Temporal Dependence Research Articles

A Novel Wind Power Prediction Model That Considers Multi-Scale Variable Relationships and Temporal Dependencies

Wind power forecasting is a critical technology for promoting the effective integration of wind energy. To enhance the accuracy of wind power predictions, this paper introduces a novel wind power prediction model that considers the evolving relationships of multi-scale variables and temporal dependencies. In this paper, a multi-scale frequency decomposition module is designed to split the raw data into high-frequency and low-frequency parts. Subsequently, features are extracted from the high-frequency information using a multi-scale temporal graph neural network combined with an adaptive graph learning module and from the low-frequency data using an improved bidirectional temporal network. Finally, the features are integrated through a cross-attention mechanism. To validate the effectiveness of the proposed model, extensive comprehensive experiments were conducted using a wind power dataset provided by the State Grid. The experimental results indicate that the MSE of the model proposed in this paper has decreased by an average of 7.1% compared to the state-of-the-art model and by 48.9% compared to the conventional model. Moreover, the improvement in model performance becomes more pronounced as the prediction horizon increases.

Integrating spatial and temporal features for enhanced artifact removal in multi-channel EEG recordings

Objective.Various artifacts in electroencephalography (EEG) are a big hurdle to prevent brain-computer interfaces from real-life usage. Recently, deep learning-based EEG denoising methods have shown excellent performance. However, existing deep network designs inadequately leverage inter-channel relationships in processing multi-channel EEG signals. Typically, most methods process multi-channel signals in a channel-by-channel way. Considering the correlations among EEG channels during the same brain activity, this paper proposes utilizing channel relationships to enhance denoising performance.Approach.We explicitly model the inter-channel relationships using the self-attention mechanism, hypothesizing that these correlations can support and improve the denoising process. Specifically, we introduce a novel denoising network, named spatial-temporal fusion network (STFNet), which integrates stacked multi-dimension feature extractor to explicitly capture both temporal dependencies and spatial relationships.Main results.The proposed network exhibits superior denoising performance, with a 24.27% reduction in relative root mean squared error compared to other methods on a public benchmark. STFNet proves effective in cross-dataset denoising and downstream classification tasks, improving accuracy by 1.40%, while also offering fast processing on CPU.Significance.The experimental results demonstrate the importance of integrating spatial and temporal characteristics. The computational efficiency of STFNet makes it suitable for real-time applications and a potential tool for deployment in realistic environments.

LLMDiff: Diffusion Model Using Frozen LLM Transformers for Precipitation Nowcasting.

Precipitation nowcasting, which involves the short-term, high-resolution prediction of rainfall, plays a crucial role in various real-world applications. In recent years, researchers have increasingly utilized deep learning-based methods in precipitation nowcasting. The exponential growth of spatiotemporal observation data has heightened interest in recent advancements such as denoising diffusion models, which offer appealing prospects due to their inherent probabilistic nature that aligns well with the complexities of weather forecasting. Successful application of diffusion models in rainfall prediction tasks requires relevant conditions and effective utilization to direct the forecasting process of the diffusion model. In this paper, we propose a probabilistic spatiotemporal model for precipitation nowcasting, named LLMDiff. The architecture of LLMDiff includes two networks: a conditional encoder-decoder network and a denoising network. The conditional network provides conditional information to guide the denoising network for high-quality predictions related to real-world earth systems. Additionally, we utilize a frozen transformer block from pre-trained large language models (LLMs) in the denoising network as a universal visual encoder layer, which enables the accurate estimation of motion trend by considering long-term temporal context information and capturing temporal dependencies within the frame sequence. Our experimental results demonstrate that LLMDiff outperforms state-of-the-art models on the SEVIR dataset.

