The Chinese Journal of Artificial Intelligence - Current Issue

Background: Reading every clinical trial for any disease is tedious, as is determining the current progress, especially when the number of clinical trials is huge. The Text Mining Platform of Artificial Intelligence (AI) can help to simplify the task.

Methods: A large pool of tuberculosis clinical trials has been searched through the International Clinical Trial Registry Platform (ICTRP) and used as a textual dataset. The exported dataset of 1635 clinical studies, in a comma-separated format, is preprocessed for data analysis and text mining. Data preparation, corpus generation, text preprocessing, and finally, cluster analysis were carried out using the text-mining widget of the open-source machine learning tool. The hierarchical cluster analysis was used for mapping research interests in tuberculosis clinical trials.

Conclusion: The data mining of the exported dataset of tuberculosis clinical trials uncovered interesting facts in terms of numbers. Text mining presented a total of 41 hierarchical clusters that were further mapped in twenty-five (25) different research interests among tuberculosis clinical trials. A novel technique for the rapid and practical review of major clinical trials is demonstrated. As an open-source and GUI-based tool is used for work, any researcher with working knowledge of text mining may also use this technique for other clinical trials.

Aims: The main goal of this paper is to address the issues of low-quality offspring solutions generated by traditional evolutionary operators, as well as the evolutionary algorithm's inability to solve multi-objective optimization problems (MOPs) with complicated Pareto fronts (PFs).

Background: For some complicated multi-objective optimization problems, the effect of the multi-objective evolutionary algorithm based on decomposition (MOEA/D) is poor. For specific complicated problems, there is less research on how to improve the performance of the algorithm by setting and adjusting the direction vector in the decomposition-based evolutionary algorithm. Considering that in the existing algorithms, the optimal solutions are selected according to the selection strategy in the selection stage, without considering whether it could produce the better solutions in the stage of individual generation to achieve the optimization effect faster. As a result, a multi-objective evolutionary algorithm based on two reference points decomposition and historical information prediction is proposed.

Objective: In order to verify the feasibility of the proposed strategy, the F-series test function with complicated PFs is used as the test function to simulate the proposed strategy.

Methods: Firstly, the evolutionary operator based on historical information prediction (EHIP) is used to generate better offspring solutions to improve the convergence of the algorithm; secondly, the decomposition strategy based on ideal point and nadir point is used to select solutions to solve the MOPs with complicated PFs, and the decomposition method with augmentation term is used to improve the population diversity when selecting solutions according to the nadir point. Finally, the proposed algorithm is compared to several popular algorithms by the F-series test function, and the comparison is made according to the corresponding performance metrics.

Results: The performance of the algorithm is improved obviously compared with the popular algorithms after using the EHIP. When the decomposition method with augmentation term is added, the performance of the proposed algorithm is better than the algorithm with only the EHIP on the whole, but the overall performance is better than the popular algorithms.

Conclusion: The experimental results show that the overall performance of the proposed algorithm is superior to the popular algorithms. The EHIP can produce better quality offspring solutions, and the decomposition strategy based on two reference points can well solve the MOPs with complicated PFs. This paper mainly demonstrates the theory without testing the practical problems. The following research mainly focuses on the application of the proposed algorithm to practical problems such as robot path planning.

Aims: The main purpose of this paper is to achieve good convergence and distribution in different Pareto fronts.

Background: Research in recent decades has shown that evolutionary multi-objective optimization can effectively solve multi-objective optimization problems with no more than 3 targets. However, when solving MaOPs, the traditional evolutionary multi-objective optimization algorithm is difficult to effectively balance convergence and diversity. In order to solve these problems, many algorithms have emerged, which can be roughly divided into the following three types: decomposition-based, index-based, and dominance relationship-based. In addition, there are many algorithms that introduce the idea of clustering into the environment. However, there are some disadvantages to solving different types of MaOPs. In order to take advantage of the above algorithms, this paper proposes a many-objective optimization algorithm based on two-phase evolutionary selection.

