The prediction of travel times is challenging because the sparseness real-time traffic data and intrinsic uncertainty on congested urban road networks. We propose a new gradient–boosted regression tree method to accurately predict times. This model accounts for spatiotemporal correlations extracted from historical adjacent target links. can deliver high accuracy by combining simple trees with poor performance. It corrects error found in existing models improved accuracy. Our was verified...

Rainfall has a significant impact on urban population mobility, posing great challenges to traffic management and planning. An understanding of this influence from multiple perspectives is urgently needed. In study, we devised multiscale comparative research framework explore the spatiotemporal effects rainfall taxi travel patterns, aiming provide new perspective investigation rainfall’s human mobility. More specifically, at macroscopic scale, computed indicators across entire study area...

The capsule network (Caps) is a novel type of neural that has great potential for the classification hyperspectral remote sensing. However, Caps suffers from issue gradient vanishing. To solve this problem, powered activation regularization based adaptive (PAR-ACaps) was proposed sensing classification, in which an routing algorithm without iteration applied to amplify gradient, and method used learn sparser more discriminative representation. performance PAR-ACaps evaluated using two public...

There is a growing interest in the interoperability between building information models (BIM) and geographic systems (GIS). BIM can provide rich for generation of GIS model, while analysis tools be used by applications, such as management material supply chains site selection. A comprehensive integration critical two domains. However, many methods including manual inspection complex heterogeneous model files are time-consuming have weak generalisation capability. This paper proposes new...

Abstract Object matching is critical for updating, maintaining, integrating, and quality assessing spatial data. However, data are often obtained from different sources have problems of positional discrepancy levels detail. To resolve these problems, this article presents a multiscale polygonal object‐matching approach, called the minimum bounding rectangle combinatorial optimization (MBRCO) with district (SD). This method starts MBRCO algorithm its enhancement using SD to find corresponding...

With hundreds of spectral bands, the rise issue dimensionality in classification hyperspectral images is usually inevitable. In this paper, a restrictive polymorphic ant colony algorithm (RPACA) based band selection (RPACA-BS) was proposed to reduce images. algorithm, both local and global searches were conducted considering similarity. Moreover, problem falling into optima, due similar subsets although travelling different paths, solved by varying pheromone matrix between ants moving...

Abstract Object matching facilitates spatial data integration, updating, evaluation, and management. However, to be matched often originate from different sources present problems with regard positional discrepancies levels of detail. To resolve these problems, this article designs an iterative framework that effectively combines the advantages contextual information artificial neural network. The proposed method can correctly aggregate one‐to‐many (1:N) many‐to‐many (M:N) potential pairs...

Abstract Volunteered geographic information (VGI) is an emerging phenomenon where anyone can create and share it with others. Compared traditional authoritative geospatial data, has several advantages, such as enriched instant updates, low cost. The object matching method widely used in VGI quality assessment data updates. However, faces certain challenges, the levels of detail that vary from to object, uneven distribution quality, automated requirement. To resolve these problems, this...

It is well known that index (discrete-time)-limited sampled sequences leak outside the support set when a band-limiting operation applied. Similarly, fractional shift causes an index-limited sequence to be infinite in extent due inherent band-limiting. Index-limited versions of discrete prolate spheroidal (DPSS) are experience minimum leakage after In this work, we consider effect half-sample and provide upper bounds on resulting energy for arbitrary sequences. Furthermore, find orthonormal...

Abstract. Urban lakes serve an indispensable role in maintaining the ecological balance of cities, ensuring flood safety, and providing recreational spaces for tourism. With development human activities economic, extent urban are inevitably influenced. Currently, ability to detect detailed temporal changes lake areas using high resolution data still has limitations. This study proposed a novel method by combining time series Gaofen-1 (GF-1) remote sensing random forest machine learning...

OpenStreetMap (OSM) is one of the most successful and well-known projects in field Volunteered Geographic Information (VGI). It has not only become supplement to basic mapping services professional surveying data, but also a popular free spatial dataset urban analysis. However, completeness OSM building data China was relatively low past. As result, there small number studies on China, especially terms patterns evolution data. In response this research gap, article proposes an model that...

The move toward Sixth-Generation (6G) networks relies on open interfaces and protocols for seamless interoperability across devices, vendors, technologies. In this context, 6G development involves multiple disciplines requires advanced simulation approaches testing. demo paper, we propose a generative approach based multi-agent Large Language Model (LLM) Network Simulator 3 (ns-3), called Generative Open xG Simulation (GenOnet), to effectively generate, debug, execute, interpret simulated...

Abstract. Homonymous entity matching is an important part of multi-source spatial data integration, automatic updating and change detection. Considering the low accuracy existing methods in dealing with multi-scale settlement data, algorithm based on Attributed Relational Graph (ARG) proposed. The firstly divides two scenes at different scales into blocks by small-scale road network constructs local ARGs each block. Then, ascertains candidate sets merging procedures obtains optimal pairs...