Shariati S.,Sadjad Institute of Higher Education |
Haghighi M.M.,University of Western Ontario
2010 International Conference on Computer Information Systems and Industrial Management Applications, CISIM 2010 | Year: 2010
In this paper we use self organized fuzzy system to diagnosis and prognosis hepatitis and thyroid diseases. Moreover, we compare the result of fuzzy Neural Networks with Support Vector Machine(SVM) and artificial neural networks. In addition to diagnosis of disease, we identify the type and the phase of disease via the networks which include six classes for hepatitis disease, namely: hepatitis B (two phase) Hepatitis C (two phase), non-viral hepatitis and non-hepatitis and for thyroid disease we determine five classes, namely: Hypothyroid, Hyperthyroid, Sub-clinical hypothyroid, Sub-clinical hyperthyroid and No thyroid. The performance of each of them has studied and the best method is selected for each of classification tasks. The overall accuracy of diagnosis systems are improved as compared with previously published papers. For hepatitis disease the best accuracies range from 97.6% to 98.77% and for thyroid disease from 95.4% to 99.5%. ©2010 IEEE.
Karim M.R.,University of Malaya |
Dehghani A.,Sadjad Institute of Higher Education
International Journal of Physical Sciences | Year: 2010
Video and image processing has been used for traffic surveillance, analysis and monitoring of traffic conditions in many cities and urban areas. This paper aims to present another approach to estimate the vehicles velocity. In this study, the captured traffic movies are collected with a stationary camera which is mounted on a freeway. The camera was calibrated based on geometrical equations that were supported directly by using references. Camera calibration for exact measurements may be possible while accurate speed estimation can still be quite difficult to achieve. The designed system has the ability to be extended to another related traffic application. The average error of the detected vehicle speed was ± 7 km/h and the experiment was operated at different resolutions and different video sequences. © 2010 Academic Journals.
Sherbabaki A.Y.,Sadjad Institute of Higher Education
2011 1st International eConference on Computer and Knowledge Engineering, ICCKE 2011 | Year: 2011
An efficient nonlinear global optimization approach is utilized to design digital finite-impulse response filters with arbitrary complex frequency responses in the least-squares sense. The adopted numerical optimization technique is based upon the well-known Imperialist Competitive Algorithm (ICA). Hear we enhanced the performance of the ICA with use of improved chaos iteration circle map. This implementation known as Chaotic ICA (CICA). Several examples and comparisons to the existing methods are presented to illustrate the effectiveness and flexibility of CICA method. © 2011 IEEE.
Sahebalam A.,Ferdowsi University of Mashhad |
Kashefi M.,Ferdowsi University of Mashhad |
Kahrobaee S.,Sadjad Institute of Higher Education
Nondestructive Testing and Evaluation | Year: 2014
The present paper describes details of the comparison on the capability of eddy current (EC) and magnetic Barkhausen noise (MBN) techniques in the assessment of different microstructures in mild steel. To produce various microstructures, AISI 1045 steel samples were subjected to different heat treatment processes including annealing, normalising, quenching and tempering. EC outputs (induced voltage, normalised impedance and phase angle) as well as MBN outputs (peak width, position and amplitude) were evaluated. Comparing the EC/MBN outputs for the microstructures, the MBN peak characteristics show better agreement with changes in the microstructures. Besides, using regression analysis, peak width has been proved to be the optimum output to separate the microstructures with high accuracy. © 2014 Taylor & Francis.
Bazzaz Bonabi S.,Semnan University |
Kahani Khabushan J.,Semnan University |
Kahani R.,Sadjad Institute of Higher Education |
Honarbakhsh Raouf A.,Semnan University
Materials and Design | Year: 2014
Composite metal foam was produced as an advanced porous material, using gravity casting technique. Light Expanded Clay Aggregate "LECA" was used as space holder for the produced composite metal foam. The used LECA density was 0.33-0.43g/cm3 and the volume fraction of its porosity was from 73 to 88vol.% and aluminum A355.0 was selected as matrix in order to produce the composite foam. Structural characterization, relative density, hardness and compressive test were studied. The composite metal foam was well investigated and found to have homogeneous structure, relatively equal pore, distributable pore and isotropy properties. The study resulted in that relative density, yield strength and energy absorption capacity were 0.44, 35.9MPa and 18MJ/m3, respectively. © 2014 Elsevier Ltd.
