Charging Pile Siting Recommendations via the Fusion of Points of Interest and Vehicle Trajectories

By mining of the requirements of lots of electric vehicle users for charging piles, this paper proposes the charging pile siting algorithm via the fusion of Points of Interest and vehicle trajectories. The proposed algorithm computes appropriate charging pile locations by: 1) mining user Points of Interest from social network; 2) mining parking sites of vehicle form GPS trajectories and 3) fusing the Points of Interest and parking sites together then clustering the fusions with our improved DBSCAN algorithm, whose clustering results indicates the final appropriate charging pile locations. Experimental results show that our proposed methods are more efficient than existing methods.

Exploiting Geo-Social Correlations to Improve Pairwise Ranking for Point-of-Interest Recommendation

Recently, as location-based social network(LBSN) rapidly grow, point-of-interest(POI) recommendation has become an important way to help people locate interesting places. Nowadays, there have been deep studies conducted on the geographical and social influence in the point-of-interest recommendation model based on the rating prediction. The fact is, however, relying solely on the rating fails to reflect the user's preferences very accurately, because the users are most concerned with the list of ranked point-of-interests(POIs) on the actual output of recommender systems. In this paper, we propose a co-pairwise ranking model called Geo-Social Bayesian Personalized Ranking model(GSBPR), which is based on the pairwise ranking with the exploiting geo-social correlations by incorporating the method of ranking learning into the process of POI recommendation. In this model, we develop a novel BPR pairwise ranking assumption by injecting users' geo-social preference. Based on this assumption, the POI recommendation model is reformulated by a three-level joint pairwise ranking model. And the experimental results based on real datasets show that the proposed method in this paper enjoys better recommendation performance compared to other state-of-the-art POI recommendation models.

结合载客热点和POI的出租车停车位划定方法

针对出租车随意停靠造成城市交通拥堵甚至交通事故的问题,利用成都实际区域的出租车GPS(Global Position System)数据和爬取的POI(Point of Interest)数据,使用DBSCAN(Density-Based Spatial Clustering of Application with Noise)聚类算法对上下客点进行聚类,得到出租车的载客热点,根据POI的类型划定载客热点区域的类型,对出租车不同时间的出行需求进行分析,进而划分出出租车的固定停车区域。研究结果表明,出租车固定停车区域的设定与出行者的出行需求有关,即将固定停车区域设置在出行者出行需求多的区域,可以满足出行者的不同出行需求。结合出租车载客热点和爬取POI数据划定固定停车区域的方法具有较高的实用性,可为城市交通安全方面提供理论和现实意义。

Analysis of the effect of repeated-pulse transcranial magnetic stimulation at the Guangming point on electroencephalograms

Here, we administered repeated-pulse transcranial magnetic stimulation to healthy people at the left Guangming （GB37） and a mock point, and calculated the sample entropy of electroencephalo- gram signals using nonlinear dynamics. Additionally, we compared electroencephalogram sample entropy of signals in response to visual stimulation before, during, and after repeated-pulse tran- scranial magnetic stimulation at the Guangming. Results showed that electroencephalogram sample entropy at left （F3） and right （FP2） frontal electrodes were significantly different depending on where the magnetic stimulation was administered. Additionally, compared with the mock point, electroencephalogram sample entropy was higher after stimulating the Guangming point. When visual stimulation at Guangming was given before repeated-pulse transcranial magnetic stimula- tion, significant differences in sample entropy were found at five electrodes （C3, Cz, C4, P3, T8） in parietal cortex, the central gyrus, and the right temporal region compared with when it was given after repeated-pulse transcranial magnetic stimulation, indicating that repeated-pulse transcranial magnetic stimulation at Guangming can affect visual function. Analysis of electroencephalogram revealed that when visual stimulation preceded repeated pulse transcranial magnetic stimulation, sample entropy values were higher at the C3, C4, and P3 electrodes and lower at the Cz and T8 electrodes than visual stimulation followed preceded repeated pulse transcranial magnetic stimula- tion. The findings indicate that repeated-pulse transcranial magnetic stimulation at the Guangming evokes different patterns of electroencephalogram signals than repeated-pulse transcranial mag- netic stimulation at other nearby points on the body surface, and that repeated-pulse transcranial magnetic stimulation at the Guangrning is associated with changes in the complexity of visually evoked electroencephalogram signals in parietal regions, central gyrus, and temporal regions.

