Building type information is crucial to many urban studies, including fine-resolution population estimation, planning, and management. Although scientists have developed methods extract buildings via remote sensing data, only a limited number of them focus on further classification the extracted results. This paper presents novel building scheme based integration height from LiDAR, textural, spectral, geometric high-resolution images, super-object integrated dataset. firstly LiDAR point...

Buildings are fundamental components of cities. Understanding the function buildings is therefore great importance for urban development and management. Some studies have identified building functions using spatiotemporal data, which assumes that with same similar temporal activity patterns. However, these methods present difficulties in coping situation when heterogeneous To solve this problem, research proposes a new method to identify from perspective spatial distribution interactions...

Urban agglomerations are becoming increasingly important in driving economic development China. Accurate representation of the status and spillover effects cities within an urban agglomeration is foundation effective approach for promoting coordinated that agglomeration. However, current studies spillovers tend to focus on as a whole, there lack scrutiny validation research data. Therefore, this study proposes framework detecting based prolonged night-time light dataset. Firstly, we explored...

Urban system is shaped by the interactions between different regions and planned government, then reshaped human activities residents' needs. Understanding changes of regional structure dynamics city function based on movement demand are important to evaluate adjust planning management urban services internal structures. This paper constructed a probabilistic factor model basis latent semantic analysis tensor decomposition, for purpose understanding higher order interactive population...

Multitask learning (MTL) has recently yielded impressive results for classification of remotely sensed data due to its ability incorporate shared information across multiple tasks. However, it remains a challenging issue achieve robust in the case that are from nonlinear subspaces. In this paper, we propose kernel low-rank MTL (KL-MTL) method handle features 2-D variational mode decomposition (2-D-VMD) domain multi-/hyperspectral classification. On one hand, nonrecursive 2-D-VMD is applied...

Dengue fever (DF) is a mosquito-borne disease that significantly endangers the well-being of people in most tropical Asia-Pacific areas. The transmission DF inherently spatial process, requiring susceptible humans encountering infectious mosquito. relationships between humans, mosquito and environment underpin dynamics patterns epidemic. In this article, objective to find out key abiotic factors DF. An interdisciplinary study has been carried by taking advantage statistics, geographical...

Nonnegative matrix factorization (NMF) is a blind source separation (BSS) method often used in hyperspectral unmixing. However, it tends to converge local optimum. To overcome this limitation, we present simple, but effective endmember initialization scheme for NMF, which realized by improving initial values through the application of automatic target generation process (ATGP) algorithm. The spectra and abundances endmembers are first obtained using ATGP algorithm nonnegative least squares...

Accurately estimating commuting flow is essential for optimizing urban planning and traffic design. The latest graph neural network (GNN) model with the encoder-decoder-predictor components has several limitations. First, it ignores temporal dependency of node features embedding. Second, different estimation methods used in decoder predictor make difficult to distinguish contribution embedding or method estimation. Third, finer-grained socio-economic nodes are obtain due low data...

Cities in an urban agglomeration closely interact with each other through various flows. Information flow, as one of the important forms interactions, is now increasingly indispensable fast development informatics technology. Thanks to its timely, convenient, and spatially unconstrained transmission ability, information flow has obvious spillover effects, which may strengthen interaction further promote coordinated development. Therefore, it crucial quantify spatial effect influencing...

The dynamic population distributions by activity type (e.g. working, shopping or in-home) are vital for resource allocation, urban planning and epidemic containment. Although studies have incorporated individual-level human mobility data to map distribution type, access such is hindered due privacy issues they rely on auxiliary provide priori knowledge. This paper presents a method generating the dynamics type. We first introduce more readily available sequential snapshot construct mixture...

International communication and global cooperation have greatly accelerated the worldwide spread of dengue fever, increasing impact imported cases on outbreaks in non-naturally endemic areas. Existing studies mostly focus describing quantitative relationship between local transmission but ignore space-time diffusion mode under influence individual mobility. In this paper, we propose a comprehensive framework at fine scale to establish disease network mathematical model, which constructs...

As the COVID-19 vaccination has been quickly rolling out around globe, evaluation of effects vaccinating populations for safe reopening schools become a focal point educators, decision-makers, and general public. Within this context, we develop contact network agent-based model (CN-ABM) to simulate on-campus disease transmission scenarios. The CN-ABM establishes networks agents based on their daily activity patterns, evaluates agents' health status change in different environments, then...

In this paper, we introduce a novel method ABM in simulating the unique process for dengue spread. Dengue is an acute infectious disease with long history of over 200 years. Unlike diseases that can be transmitted directly from person to person, spreads through must vector mosquitoes. There still no any special effective medicine and vaccine up till now. The best way prevent spread take precautions beforehand. Thus, it crucial detect study dynamic closely relates human-environment...

With rapid economic growth since the 21st century, cities in China have experienced considerable and social reconstruction. Driven by industrialization, urban spatial structures are undergoing evolution change. Therefore, this paper analyzes processes mechanisms associated with of commercial structure Guangzhou after financial crisis 2008 based on both theoretical empirical analyses. We use a Dirichlet multinomial regression (DMR) model to extract latent semantic information determine...

The longest archive makes DMSP-OLS nighttime light (NTL) images unparalleled in relevant time series studies. However, these studies have been constrained by the blooming effect. self-adjusting model (SEAM) proposed 2019 solves this problem to some extent. SEAM assumed all pixels NTL with a constant distance 3.5 km. In fact, is related land covers and brightness of artificial lights. This assumption leads large errors cities that different from To address problem, study an improved (iSEAM)...

Abstract The spatial pattern and mechanism of human flow are great significance for urban planning, economic development, transportation planning so on. In this study, we used cell phone location data to represent the network in Guangdong Province, China, using 21 cities as “nodes” intensity among them “edges”. Then explored macro micro features network, by index degree distribution, alter-based centrality power, respectively. Finally, proposed a estimation model which integrates individual...

Abstract A method is proposed for constrained multi-objective optimization problems, which based on Newton and the linear weighted sum method. The automobile impact problem studied in this paper. model of would be established. Then, an improved design front rail obtained by algorithm proposed.

Spam messages affect the normal communication of mobile phone users and public security. Fake base station (FBS) is main channel for sending spam messages. Accurate spatiotemporal prediction from FBS important implementing short-term prevention measures by police. However, existing models used modeling often focus on capturing spatial dependencies based distance, thus failing to fully exploit hidden in data. Meanwhile, they encounter difficulties mitigating impact excessive zero Therefore,...

The building age is an important feature in the vulnerability assessment of disasters and energy consumption modeling. It provides indispensable information for study built environment. However, obtaining high-precision maps ages challenging, which impedes development relevant research applications. In this study, a new mapping method based on Landsat time series classification change detection (BATSCCD) was proposed, integrates data with random forest LandTrendr algorithm to reflect...

Abstract The spatiotemporal mobility patterns and next location prediction of fake base stations (FBS) provide important technical support for the police to prevent spam messages from FBS. However, due difficulty in locating their real-time locations, our understanding predictability FBS is still limited. Based on crowdsourced data, we extract time potential locations propose a Tucker-MMC method that combines Tucker decomposition with Mobility Markov Chain (MMC) model investigate sending...

Information on the mixed use of buildings helps understand status mixed-use urban vertical land and assists in planning decisions. Although a few studies have focused this topic, methods they used are quite complex require manual intervention extracting different function patterns buildings, while building recognition rates remain unsatisfying. In paper, we propose new method to infer based tensor decomposition algorithm, which integrates information from both high-resolution remote sensing...