Related Time Series Research Articles

Analyzing the time-series relationship between learning atmosphere, negative emotions, and academic engagement in language learners

ABSTRACT This study examines the time-series relationships among learning atmosphere, negative emotions, and academic engagement in 638 non-English major students at a university in central China. The study employs the Learning Environment Inventory, the Cognitive Emotion Regulation Questionnaire, and the Students’ Engagement Questionnaire to assess the learning atmosphere, negative emotions, and academic engagement among language learners. Using R 4.4.0 and R Studio for data analysis, the researcher utilized robust statistical methodologies to investigate the intricate relationships between these variables over time. The prediction model results show a strong link between a positive environment and increased student engagement. Favorable conditions, such as supportive teachers, safe learning spaces, and resource access, significantly boost engagement, enhancing academic performance and personal development. Reducing negative emotions like stress, anxiety, and fear also raises engagement by removing barriers to learning. Creating environments that reduce these negative feelings helps students focus and participate more actively. Therefore, enhancing positive environmental factors and reducing negative feelings are crucial for fostering student engagement, leading to better academic outcomes and personal growth.

AutoLDT: a lightweight spatio-temporal decoupling transformer framework with AutoML method for time series classification

Time series classification finds widespread applications in civil, industrial, and military fields, while the classification performance of time series models has been improving with the recent development of deep learning. However, the issues of feature extraction effectiveness, model complexity, and model design uncertainty constrain the further development of time series classification. To address the above issues, we propose a Lightweight Spatio-Temporal Decoupling Transformer framework based on Automated Machine Learning technique (AutoLDT). The framework proposes a novel lightweight Transformer with fuzzy position encoding, TS-separable linear self-attention mechanism, and convolutional feedforward network, which mine the temporal and spatial features, as well as the local and global relationship of time series. Fuzzy positional encoding integrates fuzzy ideas to enhance the generalization performance of model information mining. TS-separable linear self-attention mechanism and convolutional feedforward network achieve feature extraction in a lightweight way by decoupling temporal and spatial features of time series. Notably, we adopt the Covariance Matrix Adaptation Evolution Strategy and global adaptive pruning technique to realize automated network structure design, which further improves the model training efficiency and automation, and avoids the uncertainty problem of network design. Finally, we validate the effectiveness of the proposed framework on publicly available UCR and UEA time series datasets. The experimental results show that the proposed framework not only improves the model classification performance in a lightweight way but also dramatically improves the model training efficiency.

Uncertainty-Aware Time Series Anomaly Detection

Traditional anomaly detection methods in time series data often struggle with inherent uncertainties like noise and missing values. Indeed, current approaches mostly focus on quantifying epistemic uncertainty and ignore data-dependent uncertainty. However, consideration of noise in data is important as it may have the potential to lead to more robust detection of anomalies and a better capability of distinguishing between real anomalies and anomalous patterns provoked by noise. In this paper, we propose LSTMAE-UQ (Long Short-Term Memory Autoencoder with Aleatoric and Epistemic Uncertainty Quantification), a novel approach that incorporates both aleatoric (data noise) and epistemic (model uncertainty) uncertainties for more robust anomaly detection. The model combines the strengths of LSTM networks for capturing complex time series relationships and autoencoders for unsupervised anomaly detection and quantifies uncertainties based on the Bayesian posterior approximation method Monte Carlo (MC) Dropout, enabling a deeper understanding of noise recognition. Our experimental results across different real-world datasets show that consideration of uncertainty effectively increases the robustness to noise and point outliers, making predictions more reliable for longer periodic sequential data.

