Search

Recently, most companies market their products on the web to recognize their customers’ requirements and to improve their services’ quality according to the customers’ feedback and opinions. A huge amount of reviews and opinions are posted daily on products. Obtaining and quickly analyzing these opinions become a difficult task. These opinions might lead to a tendency or disinclination to a specific point of view. To represent the products’ opinions from customers’ perspectives, opinion retrieval becomes a demanding and essential task for automatically extracting, analyzing, and summarizing customers’ reviews. Usually, online products are offered by several suppliers in e-commerce. Therefore, to keep up the competitiveness among suppliers, the need for innovative requirements is required. This paper proposed an enhanced opinion retrieval approach depending on the explicit feature based opinion mining. The proposed approach expands the initial products’ requirements using extended heuristics and linguistic patterns of the Arabic opinions. Besides the relevant score, several factors, like features’ weight, the opinion importance, and the sentiment polarity are used to rank the retrieved results. The experimental results show the capability of the proposed approach to automatically extract more innovative features compared to the conditional random field (CRF) results.

The problem of finding relevant data while searching the internet represents a big challenge for web users due to the enormous amounts of available information on the web. These difficulties are related to the well-known problem of information overload. In this work, we propose an online web assistant called OWNA. We developed a fully integrated framework for making recommendations in real-time based on web usage mining techniques. Our work starts with preparing raw data, then extracting useful information that helps build a knowledge base as well as assigns a specific weight for certain factors. The experiments show the advantages of the proposed model against alternative approaches.

Determining the resource requirements at airports especially in-ground services companies is essential to successful planning in the future, which is represented in the resources demand curve according to the future flight schedule, through which staff schedules are created at the airport to cover the workload with ensuring the highest possible quality service provided. Given in the presence of variety service level agreements used on flight service vary according to many flight features, the resources assumption method makes planning difficult. For instance, flight position is not included in future flight schedule but it's efficacious in the identification of flight resources. In this regard, based on machine learning, we propose a model for building a resource demand curve for future flight schedules. It is divided into two phases, the first is the use of machine learning to predict resources of the service level agreement required on future flight schedules, and the second is the use of implement a resource allocation algorithm to build a demand curve based on predicted resources. This proposal could be applicable to airports that will provide efficient and realistic for the resources demand curve to ensure the resource planning does not deviate from the real-time resource requirements. the model has proven good accuracy when using one day of flights to measuring deviation between the proposed model predict demand curve when flights did not include the location feature and the actual demand curve when flights include location.

In artificial neural networks, activation functions play a significant role in the learning process. Choosing the proper activation function is a major factor in achieving a successful learning performance. Many activation functions are sufficient universal approximators, but their performance is lacking. Thus, many efforts have been directed toward activation functions to improve the learning performance of artificial neural networks. However, the learning process involves many challenges, such as saturation, dying, and exploding/vanishing the gradient problems. The contribution of this work resides in several axes. First, we introduce two novel activation functions: absolute linear units and inverse polynomial linear units. Both activation functions are augmented by an adjustable parameter that controls the slope of the gradient. Second, we present a comprehensive study and a taxonomy of various types of activation functions. Third, we conduct a broad range of experiments on several deep neural architecture models with consideration of network type and depth. Fourth, we evaluate the proposed activation functions’ performance in image and text classification tasks. For this purpose, several public benchmark datasets are utilized to evaluate and compare the performance of the proposed functions with that of a group of common activation functions. Finally, we deeply analyze the impact of several common activation functions on deep network architectures. Results reveal that the proposed functions outperform most of the popular activation functions in several benchmarks. The statistical study of the overall experiments on both classification categories indicates that the proposed activation functions are robust and superior among all the competitive activation functions in terms of average accuracy.

