Predicting Forest Cover Types with Immune and Genetic

摘要：

　　Vegetation prediction is a vibrant research area.Researchers have approached this problem using various techniques such as support vector machine,artificial neural network,and etc.In order to enhance the predicting accuracy,a novel method with immune and genetic to predict vegetation types,is presented.Based on immune genetic theory,the algorithm has two indexes: affinity and fitness,which was as the basis of antibody cloning to select the next generation.The more similarity of the structure among the artificial immune cells,the greater their affinity is?? and the fitness calculation makes the population dynamic evolution for better,is good for the convergence of the antibody population.The algorithm has a better diversity,robustness,self-learning and adaptive capacity.It will provide a new solution for vegetation prediction.Experimental results of simulation demonstrate that this method has higher predicting accuracy than other methods for the same dataset.The algorithm is a better recognition solution for vegetation types.

关键词： forest cover types prediction artificial immune genetic algorithm machine learning

作者: Shaojin Feng

作者单位: School of Information Guangdong Ocean University, GDOU Zhanjiang, China

会议类型: 国际会议

会议名称: 2012 IEEE 14th International Conference on Communication Technology(2012年第十四届通信技术国际会议(ICCT 2012))

会议地点: 成都

会议语种:英文

页码: 1035-1039

在线出版日期: 2012-11-09（万方平台首次上网日期，不代表论文的发表时间）