Hesham Arafat

An Adaptive hybrid routing strategy (AHRS) for mobile ad hoc networks

Mobile ad-hoc networks (MANETs) is a collection of wireless mobile nodes forming a temporary network without any fixed infrastructure or centralized administration. Although MANETs are easily deployed, they have several constraints such as; continuously changing topology, distributed operations, limitations of nodes radio interface. Recently, Ad-Hoc routing has become an important area of research due to the massive increase in wireless devices. Routing in MANETs is based on a cooperative multi-hop manner. However, due to the highly dynamic topology routing in MANETs is a true challenge. In this paper, we propose a new routing strategy for MANETs called Adaptive Hybrid Routing Strategy (AHRS). The basic idea of AHRS is to inform the network mobile nodes continuously with any changes in the network topology without flooding the network by a huge amount of control messages. AHRS is a hybrid routing strategy that can estimate failure time of links between network nodes through the historical information about link status. Accordingly, AHRS introduces not only the shortest available routes for data transmission, but also elects those reliable ones. AHRS uses no periodic routing advertisement messages but employs a special packet called ‘Carriage’ instead, thereby reducing the network bandwidth overhead and minimizing end-to-end transmission delay. AHRS has been compared against several well-known protocols, which are; DSDV, ZRP, AODV and DSR. Experimental results have shown that AHRS outperforms all competitive protocols as it introduces the minimal routing overheads, as well as a fast route delivery.

AN EFFICIENT OBJECT ORIENTED TEXT ANALYSIS (OOTA) APPROACH TO CONSTRUCT STATIC STRUCTURE WITH DYNAMIC BEHAVIOR

In many fields of science, IT applications and business environments successfully evolved systems to receive vast amount of electronic data and information. Due to increasing electronic data and information, most recent researches have tried to find a solution to resolve the crisis of information overload. These solutions include a combination of techniques of data mining, machine learning, natural language processing and information retrieval, information extraction, and knowledge management. A great challenge is how to exploit those information and knowledge resources and turn them into useful knowledge available to concerned people. The value of knowledge increases when people can share and capitalize on it. Thus, approaches that can help researchers to benefit from existing hidden knowledge are needed. For this, tools that can analyze, extract and explore relevant and useful information with relations are required. So, the main contribution of this paper is to integrate the technology of XML with text analysis for introducing an efficient concept-based structure model, where this model can represent the text in a form that can be easily understood, shared, managed and mined. This paper describes an efficient object oriented text analysis (OOTA) approach by generating an object oriented model that transforms unstructured text to a specific structured form and stored in XML format. The experimental results show that this approach has a good promotion on results.

Automatic Color Image Segmentation Based on Illumination Invariant and Superpixelization

Superpixel and invariant methods for color images are becoming increasingly popular in many applications of computer vision and image analysis. This paper presents an automatic segmentation based on illumination invariant and superpixelization methods. We develop an automatic superpixel generation method by automatically modifying the quick-shift parameters based on invariant images. The proposed method segments a color image into homogeneous regions by applying quick-shift method with initial parameters, and then automatically get the final segmented image by calculating the best similarity between the output image and the invariant image by changing the quick-shift parameters values. To reduce the number of colors in image that will be used in comparison, a quantization process is applied to the original invariant image. Changing parameters values in iterations instead of using a specific value made the proposed algorithm flexible and robust against different image characteristics. The effectiveness of the proposed method for a variety of images including different objects of metals and dielectrics are examined in experiments.

Exploiting semantic annotations and Q-learning for constructing an efficient hierarchy/graph texts organization.

Tremendous growth in the number of textual documents has produced daily requirements for effective development to explore, analyze, and discover knowledge from these textual documents. Conventional text mining and managing systems mainly use the presence or absence of key words to discover and analyze useful information from textual documents. However, simple word counts and frequency distributions of term appearances do not capture the meaning behind the words, which results in limiting the ability to mine the texts. This paper proposes an efficient methodology for constructing hierarchy/graph-based texts organization and representation scheme based on semantic annotation and Q-learning. This methodology is based on semantic notions to represent the text in documents, to infer unknown dependencies and relationships among concepts in a text, to measure the relatedness between text documents, and to apply mining processes using the representation and the relatedness measure. The representation scheme reflects the existing relationships among concepts and facilitates accurate relatedness measurements that result in a better mining performance. An extensive experimental evaluation is conducted on real datasets from various domains, indicating the importance of the proposed approach.

An Efficient Approach to Construct Object Model of Static Textual Structure with Dynamic Behavior Based on Q-learning

Developing information technology led to raise the intricacy of information systems intensive, hence techniques with effectiveness and efficiency are required. These techniques are used to support users in using the information for rapid and correct decision-making. Conventional text mining and managing systems mainly use the presence or absence of keywords to discover and analyze useful information from textual documents. However, simple word counting and frequency distributions of term appearances do not capture the meaning behind the words, which results in limiting the ability to mine the texts. This paper has been primarily concerned with constructing text representation model and exploiting that in mining and managing operations such as gathering, searching, filtering, retrieving, extracting, clustering, classifying, and summarizing. This representation model is based on semantic notions to represent text in documents, to infer unknown dependencies and relationships among concepts in a text, to measure the relatedness between text documents, and to apply mining processes using the representation and the relatedness measure. This model reflects the existing relations among concepts and facilitates accurate relatedness measurements that result in better mining performance. The experimental evaluations were carried out on real datasets from various domains, showing the importance of the proposed model.