Recently, there has been an enormous increase in the number of reviews of popular products. Therefore, opinion analysis has become a tedious task for customers when making decisions. As a result, opinion retrieval systems have emerged as an effective tool to analyze and represent customers’ feelings toward offered services. Conventional opinion retrieval systems retrieve and rank products according to both relevance and the overall polarity scores of the opinions. However, customer reviews are usually more detailed, including multiple features with different polarities. Consequently, feature-based opinion retrieval is necessary to extract and analyze each feature separately. Customers’ opinions are usually written with a short and unclear structure and contain many implicit linguistic features that cannot be identified by retrieval systems. As a result, the recall results are negatively affected. Few studies have focused on implicit features, as most examined explicit features. Also, implicit features extraction is a challenging task in some languages like Arabic due to difficulties with morphology. This paper proposes an enhanced retrieval approach based on feature-based opinion mining to enhance retrieval performance. In addition to explicit feature extraction, a metaheuristic optimization method with several similarity measures is utilized to identify implicit features and measure its effect on the retrieval results. The experimental results on Arabic and English datasets revealed the effectiveness of the proposed approach, whereby more features were extracted compared to the explicit feature results. Furthermore, the ranking results were improved by identifying both implicit and explicit features compared to the results obtained by the conditional random field method and association rule mining.

The airport ground handling has a global trend to meet the Service Level Agreement (SLA) requirementsthat represents resource allocation with more restrictions according to flights. That can be achieved by predictingfuture resources demands. this research presents a comparison between the most used machine learning techniquesimplemented in many different fields for demand prediction and resource allocation. The prediction model nomi-nated and used in this research is the Support Vector Machine (SVM) to predict the required resources for eachflight, despite the restrictions imposed by airlines when contracting their services in the Service Level Agreement.The approach has been trained and tested using real data from Cairo International Airport. the proposed (SVM)technique implemented and explained with a varying accuracy of resource allocation prediction, showing thateven for variations accuracy in resource prediction in different scenarios; the Support Vector Machine techniquecan produce a good performance as resource allocation in the airport.

Accurate automated system for glaucoma diagnosis is very important since glaucoma is the second disease that leads to vision loss. Therefore, it is necessary to utilize all computational intelligence approaches to detect glaucoma accurately at its early stages in retinal images. The most significant sign of glaucoma in retinal fundus images, which helps doctors to diagnose if the patient has normal or glaucomatous image, is the ratio of vertical optic cup diameter to vertical optic disc diameter. Therefore, it is important to accurately segment both the optic disc and optic cup regions in the retinal fundus image. In this paper, our contribution proposed an approach that utilizes a combination of significant large-scale features to perform supervised superpixel classification by linear support vector machine for segmenting the optic disc and optic cup regions. We got an accuracy of 98.6% and 99.2% for disc and cup segmentation, respectively, and glaucoma diagnosis accuracy of 99%.

Plant diseases cause unprecedented crop loss across the world. Predictions of crop disease give the decision makers the warning that one or more diseases may occur at a particular location at a particular time in the future. This prediction ensures that control measures, especially the treatments, are used more effectively to avoid these diseases by tacking the actions to be ready, e.g., the crop will not plant in a particular area. This paper provides a fuzzy prediction model of plant diseases with climate changes. The proposed model consists of two components; one for prediction climate for next year using a climate dataset. The second one is fuzzy-based disease detection based on a set of disease cause’s fuzzy membership functions. These functions are defined based on knowledge acquired from agricultural experts. The result of this research proved that predicting the suitable time for crops diseases helps decision making to avoid them in suitable ways.

Region-of-interest (ROI) segmentation is an important critical step and challenging task in the evolution of computer-aided detection (CAD) system for breast cancer. The discovery of breast cancer in early stages can save many women lives. However, most of the early detection systems are costly in terms of complexity, price and processing time; that make it unsuited for developing countries. The digital mammography is proven to be one of the most important diagnostic techniques for breast cancer tumors. Therefore, this work proposes a CAD system for breast cancer detection from digital mammography based on Gaussian Mixture Model (GMM) followed by Support Vector Machine (SVM). The best contribution of our proposed system is the usage of GMM for the first time in the literature for mammogram images segmentation into ROI areas. Besides, the discrimination between the three classes of tissues as normal, benign or malignant, is used without previous knowledge of mammogram images’ type. Moreover, the proposed system is fully automated in all of its stages with reduced computation compared with recent used methods. Hence, it offers a suitable early detection system to our country regarding moneywise, timewise, and reduced complexity. A non-linear multi-class SVM is used for classifying the ROI into three classes: normal, benign or malignant tissue. The experiments show overall average classification accuracy of 90% for detecting normal, malignant or benign on randomly chosen 90 cases from the benchmark mini-MIAS dataset. On the other hand, the proposed method achieves 92.5% accuracy when classifying the benign from malignant cases.