Quantum long short-term memory (QLSTM) vs. classical LSTM in time series forecasting: a comparative study in solar power forecasting

Accurate solar power forecasting is pivotal for the global transition towards sustainable energy systems. This study conducts a meticulous comparison between Quantum Long Short-Term Memory (QLSTM) and classical Long Short-Term Memory (LSTM) models for solar power production forecasting. The primary objective is to evaluate the potential advantages of QLSTMs, leveraging their exponential representational capabilities, in capturing the intricate spatiotemporal patterns inherent in renewable energy data. Through controlled experiments on real-world photovoltaic datasets, our findings reveal promising improvements offered by QLSTMs, including accelerated training convergence and substantially reduced test loss within the initial epoch compared to classical LSTMs. These empirical results demonstrate QLSTM’s potential to swiftly assimilate complex time series relationships, enabled by quantum phenomena like superposition. However, realizing QLSTM’s full capabilities necessitates further research into model validation across diverse conditions, systematic hyperparameter optimization, hardware noise resilience, and applications to correlated renewable forecasting problems. With continued progress, quantum machine learning can offer a paradigm shift in renewable energy time series prediction, potentially ushering in an era of unprecedented accuracy and reliability in solar power forecasting worldwide. This pioneering work provides initial evidence substantiating quantum advantages over classical LSTM models while acknowledging present limitations. Through rigorous benchmarking grounded in real-world data, our study illustrates a promising trajectory for quantum learning in renewable forecasting.

Forecasting of Turkey's Hazelnut Export Amounts According to Seasons with Dendritic Neuron Model Artificial Neural Network

It is seen that artificial neural networks have begun to be used extensively in the literature in solving the time series forecasting problem. In addition to artificial neural networks, classical forecasting methods can often be used to solve this problem. It is seen that classical forecasting methods give successful results for linear time series analysis. However, there is no linear relationship in many time series. Therefore, it can be thought that deep artificial neural networks, which contain more parameters but create more flexible non-linear model structures compared to classical time series forecasting methods, may enable the production of more successful forecasting methods. In this study, the problem of forecasting hazelnut export amounts according to seasons in Turkey with a dendritic neuron model artificial neural network is discussed. In this study, a training algorithm based on the particle swarm optimization algorithm is given for training the dendritic neuron model artificial neural network. The motivation of the study is to investigate Turkey's hazelnut export amounts according to seasons, using a dendritic neuron model artificial neural network. The performance of the proposed method has been compared with artificial neural networks used in the literature.

A deep learning-based combination method of spatio-temporal prediction for regional mining surface subsidence

In coal mining areas, surface subsidence poses significant risks to human life and property. Fortunately, surface subsidence caused by coal mining can be monitored and predicted by using various methods, e.g., probability integral method and deep learning (DL) methods. Although DL methods show promise in predicting subsidence, they often lack accuracy due to insufficient consideration of spatial correlation and temporal nonlinearity. Considering this issue, we propose a novel DL-based approach for predicting mining surface subsidence. Our method employs K-means clustering to partition spatial data, allowing the application of a gate recurrent unit (GRU) model to capture nonlinear relationships in subsidence time series within each partition. Optimization using snake optimization (SO) further enhances model accuracy globally. Validation shows our method outperforms traditional Long Short-Term Memory (LSTM) and GRU models, achieving 99.1% of sample pixels with less than 8 mm absolute error.

Prediction of Drift Trajectory in the Ocean Using Double-Branch Adaptive Span Attention

The accurate prediction of drift trajectories holds paramount significance for disaster response and navigational safety. The future positions of underwater drifters in the ocean are closely related to their historical drift patterns. Additionally, leveraging the complex dependencies between drift trajectories and ocean currents can enhance the accuracy of predictions. Building upon this foundation, we propose a Transformer model based on double-branch adaptive span attention (DBASformer), aimed at capturing the multivariate time-series relationships within drift history data and predicting drift trajectories in future periods. DBASformer can predict drift trajectories more accurately. The proposed adaptive span attention mechanism exhibits enhanced flexibility in the computation of attention weights, and the double-branch attention structure can capture the cross-time and cross-dimension dependencies in the sequences. Finally, our method was evaluated using datasets containing buoy data with ocean current velocities and Autonomous Underwater Vehicle (AUV) data. The raw data underwent cleaning and alignment processes. Comparative results with five alternative methods demonstrate that DBASformer improves prediction accuracy.

