论文部分内容阅读
针对粒子群优化算法精度不高、容易陷入局部最优、难以满足房地产市场形势需求的问题,提出一种改进粒子群优化神经网络,并应用于房地产市场预测中,该算法将混沌引入粒子群优化神经网络算法权重和阈值的初始化与更新的过程,提高了初始样本的质量,减轻了局部极值现象,提高了算法的全局搜索能力,同时设置了躲避因子,使粒子一定程度上离开偏离真实值的区域。研究结果表明,提出的改进算法可以提高粒子群优化神经网络权重和阈值的准确性。
Aiming at the problem that the particle swarm optimization algorithm is not accurate enough, it is easy to fall into the local optimum and it is difficult to meet the needs of the real estate market. An improved particle swarm optimization neural network is proposed and applied to real estate market forecast. The algorithm introduces chaos into particle swarm optimization The initialization and updating of the weights and thresholds of the neural network algorithm improve the quality of the initial sample, reduce the local extremum phenomenon and improve the global search ability of the algorithm, meanwhile, set the avoidance factor so that the particle departs from the true value to some extent Area. The results show that the proposed improved algorithm can improve the accuracy of particle swarm optimization neural network weights and thresholds.