Search

An accurate short-term load forecasting plays an important role in modern power system's operation and economic development. However, short-term load forecasting is affected by multiple factors, and due to the complexity of the relationships between factors, the graph structure in this task is unknown. On the other hand, existing methods do not fully aggregating data information through the inherent relationships between various factors. In this paper, we propose a short-term load forecasting framework based on graph neural networks and dilated 1D-CNN, called GLFN-TC. GLFN-TC uses the graph learning module to automatically learn the relationships between variables to solve problem with unknown graph structure. GLFN-TC effectively handles temporal and spatial dependencies through two modules. In temporal convolution module, GLFN-TC uses dilated 1D-CNN to extract temporal dependencies from historical data of each node. In densely connected residual convolution module, in order to ensure that data information is not lost, GLFN-TC uses the graph convolution of densely connected residual to make full use of the data information of each graph convolution layer. Finally, the predicted values are obtained through the load forecasting module. We conducted five studies to verify the outperformance of GLFN-TC. In short-term load forecasting, using MSE as an example, the experimental results of GLFN-TC decreased by 0.0396, 0.0137, 0.0358, 0.0213 and 0.0337 compared to the optimal baseline method on ISO-NE, AT, AP, SH and NCENT datasets, respectively. Results show that GLFN-TC can achieve higher prediction accuracy than the existing common methods. [ABSTRACT FROM AUTHOR]

Simple Summary: In the intricate field of genomic research, researchers frequently look for the enrichment of genes with a common function. Traditionally, genes are analyzed as if they function independently. However, this assumption may not hold true in large genomic regions, where genes with similar functions exist in close proximity and may influence each other. Our research introduces an advanced method to discern whether the observed patterns in gene groups are due to their spatial closeness, or stem from other biological factors. This approach is particularly crucial in studying large genomic loci, where conventional methods might overlook the nuanced interplay of functionally similar genes. By implementing our technique, we significantly enhance the precision of genomic analyses, particularly in these extensive areas. This advancement is vital as it deepens our understanding of gene interactions within large genomic regions. Traditional gene set enrichment analysis falters when applied to large genomic domains, where neighboring genes often share functions. This spatial dependency creates misleading enrichments, mistaking mere physical proximity for genuine biological connections. Here we present Spatial Adjusted Gene Ontology (SAGO), a novel cyclic permutation-based approach, to tackle this challenge. SAGO separates enrichments due to spatial proximity from genuine biological links by incorporating the genes' spatial arrangement into the analysis. We applied SAGO to various datasets in which the identified genomic intervals are large, including replication timing domains, large H3K9me3 and H3K27me3 domains, HiC compartments and lamina-associated domains (LADs). Intriguingly, applying SAGO to prostate cancer samples with large copy number alteration (CNA) domains eliminated most of the enriched GO terms, thus helping to accurately identify biologically relevant gene sets linked to oncogenic processes, free from spatial bias. [ABSTRACT FROM AUTHOR]

Abstract An accurate short-term load forecasting plays an important role in modern power system’s operation and economic development. However, short-term load forecasting is affected by multiple factors, and due to the complexity of the relationships between factors, the graph structure in this task is unknown. On the other hand, existing methods do not fully aggregating data information through the inherent relationships between various factors. In this paper, we propose a short-term load forecasting framework based on graph neural networks and dilated 1D-CNN, called GLFN-TC. GLFN-TC uses the graph learning module to automatically learn the relationships between variables to solve problem with unknown graph structure. GLFN-TC effectively handles temporal and spatial dependencies through two modules. In temporal convolution module, GLFN-TC uses dilated 1D-CNN to extract temporal dependencies from historical data of each node. In densely connected residual convolution module, in order to ensure that data information is not lost, GLFN-TC uses the graph convolution of densely connected residual to make full use of the data information of each graph convolution layer. Finally, the predicted values are obtained through the load forecasting module. We conducted five studies to verify the outperformance of GLFN-TC. In short-term load forecasting, using MSE as an example, the experimental results of GLFN-TC decreased by 0.0396, 0.0137, 0.0358, 0.0213 and 0.0337 compared to the optimal baseline method on ISO-NE, AT, AP, SH and NCENT datasets, respectively. Results show that GLFN-TC can achieve higher prediction accuracy than the existing common methods.

