Temporal Network Model Research Articles

Pressure and Temperature Prediction of Oil Pipeline Networks Based on a Mechanism-Data Hybrid Driven Method

To ensure the operational safety of oil transportation stations, it is crucial to predict the impact of pressure and temperature before crude oil enters the pipeline network. Accurate predictions enable the assessment of the pipeline’s load-bearing capacity and the prevention of potential safety incidents. Most existing studies primarily focus on describing and modeling the mechanisms of the oil flow process. However, monitoring data can be skewed by factors such as instrument aging and pipeline friction, leading to inaccurate predictions when relying solely on mechanistic or data-driven approaches. To address these limitations, this paper proposes a Temporal-Spatial Three-stream Temporal Convolutional Network (TS-TTCN) model that integrates mechanistic knowledge with data-driven methods. Building upon Temporal Convolutional Networks (TCN), the TS-TTCN model synthesizes mechanistic insights into the oil transport process to establish a hybrid driving mechanism. In the temporal dimension, it incorporates real-time operating parameters and applies temporal convolution techniques to capture the time-series characteristics of the oil transportation pipeline network. In the spatial dimension, it constructs a directed topological map based on the pipeline network’s node structure to characterize spatial features. Data analysis and experimental results show that the Three-stream Temporal Convolutional Network (TTCN) model, which uses a Tanh activation function, achieves an error rate below 5%. By analyzing and validating real-time data from the Dongying oil transportation station, the proposed hybrid model proves to be more stable, reliable, and accurate under varying operating conditions.

Temporal Convolutional Network-based Approach for Forecasting Fluctuations Differential Pressure in Reverse Osmosis Systems

Providing forecasts of pressure fluctuations and changes will aid in selecting appropriate maintenance strategies to optimize efficiency and costs. This paper presents a deep-learning-based model to forecast the degradation evolution of membrane biological fouling in RO (Reverse Osmosis) systems. Although applying deep learning in forecasting still faces many challenges, applying convolutional operations in convolution 1D has yielded promising results for sequential data, particularly time series data. Thus, in this paper we study and develop the 1D convolution operation-based Temporal Convolutional Network (TCN) model to predict pressure dynamics at both ends of the RO vessel. In addition, since the deep learning technique has yet to be widely explored in this field, thus we also need to pre-process the data collected from the Carlsbad Desalination Plant in California, such as the proposed model can identify complex relationships between timestamps and pressure features. The experiment results were evaluated and compared with other existing models, such as LSTM, CNN & LSTM, and GRU. The obtain results show that the TCN-based prediction model had the slightest error in the test dataset.

A multiple behaviour temporal network analysis for health behaviours during COVID-19.

The aim of this study was to examine the temporal dynamics of multiple health behaviours (physical activity, alcohol consumption, healthy eating, cigarette consumption, recreational drug use, vaping), and pandemic-related health behaviours (e.g., hand washing, physical distancing) using network psychometrics. The International COVID-19 Awareness and Responses Evaluation (iCARE) study is an international multi-wave observational cohort study of public awareness, attitudes, and responses to public health policies implemented to reduce the spread of COVID-19 on people around the world. A sub-sample of longitudinal data from Canadians (n = 254) was analysed across four waves (February-July 2020). We used temporal network models to fit temporal networks, contemporaneous networks, and between-subject networks from items within the iCARE survey. Positive temporal associations were observed between physical activity and healthy eating, and a bidirectional relationship was evident between outdoor mask use and vaping. A contemporaneous network revealed positive associations between consumption behaviours (vaping, cigarette use, alcohol use, and recreational drug use), and negative associations between physical activity and drug use, and healthy eating and cigarette use. Health behaviours are interconnected and can be modelled as networks or behavioural systems. The application of temporal network analysis to the study of multiple health behaviours is well suited to address key research questions in the field such as 'how do multiple health behaviours co-vary with one another over time'. Future research using time series data and measuring affective and cognitive mediators of behaviour, in addition to health behaviours, has the potential to contribute valuable hypothesis-generating insights.

