Spring Festival travel rush is a phenomenon in China that population intensively surges short time around Chinese Festival. This phenomenon, which special one the urbanization process of China, brings large traffic burden and various kinds social problems, thereby causing widespread public concern. study investigates spatial-temporal characteristics 2015 through series analysis complex network based on multisource big data derived from Baidu, Tencent, Qihoo. The main results are as follows:...

This paper explores the application and effectiveness of TestTime Training (TTT) layers in improving performance recommendation systems. We developed a model, TTT4Rec, utilizing TTT-Linear as feature extraction layer. Our tests across multiple datasets indicate that base performs comparably or even surpasses other baseline models similar environments.

Federated learning (FL) is a promising technology for data privacy and distributed optimization, but it suffers from imbalance heterogeneity among clients. Existing FL methods try to solve the problems by aligning client with server model or correcting control variables. These excel on IID general Non-IID perform mediocrely in Simpson's Paradox scenarios. refers phenomenon that trend observed global dataset disappears reverses subset, which may lead fact obtained through aggregation does not...

In this study, we focus on heterogeneous knowledge transfer across entirely different model architectures, tasks, and modalities. Existing methods (e.g., backbone sharing, distillation) often hinge shared elements within structures or task-specific features/labels, limiting transfers to complex types tasks. To overcome these challenges, present MergeNet, which learns bridge the gap of parameter spaces models, facilitating direct interaction, extraction, application spaces. The core mechanism...

Predicting the spatio-temporal evolution characteristics and trade-off/synergy relationships of ecosystem service value (ESV) under different policy scenarios is great significance for realizing regional sustainable development. This study established a framework used geographical simulation optimization systems-future land use (GeoSOS-FLUS) model bivariate local autocorrelation analysis to stimulate predict impact change on ESV Anyang City from 1995 2025. We also explored trade-offs synergy...

Irrigation districts play a crucial role in guaranteeing agricultural production, and their ecological health sustainable development are of great importance for regional economic environmental security. Taking the Zhaokou irrigation district Henan Province as research object, this paper firstly constructs evaluation system consisting 26 indicators from perspective “nature–economy–society–ecology” composite system. Then, fuzzy hierarchical comprehensive method ArcGIS spatial analysis...

While it has long been believed in psychology that weather somehow influences human's mood, the debates have going on for decades about how they are correlated. In this paper, we try to study long-lasting topic by harnessing a new source of data compared from traditional psychological researches: Twitter. We analyze 2 years' twitter collected API which amounts 10% all postings and reveal correlations between multiple dimensional structure human mood with meteorological effects. Some our...

In urban and rural areas under rapid urbanization, a proper understanding of the relationship between population construction land use is important for regional sustainable development. The decoupling method particularly useful way to examine this relationship. However, only considers current land, ignoring initial status in base year. Based on an improved model, vector land-use data (1:10,000 scale) from two National Land Investigations, demographic China Statistics Bureau, paper analyzes...

Inferring latent attributes of people online is an important social computing task, but requires integrating the many heterogeneous sources information available on web. We propose learning individual representations using neural nets to integrate rich linguistic and network evidence gathered from media. The algorithm able combine diverse cues, such as text a person writes, their (e.g. gender, employer, education, location) relations other people. show that by both textual evidence, these...

Rapid urbanization accompanied with socioeconomic transformation in China has resulted significant changes urban–rural construction land and human–land relationships. Understanding the spatiotemporal characteristics of transition (URCLT) rural–urban migrants (RUMs) is for coordinated development urban rural areas. This research analyzed URCLT its decoupling relationship RUMs a case study Hubei Province, central China, period 2009–2016. The results corroborate following: (1) rapid growth slow...

At the time of writing, ongoing pandemic coronavirus disease (COVID-19) has caused severe impacts on society, economy and people's daily lives. People constantly express their opinions various aspects social media, making user-generated content an important source for understanding public emotions concerns. In this paper, we perform a comprehensive analysis affective trajectories American people Chinese based Twitter Weibo posts between January 20th, 2020 May 11th 2020. Specifically, by...

