No abstract

The need to increase road safety is a major concern, with millions of road users and pedestrians being killed in traffic accidents each year. Static speed limit signs are conventionally used to assist motorists in safe selection of speeds. Although appropriate to use under near ideal conditions, such signs fail to provide accurate information on speed selection when traffic and environmental conditions are less than ideal. To develop a variable speed limit system that utilizes fuzzy control technology to identify speed limits appropriate for differing environmental conditions the problem of structure identification of a fuzzy model was studied. This paper presents a fuzzy rulebase combined controller, which is a fuzzy rule-based combination of linear controllers, for nonlinear systems subject to parameter uncertainties. The paper discusses potential benefits and limitations associated with the model. The main interest has been on building fuzzy relationship models that are expressed by set of fuzzy linguistic propositions derived from the experience of the specialists. The proposed model was tested on a set of experimental data and against specialist knowledge the comparison was satisfactory regarding the aims of the model. This system dynamically updates posted speed limits to better reflect prevailing traffic and environmental conditions.

No abstract

Ever-growing extension of textual data has increased the necessity of processing textual data. Data imbalance in classification of textual data is one of the cases that decrease efficiency. In order to confront with imbalance problem, various methods are suggested. Some of the methods are: data-based, cost-based, algorithm-based and feature selection methods. In recent researches, some methods are considered into account using ensemble methods. In this research, a new oversampling method is suggested. In the new method the number of minor class samples is increased using ontology and then random oversampling is performed for minor class. Finally, using the methods of feature selection, appropriate features are selected. New ensemble method was tested using Hamshahri data. The results show that the ensemble method on Hamshahri collection, despite decreasing number of features, causes the improvement of classification results for polynomial Naïve Bayes and decision tree.

Forecasting the number of students who are going to take a special course in next semester in Computer Engineering field at Payam Noor University is the subject. To do this, many neural network structures have been tested with MATLAB software by existing data and were compared to real data, networks like feedforward backpropagation 3 and 4-layared, RBF network, etc. To achieve a network with optimum structure, various parameters and criteria like MAE 1 , MSE 2 and MSEREG 3 , have been examined. At last, a 3-layered feedback neural network in the form of 20-n-1 was chosen for this problem. Comparing experiential results with real data, it is shown that the obtained model can effectively forecast enrolments of students. So it can be used for forecasting tasks especially when a forecast with high accuracy is needed.