Search

In this paper, we treat optimization problems as a kind of reinforcement learning problems regarding an optimization procedure for searching an optimal solution as a reinforcement learning procedure for finding the best policy to maximize the expected rewards. This viewpoint motivated us to propose a Q-learning-based swarm optimization (QSO) algorithm. The proposed QSO algorithm is a population-based optimization algorithm which integrates the essential properties of Q-learning and particle swarm optimization. The optimization procedure of the QSO algorithm proceeds as each individual imitates the behavior of the global best one in the swarm. The best individual is chosen based on its accumulated performance instead of its momentary performance at each evaluation. Two data sets including a set of benchmark functions and a real-world problem-the economic dispatch (ED) problem for power systems-were used to test the performance of the proposed QSO algorithm. The simulation results on the benchmark functions show that the proposed QSO algorithm is comparable to or even outperforms several existing optimization algorithms. As for the ED problem, the proposed QSO algorithm has found solutions better than all previously found solutions. [ABSTRACT FROM AUTHOR]

The conventional self-organizing feature map (SOM) algorithm is usually interpreted as a computational model, which can capture main features of computational maps in the brain. In this paper, we present a variant of the SOM algorithm called the SOM-based optimization (SOMO) algorithm. The development of the SOMO algorithm was motivated by exploring the possibility of applying the SOM algorithm in continuous optimization problems. Through the self-organizing process, good solutions to an optimization problem can be simultaneously explored and exploited by the SOMO algorithm. In our opinion, the SOMO algorithm not only can be regarded as a biologically inspired computational model but also may be regarded as a new approach to a model of social influence and social learning. Several simulations are used to illustrate the effectiveness of the proposed optimization algorithm. [ABSTRACT FROM AUTHOR]

Computed tomography-guided radiofrequency ablation (CT-RFA) and laparoscopic RFA (L-RFA) have been used to treat intrahepatic recurrent small hepatocellular carcinoma (HCC) against the diaphragmatic dome. However, the therapeutic safety, efficacy, and hospital fee have never been compared between the two techniques due to scarcity of cases. In this retrospective study, 116 patients were divided into two groups with a total of 151 local recurrent HCC lesions abutting the diaphragm. We compared overall survival (OS), local tumor progression (LTP), postoperative complications, and hospital stay and fee between the two groups. Our findings revealed no significant differences in 5-year OS (36.7% vs. 44.6%, p = 0.4289) or 5-year LTP (73.3% vs. 67.9%, p = 0.8897) between CT-RFA and L-RFA. The overall hospital stay (2.8 days vs. 4.1 days, p < 0.0001) and cost (¥ 19217.6 vs. ¥ 25553.6, p < 0.0001) were significantly lower in the CT-RFA in comparison to that of L-RFA. In addition, we elaborated on the choice of percutaneous puncture paths depending on the locations of the HCC nodules and 11-year experience with CT-RFA. In conclusion, CT-RFA is a relatively easy and economic technique for recurrent small HCC abutting the diaphragm, and both CT-RFA and L-RFA are effective techniques. [ABSTRACT FROM AUTHOR]

Organophosphorus compounds (OP) are stable P source in nature, and can increase eutrophication risk in waterbodies. Lecithin was the most difficult OP to be broken down. In this study, two typical phosphate-solubilizing microorganisms, Aspergillus niger and Acinetobacter sp., were applied to evaluate their ability to decompose both inorganic phosphates and lecithin. A. niger and Acinetobacter sp. could solubilize calcium phosphates by secreting various organic acids, e.g., oxalic and formic acids. The fungus, A. niger, shows significantly higher ability of solubilizing these inorganic phosphates than Acinetobacter sp., primarily due to its secretion of abundant oxalic acid. However, the bacterium, Acinetobacter sp., could secrete more acid phosphatase than A. niger for lecithin decomposition, i.e., 9300 vs. 8500 μmol L−1 h−1. Moreover, after addition of CaCl2, the released P from lecithin was transformed to stable chlorapatite in the medium. To the contrast, Ca cations inclined to form calcium oxalate (rather than stable phosphate mineral) after the incubation of A. niger, as it induced relatively acidic environment after breaking down lecithin. Therefore, this work sheds light on the bright future of applying bacteria and Ca cations in OP pollutant management. [ABSTRACT FROM AUTHOR]