics of surface. While the ICM with constraints provided an overall accuracy of 76.40%, the hybrid DSmT models with maximum credibility decision rule and with our adaptive decision rule increase the overall accuracies coefficient to 82.02% and 84.63% respectively. In addition, the fusion of three different dates achieves a value of 96.29% for overall accuracy and 94.70% of the kappa.

Keywords: Fusion, Classification, DSmT, ICM, Adaptive decision rule, Remote sensing

Towards A Well-Secured Electronic Health Record in the Health Cloud

Babafemi O. Odusote and Nicholas A. Ikhu-Omoregbe

The major concerns for most cloud implementers particularly in the health care industry have remained data security and privacy. A prominent and major threat that constitutes a hurdle for practitioners within the health industry from exploiting and benefiting from the gains of cloud computing is the fear of theft of patients health data in the cloud. Investigations and surveys have revealed that most practitioners in the health care industry are concerned about the risk of health data mix-up amongst the various cloud providers, hacking to comprise the cloud platform and theft of vital patients’ health data. An overview of the diverse issues relating to health data privacy and overall security in the cloud are presented in this technical report. Based on identifed secure access requirements, an encryption-based eHR security model for securing and enforcing authorised access to electronic health data (records), eHR is also presented. It highlights three core functionalities for managing issues relating to health data privacy and security of eHR in health care cloud.

Keywords: Cloud Computing, Data Privacy, Data Security, Electronic Health Records

Arabic documents classification using fuzzy R.B.F classifier with sliding window

T.Zaki, M.Amrouch, D.Mammass and A.Ennaji

In this paper, we propose a system for contextual and semantic Arabic documents classification by improving the standard fuzzy model. Indeed, promoting neighborhood semantic terms that seems absent in this model by using a radial basis modeling. In order to identify the relevant documents to the query. This approach calculates the similarity between related terms by determining the relevance of each relative to documents (NEAR operator), based on a kernel function. The use of sliding window improves the process of classification. The results obtained on a arabic dataset of press show very good performance compared with the literature.

Keywords: Contextual Classification, fuzzy model, radial basis function, semantic classification, semantic neighborhood, similarity, sliding window

Combining shape moments features for improving the retrieval performance

A.Mohamed Eisa, B. Amira Eletrebi and C. Ebrahim Elhenawy

Content-based Image Retrieval (CBIR) is fast growing technology and is the field that deals with application of computer for retrieval of images from digital libraries. Recently, the CBIR has become the hot topic and the techniques of CBIR have been achieved great development. In medical field the objective of CBIR is to permit radiologist to retrieve images of similar features that lead to similar diagnosis as the input image. This is different from other field where the objective is to find the nearest image from the same category of an image.This paper aims to present a novel methods based on image moments. In many applications, different kinds of moments have been utilized to retrieval images and object shapes.Moments are important features used in recognition of different types of images. In this paper, three kinds of moments: Geometrical, Zernike and Legendre Moments have been evaluated for Retrieval images using Nearest Neighbor classifier.

Keywords: Features Extraction, Geometrical Moments, Zernike and Legendre Moments, Nearest Neighbor classifier

K-Means Clustering and Affinity Clustering based on Heterogeneous Transfer Learning

Shailendra Kumar Shrivastava, J. L. Rana, and R. C. Jain

Heterogeneous Transfer Learning aims to extract the knowledge form one or more tasks from same feature space and applies this knowledge to target task of another features space. In this paper two clustering algorithms K-means clustering and Affinity clustering both based on Heterogeneous Transfer Learning (HTL) have been proposed. In both the algorithms annotated image datasets are used. K-means based on HTL first finds the cluster centroid of Text (annotations) by K-Means. In the next step these centroids of Text are used to initialize the centroids in image clustering by K-means. Second algorithm, Affinity clustering based on HTL first finds the exemplar of annotations and then these exemplar of annotations are used to initialize the similarity matrix of image datasets to find the clusters. F-Measure Scores and Purity scores increase and Entropy Scores decreases in both the algorithms. Clustering accuracy of affinity based on HTL is better than K-Means based on HTL.