Interest Points Analysis for Internet Forum Based on Long-Short Windows Similarity

For Internet forum Points of Interest(PoI),existing analysis methods are usually lack of usability analysis under different conditions and ignore the long-term variation,which lead to blindness in method selection.To address this problem,this paper proposed a PoI variation prediction framework based on similarity analysis between long and short windows.Based on the framework,this paper presented 5 PoI analysis algorithms which can be categorized into 2 types,i.e.,the traditional sequence analysis methods such as autoregressive integrated moving average model(ARIMA),support vector regressor(SVR),and the deep learning methods such as convolutional neural network(CNN),long-short term memory network(LSTM),Transformer(TRM).Specifically,this paper firstly divides observed data into long and short windows,and extracts key words as PoI of each window.Then,the PoI similarities between long and short windows are calculated for training and prediction.Finally,series of experiments is conducted based on real Internet forum datasets.The results show that,all the 5 algorithms could predict PoI variations well,which indicate effectiveness of the proposed framework.When the length of long window is small,traditional methods perform better,and SVR is the best.On the contrary,the deep learning methods show superiority,and LSTM performs best.The results could provide beneficial references for PoI variation analysis and prediction algorithms selection under different parameter configurations.

POI推荐中的多源数据融合和隐私保护方法

随着移动定位技术的发展,兴趣点(point-of-interest,POI)推荐技术已经成为推荐领域中的研究热点之一。受限于用户的签到能力,POI推荐中存在严重的数据稀疏问题,而融合多源数据的POI推荐又面临着多重隐私挑战。涉及多来源的数据具有多样性、多元性等隐私特征,隐私泄漏机理更为复杂多样,其隐私保护问题更具挑战性。为此,本文提出一种基于注意力机制和隐私保护的多源POI推荐——MultiAM&PP_POI,能够在保护隐私的前提下有效提高POI推荐的精度。为了实现数据的有效融合,本文采用LDA主题模型提取用户在不同领域中的潜在特征,并利用注意力机制来自适应地训练,学习不同领域的潜在特征对POI推荐结果的影响,同时利用多层感知器来实现不同领域潜在特征的迁移。针对多源POI推荐中的隐私问题,本文利用联邦学习框架将原始数据保存在本地,各参与方只需交互加密后的潜在特征,并改进了注意力机制和多层感知器,使其可在密文状态下完成训练,以保护用户隐私的安全。最后通过实验验证,本文模型能够在保护用户隐私前提下,相比单源联邦模型和其他跨域模型,在推荐精度方面分别提升3.05和4.42个百分点。

Partition-based Collaborative Tensor Factorization for POI Recommendation

The rapid development of location-based social networks(LBSNs) provides people with an opportunity of better understanding their mobility behavior which enables them to decide their next location.For example,it can help travelers to choose where to go next,or recommend salesmen the most potential places to deliver advertisements or sell products.In this paper,a method for recommending points of interest(POIs)is proposed based on a collaborative tensor factorization(CTF)technique.Firstly,a generalized objective function is constructed for collaboratively factorizing a tensor with several feature matrices.Secondly,a 3-mode tensor is used to model all users' check-in behaviors,and three feature matrices are extracted to characterize the time distribution,category distribution and POI correlation,respectively.Thirdly,each user's preference to a POI at a specific time can be estimated by using CTF.In order to further improve the recommendation accuracy,PCTF(Partitionbased CTF) is proposed to fill the missing entries of a tensor after clustering its every mode.Experiments on a real checkin database show that the proposed method can provide more accurate location recommendation.

