Mohammed Hashem

Rough — Granular neural network model for making treatment decisions of Hepatitis C

Hepatitis C virus is a massive health issue affecting significant portions of the worlds population. Applying data preprocessing, feature reduction techniques, and generating rules based on the selected features for classification tasks are considered as important steps in the knowledge discovery in databases. This paper highlights a Rough-Granular Neural Networks model that incorporates Rough Sets and Artificial Neural Networks to make efficient data analysis and suggestive predictions. The Rough Sets is used as a powerful analysis tool for data pre-processing. It is used to reduce and choose the most relevant attributes for reducing the number of input vector to Artificial Neural Networks without reducing the basic knowledge of the information system. This is done to increase Classification accuracy of the proposed model. Resulting optimal data set is input to constructed neural network with supervised learning algorithm for classifying studied cases for testing new medication for HCV treatment. The experimental results show that the overall classification accuracy offered by the proposed model is a superlative result.

Distributed channel selection based on channel weight for cognitive radio network

Cognitive radio (CR) technology enables the opportunistic use of the vacant licensed frequency bands, thereby improving the spectrum utilization. However, the CR operation must not interfere with the transmissions of the licensed or primary users (PUs), and this is generally achieved by incurring a trade-off in the CR network performance. We propose an algorithm for selecting best channel based on the distributed channel assignment manner in cognitive radio (CR) networks. In this paper, we study and analyze the impact of different Primary Radio nodes activity pattern with the help of two performance metrics. And compare our protocol with two other algorithms, Random (RD), and Selective Broadcasting (SB). We implement and analyze the performance of our algorithm through NS-2 simulations.

Extending the Application of Conditional Signal Adaptive Median Filter to Impulsive Noise

In this paper, two major improvements are applied to the conditional signal adaptive median (CSAM) filter to accommodate for high density impulsive noise with significant dynamic range. Homogeneity level of a pixel gives a good estimate in separating noisy pixels from pixels belonging to an edge or a fine detail in an image, but the proper choice of a threshold of homogeneity is highly affected by the noise density and range. A more robust method is developed for choosing such a threshold than in the original CSAM filter which extends the application of the filter to impulsive noise not only salt and pepper noise. Results are also compared for both low and high density impulsive noise

Enhanced tree routing protocols for multi-hop and multi-channel cognitive radio network (EMM-TRP)

Abstract Cognitive Radio (CR) is a promising technology and innovative solution for current spectrum allocation problems. We can exploit the unused licensed bands to meet the increased demand on spectrum bands by applying CR technology. The routing process in CR environment has many challenges such as the absence of centralized infrastructure, the lack of cooperation between the network layer and lower layer, the dynamic nature of channel status, and frequent link failure according to Primary users’ traffic. In this paper, we develop an enhanced multi-hop multichannel tree routing protocol (EMM-TRP) for cognitive radio network and we contributed to the following: (i) we proposed an EMM-TRP that jointly utilized the tree routing algorithm with a spectrum management module in routing decisions. (ii) We also proposed a new metric to find the best route (The main purpose for the design of this metric is safeguarding the PUs traffic from CR node interference and quick data transmission.) (iii) We have improved the EMM-TRP routing tree algorithm search by adding neighbors table technology. (iv) Finally, we offered recovery and discovery unit in the case of link failure. We carried out our experimental evaluations in ns2 simulator. These evaluations have been shown that EMM-TRP protocol achieves better performance in terms of average throughput, end-to-end delay, overhead and hop count, compared by SAMER, CRP, STOD-RP and CTBR routing protocols.