Kolahan F.,Ferdowsi University of Mashhad |
Doughabadi M.H.,Sadjad Institute of Higher Education
Advanced Materials Research | Year: 2012
Genetic algorithm (GA) is a meta-heuristic inspired by the efficiency of natural selection in biological evolution. It is one of the most widely used optimization procedure which has successfully been applied on a variety of complex combinatorial problems. The main drawback of GA, however, is its several tuning variables which need to be correctly set. The performance of GA largely depends on the proper selection of its parameters values; including crossover mechanism, probability of crossover, population size and mutation rate and selection percent. The objective of this research is to evaluate the effects of tuning parameters on the performance of genetic algorithm using the data collected as per Central Composite Design (CCD) matrix. To gather the required data, the proposed approach is implemented on a well-known travelling salesman problem with 48 cities. Then, regression modeling has been employed to relate GA variables settings to its performance characteristic. Analysis of Variance (ANOVA) results indicate that the function can properly represent the relationship between GA important variables and its performance measure (solution quality). © (2012) Trans Tech Publications, Switzerland.
Kashefi M.,Ferdowsi University of Mashhad |
Kahrobaee S.,Sadjad Institute of Higher Education
Journal of Materials Engineering and Performance | Year: 2013
Inspection and quality control of induction hardened parts require a good understanding of the depth of the hardened layer. Traditional destructive methods to determine the case depth are considered to be costly and time-consuming. The eddy current (EC) technique is sensitive to micro-structural changes; hence, it can be used to determine the case depth based on the differences in magnetic properties between the hardened layer and the core of the specimen. In this study, identical rods of AISI 1045 mild carbon steel were surface hardened using induction hardening technique. In order to investigate the applicability of the EC technique, the relations between obtained effective and total case depths and the EC outputs (induced voltage, normalized impedance, phase angle, and their harmonic characteristics) were studied. The results show a maximum of correlation coefficient of 94% in determining case depths by EC technique. © 2012 ASM International.
Heydari R.,Sadjad Institute of Higher Education |
Hasanpour S.,Sadjad Institute of Higher Education
2014 14th International Conference on Environment and Electrical Engineering, EEEIC 2014 - Conference Proceedings | Year: 2014
With rapid increase in wind power penetration into the power grid, wind power forecasting is becoming increasingly important to power system operators and electricity market participants. Wind power in large scale in electricity market, has some drawbacks, such as uncertainties in generation. In this paper, in order to, simulating wind power plane accuracy, Weibull probability density function is used. Weibull PDF Parameters are forecasted by combination of Simulated Annealing and Artificial Neural Network (SA-ANN) in real case wind speed of Khorasan, Iran. The results illustrate, proposed method have reliable solution for Weibull PDF parameters. Finally, simulated energy market show, entry of the proposed wind energy plan, into the power energy market, increased competition belong other market players and decreased power energy price. © 2014 IEEE.
Zahraee S.M.,University of Technology Malaysia |
Hatami M.,University of Technology Malaysia |
Rohani J.M.,University of Technology Malaysia |
Mihanzadeh H.,University of Technology Malaysia |
Haghighi M.,Sadjad Institute of Higher Education
Advanced Materials Research | Year: 2014
In the manufacturing industry, managers and engineers are seeking to find methods in order to eliminate the common problems in manufacturing systems such as bottlenecks and waiting times. This is because that all of these kinds of problems impose extra cost to the companies. In addition, manufacturing companies are striving to sustain their competitiveness by improving productivity, efficiency and quality of manufacturing industry for instance high throughput and high resource utilization. The paper concentrates on the application of computer simulation to analysis manufacturing system in order to improve the productivity. Therefore, this study introduces a color manufacturing line as a case study and the basic application of arena 13.9 software. The goal of this paper is to improve the productivity and efficiency of the production line by using computer simulation. To achieve this goal, first the basic model of the current situation of production line was simulated. Second, three different alternatives were simulated and modified to find the best scenario based on the maximum productivity and minimum total cost. © (2014) Trans Tech Publications, Switzerland.
Hamidzadeh J.,Sadjad Institute of Higher Education |
Monsefi R.,Ferdowsi University of Mashhad |
Sadoghi Yazdi H.,Ferdowsi University of Mashhad
International Journal of Machine Learning and Cybernetics | Year: 2016
In instance-based classifiers, there is a need for storing a large number of samples as a training set. In this paper, we propose a large symmetric margin instance selection algorithm, namely LAMIS. LAMIS removes non-border (interior) instances and keeps border ones. This paper presents an instance selection process through formulating it as a constrained binary optimization problem and solves it by employment filled function algorithm. Instance-based learning algorithms are often confronted with the problem of deciding which instances must be stored for use during an actual test. Storing too many instances can result in large memory requirements and slow execution. In LAMIS, the core of instance selection process is based on keeping the hyperplane that separates a two-class data, to provide large margin separation. LAMIS selects the most representative instances, satisfying both objectives: high accuracy and reduction rates. The performance has been evaluated on real world data sets from UCI repository by the ten-fold cross-validation method. The results of experiments have been compared with state-of-the-art methods, where the overall results, show the superiority of the proposed method in terms of classification accuracy and reduction percentage. © 2014, Springer-Verlag Berlin Heidelberg.