International Journal of Computational Intelligence and Applications

In this work, an optimization technique is adopted to manipulate the input and output scaling factors of a modular fuzzy logic controller (MFC) for lifting and stabilizing the front wheels of a wheelchair in two-wheeled mode. A virtual wheelchair (WC) model is developed within Visual Nastran (VN) software environment where the model is further linked with Matlab/Simulink for control purposes. The lifting of the chair is done by transforming the first link (Link1), attached to the front wheels (casters) to the upright position while maintaining stability of the second link (Link2) where the payload is attached. General rules of thumb allow heuristic tuning (trial and error) of the parameters but such heuristic method does not guarantee that the system tuned with current data set will represent future system states. A global optimization mechanism such as genetic algorithm is necessary to improve the system performance. Due to its significant advantages over other searching methods, a genetic algorithm approach is used to optimize the scaling factors of the MFC and results show that the optimized parameters give better system performance for such a complex, highly nonlinear two-wheeled wheelchair system.

This paper has been removed because it was brought to our attention that Lei Li from CMU is not the author of this paper. Lei Li from CMU informed that the e-mail used in this paper is not the e-mail of Lei Li from CMU. Please contact ijcia@wspc.com

In this paper, we introduce a new hybrid learning algorithm, called DTGP, to construct cost-sensitive classifiers. This algorithm uses a decision tree as its basic classifier and the constructed decision tree will be pruned by a genetic programming algorithm using a fitness function that is sensitive to misclassification costs. The proposed learning algorithm has been examined through six cost-sensitive problems. The experimental results show that the proposed learning algorithm outperforms in comparison to some other known learning algorithms like C4.5 or naïve Bayesian.

A multi-colony ant system (MAS) is proposed for the combinatorial optimization problems. The proposed MAS is inspired by the knowledge that there are many colonies of ants in the natural world and organized with multiple colonies of ants. At first, ants perform solution search procedure by cooperating with each other in the same colony until no better solution is found after a certain time period. Then, communication between different colonies is performed to build new pheromone distributions for each colony, and ants start their search procedure again in each separate colony, based on the new pheromone distribution. The proposed algorithm is tested by simulating the traveling salesman problem (TSP). Simulation results show that the proposed method performs better than the traditional ACO.

Water quality is one of the major concerns of countries around the world. Monitoring of water quality is becoming more and more interesting because of its effects on human life. The control of risks in the factories that produce and distribute water ensures the quality of this vital resource. Many techniques were developed in order to improve this process attending to rigorous follow-ups of the water quality. In this paper, we present a comparative study of the performance of three techniques resulting from the field of the artificial intelligence namely: Artificial Neural Networks (ANN), RBF Neural Networks (RBF-NN), and Support Vector Machines (SVM). Developed from the statistical learning theory, these methods display optimal training performances and generalization in many fields of application, among others the field of pattern recognition. In order to evaluate their performances regarding the recognition rate, training time, and robustness, a simulation using generated and real data is carried out. To validate their functionalities, an application performed on real data is presented. Applied as a classification tool, the technique selected should ensure, within a multisensor monitoring system, a direct and quasi permanent control of water quality.

Damask rose (scientific name: Rosa damascene) belongs to the Rosaceae family and is valuable in medicine. In this study, the influence of air temperature and velocity are investigated on hot air dryer of the rose petals. Artificial drying of the agricultural products is one of the most common maintenance procedures. Suitable drying methods reduce the waste and damage during the storage and save the quality of the products. Optimization and control of the drying process is also based on the precise modeling. Here, moisture ratio was estimated at any temperature and air velocity by mathematical models. Later, artificial networks including feed-forward and recurrent network were applied to predict the moisture ratio via temperature, air velocity and time. The obtained results show that neural network is the best for modeling; nevertheless, the recurrent network has the best performance in predicting the moisture ratio.