Objective: In order to verify the comprehensive performance of the algorithm on the testing problem of different Pareto front, 18 examples of regular PF problems and irregular PF problems are used to test the performance of the algorithm proposed in this paper.

Method: This paper proposes a two-phase evolutionary selection strategy. The evolution process is divided into two phases to select individuals with good quality. In the first phase, the convergence area is constructed by indicators to accelerate the convergence of the algorithm. In the second phase, the parallel distance is used to map the individuals to the hyperplane, and the individuals are clustered according to the distance on the hyperplane, and then the smallest fitness in each category is selected.

Result: For regular Pareto front testing problems, MaOEA/TPS performed better than RVEA, PREA, CAMOEA and One by one EA in 19, 21, 30, 26 cases, respectively, while it was only outperformed by RVEA, PREA, CAMOEA and One by one EA in 8, 5, 1, and 6 cases. For the irregular front testing problem, MaOEA/TPS performed better than RVEA, PREA, CAMOEA and One by one EA in 20, 17, 25, and 21 cases, respectively, while it was only outperformed by RVEA, PREA, CAMOEA and One by one EA in 6, 8, 1, and 6 cases.

Conclusion: The paper proposes a many-objective evolutionary algorithm based on two phase selection, termed MaOEA/TPS, for solving MaOPs with different shapes of Pareto fronts. The results show that MaOEA/TPS has quite a competitive performance compared with the several algorithms on most test problems.

Other: Although the algorithm in this paper has achieved good results, the optimization problem in the real environment is more difficult, therefore, applying the algorithm proposed in this paper to real problems will be the next research direction.

Aims: This paper proposes a differential evolution algorithm to solve the multi-objective sparse reconstruction problem (DEMOSR).

Background: The traditional method is to introduce the regularization coefficient and solve this problem through a regularization framework. But in fact, the sparse reconstruction problem can be regarded as a multi-objective optimization problem about sparsity and measurement error (two contradictory objectives).

Objective: A differential evolution algorithm to solve multi-objective sparse reconstruction problem (DEMOSR) in sparse signal reconstruction and the practical application.

Methods: First of all, new individuals are generated through tournament selection mechanism and differential evolution. Secondly, the iterative half thresholding algorithm is used for local search to increase the sparsity of the solution. To increase the diversity of solutions, a polynomial mutation strategy is introduced.

Results: In sparse signal reconstruction, the performance of DEMOSR is better than MOEA/D-ihalf and StEMO. In addition, it can verify the effectiveness of DEMOSR in practical applications for sparse reconstruction of magnetic resonance images.

Conclusion: According to the experimental results of DEMOSR in sparse signal reconstruction and the practical application of reconstructing magnetic resonance images, it can be proved that DEMOSR is effective in sparse signal and image reconstruction.

Aim: The aim of this study is to perform short-term load forecasting.

Background: Short-term load forecasting plays a key role in power dispatching. It provides basic data for basic power generation planning and system safety analysis so that the power dispatching work is more practical and the power generation efficiency is higher.

Objective: The aim of this study is to ensure the safe operation of the electricity market and relieve the pressure of supply and demand.

Methods: In this paper, the SVR model is used for short-term load prediction.

Results: The SVR model has the advantage of minimizing the structural risk and has good generalization performance for the predicted object. At the same time, the global optimization is ensured, a lot of mapping calculation is reduced, the actual risk is reduced, and the prediction performance is improved.

Conclusion: The target model has higher forecasting accuracy than other forecasting models and can effectively solve the problems of the power market.

Background: The Particle Swarm Optimization (PSO) algorithm is amongst the utmost favourable optimization algorithms often employed in hybrid procedures by the researchers considering simplicity, smaller count of parameters involved, convergence speed, and capability of searching global optima. The PSO algorithm acquires memory, and the collaborative swarm interactions enhances the search procedure. The high exploitation ability of PSO, which intends to locate the best solution within a limited region of the search domain, gives PSO an edge over other optimization algorithms. Whereas, low exploration ability results in a lack of assurance of proper sampling of the search domain and thus enhances the chances of rejecting a domain containing high quality solutions. Perfect harmony between exploration and exploitation abilities in the course of selection of the best solution is needed. High exploitation capacity makes PSO trapped in local minima when its initial location is far off from the global minima.