Supplemental Material for Variance (Un)Explained: Experimental Conditions and Temporal Dependencies Explain Similarly Small Proportions of Reaction Time Variability in Linear Models of Perceptual and Cognitive Tasks

Supplemental Material for Variance (Un)Explained: Experimental Conditions and Temporal Dependencies Explain Similarly Small Proportions of Reaction Time Variability in Linear Models of Perceptual and Cognitive Tasks

TBConvL-Net: A hybrid deep learning architecture for robust medical image segmentation

Deep learning has shown great potential for automated medical image segmentation to improve the precision and speed of disease diagnostics. However, the task presents significant difficulties due to variations in the scale, shape, texture, and contrast of the pathologies. Traditional convolutional neural network (CNN) models have certain limitations when it comes to effectively modelling multiscale context information and facilitating information interaction between skip connections across levels. To overcome these limitations, a novel deep learning architecture is introduced for medical image segmentation, which takes advantage of CNNs and vision transformers. Our proposed model, named TBConvL-Net, involves a hybrid network that combines the local features of a CNN encoder–decoder architecture with long-range and temporal dependencies using biconvolutional long-short-term memory (LSTM) networks and vision transformers (ViT). This enables the model to capture contextual channel relationships in the data and account for the uncertainty of the segmentation over time. Additionally, we introduce a novel composite loss function that considers both segmentation robustness and boundary agreement of the predicted output with the gold standard. Our proposed model shows consistent improvement over the state of the art on ten publicly available datasets of seven different medical imaging modalities.

Economic sanctions and energy efficiency: Evidence from Iranian industrial sub-sectors

Improving energy efficiency is vital for reducing energy consumption and can have substantial impacts on reducing carbon emissions. This study investigates the impact of sanctions on Iran's energy efficiency across different industrial sub-sectors from 2015 to 2019. We compute a sanction intensity index for each industrial sub-sector using principal component analysis. This index measures how much each sub-sector has been affected by sanctions. Additionally, energy efficiency is measured using the directional distance function method, considering the emission impacts as undesirable outputs. We use fixed effects regression analysis, adjusting for various manifestations of cross-sectional (spatial) and temporal dependence and controlling for other sectoral drivers of energy efficiency. We find a significant negative effect of sanction intensity on energy efficiency at the industrial sub-sector level in Iran. The negative effect of sanctions on energy efficiency is significantly larger for industrial units with higher import dependency.

Forecasting Urban Traffic States with Sparse Data Using Hankel Temporal Matrix Factorization

Forecasting urban traffic states is crucial to transportation network monitoring and management, playing an important role in the decision-making process. Despite the substantial progress that has been made in developing accurate, efficient, and reliable algorithms for traffic forecasting, most existing approaches fail to handle sparsity, high-dimensionality, and nonstationarity in traffic time series and seldom consider the temporal dependence between traffic states. To address these issues, this work presents a Hankel temporal matrix factorization (HTMF) model using the Hankel matrix in the lower dimensional spaces under a matrix factorization framework. In particular, we consider an alternating minimization scheme to optimize the factor matrices in matrix factorization and the Hankel matrix in the lower dimensional spaces simultaneously. To perform traffic state forecasting, we introduce two efficient estimation processes on real-time incremental data, including an online imputation (i.e., reconstruct missing values) and an online forecasting (i.e., estimate future data points). Through extensive experiments on the real-world Uber movement speed data set in Seattle, Washington, we empirically demonstrate the superior forecasting performance of HTMF over several baseline models and highlight the advantages of HTMF for addressing sparsity, nonstationarity, and short time series. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: This research was supported by the Institute for Data Valorisation, the Interuniversity Research Centre on Enterprise Networks, Logistics and Transportation, the National Natural Science Foundation of China [Grants 12371456, 72101049, 72232001], the Sichuan Science and Technology Program [Grant 2024NSFJQ0038], and the Fundamental Research Funds for the Central Universities [Grant DUT23RC(3)045].