CDO-TCN-BiGRU: An Optimized Hybrid Deep Learning Model for Shared Bicycles Demand Forecasting

<div>Accurate prediction of the demand for shared bicycles is not only conducive to the operation of relevant enterprises, but also conducive to improving the image of the city, facilitating people’s travel, and solving the balance between supply and demand of bicycles in the region. To precisely predict the demand of shared bicycles, a model combining temporal convolution network (TCN) and bidirectional gating recurrent unit (BiGRU) model is proposed, and the Chernobyl disaster optimizer (CDO) is used to optimize its hyperparameters. It has the ability of TCN to extract sequence features and gated recurrent unit (GRU) to mine time series data and combine the characteristics of CDO with fast convergence and high global search ability, so as to reduce the influence of model hyperparameters. This article selects the shared bicycles travel data in Washington, analyzes its multi-characteristics, and trains it as the input characteristics of the model. In the experiments, we performed comparison study and ablation study. The results show that the prediction error of the proposed model is less than other comparative models. Therefore, CDO-TCN-BiGRU model has the characteristics of high prediction precision and good stability.</div>

Rapid and high-accuracy concentration prediction of gas mixtures based on PMH-TCN

In industrial environments, the flammable gas ethylene (C2H4) and toxic gas carbon monoxide (CO) often coexist. To ensure worker safety, it is essential to predict these gas concentrations quickly and accurately. Many studies lack prediction accuracy or speed due to insufficient time feature extraction and loss of critical features. In this work, a novel approach called the Parametric Rectified Linear Unit (PReLU)-based Multi-Head Attention Temporal Convolutional Network (PMH-TCN) model was devised to efficiently and precisely predict gas concentrations in mixtures. The model is capable of accurately predicting the gas concentration within 5 s after the introduction of the target gas. In the 5-fold cross-validation, the values of Adjusted R-Square (R2), Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of the PMH-TCN model reached 0.9850, 0.0448, and 0.0651 respectively. It was shown that the PMH-TCN model offered a very efficient method for the quick identification of electronic noses.

SWL-LSE: A Dataset of Health-Related Signs in Spanish Sign Language with an ISLR Baseline Method

Progress in automatic sign language recognition and translation has been hindered by the scarcity of datasets available for the training of machine learning algorithms, a challenge that is even more acute for languages with smaller signing communities, such as Spanish. In this paper, we introduce a dataset of 300 isolated signs in Spanish Sign Language, collected online via a web application with contributions from 124 participants, resulting in a total of 8000 instances. This dataset, which is openly available, includes keypoints extracted using MediaPipe Holistic. The goal of this paper is to describe the construction and characteristics of the dataset and to provide a baseline classification method using a spatial–temporal graph convolutional network (ST-GCN) model, encouraging the scientific community to improve upon it. The experimental section offers a comparative analysis of the method’s performance on the new dataset, as well as on two other well-known datasets. The dataset, code, and web app used for data collection are freely available, and the web app can also be used to test classifier performance on-line in real-time.

Landslide displacement prediction using time series InSAR with combined LSTM and TCN: application to the Xiao Andong landslide, Yunnan Province, China

AbstractResearch on landslide displacement prediction based on interferometric synthetic aperture radar (InSAR) deformation data involves two main issues. First, InSAR can provide only one-dimensional deformation data along the satellite’s line of sight (LOS), which cannot truly reflect the deformation of the landslide body in the downward direction along the slope. Second, the use of a single prediction model does not adequately account for both long-term and local changes in landslide displacement, affecting the accuracy of the predictions. To address this, in this study, Long Short-Term Memory networks (LSTM) and temporal convolutional network (TCN) models are combined to construct a method (LSTM-TCN) of landslide displacement prediction. This method can consider the long-term and localized changes in landslide displacement. The method is first based on InSAR technology to obtain surface deformation. The deformation of the landslide is subsequently computed in the downward direction along the slope to obtain the landslide displacement time series data. Next, the LSTM-TCN is used for landslide displacement prediction. Finally, the mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination (R2) are used to evaluate the performance of the model. The experiment is conducted on the Xiao Andong landslide in Anshi village, Fengqing County, Lincang City, Yunnan Province, China. The LSTM-TCN model achieves an R2 of 0.75, an RMSE of 0.43 cm, and an MAE of 0.36 cm. Compared with the individual LSTM and TCN models, the LSTM-TCN model exhibits the highest prediction accuracy and the smallest prediction error, which is closer to the true result that in the other models. These results demonstrate that the combined LSTM-TCN model effectively captures the complex features and long-term trends in landslide displacement data, significantly enhancing the accuracy of predictions.