Objectives: The intent of this study is to reform this drawback of PSO of getting trapped in local minima. To upgrade the potential of Particle Swarm Optimization (PSO) to exploit and prevent PSO from getting trapped in local minima, we require an algorithm with a positive acceptable exploration capacity.

Methods: We utilized the recently developed metaheuristic Grey Wolf Optimizer (GWO), emulating the seeking and hunting techniques of Grey wolves for this purpose. In our way, the GWO has been utilized to assist PSO in a manner to unite their strengths and lessen their weaknesses. The proposed hybrid has two driving parameters to adjust and assign the preference to PSO or GWO.

Results: To test the activity of the proposed hybrid, it has been examined in comparison with the PSO and GWO methods. For this, eleven benchmark functions involving different unimodal and multimodal functions have been taken. The PSO, GWO, and SGWO pseudo codes were coded in visual basic. All the functional parameters of PSO and GWO were chosen as: w = 0.7, c1 = c2 = 2, population size = 30, number of iterations = 30. Experiments were redone 25 times for each of the methods and for each benchmark function. The methods were compared with regard to their best and worst values besides their average values and standard deviations. The obtained results revealed that in terms of average values and standard deviations, our hybrid SGWO outperformed both PSO and GWO notably.

Conclusion: The outcomes of the experiments reveal that the proposed hybrid is better in comparison to both PSO and GWO in the searchability. Though the SGWO algorithm refines result quality, the computational complexity also gets elevated. Thus, lowering the computational complexity would be another issue of future work. Moreover, we will apply the proposed hybrid in the field of water quality estimation and prediction.

Aims: Different chaotic APSO-based algorithms are developed to deal with high non-linear optimization problems. Then, considering the difficulty of the problem, an adaptation of these algorithms is presented to enhance the algorithm.

Background: Particle swarm optimization (PSO) is a population-based stochastic optimization technique suitable for global optimization with no need for direct evaluation of gradients. The method mimics the social behavior of flocks of birds and swarms of insects and satisfies the five axioms of swarm intelligence, namely proximity, quality, diverse response, stability, and adaptability. There are some advantages to using the PSO consisting of easy implementation and a smaller number of parameters to be adjusted; however, it is known that the original PSO had difficulties in controlling the balance between exploration and exploitation. In order to improve this character of the PSO, recently, an improved PSO algorithm, called the accelerated PSO (APSO), was proposed, and preliminary studies show that the APSO can perform superiorly.

Objective: This paper presents several chaos-enhanced accelerated particle swarm optimization methods for high non-linear optimization problems.

Methods: Some modifications to the APSO-based algorithms are performed to enhance their performance. Then, the algorithms are employed to find the optimal parameters of the various types of hysteretic Bouc-Wen models. The problems are solved by the standard PSO, APSO, different CAPSO, and adaptive CAPSO, and the results provide the most useful method. The sub-optimization mechanism is added to these methods to enhance the performance of the algorithm.

Results: Seven different chaotic maps have been investigated to tune the main parameter of the APSO. The main advantage of the CAPSO is that there is a fewer number of parameters compared with other PSO variants. In CAPSO, there is only one parameter to be tuned using chaos theory.

Conclusion: To adapt the new algorithm for susceptible parameter identification algorithm, two series of Bouc-Wen model parameters containing standard and modified Bouc-Wen models are used. Performances are assessed on the basis of the best fitness values and the statistical results of the new approaches from 20 runs with different seeds. Simulation results show that the CAPSO method with Gauss/mouse, Liebovitch, Tent, and Sinusoidal maps performs satisfactorily.