When forecasting time series, it is important to classify them according to linearity behavior; the linear time series remains at the forefront of academic and applied research. It has often been found that simple linear time series models usually leave certain aspects of economic and financial data unexplained. The dynamic behavior of most of the time series in our real life, with its autoregressive and inherited moving average terms, pose the challenge to forecast nonlinear times series that contain inherited moving average terms using computational intelligence methodologies such as neural networks. It is rare to find studies that concentrate on forecasting nonlinear times series that contain moving average terms. In this study, we demonstrate that the common neural networks are not efficient for recognizing the behavior of nonlinear or dynamic time series which has moving average terms and hence low forecasting capability. This leads to the importance of formulating new models of neural networks such as Deep Learning neural networks with or without hybrid methodologies such as Fuzzy Logic.

Numerous endeavors have been made to improve the retrieval procedure in Textual Case-Based Reasoning (TCBR) utilizing clustering and feature selection strategies. SOPHisticated Information Analysis (SOPHIA) approach is one of the most successful efforts which is characterized by its ability to work without the domain of knowledge or language dependency. SOPHIA is based on the conditional probability, which facilitates an advanced Knowledge Discovery (KD) framework for case-based retrieval. SOPHIA attracts clusters by themes which contain only one word in each. However, using one word is not sufficient to construct cluster attractors because the exclusion of the other words associated with that word in the same context could not give a full picture of the theme. The main contribution of this chapter is to introduce an enhanced clustering approach called GloSOPHIA (GloVe SOPHIA) that extends SOPHIA by integrating word embedding technique to enhance KD in TCBR. A new algorithm is proposed to feed SOPHIA with similar terms vector space gained from Global Vector (GloVe) embedding technique. The proposed approach is evaluated on two different language corpora and the results are compared with SOPHIA, K-means, and Self- Organizing Map (SOM) in several evaluation criteria. The results indicate that GloSOPHIA outperforms the other clustering methods in most of the evaluation criteria.

Extracting useful and relevant information from the massive amount of data by web users becomes a challenging task. This work regarding applications based on the use of Web Usage Mining (WUM). Clickstream, transaction data, and user profile data represent various sources of web usage data. Preprocessing is an essential process in WUM for understanding the user's life as a whole within a session on a website. It signifies the aggregation of consequent series of page views executed by a singular user traversing through a website. Therefore, it represents a critical task that involves converting raw web log data to obtain a suitable pattern for efficient analysis. The importance of these processes relies on the complex nature of web architecture, and it takes almost 80% of the mining process. This work introduces a complete framework for data preprocessing with a comprehensive demonstration of a real dataset.

The remarkable developments in wireless communication technologies in recent years along with the anticipation of further advances in these technologies have stimulated the efforts to investigate vehicle to everything (V2X) communication to increase road safety, improve traffic management, and facilitate infotainment applications. V2X communication is based either on cellular infrastructures such as 4G and 5G, or wireless LAN technologies such as the IEEE 802 protocol family. Several challenges, however, face the deployment of V2X. Examples of these challenges are routing, security, and analysis of collected data. Several research efforts have investigated computational intelligence methods to tackle these issues. In this paper, we review recent advances in computational intelligence in V2X communications. First, we provide preliminaries of V2X communication. Second, we discuss classical and computational intelligence solutions in V2X communication. Last, we present open problems and research challenges that need to be addressed to realize the full potential of V2X systems.