Abstract Understanding the changes and coupling characteristics between rural population (RP) residential land (RRL) provides a theoretical basis for sustainable use. Based on index of human–land development, this study analyzed spatial–temporal types RRL RP levels China's national prefectural cities by using data official use survey demographic statistics from 2009 to 2016. Results showed that (a) is declining at an average annual rate 2.07%, in most decrease −3.33% −1.20%. (b) The area...

In the increasingly serious aging China, aged service is provision of one most urgent and important public services to citizens, private facilities has become an force with market opening in China. This study aims explore spatial variation accessibility residential care (RACFs) compared capacity RACFs RACFs. It facilitates be allocated rationally future achieve equalization services. A village-level analysis access by multi-catchment sizes Gaussian two-step floating catchment area...

Rural settlements are the main carriers of agriculture, rural areas and farmers; thus, optimizing production living space is highly significant to development. Taking effective allocation resources as starting point, a suitability evaluation system settlements, based on accessibility living, was proposed in this study provide scientific basis for optimization space. The measured by an improved two-step floating catchment area method, which considered proximity availability inclination...

While it has long been believed in psychology that weather somehow influences human's mood, the debates have going on for decades about how they are correlated. In this paper, we try to study long-lasting topic by harnessing a new source of data compared from traditional psychological researches: Twitter. We analyze 2 years' twitter collected API which amounts $10\%$ all postings and reveal correlations between multiple dimensional structure human mood with meteorological effects. Some our...

China has entered a new era of comprehensive promotion rural revitalization and integrated urban–rural development. The identification optimization the spatial structure urban settlements are great significance to realization This study proposes method framework for identifying optimizing from hierarchical network perspective. includes three parts—namely, identification, analysis, these settlements. this is foundation study. To realize each settlement, finds retains its strongest interaction...

310012；4.上海交通大学计算机科学与工程系，上海 200240；5.浙江大学上海高等研究院，上海 201203)

Geographical centrality is an evolving concept that differs from one perspective to another at different stages. The unprecedented development of high-speed information and transportation networks has highlighted the important role space flows restructured mode spatial interaction. geographical analysis method based on relational currently becomes mainstream, but most related methods ignore structure. In this study, we first analyze impacts interaction theory. We argue dominate short-...

This study proposes an innovative integrated method for evaluating the evacuation and rescue capabilities of open spaces through a case in Wuhan, China. A dual-scenario network analysis model was set up to calculate travel time among communities, spaces, facilities during peak non-peak hours. The distribution traffic flow derived on basis gravity used construct supply-demand indexes (SDIs). SDIs such as (ESDI), (RSDI), comprehensive (CSDI) were evaluate suitability space locations. drew five...

In this study, we focus on heterogeneous knowledge transfer across entirely different model architectures, tasks, and modalities. Existing methods (e.g., backbone sharing, distillation) often hinge shared elements within structures or task-specific features/labels, limiting transfers to complex types tasks. To overcome these challenges, present MergeNet, which learns bridge the gap of parameter spaces models, facilitating direct interaction, extraction, application spaces. The core mechanism...

Scientific quantitative measurement of the coupling relationship between urban population (UP) and land (UL) is conducive to promoting intensive use, coordinated human–land development, new urbanization development. This research proposed an improved model polar coordinates study spatiotemporal characteristics UP UL at prefecture-level city scale in China from 2010 2020. The results include following: (1) growth rate China’s cities was higher than that UP. per capita (PUL) always within...

Flooding has become more frequent and intensive due to climate change, particularly in Asian countries. However, evidence on the long-term health effects of floods from large-scale studies vulnerable aged population China is insufficient. This study analyzed exposure flood electrocardiographic (ECG) abnormalities, a commonly used indicator cardiovascular disease (CVD) screening, middle-aged elderly people. We evaluated Chinese National Stroke Screening Survey data 80,711 follow-up records...