A detection model for false data injection attacks in smart grids based on graph spatial features using temporal convolutional neural networks

Due to the intelligence and opening of future generation cyber–physical power systems, smart grids are vulnerable to the emergency of cyber-attacks aiming at the cyber–physical systems. Among these attacks, false data injection (FDI) attacks are particularly concerning in smart grids due to their stealthiness. Attackers can tamper with data transmitted through communication networks, influencing the analysis results of the control center, leading it to make wrong decisions and thereby undermining the stability of smart grids. The inability of traditional bad data detection models to detect false data injection attacks poses huge security risks to smart grids. For this reason, a new attack detection model using spatial–temporal features is proposed. The proposed detection model includes the following two parts: spatial features extraction and temporal convolutional network. First, graph convolutional operations are employed to disentangle the interactions among buses and extract spatial features of measurement; Then, the temporal convolutional network model is used to extract the temporal features. Through these processes, the proposed detection model can effectively identify the injected false data injection attacks in smart grids. The detection performance and robustness of the proposed FDI attack detection model are tested through simulations on IEEE 14-bus and 118-bus grid systems.

Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain

Electrocardiographic signals (ECG) are ubiquitous, which justifies the research of their optimal storage and transmission. However, proposals for non-uniform signal sampling must take into account the priority of diagnostic data accuracy and record integrity, as well as robustness to noise and interference. In this study, two novel methods are introduced, each utilizing a distinct neural network architecture for optimizing non-uniform sampling of ECG signal. A transformer model refines each time point selection through an iterative process using gradient descent optimization, with the goal of minimizing the mean squared error between the original and resampled signals. It adaptively modifies time points, which improves the alignment between both signals. In contrast, the Temporal Convolutional Network model trains on the original signal, and gradient descent optimization is utilized to improve the selection of time points. Evaluation of both strategies’ efficacy is performed by calculating signal distances at lower and higher sampling rates. First, a collection of synthetic data points that resembled the P-QRS-T wave was used to train the model. Then, the ECG-ID database for real data analysis was used. Filtering to remove baseline wander followed by evaluation and testing were carried out in the real patient data. The results, in particular MSE = 0.0005, RMSE = 0.0216, and Pearson’s CC = 0.9904 for 120 sps in the case of the transformer patient data model, provide viable paths for maintaining the precision and dependability of ECG-based diagnostic systems at much lower sampling rate. Outcomes indicate that both techniques are effective at improving the fidelity between the original and modified ECG signals.

A Combined Long Short-Term Memory and Temporal Convolutional Network Model for Crop Yield Prediction

A Combined Long Short-Term Memory and Temporal Convolutional Network Model for Crop Yield Prediction

A novel spatio-temporal attention-based bidirectional LSTM model for moisture content prediction in drying process

Accurate prediction of moisture content is significantly crucial for ensuring process stability and product quality in the cylinder drying process. However, the drying process exhibits complex spatio-temporal characteristics and strong interference, which make accurate prediction challenging for the deep learning approach. To address this issue, this article proposes a new spatio-temporal attention-based bidirectional long-short temporal memory network (STA-BiLSTM) model for accurate moisture content prediction. First, Maximum Relevance Minimum Redundancy (mRMR) is adopted to identify optimal features highly related to moisture content. Secondly, bidirectional long-short temporal memory (Bi-LSTM) network is utilized to extract temporal dependencies from the sequential data. Subsequently, spatio-temporal attention mechanisms are designed to adaptively focus on the most relevant features and timesteps, enhancing the model’s generalization ability. Finally, due to the harsh industrial environment, eXtreme Gradient Boosting (XGBoost) is adapted to improve generalizability and robustness. Extensive experiments on a real industrial dataset of the drying process demonstrate that the proposed STA-BiLSTM approach significantly outperforms alternative approaches for predicting moisture content, validating its effectiveness and superiority.