Mobile Ad hoc Network (MANET) is the cornerstone for the Internet of Things (IoT) and Vehicle to Everything (V2X) networks, its devices are remarkable of lightweight to be portable and free to join or disjoined the network. Therefore, one of the MANET routing types is reactive routing protocols. Reactive routing protocols set up the connection between devices either on-demand such as Ad Hoc On-demand Distance Vector (AODV) protocol or source routing such as Dynamic Source Routing (DSR) protocol. Reactive routing protocols increase routing overhead on discovering new routes. Thus routing overhead, and delay will increase. In this paper, the method of generating a fuzzy model is presented. Also, a tuned fuzzy stability model is introduced to handle the imprecision of routing decisions by the Fuzzy Stability model for Ad Hoc On-demand Distance Vector (FSAODV) and Fuzzy Stability model for Dynamic Source Routing (FSDSR). The results showed that FSAODV and FSDSR have outperformed the state of art protocols AODV and DSR respectively.

The reliability of the recommender system is highly essential for the continuity of any system. Fake and malicious users may be spoiling system predictions reliability by inserting and injecting fake profiles called “shilling attacks” into the target recommender system. Thus, the detection of these attacks is necessary for any recommender system. Therefore, several shilling attacks detection approaches have proposed. In this work, we propose a survey for the recent detection methods, which pick up famous shilling attack models against the collaborative filtering recommender systems.

This paper proposes a new swarm intelligence algorithm called vortex swarm optimization, inspired from vortex collective behavior where particles move around a common known center, they cover all the directions so they play as alarm system where any individual at any direction see the target (resources, predator…etc.) it informs other individuals to take an action. This type of collective behavior was seen in many creatures like (Bats and fishes). They use this type of collective behavior for feeding, access to resources, moving, information transmission, decision making, and protection from predators. This type is different from straight-ahead collective behavior (polarized collective behavior) where individuals move forward. The majority of swarm intelligence algorithms inspired their techniques from straight-ahead collective behavior, but vortex collective behavior had a few pieces of research so the importance of this research appears. The algorithm performs the two basics functions that any searching algorithm had (exploitation and exploration) by circling phase the algorithm will know the direction of the promising region, By swimming phase the algorithm will go to this region (exploration)and by attacking phase individuals will reduce their interaction range and reduce their velocity to get much closer to each other and best region found so far (exploitation), Algorithm skip local minimum by eliminating some individuals to a new regions to explore them and to change vortex direction to explore new directions. The algorithm was tested over ten benchmark functions and it competes with some other powerful algorithms.

Position is a vital element for ITS applications. Its accuracy helps to deliver services quickly to drivers to increase their satisfaction. GPS is a well-known position system but it suffers from multipath effect and non-line of sight in tunnel environments. Relative Position or sometimes called cooperative localization is an alternative position estimation. It utilizes different forms of v2x communication to exchange position, distance, direction, and velocity parameters. It will benefit in collecting a large amount of data to increase the accuracy of position estimation. However, the dependency of radio range communication methods has drawbacks such as poor-received signal, multipath, lose packets, delay, and overhead communication that will have inverse impact on position accuracy. In addition, safety applications require fewer seconds to make quick response. This chapter provides the latest related papers, the state art of radio range, the well-known localization algorithms, and current challenges and future direction.

Social Network Analysis measures the interconnection between humans, entities or communities and the streaming of messages between them. This kind of Analysis studies the relationship between different people in a very deep way; it shows how one node (subscriber) in the network can affect the others. This research studies the connections between the customers in many different ways to help any telecom operator increase the cross and up-selling of its products and services as follows: detect communities of subscribers which are a group of nodes collected together to form a community, identify the connection types and label the links between the customers as (business, friends , family and others), as well as identifying the top influencers in the network who can spread positive or negative messages about products and services provided by the company through communities in the network and determine off-net customers who can be acquired to be targeted by specific marketing campaigns. A real cell phone dataset of 116 Million call detailed records of SMS and Voice Calls of an Egyptian Communication Service Provider (CSP) is used.