Influence of changes in solar activity on Nigerian Rainfall

This paper focuses on the impact of solar activity changes on rainfall in Nigeria. Rainfall data were got from Gridded Time Series (CRU TS v4) of the University of East Anglia, United Kingdom. Various statistical tools like Pearson rank correlation coefficient, regression analysis, covariance, skewness, and kurtosis are employed in the study. The results show that there are generally weak correlations between rainfall and solar activity in most seasons. However, low correlation coefficients (0.0424 and 0.1040, respectively for sunspot numbers and F10.7 mean a very weak positive relationship between early rainfall, main rainfall and annual rainfall and negative for dry season rainfall and Harmattan rainfall. Also, there is a negative time-series relationship between the rainfall amount in dry and Harmattan seasons, with the highest rainfall amount during low solar activity and vice versa. Therefore, it can be concluded that solar activity has little effect on Nigeria's annual and main season rainfall. However, during the dry season and Harmattan, heavy rainfall appears to be associated with low solar activity, while high solar activity appears to be associated with low rainfall. This study will be beneficial to farmers in Nigeria, majority of whom are peasant farmers that practice rain-fed farming.

Basketball Sports Posture Recognition Technology Based on Improved Graph Convolutional Neural Network

Basketball has rapidly developed in recent years. Analysis of various moves in basketball can provide technical references for professional players and assist referees in judging games. Traditional technology can no longer provide modern basketball players with theoretical support. Therefore, using intelligent methods to recognize human body postures in basketball was a relatively innovative approach. To be able to recognize the basketball sports posture of players more accurately, the experiment proposes a basketball stance recognition model based on enhanced graph convolutional networks (GCN), that is, the basketball stance recognition model based on enhanced GCN and spatial temporal graph convolutional network (ST-GCN) model. This model combines the respective advantages of the GCN and temporal convolutional network and can handle graph-structured data with time-series relationships. The ST-GCN can be further deduced by realizing the convolution operation of the graph structure and establishing a spatiotemporal graph convolution model for the posture sequence of a person’s body. A dataset of technical basketball actions is constructed to verify the effectiveness of the ST-GCN model. The final experimental findings indicated that the final recognition accuracy of the ST-GCN model for basketball postures was approximately 95.58%, whereas the final recognition accuracy of the long short term memory + multiview re-observation skeleton action recognition (LSTM+MV+AC) model was about 93.65%.

On the Validity of Granger Causality for Ecological Count Time Series

Knowledge of causal relationships is fundamental for understanding the dynamic mechanisms of ecological systems. To detect such relationships from multivariate time series, Granger causality, an idea first developed in econometrics, has been formulated in terms of vector autoregressive (VAR) models. Granger causality for count time series, often seen in ecology, has rarely been explored, and this may be due to the difficulty in estimating autoregressive models on multivariate count time series. The present research investigates the appropriateness of VAR-based Granger causality for ecological count time series by conducting a simulation study using several systems of different numbers of variables and time series lengths. VAR-based Granger causality for count time series (DVAR) seems to be estimated efficiently even for two counts in long time series. For all the studied time series lengths, DVAR for more than eight counts matches the Granger causality effects obtained by VAR on the continuous-valued time series well. The positive results, also in two ecological time series, suggest the use of VAR-based Granger causality for assessing causal relationships in real-world count time series even with few distinct integer values or many zeros.

