论文部分内容阅读
在交通领域,研究分析旅客的出行目的地会产生很多商业价值。针对旅客出行目的地的不确定性造成研究困难的问题,现有方法利用熵衡量移动的不确定性来描述个体的出行特性,并同时考虑个体轨迹的时空相关性,并不能达到理想的预测精度,因此,提出了基于改进马尔可夫链的航线预测算法来对旅客的出行目的地进行预测。首先对旅客历史出行的距离分布、地点分布和时间规律特性进行了分析;然后又分析了人类移动对历史行为和当前地点的依赖性;最后将旅客的常住地特性和新航线的探索概率加入到转移矩阵的计算中,提出并实现了改进的马尔可夫链航线预测算法,进而对旅客的下一次出行进行预测。实验结果显示,该模型可以达到66.4%的平均预测精度。研究成果可以应用在航空领域的用户出行分析中,使航空公司更好地了解和预测旅客的出行,提供个性化的出行服务。
In the field of transportation, studying and analyzing travelers’ travel destinations has a lot of commercial value. In view of the difficulty of research on the uncertainty of travelers’ travel destinations, the existing methods use entropy to measure the travel uncertainty to describe individual travel characteristics and take into account the spatiotemporal correlation of individual trajectories, and can not achieve the desired prediction accuracy Therefore, a route prediction algorithm based on the improved Markov chain is proposed to predict the travel destination of passengers. First of all, it analyzes the distance distribution, location distribution and time regularity characteristics of the traveler’s historical travel. Secondly, it analyzes the dependence of the human movement on the historical behavior and the current location. Finally, it adds the passenger’s habitat characteristics and the exploration probability of the new route In the calculation of transfer matrix, an improved Markov chain route prediction algorithm is proposed and implemented, which can predict the next trip of passengers. Experimental results show that the model can achieve an average prediction accuracy of 66.4%. The research results can be used in the user travel analysis in the field of aviation to enable airlines to better understand and predict passenger travel and provide personalized travel services.