基于设施POI大数据的老幼友好评估体系构建及应用

兼顾老幼友好,是回应中国社会老龄化与少子化现实的关键之道。以大数据技术赋能老幼友好评估是破解当下建设过程中理论与实践困境的有效手段。文章在分析老幼友好概念与相关设施分布内在关联的基础上,凭借空间地理统计方法与设施兴趣点(Point of Interest,简称“POI”)大数据,依据累计机会算法形成了兼顾空间可及性与时间简捷性的评估指标体系,进而对天津市进行核密度分析、标准差椭圆分析、空间相关性分析等宏观空间统计与基于POI数据的老幼友好评估,发现天津市老幼友好设施在主体层面耦合水平较高,在服务供给层面存在地理分异。其中,“市内六区”老幼友好建设发展迅猛,“环城四区”与“远郊五区”有待提升,滨海新区老幼友好建设水平突出。为此,可借鉴滨海新区经验,从宏观规划、中观方案、微观技术三个维度提升城市老幼友好建设水平。

Research on Spatial Pattern and Its Industrial Distribution of Commercial Space in Mianyang Based on POI Data

The rational layout of urban commercial space is conducive to optimizing the allocation of commercial resources in the urban interior space. Based on the commercial POI (Point of Interest) data in the central district of Mianyang, the characteristics of urban commercial spatial pattern under different scales are analyzed by using Kernel Density Estimation, Getis-Ord , Ripley’s K Function and Location Entropy method, and the spatial agglomeration characteristics of various industries in urban commerce are studied. The results show that: 1) The spatial distribution characteristics of commercial outlets in downtown Mianyang are remarkable, and show a multi-center distribution pattern. The hot area distribution of commercial outlets based on road grid unit is generally consistent with the identified commercial density center distribution. 2) The commercial grade scale structure has been formed in the central urban area as a whole, and the distribution of commercial network hot spots based on road grid unit is generally consistent with the identified commercial density center distribution. 3) From the perspective of commercial industry, the differentiation of urban commercial space “center-periphery” is obvious, and different industries show different spatial agglomeration modes. 4) The multi-scale spatial agglomeration of each industry is different, the spatial scale of location choice of comprehensive retail, household appliances and other industries is larger, and the scale of location choice of textile, clothing, culture and sports is small. 5) There are significant differences in specialized functional areas from the perspective of industry. Mature areas show multi-functional elements, multi-advantage industry agglomeration characteristics, and a small number of developing areas also show multi-advantage industry agglomeration characteristics.

Development of a Best Answer Recommendation Model in a Community Question Answering (CQA) System

In this work, a best answer recommendation model is proposed for a Question Answering (QA) system. A Community Question Answering System was subsequently developed based on the model. The system applies Brouwer Fixed Point Theorem to prove the existence of the desired voter scoring function and Normalized Google Distance (NGD) to show closeness between words before an answer is suggested to users. Answers are ranked according to their Fixed-Point Score (FPS) for each question. Thereafter, the highest scored answer is chosen as the FPS Best Answer (BA). For each question asked by user, the system applies NGD to check if similar or related questions with the best answer had been asked and stored in the database. When similar or related questions with the best answer are not found in the database, Brouwer Fixed point is used to calculate the best answer from the pool of answers on a question then the best answer is stored in the NGD data-table for recommendation purpose. The system was implemented using PHP scripting language, MySQL for database management, JQuery, and Apache. The system was evaluated using standard metrics: Reciprocal Rank, Mean Reciprocal Rank (MRR) and Discounted Cumulative Gain (DCG). The system eliminated longer waiting time faced by askers in a community question answering system. The developed system can be used for research and learning purposes.