the majority cancer mortality among women is due to breast cancer over the world wide. Recent researches have shown the effectiveness of x-ray mammography in early detection of breast cancer. Unfortunately, the present systems for early detection are expensive and needs extremely complex algorithms. The crucial challenge in designing a computer-aided detection (CAD) systems for breast cancer are the segmentation phase, which requires highly complex computation. Hence, this paper proposes a CAD system to be utilized for breast cancer detection in mammographic datasets. The segmentation step is performed by a Particle Swarm Optimization Algorithm (PSO). Statistical, textural and shape feature are calculated over the segmented region. A non linear support vector machine (SVM) is exploited in the next phase in order to analyze the extracted features and classify the mammograms into normal, benign or malignant. For the sack of evaluating the performance, the experiment is performed on Mini-MIAS database. The obtained accuracy rates based on 10-folds cross validation are 85.4% for classifying normal from abnormal, 89.5% for classifying malignant from benign. The experiment shows that the classification accuracy is 81% when classifying normal, malignant or benign. The result compromises with recent researches concurs that the proposed algorithm compromises between the achieved accuracy to complexity cost.

A computer aided diagnosis and detection system (CADx) enhances the early detection accuracy for breast cancer which in turn save women life all over the world. The existing early detection CADx systems are costly and demands highly complex algorithms with complicated computation thus unsuitable for developing countries. The segmentation process is a key issue in designing CADx system for breast cancer and the most computationally costing. Hence, the contribution of this paper is proposing two CADx systems for breast cancer in mammographic datasets that compromise between efficiency, speed, and cost. The segmentation step in the first system is performed by a Particle Swarm Optimization (PSO) Algorithm while it is performed by a Gaussian Mixture Model (GMM) in the second proposed system. Textural, statistical and shape features are extracted from segmented ROIs and input for the classifier to distinguish the mammograms if normal, benign or malignant. The proposed method utilizes the nonlinear support vector machines for classification. Experiments are conducted on mini MIAS database. The resulted accuracy rates based on 10-folds cross validation for classifying normal from abnormal are 85.4% and 82.4% for PSO and GMM respectively. Besides, the ratios become 89.5%, 87.5% for classifying malignant from benign for PSO and GMM respectively. On the other hand, the experimental results show the overall average classification accuracy of 81% and 85% when classifying normal, malignant or benign. Confusion matrix is additionally evaluation metric that was also used to check and assess the process comprehensive balanced performances for both PSO and GMM based methods.

Climate change has noticeable significant impacts on development of most countries because of its direct negative effect on the production and revenue of most crops plantation process. In reality, the ongoing changes in climate variables affect the suitability of planting some crops in their traditional places at their traditional dates. Furthermore, the availability of huge volumes of agro-climatic data that almost incorporates uncertainty increases the complexity of managing and discovering the crops suitable plantation patterns from such data. Accordingly, a need appeared to an efficient approach to handle such uncertainty and to exploit such huge data volume to manage the crops plantation process accurately. This paper presents a fuzzy approach based on Hadoop for discovering crops plantation knowledge from the agro-climatic historical database of the years from 1983 to 2016 of Egypt. Commonly, the proposed approach provides a set of scenarios for plantation dates of each crop with a suitability degree for each scenario. Also, it helps managing crops plantation process from some other aspects such as harvesting dates, candidate diseases and follow up for crops water requirements respecting the data streaming of the prevailing weather data. The proposed approach has been tested on a set of crops with cooperation of researchers from Cairo University and Agricultural Research Center. The results show the added value of the proposed approach against other works respecting the more suitable crops plantation dates, harvesting dates, expected diseases and follow up for crops water requirements. Furthermore, the proposed approach benefits from Hadoop framework capabilities of handling huge amounts of data streamed from weather stations.