Bladder Cancer Diagnosis using Artificial Neural Network

ABSTRACT The analysis of Magnetic Resonance Imaging (MRI) images using Artificial Neural Network (ANN)-based system is implemented in this paper to achieve a rapid and accurate diagnosis tool for bladder cancer. The proposed approach comprises image enhancement, removal of border, feature extraction and bladder cancer recognition using multilayer perception (MLP) with sequential weight/bias training function. We develop a model that defines the cancer level in order to enhance its treatment. Experimental results show that the devised approach increases the accuracy of diagnosis of bladder cancer up to 95%. General Terms Pattern Recognition and Image Processing Keywords Bladder cancer, Image segmentation and ANN 1. INTRODUCTION The bladder cancer is potentially a very serious condition that can be life threatening [1, 2]. It is the fourth most common cancer among men, and the eighth most common cause of cancer among women [3]. It has an average age at diagnosis of 65 years. Consequently, its early detection is vital in increasing the chances of successful treatment. Bladder cancer staging is a multifaceted process that utilizes a combination of clinical and radiological assessment to evaluate the degree of disease spread [4]. A variety of clinical diagnostic and therapeutic techniques for bladder cancer have been developed to improve the quality of the diagnostic methods [5]. In the past, computed tomography (CT) has been used to stage bladder tumors, but dynamic contrast-enhanced magnetic resonance imaging (MRI) has been shown to be superior to CT for this purpose [6]. Thereby, the aim of the present work is to contribute to the improvement of biomedical systems, allowing for a non-invasive diagnosis of bladder cancerous and pre-cancerous tissues. We use artificial intelligence techniques to early detect bladder cancer and determine tumor staging using a set of functional MRI images. The accuracy of MRI in T staging bladder cancer is assessed. The MRI scans contain different types of information relating to specific 3D voxels in the bladder. We combine useful information within a particular 3D cell (3D volume in the bladder scan space) from all MRI modalities in an automatic way in order to detect or suspect the cancer in the 3D cell [7]. The paper is organized as follows. Section II reviews the basic techniques of medical imaging analysis and the artificial neural networks (ANNs) [8]. The magnetic resonance imaging (MRI) is addressed as a medical imaging technique used in radiology. In Section III, the problem to be inspected is defined. The proposed technique is discussed in Section IV. The obtained results are presented and discussed in Section V. Finally, the conclusion is outlined in Section VI.

An Efficient Methodology for Exploring Valuable Knowledge with New Evaluation for Knowledge Quality

The recent trend has been using hybrid approach rather than using a single intelligent technique to solve the problems. Meanwhile in an information technology era, knowledge is always changing, hence the flexibility in approach and in thinking is a must. Since, the on-going conversation about semantic knowledge (much information with many relations) is much more important than coming up with the right answer (information), for that performing some inferences is needed for exploring creative diverse information. Where the knowledge is an appropriate collection of actionable information. So by combining much information with many relations, more novel and useful information are found as knowledge. Since the demand for Business Intelligence (BI) applications continues to grow even at a time when the demand for most Information Technology (IT) products is soft. Business intelligence systems provide actionable information delivered at the right time, at the right location, and in the right form to assist decision makers. This paper introduces an efficient methodology for storing the explored creative information/knowledge with many relations as a graph structure with a new evaluation of the creative information/knowledge quality. That through the implementation of Oriented Directed Acyclic Info Graph (ODAIG) Algorithm to generate the actionable information map. Moreover, Creative Information Quality (CIQ) Algorithm to evaluate the creative information quality. Different experiment done shows that, this methodology has a good promotion on results.

A novel ideation causal map with a new evaluation for Ideas Quality

In an information technology era, knowledge is always changing, hence the flexibility in approach and in thinking is a must. Since, the on-going conversation about semantic knowledge (many ideas with many relations) is much more important than coming up with the right answer (idea), so performing some inferences is needed for an exploration of creative diverse ideas. By combining many ideas with many relations, more novel and useful ideas are found. Representing such combination requires a special structure (called idea map). This paper introduces an efficient ideas map as a graph structure for diverse ideas and their relationships, called Oriented Directed Acyclic Graph (ODAG) algorithm. Moreover, formulating a new evaluation of the creative ideas, called Creative Ideas Quality (CIQ) algorithm by allowing agents to link diverse ideas dynamically. These diverse ideas are generated from an intelligent inference mechanism, which based on the principles of idea associations; similarity, contrast and contiguity.