Person re-identification (Re-ID) is a computer vision technique used to determine the presence of a specific pedestrian target in an image or video sequence. It is an important branch of image retrieval. With the advancements in deep learning, notable progress has been achieved in Re-ID research. However, existing methods primarily focus on the most prominent features in the image, ignoring other less obvious yet beneficial features and spatial interdependencies within the image. To address this issue, this paper proposes a neighboring-part dependency mining and feature fusion network (NDMF-Net). The network horizontally splits pedestrian features into multiple parts, using a part-level hybrid attention module (PHAM) to focus on the salient region of each part, and a neighboring-part dependency exploration module (NDEM) to extract the spatial dependencies between neighboring parts of the image. Eventually, different features are fused to form the final representation. We validate the NDMF-Net on mainstream datasets and the experimental results demonstrate that our method is effective and achieves state-of-the-art performance.

Accurate traffic prediction plays a crucial role in improving traffic conditions and optimizing road utilization. Effectively capturing the multi-scale temporal dependencies and dynamic spatial dependencies is crucial for accurate traffic prediction. These features can effectively reflect complex dynamic spatial–temporal processes, which have not been comprehensively addressed in most existing research work. Motivated by this issue, the primary contribution of this paper lies in proposing a novel Spatial–Temporal Fusion Graph Neural Network (STFGCN) for accurate traffic prediction, achieved by extracting multi-scale temporal dependencies from multiple semantic environments and constructing a dynamic adaptive graph to model spatial dependencies based on temporal characteristics. Specifically, to capture the multi-scale dynamic temporal dependencies effectively, a Multi-Scale Fusion Convolution (MSFC) module is designed, in which the temporal dependencies are extracted from multiple textual environments by utilizing multi-scale convolution. In order to model dynamic spatial dependencies, a Spatial Adaptive Fusion Convolution (SAFC) module is designed by combining the recent coherence and periodicity to infer dynamic graphs, which are then fused to model dynamic spatial dependencies. Extensive experimental results on five real-world datasets demonstrate that the proposed STFGCN has superior performance. Specifically, compared with the state-of-the-art baselines, STFGCN reduced 1.2% to 16.4% in RMSE measure. [Display omitted] • Deep learning model to predict traffic status on large-scale road networks. • Extracting multi-scale temporal dependencies from multiple semantic environments. • Constructing a dynamic adaptive graph to model spatial dependencies based on temporal characteristics. • Extensive experiments demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Japan is becoming depopulated, with declining fertility rates and massive urban agglomeration due to emigrations from rural areas, which results in rural–urban disparities. As demographic and social divisions between rural and urban areas increase, maintenance of infrastructure and social facilities becomes much more difficult. For social and demographic sustainability, accurate predictions of long-term population distributions are needed. This study improves the Cohort Component Analysis (CCA) into two aspects of "dependent structure" in the model system. The migration sub-model is expanded to include related structures between available job opportunities and the available workforce in each region, which are specified using the spatial autoregressive model. The advantage of the improved CCA to provides rational future projections by considering the longitudinal changes in the spatial distribution of the workforce. The simulation of the proposed model gives an alternative long-term impact of population distribution in Japan, which is compared with the conventional CCA. The results show that the future Japanese populations will become more concentrated in urban areas, with a lower fertility rate. Furthermore, the manufacturing employees will be attracted to metropolitan areas or to regions with industrial zones, and that the number of retailers will undergo changes over time, even in urbanized areas. [ABSTRACT FROM AUTHOR]

