RESUMO
The flower pollination algorithm (FPA) is a novel heuristic optimization algorithm inspired by the pollination behavior of flowers in nature. However, the global and local search processes of the FPA are sensitive to the search direction and parameters. To solve this issue, an improved flower pollination algorithm based on cosine cross-generation differential evolution (FPA-CCDE) is proposed. The algorithm uses cross-generation differential evolution to guide the local search process, so that the optimal solution is achieved and sets cosine inertia weights to increase the search convergence speed. At the same time, the external archiving mechanism and the adaptive adjustment of parameters realize the dynamic update of scaling factor and crossover probability to enhance the population richness as well as reduce the number of local solutions. Then, it combines the cross-generation roulette wheel selection mechanism to reduce the probability of falling into the local optimal solution. In comparing to the FPA-CCDE with five state-of-the-art optimization algorithms in benchmark functions, we can observe the superiority of the FPA-CCDE in terms of stability and optimization features. Additionally, we further apply the FPA-CCDE to solve the robot path planning issue. The simulation results demonstrate that the proposed algorithm has low cost, high efficiency, and attack resistance in path planning, and it can be applied to a variety of intelligent scenarios.
Assuntos
Algoritmos , Polinização , Simulação por Computador , FloresRESUMO
BACKGROUND: As a prevalent metabolic disease, diabetes has different side effects and causes a wide range of co morbidity with a high rate of mortality. There is a need for certain interventions to manage this disease. Iranians usually have three main meals a day. Considering the special needs of diabetic patients and the possibility of hypoglycemia between the main meals, it is essential for these patients to eat something as a snack. Considering these conditions and the society's orientation towards modern technologies such as smart phones, designing mobile-based nutrition recommender systems can be helpful. METHODS: The snack recommender system is a knowledge-based smart phone application. This study has focused on the development of a recommender system that combines artificial intelligence techniques and makes up a knowledge base according to the guidelines posed by the American Diabetes Association (ADA). The snack menu was recommended in accordance with the patient's favorites and conditions. The accuracy of the recommended menu was assessed in 2 steps. First, it was compared with the diet prescribed by three nutrition specialists. In the second step, system's suggested menu was evaluated by the data from 30 diabetic patients using a valid questionnaire. RESULTS: The results of evaluating the snack recommender system by nutritionists showed that this system is capable of recommending various snacks according to the season (accuracy of 100%) and personal interests (accuracy of 90%) to diabetic patients. According to health nutritionists, the snacks suggested by this system are matched with Iranian culture. Moreover, the results revealed that a higher body mass index (BMI) makes the recommender system less sensitive to personal interests to suggest what is basically beneficial for one's health. CONCLUSION: This study was a pioneering research to develop a more comprehensive dietary recommender system for diabetic patients which includes main meals as well. Patients found the system useful and were satisfied with the application. This system is believed to be able to help diabetic patients to take more healthy diet which leads to a better lifestyle.