Gas turbine prognostics via Temporal Fusion Transformer

Abstract Gas turbines play a vital role in various industries. Timely and accurately predicting their degradation is essential for efficient operation and optimal maintenance planning. Diagnostic and prognostic outcomes aid in determining the optimal compressor washing intervals. Diagnostics detects compressor fouling and estimates the trend up to the current time. If the forecast indicates fast progress in the fouling trend, scheduling offline washing during the next inspection event or earlier may be crucial to address the fouling deposit comprehensively. This approach ensures that compressor cleaning is performed based on its actual health status, leading to improved operation and maintenance costs. This paper presents a novel prognostic method for gas turbine degradation forecasting through a time-series analysis. The proposed approach uses the Temporal Fusion Transformer model capable of capturing time-series relationships at different scales. It combines encoder and decoder layers to capture temporal dependencies and temporal-attention layers to capture long-range dependencies across the encoded degradation trends. Temporal attention is a self-attention mechanism that enables the model to consider the importance of each time step degradation in the context of the entire degradation profile of the given health parameter. Performance data from multiple two-spool turbofan engines is employed to train and test the method. The test results show promising forecasting ability of the proposed method multiple flight cycles into the future. By leveraging the insights provided by the method, maintenance events and activities can be scheduled in a proactive manner. Future work is to extend the method to estimate remaining useful life.

Directed causal effect with PCMCI in hyperscanning EEG time series.

Social activities are likely to cause effects or reactivity in the brains of the people involved in collaborative social situations. This study assesses a new method, Tigramite, for time domain analysis of directed causality between the prefrontal cortex (PFC) of persons in such situations. An experimental situation using hyperscanning EEG was applied while individuals led and followed each other in finger-tapping rhythms. This structured task has a long duration and a high likelihood of inter-brain causal reactions in the prefrontal cortices. Tigramite is a graph-based causal discovery method to identify directed causal relationships in observational time series. Tigramite was used to analyze directed causal connections within and between the PFC. Significantly directed causality within and between brains could be detected during the social interactions. This is the first empirical evidence the Tigramite can reveal inter- and intra-brain-directed causal effects in hyperscanning EEG time series. The findings are promising for further studies of causality in neural networks during social activities using Tigramite on EEG in the time domain.

Energy-Saving Data Acquisition Model of Wireless Sensor Network Based on Nonlinear Algorithm

Wireless sensor network significant data acquisition has a high cost, long completion time, and low accuracy. This paper adopts a sensor network data acquisition method based on a nonlinear algorithm to solve the above problems. In this paper, a distributed data acquisition method based on nonlinear regression is established by combining the time series relationship of data. First, this paper uses nonlinear regression analysis technology to establish the sensing data model and retain the characteristics of the sensing data. This makes the node pass only the parametric data of the regression model. This paper uses this method to replace the transmission of actual monitoring sensory data information. Experiments show that this method can effectively reduce data redundancy and network traffic under any conditions. The method has been verified in practical WSN applications.

A new grey adaptive integrated model for forecasting renewable electricity production

Fossil fuel consumption is a major source of greenhouse gas emissions. The Russia–Ukraine conflict has led to energy price volatility. Therefore, affordable energy poses a significant threat. The development of renewable energy to meet consumption demands has attracted researchers’ attention in worldwide. In this study, a novel grey adaptive integrated model is proposed to balance the fitting and generalization abilities for renewable energy generation trends. First, feature selection was performed using the mutual information filter method for influencing factors and the wrapper method. Second, FGM(1,1) was used to mine the data features, and AGMC(1,n) was used to extract multivariate time-series relationships. Finally, an adaptive integrated model with a Gaussian kernel function was proposed in order to assign weights. It balances the results of the two forecasting models to avoid the underfitting/overfitting problem generated by excessive data volatility and the abrupt shift of the influencing factors. The study results have shown that the proposed integrated model solved the underfitting and overfitting problems to a certain degree. Its performance is better than single model. We analyze the forecasting results and propose corresponding suggestions for the government and enterprises separately.