An implicit solution for Asay foil trajectories generated by separable, sustained-production ejecta source models

We present a simple implicit solution for the time-dependent trajectory of a thin Asay foil ejecta diagnostic for the general case where the impinging ejecta cloud is generated by a source function characterized by an arbitrary (sustained) time dependence and a time-independent (stationary) particle velocity distribution. In the limit that the source function time dependence becomes a delta function, this solution—which is amenable to rapid numerical calculations of arbitrary accuracy—exactly recovers a previously published solution for the special case of instantaneous ejecta production. We also derive simple expressions for the free-surface arrival (catch-up) time as well as the true ejecta areal mass accumulation on the accelerating foil and place bounds on the level of error incurred when applying instant-production mass solutions to a sustained-production trajectory. We demonstrate these solutions with example calculations for hypothetical source functions spanning a wide range of ejecta production durations, velocity distributions, and temporal behaviors. These calculations demonstrate how the foil trajectory is often insensitive to the temporal dependence of the source function, instead being dominated by the velocity distribution. We quantify this insensitivity using a “compatibility score” metric. Under certain conditions, one may capitalize upon this insensitivity to obtain a good approximation of the second integral of the velocity distribution from the observed foil trajectory.

Vehicle trajectory prediction method integrating spatiotemporal relationships with hybrid time-step scene interaction

In vehicle trajectory prediction, constructing the interactive relationships among vehicles within the traffic environment poses a significant challenge. Existing models predominantly focus on temporal dependencies within vehicle histories and spatial correlations among neighboring vehicles, overlooking the continuous influence of historical vehicle states on the current time step and the interplay of multiple sequences over time. To address these limitations, we propose a method for multimodal vehicle trajectory prediction that integrates Hybrid Time-step Scene Interaction (HTSI) into the spatiotemporal relationships. Firstly, we introduce the HTSI module, comprising Multi-step Temporal Information Aggregation (MTIA) and Single-step Temporal Information Aggregation (STIA) methods. MTIA utilizes multi-head attention mechanisms to capture temporal dependencies between consecutive frames, thereby generating new time series amalgamating the ongoing influence of historical time states on the current timestamp. Simultaneously, STIA employs multi-head attention mechanisms to capture the spatial dimension weights of multiple time series and, by aggregating spatial interaction features at each timestamp, generates new time series fused with spatial interaction influences. Subsequently, feature extraction is performed through LSTM layers. Moreover, we propose an improved DIPM pooling module, improving the model’s long-term prediction capability by selectively reusing historical hidden states. Ultimately, based on training results from the HighD and NGSIM datasets, our model demonstrates significant advantages in long-term prediction compared to other state-of-the-art trajectory prediction models. Specifically, within the 5 s prediction window, the model achieved a root mean square error (RMSE) of 2.79 m on the NGSIM dataset, representing a 33.62% improvement over the baseline model’s average accuracy. Additionally, on the HighD dataset, the model attained an RMSE of 2.16 m, reflecting a 33.43% enhancement. The crucial code can be obtained from the provided link: https://github.com/gyhhq/Prediction-trajectory .

Sea clutter prediction based on fusion of Fourier transform and graph neural network

ABSTRACT Radar is a crucial tool for remote sensing and monitoring of marine environments. However, its effectiveness is significantly influenced by sea clutter. The complex interplay between radar parameters and various maritime environmental factors gives rise to a dynamic and intricate sea clutter pattern. The conventional approach to sea clutter prediction only considers the temporal dependence, neglecting the spatial changes. To address this limitation, this study proposes the Fusion of Fourier Transform and Graph Neural Network (FFTaGNN) to enhance the accuracy of multi-dimensional sea clutter data forecasting. FFTaGNN captures the correlations and time dependencies among sequences in the spectral domain. By combining the discrete Fourier transform (DFT) and graph Fourier transform (GFT), it extracts the temporal correlation characteristics and establishes correlations between multidimensional sea clutter data sequences. Importantly, FFTaGNN can automatically discover data correlations between sequences without relying on predetermined priors. To validate the effectiveness of the model, an experimental verification process is conducted, considering different grazing angles and sea clutter High Range Resolution Profile (HRRP) data. The results of the experiment demonstrate that the proposed strategy achieves a minimum Root Mean Square Error (RMSE) of 0.0574 in predicting sea clutter HRRP data. This technique holds great potential in effectively suppressing sea clutter, thereby enhancing the overall performance of radar systems in marine environments and small target detection capabilities at the sea surface.

