Abstract Computer analysis of electrocardiogram (ECG) data has proven to be an important method to detect cardiac arrhythmias, so that can be of great assistance to the experts in detecting cardiac abnormalities. In this study, we purpose to develop a system to aid in the diagnosis of anomalies cardiac signals. This system is based on data fusion and architected by using... Computer analysis of electrocardiogram (ECG) data has proven to be an important method to detect cardiac arrhythmias, so that can be of great assistance to the experts in detecting cardiac abnormalities. In this study, we purpose to develop a system to aid in the diagnosis of anomalies cardiac signals. This system is based on data fusion and architected by using the multi-agents system for ECG classification. Therefore, the proposed system helps doctors to quickly and precisely diagnose a heart disease by examining only the class of the ECG beats. In order to achieve the goal of real-time classification, the data used are divided into two datasets: the training set for the unsupervised learning of the classifier and the testing set for the real-time classification. This system is tested on a MITBIH arrhythmia database. Read More Read Less

Abstract During the last two decades, the mobile communication has become a dominant medium of communication. In numerous countries, especially the developed ones, the market is saturated to the extent that each new customer must be won over from the competitors. Advancements in technology and rapid improvements in telecom industry have provided customers with many choices. Customer retention is one of... During the last two decades, the mobile communication has become a dominant medium of communication. In numerous countries, especially the developed ones, the market is saturated to the extent that each new customer must be won over from the competitors. Advancements in technology and rapid improvements in telecom industry have provided customers with many choices. Customer retention is one of the major tasks for the telecom industry. On the other hand, public policies and standardization of mobile communication now allow customers to easily switch over from one carrier to another, resulting in a highly fluid market. Churn refers to customers who will leave or turn to other service providers. Acquiring new customers is much more expensive as compared to retaining existing customers. Therefore, it is far more cost-effective for service providers to predict customers who will churn in future and customize services or packages according to the customer’s demands. As a result, churn prediction has emerged as one of the most crucial Business Intelligence (BI) applications that aim at identifying customers who are about to transfer to a competitor. In this paper, we present commonly used data mining techniques for the identification of customers who are about to churn. Based on historical data, these methods try to find patterns which can identify possible churners. Some of the well-known algorithms used during this research are Regression analysis, Decision Trees and Artificial Neural Networks (ANNs). The data set used in this study was obtained from Customer DNA website. It contains traffic data of 106,000 customers and their usage behavior for 3 months. The data set comprises of 48 variables. Spearman’s correlation coefficient is used to select the variables of high impact.In order to solve the problem of class imbalance in the data set, re-sampling is used.The results show that the decision treesisthe most accurate classifier algorithm while identifying potential churners. Read More Read Less

Abstract In this paper, we propose a light robust edge preserving smoothing filter named self-quotient referential ε-filter. Although many filters for edge preserving smoothing have been proposed, as it often uses local information, it is difficult to preserve edge information when the images are taken under light variation. To solve the problems, we pay attention to the feature of self-quotient filter,... In this paper, we propose a light robust edge preserving smoothing filter named self-quotient referential ε-filter. Although many filters for edge preserving smoothing have been proposed, as it often uses local information, it is difficult to preserve edge information when the images are taken under light variation. To solve the problems, we pay attention to the feature of self-quotient filter, and combine self-quotient filter and ε-filter. Some experiments were done to show the effectiveness of the proposed method. Throughout the experiments, the validity of our method was verified. Read More Read Less

Abstract Offshore wind turbine blades suffer from various faults such as blade angle asymmetry, icing, and bends. Replacement of rotor blades normally involves heavy transportation (e.g., vessel and crane), and dependency on weather conditions. As a result, wind turbines come to a long standstill and costs on energy production increase. One approach to reducing the downtime and costs is to apply... Offshore wind turbine blades suffer from various faults such as blade angle asymmetry, icing, and bends. Replacement of rotor blades normally involves heavy transportation (e.g., vessel and crane), and dependency on weather conditions. As a result, wind turbines come to a long standstill and costs on energy production increase. One approach to reducing the downtime and costs is to apply a proper maintenance strategy, e.g., corrective, time-based, failure-based, condition-based, or reliabilitycentered maintenance. This article introduces an approach, which combines the knowledgebased approach with the force analysis technique, to supporting maintenance of offshore wind turbine blades. The approach solves the semantic ambiguity of offshore wind information and provides the possibility of monitoring the performance of wind turbine blades in real-time, leading to advanced alarms when needed. The approach can be adapted and applied to other wind turbine components. Read More Read Less