Objectives: This paper proposes an enhanced data access security approach to allow virtual private database security mechanism in heterogeneous multi-tier applications regardless of the data access security features provided by each database management system. Methods/Statistical Analysis: An implementation of Data Access Layer has been done respecting the proposed approach. This implementation enhances Microsoft’s Entity Framework that is widely used in commercial multi-tier database applications as a Data Access Layer. Accordingly, it’s overloaded by the required functionality including query modification and data validation. The output assembly then is tested in a typical HR database application that targets three different DBMS’s (SQL Server, MySQL, Oracle) with exactly same database state. A time measurement takes place to evaluate the processing cost of issuing CRUD operations compared with the same application architecture without using the proposed approach (e.g. relying on the row-level security provided by Oracle on the DBMS level). Findings: An illustrated case study respecting the proposed approach shows its scalability, reliability and efficiency. It allows data access security in both homogenous and heterogeneous database applications. On the other hand, the results show that the cost of processing both of data retrieval and data manipulation operations respecting predefined data access security policies of the proposed approach compared with Oracle VPD are reduced by around 59% and 57% respectively. Application/Improvements: As presented in the illustrative case study, the proposed approach can be easily applied and reused in any modern heterogeneous multi-tier database application. It allows defining data access security policies regardless of the target database management system type. Also, the results show an improvement in the processing cost of the proposed approach compared with the Oracle virtual private database with both data retrieval and data manipulation operations. Keywords: Data Privacy; Data Access; Database; Heterogeneous Database Applications

When forecasting time series, it is important to classify them according linearity behavior that the linear time series remains at the forefront of academic and applied research, it has often been found that simple linear time series models usually leave certain aspects of economic and financial data unexplained. The dynamic behavior of most of the time series in our real life with its autoregressive and inherited moving average terms issue the challenge to forecast nonlinear times series that contain inherited moving average terms using computational intelligence methodologies such as neural networks. It is rare to find studies that concentrate on forecasting nonlinear times series that contain moving average terms. In this study, we demonstrate that the common neural networks are not efficient for recognizing the behavior of nonlinear or dynamic time series which has moving average terms and hence low forecasting capability. This leads to the importance of formulating new models of neural networks such as Deep Learning neural networks with or without hybrid methodologies such as Fuzzy Logic.

This paper proposes an approach for liver segmentation in MRI images based on Whale optimization algorithm (WOA). It is used to extract the different clusters in the abdominal image to support the segmentation process. A statistical image is prepared to define the potential liver position in the abdominal image. Then, WOA divides the image into a predefined number of clusters. The prepared statistical image is converted into a binary image and multiplied by the image clustered by WOA. This multiplication process removes a great part of other organs from the image. It is followed by some points, picked up by user interaction, representing the required clusters which reside in the area of liver. The morphological operations enhance the initial segmented liver and produces the final image. The proposed approach is tested using a set of 70 MRI images, annotated and approved by radiology specialists. The resulting image is validated using structural similarity index measure (SSIM), similarity index (SI) and other five measures. The overall accuracy of the experimental result showed accuracy of 96.75% using SSIM and 97.5 using SI%.

Satellites is the bird’s-eyes that enable us to view massive areas of earth at the same time, satellites can gather more data, more quickly, than tools on the ground. Satellites also can view into space better than telescopes at earth’s surface. Development of such artificial satellites which composed of many subsystem, requires a lot of time and money that any deadly failure is unacceptable, the satellite operating in a remote environment, so it is practically very hard or impossible to repair it once a severe failure occurs, so detecting the anomalies of the subsystems measurement values (Telemetry data) is the first step in satellite failure protection and early warning. Traditional spectral-based methods like PCA is traditional for detecting anomalies in a variety of domains and problems. However, if the collected data contains tensor (multiway) structure, for example space-time-measurements values, such as the satellites subsystems measurement, some significant anomalies may stay hidden with these traditional methods. Tensor-based anomaly detection (TAD) applied in a variety set of disciplines over the recent years, although it is not recognized yet as an official category of anomaly detection techniques. This work target to highlight the candidate of tensor-based technique as a new approach for identification and detection of abnormalities and dud in the satellite telemetry data.

Social Network Analysis determines the relationships between people, organizations, groups or entities and the flow of information between them. A literature review is done for social network analysis and the prediction of links that could be done in future between the different entities within the network, many use cases are shown here for applying Social Network Analysis in different industries. This survey introduces different approaches to anticipating the connection between nodes in the social network. It will also support future research and development work as well as raising the awareness for the presented approaches.

