Search

The growing use of internet and the existence of vulnerable points in networks have made the use of intrusion detection systems as one of the most important security elements. Intrusion detection is essentially a classification problem and it is the identification of effective features such as important issues in the classification This paper presents a novel method for selecting effective features in network intrusion detection based on an estimation of distribution algorithm that uses a probabilistic dependency tree to identify important interactions between features. To evaluate the performance of the proposed method, the NSL- KDD dataset is used, in which the packets are divided into five normal types and intrusive types of DOS, U2R, R2L and Prob. The performance of the proposed algorithm has been compared alone and in combination with other feature selection algorithms such as forward selection, backward selection and genetic algorithm. Moreover, the effect of algorithm parameters like population size on intrusion detection accuracy is tested. Based on this analysis and also considering the intra-class accuracy of different feature selection methods studied in this paper, an effective subset of features for intrusion detection is identified. [ABSTRACT FROM AUTHOR]

In this paper, in the first step, the present weather of METAR reports of the year 2013 in Mehrabad synoptic station was studied and the period with most occurrences of the instability producing the Gusty wind was identified. This period is from January to June of every year. Then, all data of selected period, except the data of Gusty wind direction and speed, were normalized to interval 0.1-0.9. The considered data for training, testing and validation were 60%, 20% and 20%, respectively. The related features of Gusty wind direction and speed were selected from 58 features recorded by 3 sensors located on the runway. The Mehrabad runway direction is from the east to the west with 4000 meters long and 45 meters wide. The sensor No. 29 was on the east end of band, the sensor No. 11 was on the west edge of the band, and location of the mid sensor was on the middle of band which its distance from the band is 600 meters to the north direction. The feature selection methods in this study are mutual information (MI) with the Maximum-Relevance Minimum-Redundancy criterion (filter type) and Sequential Floating Forward Selection (SFFS) (wrapper type) with the k Nearest Neighbors (kNN) algorithm. Selected features for Gusty wind speed at each band are the maximum and mean wind speed in 2 and 10 minutes, and the momentary wind speed by the MI method. The selected feature by SFFS method is the wind direction deviation in past 10 minutes on band No. 11 and mid band, momentary pressure on mid band and maximum wind speed in 10 minutes on band No. 29. For Gusty wind direction by first method, the selected features are minimum, mean and maximum wind direction in 2 minutes, minimum and mean wind direction in 10 minutes and momentary wind direction on band No. 29. Selected features with second method are the wind direction deviations in past 10 minutes on the band No. 29 and mid band, and the mean sea level pressure and mean wind direction in 10 minutes on band No. 29. In the final step, these selected features were used as inputs of the multilayer perceptron neural network in different modes such as: layer number, neuron number, learning rate and threshold value for weight of neuron. The model output results were compared to predict the Gusty wind direction and speed and the best model was selected. The results show that to predict the wind speed, the best model is a multilayer perceptron neural network with four layers: input layer with 4 neurons, two hidden layers with 4 neurons in the first layer and 2 neurons in the second layer and 1 neuron in the output layer; learning rate of 0.1 and initial weight neurons of 0.5. For predicting the wind direction, the best model has four layers, 6 neurons in the first and second layers and 3 neurons at the third layer and one neuron at the fourth layer with the same learning rate and initial threshold. The MLP performance is better in predicting the Gusty wind speed. [ABSTRACT FROM AUTHOR]

Organizations should consider process improvement for promoting their performance. The main problem is the high volume of process dataset along with the wide variety of their features that leads to increase the complexity in process improvement methods. Previous methods cannot improve processes in a high volume of process dataset. Data mining approach can support improvement methods by identifying valuable hidden patterns in high volume of process dataset. In this paper a framework of using data mining techniques for extracting valuable hidden patterns in high volume of process dataset is developed for presenting the improvement suggestions. In order to evaluate the proposed framework, a real set of processes along with their features were gathered. After that, using classification, clustering, and features selection algorithms, valuable patterns in high volume of process dataset were identified. After evaluating these patterns, improvement suggestions were recommended by the identified patterns. The results showed that identified patterns can support processes improvement activities with recommending the improvement suggestions. [ABSTRACT FROM AUTHOR]

Increasing the number of processor cores leads to increasing the density of the computing power processor and also raising the temperature. Temperature management is very important in these processors. Thermal management methods are introduced to reduce the CPU temperature. Reactive and proactive approaches are two sets of these schemes. Unlike the reactive techniques, proactive methods predict the temperature using thermal prediction model before reaching its threshold. In this paper, a hybrid model of several SVR models is proposed for predicting temperature. An appropriate dataset is created for training proposed model that includes a high diversity of processor temperature variations. Some features of dataset are measured using temperature sensors and system performance counters. Other features, with historical and control names are calculated with the proposed processes to increase the accuracy of thermal model. Two SVR models are used in the proposed thermal model to reduce its operational overhead. The proper features for each SVR model are selected by the feature selection algorithm based on mutual information. The proposed model is evaluated for temperature prediction for 2 to 5 time distances. The results show that with a selection of 11 features for thermal prediction model of the next 2 seconds, the mean absolute error is about 0.5 °C. [ABSTRACT FROM AUTHOR]

Background: Data mining as a multidisciplinary field is rooted in the fields such as statistics, mathematics, computer science and artificial intelligence and has been gaining momentum in scientific, managerial, and executive applications in health care. Data mining can be defined as the automated extraction of valuable, practical and hidden knowledge and information from large data. Applying data mining in medical records and data is of utmost importance for health care givers and providers and brings vital and valuable outcomes. Data mining can help doctors come up with better recommendations and plans for treatment which actually in many respects have significant impact on patients' life and satisfaction In this paper we have proposed and utilized data mining methods to extract hidden information in medical records of pelvis stone patients with ureteral stone. We have tried to design a decision support system model to be applicable for selecting type of treatment for these groups of patients. Methods: We gathered needed information from Shahid Hashemi Nejad hospital. In this research we have used decision tree as a data mining tool, for selecting suitable treatment for patients with ureteral stone. This model can predict probability of success of each treatment. Results: In this research we extracted effective attributes in selecting type of treatment for patients with ureteral stone. Conclusions: By using this model we can have eight percent improvement in number of patients who have stone free output after treating. In fact, this model has a better functionality than expert system of hospitals. [ABSTRACT FROM AUTHOR]