A New Point-of-Interest Classification Model with an Extreme Learning Machine
A New Point-of-Interest Classification Model with an Extreme Learning Machine
复制标题
具有极限学习机的新兴趣点分类模型
DOI：
10.1007/s12559-018-9599-0
复制
发表时间：
2018-10
影响因子：
5.4
通讯作者：
Xin Bi
中科院分区：
文献类型：
--
作者：
Zhen Zhang;Xiangguo Zhao;Guoren Wang;Xin Bi
随着基于位置的社交网络（LBSN）的日益普及，越来越多的人通过签到活动与朋友分享他们的位置。兴趣点推荐是LBSNs的重要任务之一，它向用户推荐新的地点。然而，在推荐之后，还感兴趣的是考虑用户是否将频繁地访问所推荐的POI，这可能对用户的日常移动行为或个人偏好具有重大影响。因此，在本文中，我们提出了一个新的POI分类问题，其中推荐给用户的POI被分为四类，根据用户的预测未来的签到频率：每日签到POI，每周签到POI，每月签到POI，每年签到POI。为了解决这个问题，我们还提出了一个新的POI分类模型POIC-ELM。在POIC-ELM模型中，我们首先提取与三个因素相关的九个特征：每个POI本身，用户的个性和用户的社会关系。然后，我们使用这些特征来训练基于极端学习机（ELM）的POI分类器，极端学习机是最先进的分类技术中最流行的分类器类型之一。一系列实验表明，POIC-ELM的有效性和效率优于其他方法的上级。POIC-ELM模型是解决兴趣点分类问题的有效方法。
With the increasing popularity of location-based social networks (LBSNs), an increasing number of people are sharing their locations with friends through check-in activities. Point-of-interest (POI) recommendation, in which new places are suggested to users, is one of the most important tasks in LBSNs. However, after recommendation, it is also of interest to consider whether a user will frequently visit a recommended POI, which may have significant implications regarding the user’s daily mobility behavior or personal preferences. Therefore, in this paper, we propose a new POI classification problem in which the POIs recommended to a user are divided into four classes according to the user’s predicted future check-in frequency: daily check-in POIs, weekly check-in POIs, monthly check-in POIs, and yearly check-in POIs. To solve this POI classification problem, we also propose a new POI classification model called POIC-ELM. In the POIC-ELM model, we first extract nine features related to three factors: each POI itself, the user’s personality, and the user’s social relationships. Then, we use these features to train a POI classifier based on an extreme learning machine (ELM), which is one of the most popular types of classifiers among state-of-the-art classification techniques. A series of experiments show that the effectiveness and efficiency of POIC-ELM are superior to those of other methods. The POIC-ELM model is a valid method for solving the POI classification problem.
登录
查看更多内容
影响因子：
6
作者：
Zhang Xiekai;Ding Shifei;Xue Yu
通讯作者：
Xue Yu
DOI：
10.1145/3041021.3051145
发表时间：
2017-04
期刊：
Proceedings of the 26th International Conference on World Wide Web Companion
影响因子：
--
作者：
Ammar Sohail;D. Taniar;Andreas Züfle;Jeong-Ho Park
通讯作者：
Ammar Sohail;D. Taniar;Andreas Züfle;Jeong-Ho Park
影响因子：
11.8
作者：
Xiaoxuan Lu;Han Zou;Hongming Zhou;Lihua Xie;G. Huang
通讯作者：
Xiaoxuan Lu;Han Zou;Hongming Zhou;Lihua Xie;G. Huang
影响因子：
10.6
作者：
Yisong Chen;Antoni B. Chan
通讯作者：
Yisong Chen;Antoni B. Chan
DOI：
10.1109/icde.2017.135
发表时间：
2017-04
期刊：
2017 IEEE 33rd International Conference on Data Engineering (ICDE)
影响因子：
--
作者：
Yurong Cheng;Ye Yuan;Lei Chen;C. Giraud-Carrier;Guoren Wang
通讯作者：
Yurong Cheng;Ye Yuan;Lei Chen;C. Giraud-Carrier;Guoren Wang