Graph network-based human movement prediction for socially-aware robot navigation in shared workspaces

AbstractMethods for socially-aware robot path planning are increasingly needed as robots and humans increasingly coexist in shared industrial spaces. The practice of clearly separated zones for humans and robots in shop floors is transitioning towards spaces where both humans and robot operate, often collaboratively. To allow for safer and more efficient manufacturing operations in shared workspaces, mobile robot fleet path planning needs to predict human movement. Accounting for the spatiotemporal nature of the problem, the present work introduces a spatiotemporal graph neural network approach that uses graph convolution and gated recurrent units, together with an attention mechanism to capture the spatial and temporal dependencies in the data and predict human occupancy based on past observations. The obtained results indicate that the graph network-based approach is suitable for short-term predictions but the rising uncertainty beyond short-term would limit its applicability. Furthermore, the addition of learnable edge weights, a feature exclusive to graph neural networks, enhances the predictive capabilities of the model. Adding workspace context-specific embeddings to graph nodes has additionally been explored, bringing modest performance improvements. Further research is needed to extend the predictive capabilities beyond the range of scenarios captured through the original training, and towards establishing standardised benchmarks for testing human motion prediction in industrial environments.

Risk spillovers and diversification benefits between crude oil and agricultural commodity futures markets

This study examines the dependence structure and risk spillovers between crude oil and eight major agricultural futures (wheat, corn, soybean coffee, cotton, lumber, cocoa, and live cattle) markets. It also analyzes the potential conditional diversification benefits using a variety of copula functions and Conditional Value at Risk (CoVaR) measure. The results show significant crisis-sensitive and temporal dependence between oil and agricultural markets. Moreover, crude oil shows a symmetric tail dependence with both wheat, corn, soybeans, and cotton futures, whereas oil exhibits an average dependence with coffee. A strong dependence is observed between oil and cocoa (lumber) during bearish (bullish) market conditions. Oil and Live cattle have a symmetric dependence during bearish and bullish market conditions. On the other hand, we find asymmetric and bidirectional risk spillovers from oil to agricultural markets. Furthermore, the wheat futures contract appears to be the most dominating and vulnerable asset to oil price shocks, followed by lumber and corn futures, respectively, while the live cattle contracts are the least. Finally, an equally weighted portfolio offers the highest diversification benefits at a 5 % expected shortfall.

HybridCBAMNet: Enhancing time series binary classification with convolutional recurrent networks and attention mechanisms

The rapid advancement of Internet of Things technology and the increasing availability of big data have resulted in an exponential growth of time series data, highlighting a pressing need for effective classification methods. This study introduces HybridCBAMNet, a novel convolutional recurrent neural network model enhanced with recurrent networks and attention mechanisms for binary time series classification. The architecture integrates Conv1D-based feature extraction modules to extract relevant features, alongside attention enhancement modules and convolutional block attention modules. Additionally, bidirectional recurrent units are utilized to capture temporal dependencies and contextual information in both forward and backward directions. The model achieves top F1-scores in seven out of thirty-six binary classification tasks, significantly surpassing the performance of fourteen existing state-of-the-art models from the UCR archive. These results demonstrate that HybridCBAMNet not only enhances classification accuracy but also improves the model generalization capabilities, contributing valuable insights to the field of time series analysis.

Research on Fault Diagnosis of Rolling Bearing Based on Gramian Angular Field and Lightweight Model.

Due to the limitations of deep learning models in processing one-dimensional signal feature extraction, and high model complexity leading to low training accuracy and large consumption of computing resources, this paper innovatively proposes a rolling bearing fault diagnosis method based on Gramian Angular Field (GAF) and enhanced lightweight residual network. Firstly, the one-dimensional signal is transformed into a two-dimensional GAF image, fully preserving the signal's temporal dependency. Secondly, to address the parameter redundancy and high computational complexity of the ResNet-18 model, its residual blocks are improved. The second convolutional layer in the downsampling residual blocks is removed, traditional convolutional layers are replaced with depthwise separable convolutions, and the lightweight Efficient Channel Attention (ECA) module is embedded after each residual block. This further enhances the model's ability to capture key features while maintaining low computational cost, resulting in a lightweight model referred to as E-ResNet13. Finally, the generated GAF feature maps are fed into the E-ResNet13 model for training, and through a global average pooling layer, they are mapped to a fully connected layer for classifying the faults of rolling bearings. Verifying the superiority of the proposed GAF-E-ResNet13 model, experimental results show that the GAF image encoding method achieves higher fault recognition accuracy compared to other encoding methods. Compared with other intelligent diagnosis methods, the E-ResNet13 model demonstrates strong diagnostic performance and generalization capability under both a single condition and complex varying conditions, fully proving the innovation and practicality of this method.

