In contemporary urban management, the rapid advancement of technology and widespread use of location-based services provide critical insights, particularly in traffic planning. Analyzing urban spatiotemporal trajectory data reveals diverse perspectives that inform effective city management. This paper focuses on extracting insights from spatiotemporal trajectories and introduces a suite of urban data mining techniques applicable across scenarios, including points of interest diversification. The framework aids in understanding city dynamics, including the distribution and activities of individuals. The method begins by constructing spatiotemporal stay information through two processes: stay point and stay area extraction. Spatiotemporal semantic trajectory data is then integrated with Points of Interest (POI) semantic details. A novel clustering method based on network community detection is proposed. Our experiments show that the method not only achieves comparable or superior results but also ensures time efficiency, aligning with the demands of the big data era. © 2025 IEEE.

Background: The Central China Rise Strategy is one of China’s important regional development strategies, and it has been officially implemented since 2006. Despite the obvious economic development resulting from the strategy, its impact on the environment remains unclear. Objective: Previous studies have focused more on the economic benefits of the Central China Rise Strategy while ignoring its environmental impact. This paper focuses on the environmental benefits and aims to promote the coordinated development between the economy and the environment. Methods: Panel data of 30 Chinese provinces from 2000 to 2017 were selected to construct a propensity score matching-difference-in-difference (PSM-DID) framework for systematic research that includes benchmark modeling, as well as dynamic effect and mechanism analyses. Results: 1) The benchmark model and placebo test proved that the Central China Rise Strategy had increased environmental pollution. 2) Dynamic effect analysis revealed that the impact of the Central China Rise Strategy on environmental pollution has gradually increased in the short-and medium-term, with 2012 exhibiting the greatest augmentation, significantly reducing from 2016 on-wards. 3) The mechanism of action considers three mechanisms. The level of economic development is a path through which the Central China Rise Strategy leads to the aggravation of environmental pollution while the city size is not. Foreign direct investment has improved environmental pollution. Conclusion: The Central China Rise Strategy has aggravated environmental pollution, especially in the short and medium-term. In view of the mechanism path, we put forward three targeted suggestions. In the future, we will study some of the limitations of this paper: more mechanisms of action will be considered, and the use of new technologies, such as neural networks, will be compared with our results. © 2023 Bentham Science Publishers.

Spark Streaming是一种典型的批量流式计算平台,可用于处理持续到达的数据流。流式数据最重要的两个特征是波动性和时效性。利用动态调整系统参数和动态调整资源满足不同数据到达速率的响应延迟,但调整参数的方式具有局限性,其用户成本较大。因此提出一种参数和资源协同调整策略,采用动态邻域粒子群算法找到一种满足SLO目标且使用资源最少的系统方案。实验表明,AdaStreaming与DyBBS相比,延迟性降低了70.1%,在资源使用量上比DRA降低了42.1%。

标签作为Web 2.0时代信息分类和检索的有效方式,已经成为近年的热点研究对象。标签推荐系统旨在利用标签数据为用户提供个性化推荐。现有的基于标签的推荐方法在预测用户对物品的兴趣度时往往倾向于赋予热门标签及其对应的热门物品较大的权重,导致权重偏差,降低了推荐结果的新颖性,未能充分反映用户个性化的兴趣。针对上述问题,定义了标签熵的概念来度量标签的不确定性,提出了标签熵特征表示的协同过滤个性化推荐算法。该算法通过引入标签熵来解决权重偏差问题,利用三分图形式描述用户-标签-项目之间的关系;构建基于标签熵特征表示的用户和项目特征表示,并通过特征相似性度量方法计算项目的相似性;最后利用用户标签行为和项目的相似性线性组合预测用户对项目的偏好值,并根据预测偏好值排序生成最终的推荐列表。在Last.fm数据集上的实验结果表明,该方法能够提高推荐准确性和新颖性,满足用户的个性化需求。

随着我国经济的高速发展,大型活动举办越来越频繁,一旦活动发生突发事件,将会造成重大人员伤亡和经济损失。如何对活动突发事件实现实时精确地感知预测,已经成为大型活动安全管理相关研究亟待解决的关键问题。实践应用方面,随着物联网、云计算、大数据、智慧城市等科学技术的快速发展,伴随着移动通讯、北斗和GPS全球定位、视频监控等感知技术和设备的普及,传统的大型活动场馆已经积累起海量的时空监测数据,这些数据为活动突发事件感知和预测带来了新的挑战和机遇。从理论研究方面,大数据分析挖掘研究和应用相关领域也已形成一批成熟的模型、技术及方法,这些成果为基于时空大数据进行分析挖掘研究,进而实现突发事件感知及预测提供了坚实的理论基础。研究成果不仅能够最大限度避免人财损失,而且对应急决策与资源调度能够产生巨大帮助。与传统以经验数据为支撑的事件感知及预测方法不同,本文以时空大数据分析为基础驱动,依靠机器学习、数据挖掘方法发现突发事件特征及模式,进而实现对复杂多变的大型活动突发事件处置应对。本文主要围绕大型活动中突发事件感知及预测相关的关键问题展开研究,论文主要工作和创新点如下:（1）基于时间序列实现大型活动历史数据建模及分类本文首先基于图结构对具有物理不变性的大型活动场馆进行建模研究;其次,基于大型活动历史数据分析,研究大型活动历史数据建模,提出基于时间序列的大型活动人群密度模型,并给出活动相似性度量方法;最后,采用KMeans实现对特定时间间隔及空间的数据模式聚类研究,实现对大型活动的自动分类。（2）基于马尔可夫实现突发事件感知现有研究往往只是简单通过历史数据对当前状态进行判定,无法感知事件状态变化过程。本文首先基于大型活动人群密度时间序列,研究并建立大型活动区域时序状态模型;其次,以人群密度等级与时间间隔的笛卡尔集为状态,基于马尔可夫过程,实现场馆单个特定区域人群密度状态随时间变化的模型表达;最后,基于上述模型,设计活动突发事件感知算法,通过活动当前状态与模型所总结出的规律对比,发现异常,实现对该区域突发事件的感知。（3）基于时空情景时间序列实现突发事件预测现有突发事件预测方法大多针对特定领域的微观事件进行研究,很难独立应用于活动突发事件的监测上。本文创新性提出将已有研究成果输出纳入到活动统一时空模型方法:首先,研究建立活动时空情景模型;其次,通过构建时空情景时间序列,对数据空间按时间及空间同时进行有效分割,进而挖掘不同活动历史数据的时空规律;最后,采用K最近邻设计突发事件预测算法,实现对当前活动突发事件的预测。（4）设计实现大型活动突发事件感知及预测原型系统为更好地验证论文研究算法及成果,解决将成果应用于实际工作中的问题,本文设计并实现了一个大型活动突发事件感知及预测原型系统。系统基于HTML5技术设计,在本文所提出突发事件感知及预测算法的基础上,实现了大型活动感知及预测原型系统的搭建及Web端应用开发,并以实例为背景对原型系统进行了功能展示。

