Associative classification (AC) or class association rule (CAR) mining is a very efficient method for the classification problem. It can build comprehensible classification models in the form of a list of simple IF-TH...
详细信息
Associative classification (AC) or class association rule (CAR) mining is a very efficient method for the classification problem. It can build comprehensible classification models in the form of a list of simple IF-THEN classification rules from the available data. In this paper, the authors present a new and improved discrete version of the crowsearchalgorithm (CSA) called NDCSA-CAR to mine the class association rules. The goal of this article is to improve the data classification accuracy and the simplicity of classifiers. The authors applied the proposed NDCSA-CAR algorithm on 11 benchmark datasets and compared its result with traditional algorithms and recent well known rule-based classification algorithms. The experimental results show that the proposed algorithm outperformed other rule-based approaches in all evaluated criteria.
crowsearchalgorithm is one of bio-inspired optimization algorithms which is essentially derived for solving continuous based optimization problems. Although many main-frame discrete optimizers are available, they st...
详细信息
crowsearchalgorithm is one of bio-inspired optimization algorithms which is essentially derived for solving continuous based optimization problems. Although many main-frame discrete optimizers are available, they still have some performance challenges. This paper proposes three discretecrow inspired algorithms for enhancing the performance of the original crowsearchalgorithm when it is applied for solving discrete traveling salesman problems. The proposed algorithms are derived based on modular arithmetic, basic operators and dissimilar solutions techniques. Each technique guarantees switching from continuous spaces into discrete spaces without losing information. Such algorithms are called Modular Arithmetic, Basic Operators, and Dissimilar Solutions algorithms. For evaluating their performance, the proposed algorithms are compared with the most state-of-the-art discrete optimizers for solving 111 instances of traveling salesman problems. Simulation results illustrate that, the performance of the proposed algorithms is much better than the performance of most state-of-the-art discrete optimizers in terms of the average optimal solutions accuracy, the average errors from the optimal solutions and the average of computational time.
暂无评论