Enzymes are important in our life and it plays a vital role in the most biological processes in the living organisms and such as metabolic pathways. The classification of enzyme functionality from a sequence, structure data or the extracted features remains a challenging task. Traditional experiments consume more time, efforts, and cost. On the other hand, an automated classification of the enzymes saves efforts, money and time. The aim of this chapter is to cover and reviews the different approaches, which developed and conducted to classify and predict the functions of the enzyme proteins in addition to the new trends and challenges that could be considered now and in the future. The chapter addresses the main three approaches which are used in the classification the function of enzymatic proteins and illustrated the mechanism, pros, cons, and examples for each one.

Machine vision studies opens a great opportunity for different domains as manufacturing, agriculture, aquaculture, medical research, also research studies and applications for better understanding of processes and operations. As scientists' efforts had been directed towards deep understanding of the particular material systems or particular classes of types of specific fruits, or diagnosis of patients through medical images classification and analysis, also real time detection and inspection of malfunction piece, or process, as various domains witnessed advancement through using machine vision techniques and methods.

Topics selection for an educational material can take a lot of manual work. The manual operations can be exhaustive, especially in case of large volume of materials. In order to overcome this problem, we have proposed an automated topic selection approach, which is able to select topics automatically for any educational material with a consideration of achieving course specifications. Our research focused on text mining and n-gram analysis. In addition, filtering criteria was applied to improve efficiency and to eliminate as many irrelevant or non-critical keyphrases as possible. The proposed method was applied on educational materials in Institute of Statistical Studies and Research (ISSR), information technology and Computer Sciences department, Cairo University and in the American University of Beirut (AUB), electrical and computer engineering department, Beirut, Lebanon. The results show that the automatic selection technique is more reliable than the manual selection and reduced a lot of time and effort for course coordinators and teachers to choose the topics that will be taught and discover them automatically.

Limited usage of online services by citizens is one of the main obstacles to the success of e-government projects. Most of the previous studies have focussed on identification of the main significant factors affecting adoption of online services by using statistical methods for hypotheses tests. However, there is a need to go a further step and propose methodologies to examine to what extent such identified adoption factors are practically achieved. This turns the adoption process of online services to be a multi-criteria decision-making problem which make it more practical for handling. Therefore, this paper aims to propose a methodology to evaluate the performance of online services utilising two of the most well-known and extensively used multi-criteria decision-making methods. It uses the hierarchy structure of AHP while using ranking procedure of PROMETHEE. The proposed methodology has been applied to evaluate the performance of a sample of 24 services available on the Egyptian national portal. Each service has been analysed against nine acceptance criteria covering application and service aspects. It is found that 46% of the evaluated services tend to be performing quite reasonably.

Cancer is the second leading cause of death after cardiovascular diseases. Out of all types of cancer, brain cancer has the lowest survival rate. Brain tumors can have different types depending on their shape, texture, and location. Proper diagnosis of the tumor type enables the doctor to make the correct treatment choice and help save the patient's life. There is a high need in the Artificial Intelligence field for a Computer Assisted Diagnosis (CAD) system to assist doctors and radiologists with the diagnosis and classification of tumors. Over recent years, deep learning has shown an optimistic performance in computer vision systems. In this paper, we propose an enhanced approach for classifying brain tumor types using Residual Networks. We evaluate the proposed model on a benchmark dataset containing 3064 MRI images of 3 brain tumor types (Meningiomas, Gliomas, and Pituitary tumors). We have achieved the highest accuracy of 99% outperforming the other previous work on the same dataset.

Advancement of location-acquisition technologies with fast development of mobile devices and wireless communication caused a revolution of information. It has been used in location-based social networks (LBSNs), has attracted millions of users to Facebook places, Gowalla, and Foursquare, is an important task to make location recommendations to users, and utilizes user preferences and other information that not only help users explore new places but also make LBSNs more attractive to users. This chapter discusses recommender systems (RS) and its application in different fields like LBSN, big data, and real life. It describes traditional recommendation approaches as well as modern approaches and explains smart community as one of powerful techniques to be used. It also introduces the state-of-art geographical techniques and presents a comparative study of recommendation techniques that can be served as a good guide and a roadmap for research and practice in this area. Finally, the authors discuss measurements and the limitations of RS.