A study of spatial machine learning for business behavior prediction in location based social networks

Understanding business behaviors requires acquiring huge amounts of data from diverse field studies. Location Based Social Networks can provide such large amounts of data that can be used in urban analysis to understand business behaviors. Towards more insight for business behavior, a novel analytical prespective that exploits data collected from Location Based Social Networks is introduced to predict business turnouts. Prediction is implemented using machine learning techniques. Spatial regression models are investigated through a comparative study to model the dataset features relationships for business behavior prediction. Geographically Weighted Regression model is found to be the most appropriate in predicting business turnouts of objects provided by Location Based Social Networks. Moreover, a Partitioned Geographically Weighted Regression model is proposed to deal with the data heterogeneity nature pursuing more accurate predictions for the business turnouts. An experimental case study, using data about venues registered in Foursquare is conducted to assess the performance of the proposed methods. The experimental results confirm the best performance by the Geographically Weighted Regression compared to Durbin, Durbin Error, Spatial Lag, Spatial Error, and Spatial Lag X regression models presented in this study. Moreover, the proposed Partitioned Geographically Weighted Regression model experimental results showed better prediction accuracy compared to the classical Geographically Weighted Regression model.

Exploiting location based social networks in business predictions

The growing use of Location Based Social Networks especially in recent years provides large amount of data transactions. These data transactions attract many data mining researchers to infer various information from them. In this paper, a geographic business prediction technique is proposed, which infers business usage by exploiting data published about venues in Location Based Social Networks. The proposed technique is beneficial for investors and business decision makers. The proposed geo-business prediction technique considers spatial and categorical factors in the prediction process. Both factors affect the prediction accuracy rather than using traditional spatial prediction techniques, which are usually used where only the location feature is involved in the prediction process. Additionally, an outlier filter is proposed and applied to the data to avoid extreme values involvement in the prediction process in order to achieve better prediction accuracy. To test the proposed technique, an experimental case study is implemented. It uses data extracted from Foursquare about business venues in Texas State in the United States of America. The proposed geo business prediction technique has shown to provide better prediction accuracy than k nearest neighbor spatial prediction. The Application of the outlier filter, results in even higher prediction accuracy for the proposed technique.

Business Behavior Predictions Using Location Based Social Networks in Smart Cities

Understanding business behaviors require acquiring lots of data through numerous amounts of field research. The growing use of mobile devices, especially in recent years, provides large amount of data transactions that can replace the data acquired by field researchers. Data acquired from location based social networks can be exploited in urban analysis for economic reasons. Such research studies the spatial correlation of business turnouts for venues in location based social networks. Towards more insight for business behavior in smart cities, data acquired from location based social networks is used for predicting the business turnouts based on their spatial locations. The presented work moves along this direction by proposing a machine learning approach using spatial interpolation applied to predict business turnouts. In this approach, a similarity embedded spatial interpolation technique is additionally proposed. The proposed technique, with the exploitation of the multiple features provided by location based social networks, can issue better prediction performance. To test the proposed technique, an experimental case study is implemented. The case study uses training data extracted from Foursquare about venues in Texas in the United States of America. The proposed similarity embedded spatial interpolation technique has shown better prediction accuracy for business turnouts than classical spatial interpolation predictions.

Machine Learning Techniques for Mining Location-Based Social Networks for Business Predictions

The vast use of Location-Based Social Networks over the last decade results in a considerably large amount of data transactions accumulated over time. Data mining researchers exploit these large amounts of data produced by location-based social networks users to predict useful information. One of the highly recommended methods for prediction is learning from statistical observations through machine learning. In this paper, spatial machine learning techniques are suggested for predicting potential business investment openings in Location-Based Social Networks. Two spatial techniques are studied; Spatial Auto Regression model, and Inverse Distance Weight spatial interpolation technique. A modification for the Inverse Distance Weight spatial interpolation has been suggested where an extreme avoidance criterion is proposed, in order to enhance the prediction accuracy of the classical method. The modified interpolation method is compared to the spatial Auto Regression model and the classical Inverse Distance Weight spatial Interpolation technique, for considerations of computational complexity and prediction accuracy. An experimental case study involving data extracted from Foursquare has been tested for Business venue usage prediction. The results show better prediction accuracy for the Inverse Distance Weight spatial interpolation than the Spatial Moreover, better prediction accuracy for the proposed Extreme Avoidance spatial interpolation over both the Inverse Distance Weight spatial interpolation and Spatial Auto Regression is obtained while maintaining the low computational complexity of the spatial interpolation.