Modeling the two-dimensional variations in EEG signals to analyze the impact of music on sleep states

Variations in music intensity and pitch can significantly impact sleep and alleviate insomnia through relaxing music. Traditional EEG analysis methods struggle with capturing temporal features and managing time-series data complexity. To address these challenges, we propose an improved Temporal Network model integrated with a Temporal Self-Attention (TSA) mechanism. This model enhances time-step feature capture in EEG signals, transforming one-dimensional EEG data into two-dimensional tensors to capture multi-scale temporal features. Experiments on the DEAP dataset demonstrate significant performance improvements, with 84.26% accuracy, 90.06% precision, and 97.82% recall, outperforming current models. Our model effectively analyzes the impact of relaxing music on different sleep stages, providing insights for improving sleep quality. Future work will optimize the model structure, incorporate additional deep learning techniques, and expand the scope to include multiple physiological signals, aiming to enhance the clinical value for sleep disorder diagnosis and personalized music therapy.

Longitudinal correlates of learning burnout among Chinese adolescents during the COVID-19 pandemic: A cross-lagged panel network analysis

BackgroundLearning burnout as a serious psychological distress problem among adolescents during the COVID-19 pandemic was investigated using the cross-lagged panel network models. MethodsA three-wave study using a sample of 11 to 18-year-olds in China was conducted, with baseline data collected in June 2020 (n = 4156) and follow-ups in December 2020 (n = 3209) and August 2021 (n = 2324). Two temporal cross-lagged panel network models were computed to analyze adolescent learning burnout over time. ResultsThe predictive pathway of adolescent learning burnout demonstrates significant temporal specificity. In the early outbreak period, Positive thinking, Appreciation of life and Depression are the most influential predictive symptoms. In the normalized epidemic prevention period, Goal planning, Affect control and Positive thinking are the most influential predictive symptoms. However, during this period, the extent to which adolescent learning burnout is predicted by other symptoms in the networks is significantly reduced. LimitationsThe samples used in this study are not expected to be nationally representative, and therefore the generalizability of the results may be limited. ConclusionsThese findings highlight the predictive roles of Positive thinking, Appreciation of life, and Depression in adolescent learning burnout and the importance of timely intervention on these symptoms in the early outbreak period of public health emergency similar to the COVID-19 pandemic. Findings also illustrate the essentiality of eliminate unstable factors in the school environment during the normalized epidemic prevention period.

Damage identification for UAV composite propeller blades based on transmissibility probabilistic distance and attention bidirectional temporal convolutional network

Damage identification of composite propeller blades is critical to the operational safety of unmanned aerial vehicles (UAVs). The transmissibility function (TF) was employed to characterize the damage and its probabilistic distance was used to deal with the uncertainty problem. The damage indicator fusing multiple TFs in a specific frequency band was proposed to detect the blade damage. In addition, to localize the damage in the blade, an attentional bidirectional temporal convolutional network (ABiTCN) model was developed, in which the Squeezeand-Excitation (SE) attention module was introduced to enhance the model’s capability to learn critical features. The proposed method was investigated by numerical and experimental cases. The results showed that the proposed damage indicator has more sensitivity to weak damage and better robustness than the common indicator. The established ABiTCN model predicted the positions of the damages with 91.89 % accuracy, which outperforms other methods in terms of accuracy and convergence speed.