Privacy-preserving coordination of power and transportation networks using spatiotemporal GAT for predicting EV charging demands

The gradual replacement of conventional-fuel vehicles by electric vehicles (EVs) in recent years provides a growing incentive for the collaborative optimization of power distribution networks (PDNs) and urban transportation networks (UTNs). However, the implementation of a centralized optimization model for PDNs and UTNs is currently unrealistic due to the requirement for establishing information privacy barriers between the two independently operated networks. The present work proposes a predict-then-optimize (PTO) framework that combines Spatiotemporal Graph Attention Network (STGAT) with enhanced queueing theory to achieve accurate prediction of EV charging demands. Building upon this, it efficiently coordinates optimization between the PDN and UTN, while preserving the information privacy of both independently operated networks. Specifically, the proposed STGAT model predicts vehicle flow by simultaneously exploiting the dynamic temporal and spatial dependencies in the historical traffic data of the target UTN. It then converts the predicted flow into spatiotemporal EV charging demands using an enhanced queuing model that considers the service capacity constraints of charging stations (CSs) and the behavior of EV users. Subsequently, the predicted EV charging demands are integrated into a multi-period PDN scheduling model. The results of numerical computations based on an IEEE 33-bus PDN and real-world traffic flow datasets demonstrate that the scheduling results provided by the proposed approach differ by only 0.5% compared to results obtained when applying actual EV charging demands.

SENGraph: A Self-Learning Evolutionary and Node-Aware Graph Network for Soft Sensing in Industrial Processes.

The last decade has witnessed the growing prevalence of deep models on soft sensing in industrial processes. However, most of the existing soft sensing models are developed to learn from regular data in the Euclidean space, ignoring the complex coupling relations among process variables. On the other hand, graph networks are gaining attraction in handling non-Euclidean relations in industrial data. However, the existing graph networks on soft sensing models still suffer from two major issues: 1) how to capture the intervariable structural relations and intravariable temporal dependencies from dynamic and strongly coupled industrial data and 2) how to learn from nodes with distinctive importance for the soft sensing task. To address these problems, we propose a self-learning evolutionary and node-aware graph network (SENGraph) for industrial soft sensing. We first develop a self-learning graph generation (SLG) module to combine the coarse-and fine-grained graphs to capture the global trend and local dynamics from process data. Then, we build a self-evolutionary graph module (EGM) to obtain diversified node features from the entire graph using mutation and crossover strategies. Finally, we design a node-aware module (NAM) to highlight the informative nodes and suppress the less significant ones to further improve the discriminative ability of the downstream soft sensing. Extensive experimental results and analysis on four real-world industrial datasets demonstrate that our proposed SENGraph model outperforms the existing state-of-the-art (SOTA) soft sensing methods.

Physical model learning based false data injection attack on power system state estimation

The cyber security of power system state estimation (PSSE) is crucial, and its robustness against evolving false data injection attacks (FDIA) is being rigorously assessed to develop advanced countermeasures. Existing FDIA methods have achieved satisfactory success rates but often fail to align with practical constraints such as the assumption of partial or complete knowledge of the power system network by the attacker, modifications in generator output measurements, and the sparsity of the attacks. This work proposes a near practical, stealthy approach using a deep generative adversarial network-long short-term memory autoencoder (GAN-LSTMAE) learning based sparse FDIA method against AC PSSE, leveraging only measurement data. To evade the bad data detection (BDD) mechanism effectively, an LSTMAE-based PSSE mimic is proposed, further optimizing the GAN-based attack generator to embed the physical laws of the system along with measurement residuals and temporal dependencies of states to the generated false data. The proposed modified training data preparation algorithm, coupled with the attack sub-graph method, defines the optimal attack region while keeping generator output measurements intact. The generated attack is validated extensively using IEEE 14 and 118 bus test benchmarks against various defense techniques, demonstrating high success rates.

