Assessing seismic hazards involves specifying the likelihood, magnitude and location of earthquakes in a region. Predicting the seismic hazards is the first step in reducing the impact of the damage caused by an earthquake. In this study, to fully utilize all the known parameters which may possibly affect the occurrence of earthquakes (mb ≥ 4.5); a data-driven rule-extraction method called the Classification and Regression Tree (CART) was used to find the rules governing the earthquakes that occur. The method produces Predictive Rule Based Seismicity Map (PRBSM) of Iran that shows regions with high earthquake hazards. The rules are based on a large number of geophysical and geological parameters. The PRBSM has been built based on earthquake data from the year 1900 up to the end of 2006 and has been validated using earthquakes from 2007 to the end of 2015. In addition, this method allows for the identification of the most important combination of parameters associated with earthquakes. For example, the isostatic anomaly has the highest correlation with earthquakes in Iran. A distinctive character of this paper is the predictive rule based method which can create online as well as offline maps which are flexible and readily automated.

In this paper an attempt is made to identify the rules that determine changes in oil prices behavior in order to better forecast the oil market. Rule extraction in this research is done by the GMDH (Group Method of Data Handling) algorithm according to the Fujimoto and Nakabayashi (2001) approach. The results confirm that while there are not any absolute rules in the oil prices behaviour, we can extract relative rules on frontier points in various position of the oil market.

Knowledge embedded within artificial neural networks (ANNs) is distributed over the connections and weights of neurons. So, the user considers ANN as a black box system. There are many researches investigating the area of rule extraction by ANNs. In this paper, a dynamic cell structure (DCS) neural network and a modified version of LERX algorithm are used for rule extraction. On the other hand, intrusion detection system (IDS) is known as a critical technology to secure computer networks. So, the proposed algorithm is used to develop IDS and classify the patterns of intrusion. To compare the performance of the proposed system with other machine learning algorithms, multi-layer perceptron (MLP) with output weight optimization-hidden weight optimization (OWO-HWO) training algorithm is employed with selected inputs based on the results of a feature relevance analysis. Empirical results show the superior performance of the IDS based on rule extraction from DCS, in recognizing hard-detectable attack categories, e.g. userto- root (U2R) and also offering competitive false alarm rate (FAR). Although, MLP with 25 selected input features, instead of 41 standard features introduced by knowledge discovery and data mining group (KDD), performs better in terms of detection rate (DR) and cost per example (CPE) when compared with some other machine learning methods, as well.

Introduction: Parkinson's disease has become an increasing public health issue that its symptoms become more severe over time. Early diagnosis and treatment of this disease leads to improving the skills, abilities and performance of patients in daily life. In order to diagnose the disease early, it is necessary to produce clinical decision-making assistance systems that are able to detect the diagnostic rules of the disease. Methods: This study provides an automatic way to extract novel diagnostic rules for Parkinson's disease. The proposed method is based on logic regression and simulated annealing algorithm. To evaluate the method, the Oxford Parkinson's data set was used, which contains 22 biomedical voice measurements from 31 people, 23 with Parkinson's disease. The dataset has 195 voice recording from these individuals. Results: The results include two diagnostic rules; If high accuracy was the main concern, a new rule has been proposed that includes 21 logical statements that have an accuracy of 92. 31%, a sensitivity of 85. 42%, and a specificity of 94. 56%. However, for real-time systems and clinical decision-making assistance with high interpretability, a rule consisting of 3 logical statements has been proposed, which has an accuracy of 78. 97%, a sensitivity of 77. 08% and a feature of 79. 59%. Conclusion: The results show the high power of interpretability and reliability of the proposed rules in the diagnosis of Parkinson's disease, which can be used in the implementation of remote diagnostic systems.

Background and Aim: Although orthodontists have long recognized that the extraction (Ext) of premolars often is accompanied by changes in the soft tissue profile, investigations indicate that the soft tissue does not always respond favorably to hard-tissue retraction. This study was designed to evaluate the effects of treatment, with and without premolar Ext, on the lateral facial profiles of borderline patients with particular reference to the curvature of the upper and lower lips.Materials & Methods: Eighty-nine border line patients were included in this study. 41 patients were treated with a non-extraction (Non-Ext) protocol, 16 patients were treated with extractions of 5.5, 18 patients with 4.4 and 14 patients with 4.5. All pre-and posttreatment lateral cephalograms were traced and analysis by one examiner. To quantify the soft tissue effects of growth and treatment, the depths of the upper and lower lip curves were calculated in two ways relative to the PM reference line and anterior soft tissue reference line.Results: The changes in depth of upper and lower lip curves were statistically significant (P<0.001).The Non-Ext group showed an increase in depth of upper and lower lip curves, whereas the Ext group showed a decrease in depth of upper and lower lip curves. No significant differences were found between the various extraction sequences (5.5, 4.4, 4.5) for depth of the upper and lower lip curves changes.Conclusions: l) The upper and lower lip changes were significant; more retrusive in the Ext group and more protrusive in the Non-Ext group. 2) There were no significant post treatment differences in the depths of upper and lower lip curves between premolar extraction sequences.

Background & Aim: Extraction of first premolars and their influence on the third molars' eruption and impaction has been of concern to dental profession. The aim of this study, was to determine the relation between the changes of third molar angulation and the first premolar extraction in orthodontic treatment.Materials and Methods: This analytical study was carried out on total 90 subjects selected from two orthodontic clinics. Forty five subjects (14 males and 31 females) 14.46±1.64 years old treated with extraction of four first premolars (extraction group) and the other 45 subjects (13 males, 32 females) 13.9±1.99 years old treated by nonextraction were studied. Lateral cephalometric and panoramic films were studied before and after treatment. Eight angles in panoramic, four angles and 4 linear variables on the lateral cephalometric films were measured. Age, gender, amount of crowding in both dental arches and treatment duration were matched in the two groups. Student t and chi square tests were used to analyze the data.Results: The upper eruption space and the lower eruption spaces were more in extraction group and the difference was significant (P=0.02, P=0.004, P<0.001). The changes of third molar angulation were not significant between the two groups. Eruption rate of the third molars in both arches were more in extraction group and the difference was significant (P<0.001).Conclusion: Extraction of the first premolars did not influence the changes in the third molar angulation, while it affected the third molar eruption by space creation. It seems that extraction of the first premolars is not a way for secure eruption of the third molar.

There are many methods introduced to solve the credit scoring problem such as support vector machines, neural networks and rule based classifiers. Rule bases are more favourite in credit decision making because of their ability to explicitly distinguish between good and bad applicants. In this paper multi-objective particle swarm is applied to optimize fuzzy apriori rule base in credit scoring. Different support and confidence parameters generate different rule bases in apriori. Therefore Multi-objective particle swarm is used as a bio-inspired technique to search and find fuzzy support and confidence parameters, which gives the optimum rules in terms of maximum accuracy, minimum number of rules and minimum average length of rule. Australian, Germany UCI and a real Iranian commercial bank datasets is used to run the algorithm. The proposed method has shown better results compared to other classifiers.