Home‎ > ‎

August2012

======================================================================================================

A Data Mining System for Prediction of Breast Cancer Using Artificial Neural Network

Authors: Adeyemo Omowunmi .O and Olurotimi Oluseun

Abstract

Breast cancer is the most common cancer among women and men in both the developed and the developing country. The most pragmatic solution to early detection lies in breast cancer education of women. Few studies have examined the effect of breast implants after mastectomy on long-term survival in breast cancer patients, despite growing public health concern over potential long-term adverse health effects. Early diagnosis was stressed as the best protection against breast cancer morbidity. Some risk factors, such as smoking, drinking, and diet are linked to things a person does. Others, like a person's age, race, or family history, can't be changed. Screening for breast cancer has been extensively endorsed and most women of 40 years old participate in screening activities. Blackman, et al., (1999) and Weir et al., (2003). In the community mammography remains the main screening tool. Elmore, et al.,(2005). However, there have been several important developments in the ability to predict and modify breast cancer risk. Recently, data have become available regarding the evaluation of risk, screening strategies for high- risk women, and medical and surgical approaches that can decrease breast cancer risk. Data mining techniques was employed to extract hidden knowledge about the interaction between these parameters. This study explored and analyzed the massive data generated from the breast cancer patients from the reputable teaching hospital for several years and and these data were transformed in a way that can be accepted to neural network datamining software. The Artificial Neural Network (back propagation learning algorithms on multilayer perceptrons) was used to detect the existence of cancer in a patient. The System was trained using back-propagation learning algorithm (pattern-by-pattern and delta-delta) on dataset acquired from a teaching hospital, in Ibadan. The Multi-Layer perceptron and the two learning algorithms are implemented using Java programming language. The implemented algorithms are tested on a real world problem, the breast cancer Classification and Prediction Problem. The result obtained after the application of the learning algorithms are reported and compared. Additionally the basic UML design and other analysis tools are used in the design.

(pp. 576-584)                    Download PDF

======================================================================================================

A Novel Strategy Variance Based Intrusion Detection and Log Management in Cloud Computing

Authors: Chaitanya Thota, Lavanya Thota, Preethi M

Abstract

Cloud computing is clearly one of today’s most enticing technology areas due, at least in part, to its cost-efficiency and flexibility. However, despite the surge in activity and interest, there are significant, persistent concerns about security of cloud computing that are impeding momentum and will eventually compromise the vision of cloud computing as a new IT procurement model. In this paper, we propose Variance based Intrusion Detection Systems (IDSs) and log management method based on consumer behavior for applying IDS effectively to Cloud Computing system. IDSs are one of the most popular devices for protecting Cloud Computing systems from various types of attack. Because an IDS observes the traffic from each VM and generates alert logs, it can manage Cloud Computing globally. In this case, there exists a tradeoff between the security level of the IDS and the system performance. If the IDS provide greater security service using more rules or patterns, which cause apparent slowdown in network functionality in proportion to the strength of security. So the amount of resources allocating for customers decreases. One more problem in Cloud Computing is that, vast amount of logs makes system administrators hard to examine them. Proposed method enables Cloud Computing system to accomplish both efficacy of using the system resource and strength of the security service without tradeoff between them.

(pp. 585-589)                     Download PDF

======================================================================================================

Color Image Contrast Enhancement Using L*a*b* Color space

Authors: T.S.R.Krishna Prasad, D.Tejaswi

Abstract

The most familiar methods for color image enhancement is performed using RGB and YCBCR color spaces, but the disadvantage of this method is it requires more number of pixels. This paper presents a technique which enhances image with less number of pixels. This is done by using L*a*b* color space. The reconstruction of image with less number of pixels is referred as sparse. Sparsity is that which pertains the signals of interest and can be recovered from signals of interest and can be recovered from a small salient set of projections. This paper proposes color image enhancement with use of sparse representation of orthogonal transform based on the characteristics of discrete cosine transform coefficients. Image quality assessment is used along with traditional method peak signal to noise ratio. The structural similarity index matrix (SSIM) between two images is calculated as SSIM is improved method than PSNR.

(pp. 590-593)                    Download  PDF

======================================================================================================

Recent Advance in Underwater Acoustic Channel Modeling

Author: Xisheng Wang

Abstract

Acoustic propagation in underwater environments exhibits the properties of attenuation that increases with signal frequency, severe time-varying multipath propagation, and low speed of sound, especially in the shallow water environments. Since there is no typical shallow water channel, each environment possesses different characteristics that will affect the performance of a digital communication system. This paper will take shallow water environments as an example, and provide an overview of the properties of shallow water acoustic channels. Additionally, several typical underwater acoustic channel models will be introduced and compared.

(pp. 594-598)                  Download PDF

======================================================================================================