Search

In order to avoid particle swarm optimization algorithm easy to fall into local optimum in solving complex problems, this paper proposed a new adaptive dynamic cultural particle swarm optimization algorithm. It introduced the evaluation of particle swarm premature convergence indicators into population space. By calculating the evaluation of particle swarm premature convergence indicators, decisions whether to have mutated operation on population space. It made the improved algorithm could make better use of mechanism of dual evolution and dual promotion in cultural particle swarm optimization algorithm. It adjusted the inertia weight of the particle adaptively based on the premature convergence degree of the swarm. The diversity of inertia weight made a compromise between the global convergence and convergence speed. It tested the proposed algorithm with four well-known benchmark functions. The experimental results show that the new algorithm has great global search ability convergence accuracy and convergence velocity is also increased and avoid the premature convergence problem effectively. [ABSTRACT FROM AUTHOR]

In hot topics found on micro-blog, because the text of micro-blog is short and less words, and the terms are not standard, so the traditional hot topic detection method can not find hot topics effectively. In order to solve this problem, this paper presented a method of hot topics found based on speed growth. Firstly, it divided the pretreated micro-blogs on the basis of the equal number of window, and added up the term frequency in each window, and expressed as feature trajectory of binary group sequence. Secondly, it calculated the growth slope of every adjacent two windows to find the words with growth speed. Thirdly, it calculated the growth speed of the word's relevant users and the growth speed of the word's relevant micro-blogs to ensure the word was hot subject or not. Finally, it found hot topics through the hot subject clustering. The experimental proves the feasibility of the algorithm, results show that the method improves the efficiency of the detection to a certain extent, and reduces the undetected rate and false detection rate, it can effectively discover hot topics on micro-blog in time. [ABSTRACT FROM AUTHOR]