Sika deer trajectory prediction considering environmental factors by timeseries transformer-based architecture

Recently, the damage to agriculture, forestry, and fishery by wildlife has become a serious social problem. The damage caused by a conflict between wildlife and human society often causes less motivation for farming and is expected to significantly inhibit the development of local agriculture and forestry. However, the current management of wildlife is limited to primitive methods such as stabilizing the population by culling reliant on experience. To prevent this problem, the trajectory prediction of wildlife is one of the solutions for efficient wildlife management.In this study, we propose a machine learning architecture for predicting wildlife trajectories, considering surrounding environmental factors. Particularly, we propose a machine learning architecture that more accurately predicts trajectories using a timeseries transformer model that can learn long-term dependencies and add a submodel that can consider surrounding environmental factors. The proposed architecture allows interpreting which past trajectory areas should be focused on when predicting a trajectory by visualizing the weight of the focus mechanism, one of the elements comprising the transformer model. Further, the proposed architecture can decide the priority of elements of a multivariate timeseries input by considering a variable selection network (VSN), which considers the relationship of timeseries between a given time point and those before and after using casual convolutions. The main advantage of our methods is to understand the potential environmental factors to predict animal trajectories by analyzing the importance of each input feature representation in VSN.We experimented to evaluate the proposed method using one of the largest biologging datasets of sika deer (Cervus nippon) in Kanagawa Prefecture, Japan. The proposed method outperforms existing methods on various evaluation metrics and can effectively consider environmental factors in predicting trajectories. In addition, we analyze the results and show that the proposed architecture can pay attention to the times that individuals moved significantly within the observation period by visualizing the trajectories for the best and worst cases and the weight of each environmental factor.

Stock Price Prediction Using Candlestick Patterns and Sparrow Search Algorithm

Accurately forecasting the trajectory of stock prices holds crucial significance for investors in mitigating investment risks and making informed decisions. Candlestick charts visually depict price information and the trends in stocks, harboring valuable insights for predicting stock price movements. Therefore, the challenge lies in efficiently harnessing candlestick patterns to forecast stock prices. Furthermore, the selection of hyperparameters in network models has a profound impact on the forecasting outcomes. Building upon this foundation, we propose a stock price prediction model SSA-CPBiGRU that integrates candlestick patterns and a sparrow search algorithm (SSA). The incorporation of candlestick patterns endows the input data with structural characteristics and time series relationships. Moreover, the hyperparameters of the CPBiGRU model are optimized using an SSA. Subsequently, the optimized hyperparameters are employed within the network model to conduct predictions. We selected six stocks from different industries in the Chinese stock market for experimentation. The experimental results demonstrate that the model proposed in this paper can effectively enhance the prediction accuracy and has universal applicability. In comparison to the LSTM model, the proposed model produces an average of 31.13%, 24.92%, and 30.42% less test loss in terms of MAPE, RMSE and MAE, respectively. Moreover, it achieves an average improvement of 2.05% in R2.

Base on temporal convolution and spatial convolution transformer for fluid prediction through well logging data

Fluid prediction is important in exploration work, helping to determine the location of exploration targets and the reserve potential of the estimated area. Machine learning methods can better adapt to different data distributions and nonlinear relationships through model training, resulting in better learning of these complex relationships. We started by using the convolution operation to process the log data, which includes temporal convolution and spatial convolution. Temporal convolution is specifically designed to capture time series relationships in time series data. In well log data, time information is often critical for understanding fluid changes and other important details. Temporal convolution learns trends and cyclical changes in the data. The spatial convolution operation makes the model more sensitive to the local features in the logging data through the design of the local receptive field and improves the sensitivity to fluid changes. Spatial convolution helps capture spatial correlations at different depths or locations. This can help the model understand the change of fluid in the vertical direction and identify the spatial relationship between different fluids. Then, we use the transformer module to predict the fluid. The transformer module uses a self-attention mechanism that allows the model to focus on information with different weights at different locations in the sequence. In the well log data, this helps the model to better capture the formation characteristics at different depths or time points and improves the modeling ability of time series information. The fully connected structure in the transformer module enables each position to interact directly with other locations in the sequence. By applying it to the data of Tarim Oilfield, the experimental results show that the convolutional transformer model proposed in this paper has better results than other machine learning models. This study provides a new idea in the field of logging fluid prediction.