Image quality assessment (IQA) aims to build a quality prediction model to assess image quality automatically rather than artificially. Due to a lack of reference images, blind image quality assessment (BIQA) has become an attractive yet challenging research topic. Inspired by the hierarchical perception mechanism in the human visual system, some existing BIQA methods aggregate multi-stage features of a convolutional neural network (CNN). However, they are regardless of the latent dependencies. To solve this problem, we propose a novel BIQA method based on hierarchical dependency learning and quality aggregation (HDLaQA). The proposed method includes multi-stage feature extraction, hierarchical dependency learning, and quality aggregation. In multi-stage feature extraction, a CNN is used as the feature extractor and multi-stage features are output for further learning. In hierarchical dependency learning, spatial and channel dependencies among the multi-stage features are modeled. To this end, a dual-head spatial dependency (DSD) module is designed to harvest the spatial dependencies between the adjacent-stage features and deliver these dependencies to the next stage. Moreover, exponential bilinear pooling (EBP) is presented to learn the channel dependencies, which is more stable than commonly used BP. In quality aggregation, multiple quality scores are predicted based on the learned dependencies, and multiple learnable weights are used to measure the importance of the predicted scores for final quality evaluation. Experimental results on seven IQA databases demonstrate the competitiveness of the proposed method on both synthetic and authentic distortions. [ABSTRACT FROM AUTHOR]

Future climate change will likely impact the multiple freshwater ecosystem services (fES) provided by catchments through their landscapes and river systems. However, there is high spatio-temporal uncertainty on those impacts linked to climate change uncertainty and the natural and anthropogenic interdependencies of water management systems. This study identifies current and future spatial patterns of fES production in a highly managed water resource system in northern India to inform the design and assessment of plausible adaptation measures to enhance fES production in the catchment under uncertain climate change. A water resource systems modelling approach is used to evaluate fES across the full range of plausible future scenarios, to identify the (worst-case) climate change scenarios triggering the greatest impacts and assess the capacity of adaptation to enhance fES. Results indicate that the current and future states of the fES depend on the spatial patterns of climate change and the impacts of infrastructure management on river flows. Natural zones deliver more regulating and cultural services than anthropized areas, although they are more climate-sensitive. The implementation of a plausible adaptation strategy only manages to slightly enhance fES in the system with respect to no adaptation. These results demonstrate that water resource systems models are powerful tools to capture complex system dependencies and inform the design of robust catchment management measures. They also highlight that mitigation and more ambitious adaptation strategies are needed to offset climate change impacts in highly climate-sensitive catchments. [ABSTRACT FROM AUTHOR]

Interdependencies among neighboring regions appear to be important in forming the shape of local labor markets. Nevertheless, only a few studies exist which have applied spatial models to forecast over small spatial units such as cities, districts or counties. The majority of predictions are developed with quarterly or yearly time series for a country or at regional level. The paper presents the above phenomena and deals with the problem of simultaneous forecasting of the unemployment rate over 35 poviats (districts and cities) in one of the Polish provinces. Two extremely different models with spatial dependencies were developed and estimated in this paper: the Spatial Vector Autoregressions (SpVAR) and the Spatial Artificial Neural Network (SpANN). The 13-month out-of-sample forecast is based on high frequency, raw, monthly panel data extracted from 31 local labor offices. The procedure worked out here allows comparing the forecasting performance of spatial models with their non-spatial and seasonal equivalents. The inclusion of a spatial component into the models significantly improves the accuracy of forecasts; however, the overall performance of SpVAR is 30% better than SpANN. [ABSTRACT FROM AUTHOR]

This paper discusses the impact of linguistic contact on the make-up of consonantal inventories of the languages of Eurasia. New measures for studying the importance of language contact for the development of phonological inventories are proposed, and two empirical studies are reported. First, using two different measures of dissimilarity of phonemic inventories (the Jaccard dissimilarity measure and the novel Closest-Relative Cumulative Jaccard Dissimilarity measure), it is demonstrated that language contact—operationalized as languages being connected by an edge in a neighbor network—makes a significant contribution to between-inventory differences when phylogenetic variables are controlled for. Second, a novel measure of the exposure of a language to a particular segment—the Neighbor-Pressure Metric (NPM)—is proposed as a means of quantifying language contact with respect to phonological inventories. It is shown that addition of NPM helps achieve higher prediction accuracy than using bare phylogenetic data and that distributions of different consonants display a different degree of dependence on language-contact processes. Finally, more complex models for predicting consonant inventories are briefly explored, demonstrating the presence of complex non-linear relationships between inventories of neighboring languages. [ABSTRACT FROM AUTHOR]