Fusion of Multiple Data Sources for Vehicle Crashworthiness Prediction Using CycleGAN and Temporal Convolutional Networks

Abstract Computer-aided engineering (CAE) models play a pivotal role in predicting crashworthiness of vehicle designs. While CAE models continue to advance in fidelity, an inherent discrepancy between CAE model predictions and the responses of physical tests remains inevitable. Machine learning (ML) models have shown promising potential in improving the prediction accuracy of CAE models. Nevertheless, the scarcity of vehicle crash data poses a significant challenge for the training of such models. This paper overcomes these challenges by fusing multiple data sources from two different types of vehicles. More specifically, the Cycle-Consistent Generative Adversarial Neural networks (CycleGAN) are first employed to translate features of time-series test data from one domain to another using cycle consistency loss. Such a translation allows for the generation of synthetic crash test data for the second vehicle type by leveraging existing tests from both vehicle types. In parallel, an initial temporal convolutional network (TCN) model is trained using CAE simulation data and physical test data of the first vehicle type. This pre-trained TCN model is then fine-tuned using three sources of data from the second vehicle type, namely the CAE data, test data, and the augmented virtual test data generated using CycleGAN. Through these data fusion, the crashworthiness prediction accuracy of the second vehicle type can be improved. The proposed method is demonstrated by a real-world case study with a small-size SUV and a medium-size SUV. Results show enhancements in the predictive performance of the medium-size SUV model.

Predictors of substance use during treatment for addiction: A network analysis of ecological momentary assessment data.

Ecological momentary assessment (EMA) studies have previously demonstrated a prospective influence of craving on substance use in the following hours. Conceptualizing substance use as a dynamic system of causal elements could provide valuable insights into the interaction of craving with other symptoms in the process of relapse. The aim of this study was to improve the understanding of these daily life dynamic inter-relationships by applying dynamic networks analyses to EMA data sets. Secondary analyses were conducted on time-series data from two 2-week EMA studies. Data were collected in French outpatient addiction treatment centres. A total of 211 outpatients beginning treatment for alcohol, tobacco, cannabis, stimulants and opiate addiction took part. Using mobile technologies, participants were questioned four times per day relative to substance use, craving, exposure to cues, mood, self-efficacy and pharmacological addiction treatment use. Multi-level vector auto-regression models were used to explore contemporaneous, temporal and between-subjects networks. Among the 8260 daily evaluations, the temporal network model, which depicts the lagged associations of symptoms within participants, demonstrated a unidirectional association between craving intensity at one time (T0) and primary substance use at the next assessment (T1, r = 0.1), after controlling for the effect of all other variables. A greater self-efficacy at T0 was associated with fewer cues (r = -0.04), less craving (r = -0.1) and less substance use at T1 (r = -0.07), and craving presented a negative feedback loop with self-efficacy (r = -0.09). Dynamic network analyses showed that, among outpatients beginning treatment for addiction, high craving, together with low self-efficacy, appear to predict substance use more strongly than low mood or high exposure to cues.

Wave Downscaling Approach with TCN model, Case Study in Bengkulu, Indonesia

When conducting marine operations that rely on wave conditions, such as maritime trade, the fishing industry, and ocean energy, accurate wave downscaling is important, especially in coastal locations with complicated geometries. Traditional approaches for wave downscaling are usually obtained by performing nested simulations on a high-resolution local grid from global grid information. However, this approach requires high computation resources. In this paper, to downscale global wave height data into a high-resolution local wave height with less computation resources, we propose a machine learning-based approach to downscaling using the Temporal Convolutional Network (TCN) model. To train the model, we obtain the wave dataset using the SWAN model in a local domain. The global datasets are taken from the ECMWF Reanalysis (ERA-5) and used to train the model. We choose the coastal area of Bengkulu, Indonesia, as a case study. The results of TCN are also compared with other models such as LSTM and Transformers. It showed that TCN demonstrated superior performance with a CC of 0.984, RMSE of 0.077, and MAPE of 4.638, outperforming the other models in terms of accuracy and computational efficiency. It proves that our TCN model can be alternative model to downscale in Bengkulu’s coastal area.