Voice communication is an emerging technology and has great importance in our routine life. Perceptual, Voice over Internet Protocol quality is an important issue for VoIP Apps services because VoIP Apps require real-time support. Many network factors (packet loss, packet delay, and jitter) affect to VoIP quality, to achieve this objective we used an approach based on Fuzzy Logic. We configure Resource Reservation Protocol application to control Token Bucket Algorithm and the simulation experiments are carried out with Opnet. In addition, compare Token Bucket with and without Quality of Service for measure network factors. In this paper, building Fuzzy Token Bucket System consists of three variables (Bandwidth Rate, Buffer Size, and New Token) in order to improve Token Bucket Shaper output variable (New Token) by Fuzzy Stability model for Voice over IP quality maintaining.

Nowadays the fast growth and evolution on technologies such as cloud computing, mobile computing and geographic information systems (GIS) inherently exhibit spatiotemporal phenomena. These technologies have created opportunities for business implementation that utilize advanced mapping, mobile field-based applications and location aware systems. The capability to process and handle a big volume of data using cloud computing and to access location information via mobile have made GIS technology utilizes more widely. In this paper, we introduce a new mobile GIS cloud computing architecture that increase the efficiency of processing by decreasing the transmission time for data this is based on decreasing the size of transmitted data. The mobile geographic patrolling system based on cloud GIS has great significance for the development of gas pipeline patrolling. We propose pipeline patrolling prototype system which utilizes such technology.

The shadowed sets are proposed by Pedrycz as a granule manner to approximate the fuzzy sets with preserving the uncertainty features. Many methods have been made in this context to maintain various characteristics of uncertainty for fuzzy sets. In this paper, a new method is proposed which it is preserve more than one kind of uncertainty in fuzzy sets. The new technique is based on the use of measures of uncertainty directly to induce ideal values of shadowed set. It's more simply and accurate for describing uncertainty. The features of new method are important for decision applications. General Terms Soft Computing, Uncertainty, Granular Computing . Keywords Fuzzy sets, Shadowed sets, Fuzziness measure, Non-specificity measure. 1. INTRODUCTION Fuzzy sets proposed by Zadeh [1] are very important in modeling and process vague information. Membership functions play vital role to describe vagueness and imprecision in linguistic terms. The shadowed sets are proposed by Pedrycz [2] for representing uncertainty in fuzzy sets and simplify computations complexity. In the literature, two other methods proposed to induce shadowed sets. One method [3] constructed shadowed sets based on fuzziness set induced from fuzzy sets and preserve fuzziness measure of fuzzy sets. Another method[4], induced shadowed sets based on combine two interval approximations for values possibly belong to fuzzy sets and another almost surely belong to fuzzy sets. This approach preserves uncertainty of fuzzy sets in the form of expected interval and width of fuzzy sets. In this paper, we will propose a new method to construct shadowed sets using non-specificity measure and fuzziness measure which it is maintenance two types of uncertainty in fuzzy sets. It is also, very simple in calculations. This paper is organized as follows: in section 2, we present brief review about shadowed sets and different methods proposed to induce it. In section 3, we display uncertainty measures of fuzzy sets and types used in every method for construct shadowed sets. In section 4, we display proposed approach for building shadowed sets. In section 5, we use fuzzy numbers examples to apply new method to illustrate the proposed algorithm and discussion the new method with previous methods. Finally conclusions have been evolved in section 6.

The automated segmentation of the liver area is an essential phase in liver diagnosis from medical images. In this paper, we propose an artificial bee colony (ABC) optimisation algorithm that is used as a clustering technique to segment the liver in CT images. In our algorithm, ABC calculates the centroids of clusters in the image together with the region corresponding to each cluster. Using mathematical morphological operations, we then remove small and thin regions, which may represents flesh regions around the liver area, sharp edges of organs or small lesions inside the liver. The extracted regions are integrated to give an initial estimate of the liver area. In a final step, this is further enhanced using a region growing approach. In our experiments, we employed a set of 38 images, taken in pre-contrast phase, and the similarity index calculated to judge the performance of our proposed approach. This experimental evaluation confirmed our approach to afford a very good segmentation accuracy of 93.73% on the test dataset.