Air pollution control is one of the main challenges facing modern societies. Consequently, the estimation of population, affluence, and technology impacts on air pollution concentrations (STIRPAT modeling) has become the cornerstone of environmental decision-making. Spatial effects are not usually included in STIRPAT modeling of air pollution. However, space matters: accounting for spatial dependencies significantly improves the accuracy of estimates and forecasts, especially (or only) when dealing with small information units rather than with large ones (countries, large regions, provinces in China, counties and states in the USA, etc.). The latter scale is typical in the literature on air pollution due to the difficulties in finding data on its drivers at a true local scale. Accordingly, this paper has a double objective. The first is the estimation of a spatial panel data STIRPAT model, with the spatial units being both very small and also highly autonomous, developed municipalities. The second is to examine whether an environmental Kuznets curve relationship exists between income per capita and NOx concentrations. A case study has been carried out in the Autonomous Community of Madrid, Spain, at the municipal level.

This paper is aimed at answering the question of whether absolute income (GDP per capita) beta-convergence exists in the case of regions in new EU Member States before the period of 2000–2008 and during the 2008–2011 crisis. The sample consists of 211 regions (NUTS 3-level) of Bulgaria, Czech Republic, Estonia, Hungary, Latvia, Lithuania, Poland, Romania, Slovenia and Slovakia.

Financial support is the main instrument of regional development policy in the European Union. Concentration, programming and partnership, are presented as "core principles" for improving the effectiveness of structural expenditure based on compensating the structural disadvantage of the assisted regions. The purpose of this paper is to analyze the spatial dependencies in level of absorption of funds in comparison to allocation criteria of intervention funded from Regional Operational Programmes. The research was based on data about the state of implementation of European funds in the subregions (NUTS 3) in 2007-2012., generated from the National Information System SIMIK 07-13. [ABSTRACT FROM AUTHOR]

The aim of this study is to show whether the Greater Paris housing market is integrated and can be defined globally or whether housing submarkets are present. Therefore, we analyze if macroeconomic shocks are homogeneous across the metropolis and check for the presence of ripple effects. For this purpose, we implement a panel vector autoregressive model at the metropolis and submarket levels to capture, through impulse response functions, the consequences of macroeconomic shocks on housing prices. In a second step, we perform a spatial panel vector autoregressive model to test for the presence of ripple effects and to check for robustness. We find the presence of housing submarkets and, hence, heterogeneous reactions of house prices to macroeconomic shocks across submarkets. Finally, we notice the presence of ripple effects in all submarkets with different spatial effects at play. • The impact of macroeconomics shocks and ripple effects in the Greater Paris housing market from 2006 to 2017 are analyzed. • Panel vector autoregressive model (PVAR) at the metropolis and submarkets level is developed. • Spatial autocorrelation and ripple effects are tested using spatial panel vector autoregressive model (SpVAR). • Results demonstrate the presence of housing submarket in Greater Paris as well as the presence of ripple and feedback effect at the metropolis and submarkets level. • SpVAR results indicate that housing submarkets react differently to macroeconomic shocks. [ABSTRACT FROM AUTHOR]

Highlights: [•] Present a modeling approach for spatially correlated zero-inflated continuous data. [•] Habitat associations were modeled for the three marine invertebrate taxa. [•] Models were fit and predictive abilities were evaluated using survey data. [•] Approach is useful for producing distribution maps for marine spatial planning. [Copyright &y& Elsevier]