The Relationship between the Carbon Fixation Capacity of Vegetation and Cultivated Land Expansion and Its Driving Factors in an Oasis in the Arid Region of Xinjiang, China

In the process of agricultural development in arid and semi-arid areas, the carbon fixation capacity of vegetation can be affected to different degrees, but research on its driving factors is lacking. Consequently, this paper focuses on the Weiku Oasis in Xinjiang as its research area, in which the carbon fixation capacity of vegetation is estimated with the chemical equation of a photochemical reaction, using methods such as linear system models and Geodetector to analyze the relationship between cropland expansion characteristics and the carbon fixation capacity of vegetation from 1990 to 2020. The influence of land-use changes on the space differentiation of carbon fixation was elucidated through a time series relationship, and the synergistic effects of nine influencing factors on the carbon fixation capacity during the process of vegetation changes were discussed. The results were as follows: (1) In the process of agricultural development, the proportions of cultivated land area and spatial agglomeration had significant negative correlations with carbon sequestration, and the significance was rising, but the effect of cultivated land area proportion was more significant. (2) Through temporal sequential cooperativity analysis, when other land-use types were converted into cultivated land, the carbon fixation capacity of vegetation suddenly and significantly decreased in the initial year of the transformation, but the effect of cultivated land reclamation on the carbon fixation capacity of vegetation did not have a significant time lag. Moreover, after a certain period of time, cultivated land can gradually recover part of its lost carbon fixation capacity. (3) Among the nine driving factors, potential evapotranspiration is the most prominent in explaining the carbon fixation capacity of vegetation. This single-factor pairwise interaction presents the relationship between bivariate enhancement and nonlinear enhancement. When terrain factors interact with other factors, the enhancement effect of the influence on the carbon fixation capacity of vegetation has an obvious promotion effect. However, the change in the carbon fixation capacity of vegetation is more significantly influenced by potential evapotranspiration and the interaction between the normalized difference vegetation index (NDVI) and other factors. This research is helpful to understanding the basic theories related to the change in the carbon fixation capacity of vegetation during the process of agricultural development in arid and semi-arid areas, as well as providing theoretical reference for ecological environment construction and sustainable development.

Relation-driven Query of Multiple Time Series.

Querying time series based on their relations is a crucial part of multiple time series analysis. By retrieving and understanding time series relations, analysts can easily detect anomalies and validate hypotheses in complex time series datasets. However, current relation extraction approaches, including knowledge- and data-driven ones, tend to be laborious and do not support heterogeneous relations. By conducting a formative study with 11 experts, we concluded six time series relations, including correlation, causality, similarity, lag, arithmetic, and meta, and summarized three pain points in querying time series involving these relations. We proposed RelaQ, an interactive system that supports the time series query via relation specifications. RelaQ allows users to intuitively specify heterogeneous relations when querying multiple time series, understand the query results based on a scalable, multi-level visualization, and explore possible relations beyond the existing queries. RelaQ is evaluated with two cases and a user study with 12 participants, showing promising effectiveness and usability.

Short-term household load forecasting based on Stacking-SCN

The household load has high volatility and uncertainty, which plays an increasingly important role in short-term power load forecasting for individual residential customers in the operation and planning of future power grids. There is still room for improvement in the prediction accuracy of traditional machine learning and deep learning models. This paper firstly analyzes the complexity of household load data and formulates forecasting problems. Then, the principle of stochastic configuration network (SCN), stacking algorithm and a stacking integrated stochastic configuration network (Stacking-SCN) is introduced, which constructs a short-term household load forecasting model. By adaptively constraining the output weight distribution of the network model, the prediction accuracy can be improved. To show the prediction performance of the algorithm, the experiment comparing the Stacking-SCN model with incremental random vector functional link network (IRVFLN) models, the traditional SCN, ensemble-SCN (E-SCN), deep neural networks (DNN) and long short-term memory (LSTM), and verify it with RMSE, MAE and APE performance metrics. Experimental results show that Stacking-SCN can more effectively express the time series relationship of household short-term load, has higher prediction accuracy, effectively prevents network over-fitting problems, and improves the accuracy of prediction capabilities.