Fuzzy C-means (FCM) clustering is the widest spread clustering approach for medical image segmentation because of its robust characteristics for data classification. But, it does not fully utilize the spatial information and is therefore very sensitive to noise and intensity inhomogeneity in magnetic resonance imaging (MRI). In this paper, we propose a conditional spatial kernel fuzzy C-means (CSKFCM) clustering algorithm to overcome the mentioned problem. The approach consists of two successive stages. First stage is achieved through the incorporation of local spatial interaction among adjacent pixels in the fuzzy membership function imposed by an auxiliary variable associated with each pixel. The variable describes the involvement level of each pixel for construction of membership functions and different clusters. Then, we adapted a kernel-induced distance to replace the original Euclidean distance in the FCM, which is shown to be more robust than FCM. The problem of sensitivity to noise and intensity inhomogeneity in MRI data is effectively reduced by incorporating a kernel-induced distance metric and local spatial information into a weighted membership function. The experimental results show that the proposed algorithm has advantages in accuracy and robustness against noise in comparison with the FCM, SFCM and CSFCM methods on MRI brain images.

No abstract

The electricity consumption forecast is especially important with regard to policy making in developing countries. In this paper, the electricity consumption rate is predicted using the data mining techniques. The datasets that were collected for predicting the electricity consumption are related to Islamic Republic of Iran -Mazandaran province pertaining to the years 1991 to 2013. The research objective is analyzing the electricity consumption rate in recent years and predicting future consumption. According to a study the electricity consumption growth rate between the years 2006 to 2013 and the years 1999 to 2006 equaled 28.41 and 73.53, respectively. The results of the research conducted using the regression model indicate a 2.48 relative error. The output of this prediction shows that the total electricity consumption rate increases about 3.2% annually on average and will reach 7076796 megawatts by the year 2020 that shows a 22.28% growth comparing to the year 2013.

Image segmentation is an essential step in image processing. Many image segmentation methods are available but most of these methods are not suitable for noisy images or they require priori knowledge, such as knowledge on the type of noise. In order to overcome these obstacles, a new image segmentation algorithm is proposed by using a self-organizing map (SOM) with some changes in its structure and training data. In this paper, we choose a pixel with its spatial neighbors and two statistical features, mean and median, computed based on a block of pixels as training data for each pixel. This approach helps SOM network recognize a model of noise, and consequently, segment noisy image as well by using spatial information and two statistical features. Moreover, a two cycle thresholding process is used at the end of learning phase to combine or remove extra segments. This way helps the proposed network to recognize the correct number of clusters/segments automatically. A performance evaluation of the proposed algorithm is carried out on different kinds of image, including medical data imagery and natural scene. The experimental results show that the proposed algorithm has advantages in accuracy and robustness against noise in comparison with the well-known unsupervised algorithms.

With an explosive growth of wireless sensor networks (WSN), many of their features and applications have become important. Localization of sensor nodes is one of the most important problems in WSN whose accuracy has a very large impact on its performance. Global positioning system (GPS) is a well-known and powerful way which differentiates methods of its use on each node individually. But, because of high energy consuming and processing GPS, it is inappropriate for WSNs. Different algorithms are suggested to overcome the consumed cost of GPS by putting GPS on only some nodes instead of all nodes in the network for localization. So, for nodes localization, just a number of nodes exploit GPS and, they can help other nodes of network in localization via distribution of their coordinates. The use of a mobile robot to send signals to coordinate the target node localization is a good idea. The mobile robot should move in the right path and can localize node more accurately at lower cost. This paper proposes a new method to localize all nodes through some localized nodes based on graph theory in a tree and network topology. The proposed method provides better performance at the cost of accuracy and the number of nodes that can be made up of local consumption.