A novel hybrid BWO-BiLSTM-ATT framework for accurate offshore wind power prediction

Accurate wind power forecasting is pivotal in facilitating the efficient integration of renewable energy sources into existing power grids. This study proposes a novel hybrid framework, termed BWO-BiLSTM-ATT, which synergistically combines the strengths of a bidirectional long short-term memory (BiLSTM) network, a self-attention mechanism, and the Beluga Whale Optimization (BWO) algorithm. The BiLSTM architecture, with its unique ability to capture bidirectional temporal dependencies, effectively models the intricate dynamics present in wind power time series data. Integrating the self-attention mechanism further enhances the model's performance by discerning and emphasizing the most salient features within the input data. Furthermore, employing the BWO algorithm optimizes the model's hyperparameters, ensuring optimal configuration and enhancing its predictive accuracy and generalization capabilities. The proposed BWO-BiLSTM-ATT framework was rigorously evaluated using real-world data from an offshore wind farm in Yangjiang City, China. Comparative analyses were conducted against several baseline algorithms, including persistence, ARIMA, SVR, and vanilla LSTM models. The results demonstrate the superior performance of the BWO-BiLSTM-ATT framework, achieving higher R-squared and explained variance scores, coupled with lower error metrics such as MSE, RMSE, MedAE, and MAE. Statistical significance tests further corroborated the substantial performance improvements offered by the proposed framework. The combination of advanced deep learning techniques and metaheuristic optimization algorithms embedded in the BWO-BiLSTM-ATT framework provides a robust and accurate solution for wind power forecasting, enabling efficient management and seamless integration of renewable energy resources into existing power grids.

TFformer: A time–frequency domain bidirectional sequence-level attention based transformer for interpretable long-term sequence forecasting

Transformer methods have shown strong predictive performance in long-term time series prediction. However, its attention mechanism destroys temporal dependence and has quadratic complexity. This makes prediction processes difficult to interpret, limiting their application in tasks requiring interpretability. To address this issue, this paper proposes a highly interpretable long-term sequence forecasting model, TFformer. TFformer decomposes time series into low frequency trend component and high frequency period component by frequency decomposition, and forecasts them respectively. The periodic information in high-frequency component is enhanced with the sequential frequency attention, and then the temporal patterns of the two components are obtained by feature extraction. According to the period property in time domain, TFformer through periodic extension to predict the future period patterns using sequential periodic matching attention. Finally, the predicted future period pattern and the extracted trend pattern are reconstructed to future series. TFformer provides an interpretable forecasting process with low time complexity, as it retains temporal dependence using sequence-level attentions. TFformer achieves significant prediction performance in both univariate and multivariate forecasting across six datasets. Detailed experimental results and analyses verify the effectiveness and generalization of TFformer.

Predicting Stock Prices in the Electric Vehicle and Technology Sectors Using Long Short-Term Memory Models

Forecasting stock prices is a complex task because of the volatility and intricate temporal dependencies present in financial markets. Long Short-Term Memory (LSTM) networks, known for their proficiency in handling extended time-series data, offer an effective solution to these challenges. This paper delves into the applications in LSTM networks to forecast stock prices for various companies in the electric vehicle and related sectors, specifically examining data from Tesla, BYD, Panasonic, and NVIDIA. The study assesses the predictive accuracy and performance of these models using RMSE, MSE, MAE, and R metrics. By comparing these metrics across different companies, the paper provides an in-depth analysis of LSTM networks' effectiveness in financial forecasting. The findings indicate that when LSTM networks are optimized through hyperparameter tuning and architectural adjustments, they can accurately identify patterns in stock price data, offering valuable insights for investors and analysts in the electric vehicle, technology, and energy industries.