自注意力下时空-语义相融合的POI序列推荐

近年来,随着基于位置的社交网络(Location-Based Social Network, LBSN)不断发展,POI序列推荐逐渐成为近年来研究的热点问题.现有的POI序列推荐方法仅仅按照时间的先后顺序建模用户历史签到序列,默认用户POI轨迹中连续POI之间具有相等的时间间隔,忽略了用户签到记录之间的时间间隔影响.另外,POI之间的地理距离以及语义信息也是影响推荐准确性的重要因素.基于此,本文提出自注意力下时空-语义相融合的POI序列推荐模型(POI sequence recommendation model based on the integration of spatiotemporal and semantics under self-attention, SA-TDS-PRec).首先,根据用户的实际签到时间建模POI轨迹.其次,融合POI绝对位置、时空间隔以及语义相关信息.最后利用自注意力机制捕捉用户动态偏好的演化,从而提高POI推荐的准确性.在公开数据集Gowalla和Yelp上进行可扩展实验.结果表明,该模型优于目前主流的基准模型,有效提升推荐结果准确性.

An Entropy-Based Model for Recommendation of Taxis’Cruising Route

Cruising route recommendation based on trajectory mining can improve taxi-drivers'income and reduce energy consumption.However,existing methods mostly recommend pick-up points for taxis only.Moreover,their performance is not good enough since there lacks a good evaluation model for the pick-up points.Therefore,we propose an entropy-based model for recommendation of taxis'cruising route.Firstly,we select more positional attributes from historical pick-up points in order to obtain accurate spatial-temporal features.Secondly,the information entropy of spatial-temporal features is integrated in the evaluation model.Then it is applied for getting the next pick-up points and further recommending a series of successive points.These points are constructed a cruising route for taxi-drivers.Experimental results show that our method is able to obviously improve the recommendation accuracy of pick-up points,and help taxi-drivers make profitable benefits more than before.

基于空间句法和POI数据的综合性公园可达性研究——以成都市中心城区为例

成都市是“公园城市”首提地和示范区,科学评估其综合性公园可达性,对成都优化公园空间布局,建设美丽宜居公园城市具有重要意义。本文以成都市中心城区23个综合性公园作为研究对象,利用空间句法和ArcGIS软件建立线段模型,并利用POI(point of interest)数据对比分析与模型校验,从全局可达性、局部可达性和感知可达性3个方面对成都市中心城区综合性公园的空间分布特征和可达性进行研究。结果表明:成都市中心城区综合性公园分布不均衡,POI高值区域综合性公园分布偏少,与城市居民需求匹配性偏弱;城市道路交通网络有待完善,区域发展不够协调;公园全局、局部可达性总体水平较高,大部分公园分布于可达性高值区域,部分公园自身缺乏一定的吸引力,感知可达性一般。影响公园可达性的因素包括空间路网结构、公园空间分布、自然和人文环境等多方面,在此基础上提出合理布局和增设综合性公园;优化城市道路交通网络;增设公交站台、地铁站点;融合成都独特的山水文化和历史文化以提升景观吸引力等建议。

基于混合图神经网络的个性化POI推荐方法研究

随着基于位置的社交网络的快速发展,POI(Point of Interest)推荐已成为推荐领域的研究热点,然而已有的工作未能充分挖掘用户的POI交互偏好以及POI转移偏好,影响了POI推荐效果.提出一种基于混合图神经网络的个性化POI推荐方法.首先构建用户社交网络图,利用图注意力网络(Graph Attention Networks,GAT)学习含有社交关系的用户特征;其次,构建用户与POI的标号交互二部图,基于标号二部图神经网络(Signed Bipartite Graph Neural Networks,SBGNN)学习含有用户POI交互偏好的用户特征与POI特征;构建POI有向转移图,基于会话图神经网络(SessionBased Recommendation with Graph Neural Networks,SRGNN)学习含有用户POI转移偏好的POI特征;之后,融合含有社交关系的用户特征与含有POI交互偏好信息的用户特征得到最终的用户特征表示,融合含有用户POI交互偏好的POI特征与含有用户POI转移偏好的POI特征,得到最终的POI特征表示;最后,将用户特征表示与POI特征表示做乘积操作,通过Sigmoid函数得到用户对每个POI的预测评分,并以此向用户推荐Top-K POI序列.基于三个公共数据集(Gowalla,Foursquare和Yelp)开展了大量的实验,结果表明,与七种基线模型的推荐效果相比,提出的方法的准确率和召回率分别平均提升19.95%和1.35%.

