Shahram Golzari

Artificial Immune Recognition System with Nonlinear Resource Allocation Method and Application to Traditional Malay Music Genre Classification

Artificial Immune Recognition System (AIRS) has shown an effective performance on several machine learning problems. In this study, the resource allocation method of AIRS was changed with a nonlinear method. This new algorithm, AIRS with nonlinear resource allocation method, was used as a classifier in Traditional Malay Music (TMM) genre classification. Music genre classification has a great important role in music information retrieval systems nowadays. The proposed system consists of three stages: feature extraction, feature selection and finally using proposed algorithm as a classifier. Based on results of conducted experiments, the obtained classification accuracy of proposed system is 88.6 % using 10 fold cross validation for TMM genre classification. The results also show that AIRS with nonlinear allocation method obtains maximum classification accuracy for TMM genre classification.

A hybrid approach to Traditional Malay Music genre classification: Combining feature selection and artificial immune recognition system

Music genre classification has a great important role in music information retrieval systems. In this study we propose hybrid approach for Traditional Malay Music (TMM) genre classification. The proposed approach consists of tree stages: feature extraction, feature selection and classification with Artificial Immune Recognition System (AIRS). The new version of AIRS is used in this study. In Proposed algorithm, the resource allocation method of AIRS has been changed with a nonlinear method. Based on results of conducted experiments, the obtained classification accuracy of proposed system is 88.6 % using 10 fold cross validation. This accuracy is maximum accuracy among the classifiers used in this study.

Automatic Musical Genre Classification and Artificial Immune Recognition System

Artificial Immune Recognition System (AIRS) has been shown to be an effective classifier for several machine learning problems. In this study, AIRS is investigated as a classifier for musical genres from differing cultures. Musical data of two cultures were used - Traditional Malay Music (TMM) and Latin Music (LM). The performance of AIRS for the classification of these genres was compared with performances using several commonly used classifiers. The best classification accuracy for TMM was obtained using AIRS and was comparable, almost similar, to the performance obtained with the popular classifiers. However, the performance of AIRS for LM genre classification was shown to be not promising.

Improving the accuracy of AIRS by incorporating real world tournament selection in resource competition phase

Artificial Immune Recognition System (AIRS) is an immune inspired classifier that competes with famous classifiers. One of the most important components of AIRS is resource competition. The goal of resource competition is the development of the fittest individuals. Resource competition phase removes weakest individuals and selects strongest (seemly good) individuals. This type of selection has high selective pressure with a loss of diversity. It may generate premature memory cells and decrease the accuracy of classifier. In this study, the Real World Tournament Selection (RWTS) method is incorporated in resource competition phase of AIRS to prevent this issue and experiments are conducted to evaluate the accuracy of new algorithm (RWTSAIRS). The combination of cross validation and t test is used as evaluation method. Algorithms tested on benchmark datasets of the UCI machine learning repository show that RWTSAIRS obtained higher accuracy than AIRS in all cases and that the difference between accuracies of two algorithms was significant in majority of cases.

A maze routing algorithm based on two dimensional cellular automata

This paper propose a maze routing algorithm based on cellular automata The aim of this algorithm is find the shortest path between the source cell and the target cell , so that the path does not pass from the obstacles Algorithm has two phases, exploration and retrace In exploration phase a wave is expanded from source cell and it puts token on cells which it passes via them while expanding In the retracing phase , we start from target cell, follow the wave and arrive to source cell; the path created in this phase is desirable Propose algorithm is simple and its transactions are local and follow the cellular automata properties This algorithm find the desirable path in m×m two dimensional CA in O(m2) time step.

Incorporation of Adapted Real World Tournament Selection into Artificial Immune Recognition System

The resource competition phase of the Artificial Immune Recognition System (AIRS) incorporates a selection mechanism with a high selective pressure and loss of diversity. This selection mechanism generates premature memory cells and decreases the classification accuracy. In this study, the Real World Tournament Selection (RWTS) method is incorporated in resource competition phase of AIRS to tackle this limitation. Some experiments are conducted to evaluate the accuracy of new algorithm, named RWTSAIRS. Algorithms were tested on benchmark datasets of UCI machine learning repository and RWTSAIRS achieved better classification accuracy in all cases.

A Review on Concepts, Algorithms and Recognition Based Applications of Artificial Immune System

This paper reviews the concepts and some basic algorithms of artificial immune system as a bio inspired computational model and considers works that have been done based on the learning and recognition capabilities of artificial immune system.

File Transfer Scheduling Optimization Using Artificial Immune System

Natural immune system has features such as pattern recognition, diversity, learning, distributed detection, stochastic detection, and adaptability, that make it a great metaphor to solve hard problems. In two last decades artificial immune systems, as a novel computational artificial intelligence approach, are used to solve hard optimization problems. As for existence of different theories and models in theoretical immunity society, researchers have created various algorithms to simulate processes of immune system, such as immune network based models, negative selection, clonal selection. In this paper a clonal selection algorithm have been used to solve File Transfer Scheduling optimization problem. In proposed approach, antibodies have been created such that, the degree of simultaneous sending of files be maximized for a given transfer sequence of files, this cause make-span of schedule be minimized for that sequence. The proposed algorithm have been examined on this problem with different size, the result of experiments shown that, reaching global optimum rate of the algorithm are acceptable. Also a population control strategy is used to reduce the run time of algorithm.

Improving the precision of KNN classifier using nonlinear weighting method based on the spline interpolation

Precision improvement of the classifiers is one of the main challenges for the Artificial Intelligence researchers. Feature weighting is one of the most common ideas in this area. In this study, in order to increase the accuracy of the K-Nearest Neighbors (KNN) classifier, a nonlinear feature weighting method based on the Spline interpolation is used. In this approach, a unique nonlinear function is estimated for each feature. In order to find the best estimated parameters of the nonlinear function which is suitable for each feature, the evolutionary Genetic Algorithm is applied. Numerical results show that the nonlinear weighting method increases the accuracy of the classifiers compared to the linear weighting method.

Dynamic artificial immune system and its application to File Transfer Scheduling optimization

There are different theories and models in natural immune system, so computer science researchers have created various algorithms to simulate processes of immune system, such as immune network based models, negative selection, and clonal selection. In this paper a novel dynamic clonal selection algorithm has been used to solve File Transfer Scheduling optimization problem. In proposed algorithm, the parameters of clonal selection algorithm will be changed over generations with hope of decreasing run-time, and at the same time the performance of the algorithm remains at an acceptable level. Then after some generations a population control strategy handles the size of antibody population. Antibodies have been created such that, the degree of simultaneous sending of files be maximized for a given transfer sequence of files. This causes make-span of schedule be minimized for that sequence. The proposed algorithm has been examined on these problems with different sizes. The results of experiments show that, the rate of reaching to global optimum is acceptable.