Traditional background subtraction methods perform poorly when scenes contain dynamic backgrounds such as waving tree branches, spouting fountain, illumination changes, camera jitters, etc. In this paper, from the view of spatial context, we present a novel and effective dynamic background method with three contributions. First, we present a novel local dependency descriptor, called local dependency histogram (LDH), to effectively model the spatial dependencies between a pixel and its neighboring pixels. The spatial dependencies contain substantial evidence for differentiating dynamic background regions from moving objects of interest. Second, based on the proposed LDH, an effective approach to dynamic background subtraction is proposed, in which each pixel is modeled as a group of weighted LDHs. Labeling a pixel as foreground or background is done by comparing the LDH computed in current frame against its model LDHs. The model LDHs are adaptively updated by the current LDH. Finally, unlike traditional approaches using a fixed threshold to judge whether a pixel matches to its model, an adaptive thresholding technique is also proposed. Experimental results on a diverse set of dynamic scenes validate that the proposed method significantly outperforms traditional methods for dynamic background subtraction. [ABSTRACT FROM AUTHOR]

• We design a GAM to capture the inter-image dependencies among a series of different pedestrian images. • We present a LAM to compute the intra-image dependencies from any pair of pixels within each pedestrian image. • We propose a specific network integration mechanism to match well the solution of the spatial dependency problem. • Extensive experiments verify that the proposed method exceeds the state-of-the-art methods. Person re-identification (Re-ID) aims to search for the same pedestrian in different cameras, which is a crucial research direction in pattern recognition. Recent deep learning methods have advanced the development of Re-ID. However, the existing approaches easily result in performance degradation in the case of larger scene data because they do not adequately consider the spatial dependencies of both the inter-image and the intra-image. The paper proposes a novel Spatial-Driven Network (SDN) to learn particularly discriminative features with abundant semantic information from both the inter-image and the intra-image dependencies for person Re-ID. Firstly, we design a global-correlation attention module to capture the inter-image dependencies among a series of different pedestrian images. Secondly, we present a local-correlation attention module to compute the intra-image dependencies from any pair of pixels within each pedestrian image. Furthermore, we propose a specific network integration mechanism, which carefully combines the above two complementary modules to match well the solution of the spatial dependency problem. We implement numerous experiments to assess the proposed SDN on mainstream person Re-ID databases. The results demonstrate that the proposed SDN outperforms most of the state-of-the-art methods in typical key criteria. [ABSTRACT FROM AUTHOR]

An image segmentation approach, which is based on heat diffusion and graph cuts optimisation, is proposed. The prior segmentation result is obtained by temperature maximisation on the heat diffusion system. In the random walk‐based label‐assigning process, due to lack of spatial dependencies of neighbouring pixels, the segmentation may deteriorate notably when pixels from disconnected regions of an image show similar features. To overcome this problem, a multilayer graph‐based model is presented and image segmentation is considered as an energy minimisation problem. The parameters in the model are learned from the results of temperature maximisation on the heat diffusion system. It is shown that the presented variational model can be discretely optimised by the graph cuts method efficiently. Therefore, the spatial dependences of the neighbouring pixels can be integrated to obtain better segmentation results. A number of comparison experiments demonstrate the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Air pollution control is one of the main challenges facing modern societies. Consequently, the estimation of population, affluence, and technology impacts on air pollution concentrations (STIRPAT modeling) has become the cornerstone of environmental decision-making. Spatial effects are not usually included in STIRPAT modeling of air pollution. However, space matters: accounting for spatial dependencies significantly improves the accuracy of estimates and forecasts, especially (or only) when dealing with small information units rather than with large ones (countries, large regions, provinces in China, counties and states in the USA, etc.). The latter scale is typical in the literature on air pollution due to the difficulties in finding data on its drivers at a true local scale. Accordingly, this paper has a double objective. The first is the estimation of a spatial panel data STIRPAT model, with the spatial units being both very small and also highly autonomous, developed municipalities. The second is to examine whether an environmental Kuznets curve relationship exists between income per capita and NOx concentrations. A case study has been carried out in the Autonomous Community of Madrid, Spain, at the municipal level. [ABSTRACT FROM AUTHOR]