Improving POI Recommendation via Non-Convex Regularized Tensor Completion

The problem of low accuracy of POI(Points of Interest)recommendation in LBSN(Location-Based Social Networks)has not been effectively solved.In this paper,a POI recommendation algorithm based on non-convex regularized tensor completion is proposed.The fourth-order tensor is constructed by using the current location category,the next location category,time and season,the regularizer is added to the objective function of tensor completion to prevent over-fitting and reduce the error of the model.The proximal algorithm is used to solve the objective function,and the adaptive momentum is introduced to improve the efficiency of the solution.The experimental results show that the algorithm can improve recommendation accuracy while reducing the time cost.

基于POI数据的社区生活圈体育服务设施空间分异

基于兴趣点(POI)数据与ArcGIS软件方法,划定福建省5 336个社区生活圈公里格网,构建社区生活圈体育服务设施分类指标体系,测算分析区域与市域的社区生活圈体育服务设施空间分异。结果表明:闽东北匹配协同程度总体高于闽西南,福州市和厦门市分别贡献主要力量;两大协同发展区内部呈现多组团、高值集聚、低值分散的状态;闽东北高值聚类多于低值聚类;社区生活圈体育服务设施均等化水平为闽东北>闽西南,并可按照厦门-莆田-福州、漳州-泉州-南平、龙岩-宁德-三明划分出高、中、低三个等级。

On the relationship between the activity at point of interests and road traffic

The estimation and analysis of road traffic represent the preliminary steps towards satisfying the current needs for smooth,safe,and green transportation.Therefore,effective traffic monitoring is an essential topic alongside the planning of sustainable transportation systems and the development of new traffic management concepts.In contrast to classical traffic detection solutions,this study investigates the correlation between travelers'social activities and road traffic.The s's primary goal is to investigate the presence of the relationship between social activity and road traffic,which might allow an infrastructure-independent traffic monitoring technique as well.People's general activities at Point of Interest(POI)locations(measured as occupancy parameter)are correlated with traffic data so that,finally,proper proxys can be defined for link-level average traffic speed estimation.The method is tested and evaluated using real-world traffic and POI occupancy data from Budapest(District XI.).The results of the correlation investigation justify an indirect relationship between activity at POIs and road traffic,which holds promise for future practical applicability.

时空邻域感知的时序兴趣点推荐

如何捕捉用户行为的动态变化和依赖关系是当前兴趣点推荐的一个重要问题,主要面临着数据稀疏、时空序列特征提取难以及用户个性化差异不易捕捉等挑战。为了解决这些挑战,提出了一种基于时空邻域感知及隐含状态变化的时序兴趣点推荐方法。该方法将用户行为的学习转换成了潜在状态的学习,并以一种结合距离信息的方式引入空间信息,有效地捕捉了用户的移动特征。首先,利用变分自编码器表征用户的潜在状态,再通过图神经网络学习到潜在状态之间的依赖关系,从而捕捉到用户行为的时序依赖;然后,利用注意力机制和径向基函数来捕捉用户与地点候选集之间的空间依赖,进而评估用户访问每个地点的概率,实现兴趣点推荐。在三个真实数据集上进行了实验比较和分析,显示了该方法相比于现有的基准算法具有更好的时序推荐性能。

基于用户偏好的多媒体视频个性化智能推荐方法研究

为了满足用户个性化需求,提出基于用户偏好的多媒体视频个性化智能推荐方法。采集用户历史浏览行为数据,对提取的视频特征向量作相似度计算,生成视频候选集,建立视频浏览兴趣点(PoI)关联图,根据用户浏览时间计算其对不同类别视频PoI的兴趣偏好度,选择排名靠前的N个视频生成推荐列表,实现多媒体视频个性化智能推荐。实验结果表明,该方法可实现多媒体视频个性化推荐,当其维度为180时,视频推荐的Top-1指标最高;兴趣吻合度指标均值达到94.9%,Top-1均值为95.51%。