Keywords: Heterogeneous Transfer learning, clustering, affinity propagation, K-Means, feature space

Impact of Software Project Uncertainties over Effort Estimation and their Removal by Validating Modified General Regression Neural Network Model

Brajesh Kumar Singh and A. K. Misra

Software cost estimation accuracy is one of the greatest challenges for software developer and customers. In general algorithmic models like Constructive Cost Model (COCOMO) are used but these have inability to deal with uncertainties related to software development environment and other factors. The Soft computing approach provides the solution for estimating the effort along with handling these uncertainties. In this paper, COCOMO is used as algorithmic model and an attempt is being made to validate the soundness of modified general regression neural network technique (MGRNN) using NASA project data. The main objective of this research is to analyze the accuracy of system’s output when MGRNN model is applied to the NASA dataset to derive the software effort estimates. MGRNN model is validated by using 93 NASA project dataset. Empirical results show that application of the GRNN model for software effort estimates resulted in smaller mean magnitude of relative error (MMRE) and probability of a project having a relative error of less than or equal to 0.25 as compared with results obtained with COCOMO is improved by approximately 28.21%.

Keywords: Modified General Regression Neural Network, COCOMO, Soft Computing, Effort Estimation, Mean Magnitude of Relative Error

Impact of Facebook Usage on the Academic Grades: A Case Study

Lamia M. Ketari and Mohammadi A. Khanum

This paper raises the question about the potential impact of Facebook usage upon undergraduate students time, and ultimately their academic performance, usually measured by Grade Point Average (GPA). The purpose of this study is to investigate if there is any relationship between Facebook use and student’s GPA. We based our study on the hypothesis that Facebook usage has a negative effect on the academic grades of students. Data were collected using self-administered questionnaires completed by over 100 female students from the department of Information Technology (IT) in the College of Computer and Information Sciences at King Saud University (KSU). The study findings showed that 55% of the students feel that the use of Facebook or Socail Networking Sites (SNSs) could be negatively related to their academic performance. Hence, our hypothesis found a partial support from the results of the case study.

Keywords: Social Networking Sites, Facebook, Academic Performance

Secure, Robust, and High Quality DWT Domain Audio Watermarking Algorithm with Binary Image

A. R. Elshazly, M. M. Fouad and M. E. Nasr

To enhance security and robustness of digital audio watermarking algorithms, this paper presents a secure, robust audio watermarking algorithm based on mean-quantization in Discrete Wavelet Transform (DWT) domain. A binary image is used as a watermark, and is encrypted with chaotic encryption with secret key. This approach is based on the embedding of an encrypted watermark in the low frequency components using a two wavelet functions with adaptation to the frame size. The reason for embedding the watermark in the low frequency components is that these components’ energy is high enough to embed the watermark in such a way that the watermark is inaudible; therefore, it should not alter the audible content and should not be easy to remove. The algorithm has a good security because only the authorized can detect the copyright information embedded to the host audio signal. The watermark can be blindly extracted without knowledge of the original signal. To evaluate the performance of the presented audio watermarking method, objective quality tests including bit error rate (BER), normalized cross correlation(NCC), peak-signal to noise ratio (PSNR) are conducted for the watermark and Signal-to-Noise Ratio(SNR) for audio signals. The tests’ results show that the approach maintains high audio quality, and yields a high recovery rate after attacks by commonly used audio data manipulations such as noise addition, amplitude modification, low-pass filtering, re-quantization, re-sampling, cropping, cutting, and compression. Simulation results show that our approach not only makes sure robustness against common attacks, but it also further improves systemic security and robustness against malicious attack.

Keywords: Audio watermarking, Binary image, normalized cross correlation, Robustness, Security

Detection of Retinal Blood Vessel using Kirsch algorithm

N. Nithin, Anupkumar M Bongale and R. Jayakrishna

This paper presents a new method for detecting and extracting blood vessels in retinal fundus images using Kirsch edge detection algorithm. We have used the gold standard public database which contains retinal images of healthy patients, patients with diabetic retinopathy and glaucomatous patients. The performance of the proposed technique is evaluated based on whether the blood vessel is properly detected or not. We have considered estimated positive value (Ep) and estimated negative value (En) as evaluation parameters and obtained considerably good results. The segmentation technique is very simple and found effective and robust with different image conditions.

Keywords: Retinal blood vessel, Kirsch algorithm, segmentation, edge detection