To overcome the shortcomings of the harmony search algorithm, such as its slow convergence rate and poor global search ability, a reward population-based differential genetic harmony search algorithm is proposed. In this algorithm, a population is divided into four ordinary sub-populations and one reward sub-population, for each of which the evolution strategy of the differential genetic harmony search is used. After the evolution, the population with the optimal average fitness is combined with the reward population to produce a new reward population. During an experiment, tests were conducted first on determining the value of the harmony memory size (HMS) and the harmony memory consideration rate (HMCR), followed by an analysis of the effect of their values on the performance of the proposed algorithm. Then, six benchmark functions were selected for the experiment, and a comparison was made on the calculation results of the standard harmony memory search algorithm, reward population harmony search algorithm, differential genetic harmony algorithm, and reward population-based differential genetic harmony search algorithm. The result suggests that the reward population-based differential genetic harmony search algorithm has the merits of a strong global search ability, high solving accuracy, and satisfactory stability.

With the improvement of people’s living standards and entertainment interests, theme parks have become one of the most popular holiday places. Many theme park websites provide a variety of information, according to which tourists can arrange their own schedules. However, most theme park websites usually have too much information, which makes it difficult for tourists to develop a tourism planning. Therefore, the theme park routing problem has attracted the attention of scholars. Based on the Traveling Salesman Problem (TSP) network, we propose a Time-Dependent Theme Park Routing Problem (TDTPRP), in which walking time is time-dependent, considering the degree of congestion and fatigue. The main goal is to maximize the number of attractions visited and satisfaction and to reduce queues and walking time. To verify the feasibility and the effectiveness of the model, we use the Partheno-Genetic Algorithm (PGA) and an improved Annealing Partheno-Genetic Algorithm (APGA) to solve the model in this paper. Then, in the experimental stage, we conducted two experiments, and the experimental data were divided into real-world problem instances and randomly generated problem instances. The results demonstrate that the parthenogenetic simulated annealing algorithm has better optimization ability than the general parthenogenetic algorithm when the data scale is expanded.

JAIT is a scientific open access journal which focuses on empirical research results and critical analysis of technology development, use, management and impacts in information technology.

Predicting carbon emissions is important in various sectors, including environmental management, economic planning, and energy policy. Traditional forecasting models typically require extensive training data to achieve high accuracy. However, carbon emission data are usually available on an annual basis, which is insufficient for effectively training conventional forecasting models. To address this challenge, this paper introduces an innovative carbon emissions prediction model that integrates Fibonacci attenuation particle swarm optimization (FAPSO) with the gated recurrent unit (GRU). The FAPSO algorithm is used to optimize the hyperparameters of the GRU, thereby alleviating the decline in prediction accuracy that conventional recurrent neural networks often face when dealing with limited training data. To evaluate the effectiveness of the FAPSO-GRU model, we tested it using carbon emission data from Hainan Province. Compared to the conventional GRU model, the FAPSO-GRU model achieved a significant reduction in the mean absolute error (42.27%), root mean square error (42.38%), and mean absolute percentage error (43.06%). Furthermore, we validated the FAPSO-GRU model with real data from Beijing, Guangdong, Hubei, Hunan, and Shanghai. The experimental results convincingly demonstrate that the proposed model provides a highly accurate solution for carbon emission prediction tasks, effectively addressing the limitations posed by limited training data.