ST-TDCN: A two-channel tree-structure spatial–temporal convolutional network model for traffic velocity prediction

In the development of intelligent transport systems which aims to provide safe, convenient, and comfortable transport and effectively addresses issues with traffic congestion and pollution, accurate collection of spatial–temporal data is of great significance. Based on the study of the topology and spatial characteristics of the transportation network, data with spatial–temporal attributed can be predicted by relevant models. Thus, the purpose of providing additional information for decision making and labor cost saving is achieved. This study proposed a more accurate traffic velocity prediction model, named Spatial-Temporal Tree-structure Dual-channel Convolution Network. The model designs a spatial tree convolution module for capturing the spatial features of nodes in the traffic network represented by the tree structure and applies a dual-channel temporal convolutional network module to capture the temporal information of velocity data more accurately. Comparative tests have demonstrated that the model proposed in this study has the advantages of higher accuracy, better convergence and more flexibility in responding to dynamic changes of traffic velocity.

Accurate short-term GHI forecasting using a novel temporal convolutional network model

Global energy demand is on the rise, driven by factors such as population growth and economic development.Utilizing renewable energy is crucial to meeting this energy demand in light of global warming and the depletion of fossil resources.One of the renewable energy sources that is extensively utilized in multiple countries worldwide is photovoltaic energy.While integrating photovoltaic (PV) energy into the grid offers substantial economic and environmental advantages, its intermittent nature presents challenges to maintaining grid stability at high penetration levels. Accurate solar energy estimations are essential for photovoltaic (PV) based energy facilities to enable early participation in energy markets and efficient resource planning. This study proposes and evaluates a Temporal Convolutional Network (TCN) model that can rapidly predict global horizontal irradiance (GHI) using univariate and multivariate approaches. To our knowledge, this is the first study to employ a TCN model for GHI forecasting. The univariate model solely considers GHI, while the multivariate time series models incorporate a combination of six variables: global horizontal irradiance, active power of a module plant, PV module temperature, wind speed, air temperature, and air pressure. The proposed model’s effectiveness is validated by comparing its performance to benchmark models, including MLP, RNN, GRU, and LSTM. The prediction models’ performance is evaluated using root mean square error (RMSE), coefficient of determination (R2), and mean absolute error (MAE). The results demonstrate that the effectiveness of univariate TCN models is evident in their performance for 5, 10, 15, and 20 min ahead short-term GHI forecasting, its mean absolute error (MAE) values achieved are 22.935 W/m2 33.47 W/m2, 36.9994 W/m2, and 41.9946 W/m2, respectively. The multivariate model, incorporating additional variables, yielded higher MAE values : 37.928 W/m2, 55.88 W/m2, 66.61 W/m2, and 74.82 W/m2, respectively. These results suggest that the TCN model’s capability to capture both long-term and short-term dependencies within the data contributes to its accuracy for GHI forecasting compared to other models.

A Short-Term Vessel Traffic Flow Prediction Based on a DBO-LSTM Model

To facilitate the efficient prediction and intelligent analysis of ship traffic information, a short-term ship traffic flow prediction method based on the dung beetle optimizer (DBO)-optimized long short-term memory networks (LSTM) is proposed. Firstly, according to the characteristics of vessel traffic flow, speed, and density, the traffic flow parameters are extracted from the AIS data; secondly, the DBO-LSTM model is established, and the optimal hyperparameter combinations of the LSTM are found using the DBO algorithm to improve the model prediction accuracy; then, taking the AIS data of a part of the coastal port area in Xiangshan as an example, we compare and analyze the results of the recurrent neural network, temporal convolutional network, LSTM, and DBO-LSTM prediction models; finally, the results are displayed and analyzed by visualization. The experimental results show that each error is reduced in predicting the flow parameter, speed parameter, and density parameter, and the accuracy reaches 95%, 92%, and 95%, respectively. After predicting the three parameters in the next 24 h, the accuracy rate reaches 93%, 91%, and 94%, respectively, compared with the real data, which surpasses the comparison model and achieves better prediction accuracy, verifying the feasibility and reasonableness of the proposed prediction model.