为了解决Docker容器在线迁移过程中由容器迁移产生冗余Docker镜像的问题,利用联合文件系统容器层文件与镜像层文件通过联合挂载统一显示以及容器内操作过的文件存在于容器层的特性,提出一个Docker容器在线迁移方案.该方案在迁移容器数据时,采用仅迁移容器层数据的方式,有效避免了冗余Docker镜像的生成.基于上述设计方案,在当前最具代表性的2类联合文件系统存储驱动（aufs和overlay2）上进行了验证实验.实验结果表明,在容器迁移过程中,不仅实现了容器数据的迁移,而且并未产生多余Docker镜像.

标签推荐系统旨在利用标签数据为用户提供个性化推荐。已有的基于标签的推荐方法往往忽视了用户和资源本身的特征,而且在相似性度量时仅针对项目相似性或用户相似性进行计算,并未充分考虑二者之间的有效融合,推荐结果的准确性较低。为了解决上述问题,将标签信息融入到结合用户相似性和项目相似性的协同过滤中,提出融合标签特征与相似性的协同过滤个性化推荐方法。该方法在充分考虑用户、项目以及标签信息的基础上,利用二维矩阵来定义用户-标签以及标签-项目之间的行为。构建用户和项目的标签特征表示,通过基于标签特征的相似性度量方法计算用户相似性和项目相似性。基于用户标签行为和用户与项目的相似性线性组合来预测用户对项目的偏好值,并根据预测偏好值排序,生成最终的推荐列表。在Last.fm数据集上的实验结果表明,该方法能够提高推荐的准确度,满足用户的个性化需求。

Many actions have been carried out to promote the low-carbon society construction in China, emission trading system (ETS) and energy efficiency trading (EET) are two typical instruments during the past five years. This paper focused on the coexistence between ETS and EET aiming to explore whether policy-mix could enhance industries' interests through the partial-equilibrium model. The results showed that when overlapping transaction scope is allowed, the shadow price of energy saving is certain for the industries. When is not, setting up the policy-mix would not improve energy savings of industries but would make the two trading systems complementary, via the internal mechanism of the policy-mix and providing multiple policy options. The analysis indicated that EET and ETS could coexist and yield better results. Energy saving quota and CO2 quotas can be mutually recognized in a certain method avoiding the repeated accounting between two quotas, which will not increase the burden of enterprises but encourage them to conduct flexible emission reduction to enhance the competitiveness. (c) 2021 The Author(s). Published by Elsevier Ltd.

With the development of mobile networks and the rapid prevalence of location-based social networks (LBSN), a massive volume of spatiotemporal data has been generated, which is valuable for points of interest (POI) recommendation. However, current studies have not unleashed the full power of such spatiotemporal data, which either explore only a single dimension of the data or consider multiple factors in an asynchronous fashion. In this article, we propose a novel spatiotemporal network-based recommender framework (STNBR) to effectively recommend POIs for users. Specifically, we first establish a comprehensive conceptual model of spatiotemporal data, involving various essential factors for POIs recommendation. On top of the conceptual model, we design a series of meaningful meta-paths that simultaneously consider the time and location factors to precisely capture the semantics of user behaviours. By profiling users based on their embedded meta-paths, our approach can yield meaningful POIs recommendations. We have evaluated our proposal using a realistic dataset obtained from Foursquare and Gowalla, the results of which show that our STNBR model outperforms existing approaches.

As the world's largest coal consumer, China's coal consumption in 2021 was 2934.4 million tons of standard coal. Thermal coal occupies an important position in the coal market and industry system, as an important raw material in the power industry, steel industry and other industries. The price of thermal coal in 2021 was at its highest level in a decade, and reached a historical level of about 2587.5 yuan per ton in October 2021. In the same month, the government intervened in the thermal coal price, which fell 51.9% by the end of the year under the influence of the policy. In previous studies, there has been little research on thermal coal and the impact of the variable "policy" on the thermal coal price. Thus, this paper analyzed the factors that affect the price fluctuation of thermal coal, and the impact of economic policy uncertainty on the thermal coal price. The cointegration test and forecast-error variance decomposition (FEVD) are adopted in this study. Our results show that the impact of policy uncertainty on the thermal coal price gradually increases over time, but the impact of policy uncertainty on price is negative and not as strong as expected. On the contrary, inventory and other energy prices have a greater positive impact on the price of thermal coal. The results of this study are of significance for the prediction of thermal coal prices in the future.