Extracted Time Series Research Articles

CLTNet: A Hybrid Deep Learning Model for Motor Imagery Classification

Background: Brain–computer interface (BCI) technology opens up new avenues for human–machine interaction and rehabilitation by connecting the brain to machines. Electroencephalography (EEG)-based motor imagery (MI) classification is a key component of BCI technology, which is capable of translating neural activity in the brain into commands for controlling external devices. Despite the great potential of BCI technology, the challenges of extracting and decoding brain signals limit its wide application. Methods: To address this challenge, this study proposes a novel hybrid deep learning model, CLTNet, which focuses on solving the feature extraction problem to improve the classification of MI-EEG signals. In the preliminary feature extraction stage, CLTNet uses a convolutional neural network (CNN) to extract time series, channel, and spatial features of EEG signals to obtain important local information. In the deep feature extraction stage, the model combines the long short-term memory (LSTM) network and the Transformer module to capture time-series data and global dependencies in the EEG. The LSTM explains the dynamics of the brain activity, while the Transformer’s self-attention mechanism reveals the global features of the time series. Ultimately, the CLTNet model classifies motor imagery EEG signals through a fully connected layer. Results: The model achieved an average accuracy of 83.02% and a Kappa value of 0.77 on the BCI IV 2a dataset, and 87.11% and a Kappa value of 0.74 on the BCI IV 2b dataset, both of which outperformed the traditional methods. Conclusions: The innovation of the CLTNet model is that it integrates multiple network architectures, which offers a more comprehensive understanding of the characteristics of the EEG signals during motor imagery, providing a more comprehensive perspective and establishing a new benchmark for future research in this area.

A Temporal Network Based on Characterizing and Extracting Time Series in Copper Smelting for Predicting Matte Grade.

Addressing the issues of low prediction accuracy and poor interpretability in traditional matte grade prediction models, which rely on pre-smelting input and assay data for regression, we incorporate process sensors' data and propose a temporal network based on Time to Vector (Time2Vec) and temporal convolutional network combined with temporal multi-head attention (TCN-TMHA) to tackle the weak temporal characteristics and uncertain periodic information in the copper smelting process. Firstly, we employed the maximum information coefficient (MIC) criterion to select temporal process sensors' data strongly correlated with matte grade. Secondly, we used a Time2Vec module to extract periodic information from the copper smelting process variables, incorporates time series processing directly into the prediction model. Finally, we implemented the TCN-TMHA module and used specific weighting mechanisms to assign weights to the input features and prioritize relevant key time step features. Experimental results indicate that the proposed model yields more accurate predictions of copper content, and the coefficient of determination (R2) is improved by 2.13% to 11.95% and reduced compared to the existing matte grade prediction models.

Decentralized optimal voltage control for wind farm with deep learning-based data-driven modeling

The random fluctuations of wind energy and external grid voltage disturbances can both lead to serious voltage fluctuations and voltage deviations in the wind farm (WF). Voltage/reactive power control is an effective way to improve the voltage stability of WF. The existing research is based on complex physical models with prior parameter information, and the accuracy and calculation speed of the WF model are difficult to guarantee. To address this issue, this paper explores a decentralized optimal voltage control method for WF with deep learning-based (DL) data-driven modeling (DL-DOVC). A hybrid convolutional neural network (CNN)-Transformer architecture is proposed to establish the data-driven model of WF, leveraging its enhanced capabilities for extracting time series correlation, to learn complex patterns and dynamics from time series data. Then, we develop a fully decentralized voltage control method for WF to regulate the terminal bus voltage of wind turbines (WTs) within a feasible range. A DL-based data-driven predictive controller is specially designed to solve the established data-driven voltage optimization problem, it eliminates the necessity for frequent manual model maintenance and is suitable for real-time application. Additionally, the difficulty of WF decentralized optimal voltage control arises from the inability of local controllers to fully consider the impact of all non-local WTs on the local WT states. By designing the DL-based auxiliary state-feedback controller, the effects of non-local WTs are implicitly considered in the auxiliary feedback control law. A WF with 32*6.25 MW WTs is used to test the proposed DL-DOVC method. Simulation results show that the proposed DL-based model can efficiently learn and predict the WF dynamics under different operating scenarios. The near-global optimal voltage control performance is achieved only with local measurements by employing the DL-DOVC method.

A novel fault detection and identification method for complex chemical processes based on OSCAE and CNN

The safety and reliability of chemical processes are of paramount importance. However, due to the complicated heat, mass, and momentum transfer processes coupled with chemical reactions, and the interrelated effects among various equipment units, it is difficult to accurately detect and identify faults occurring in the chemical system. This study proposes an innovative fault diagnosis framework specifically designed for chemical systems. A method based on orthogonal self-attention convolutional autoencoder (OSCAE) is constructed for fault detection. The convolutional autoencoder is combined with an orthogonal attention mechanism to extract time-series characteristic information of the operational state, thereby achieving precise detection of fault conditions. Additionally, a convolutional neural network (CNN) model uses both raw signals and data reconstructed by OSCAE to identify different faults, which enhances the features of the input and enables highly accurate fault identification. The effectiveness and robustness of the propose method is validated with simulation data of our self-established chemical distillation system and the publicly available Tennessee Eastman process system. The diagnosis efficacy in fault detection and identification is validated by applying fault detection metrics, high-dimensional feature visualizations, and confusion matrix analyses across two case studies. This paper not only provides an effective diagnostic framework for chemical systems but also offers a usable benchmark dataset for chemical distillation systems to the academic community, with the hope that the research content can enhance the stability and reliability of chemical processes.

Using enhanced Variational Modal Decomposition and Dung Beetle Optimization Algorithm optimization-kernel Extreme Learning Machine model to forecast short-term wind power

With the widespread use of clean energy, the forecasting of wind power has become increasingly significant. Extracting time series from sophisticated wind power data and thus improving the prediction accuracy of wind power generation has become the key to short-term forecasting. This paper proposes a Kernel Extreme Learning Machine (KELM) prediction model based on Crested Porcupine Optimizer (CPO), Variational Modal Decomposition (VMD) with Improved Dung Beetle Optimization Algorithm (QHDBO). Firstly, by analyzing the correlation between the variables in the wind power data, the CPO algorithm is used to optimize the modal decomposition number and the penalty parameter of the VMD and extract the time-series information of the wind power series, and smooth it to obtain a number of sub-sequences with strong regularity. Then, the KELM prediction model is constructed for different subsequences, and the kernel parameters and regularization coefficients of KELM are optimized using the QHDBO algorithm. Finally, the predicted values of different subsequences are reconstructed to obtain the final prediction results. The simulation results show that the CVMD-QHDBO-KELM model can effectively improve the wind power prediction performance, and the MAPE values are all below 9 %, and most of the RE values are below 10 %.

Efficient Clothing Fashion Prediction using Machine Learning

Fashion trend forecasting is a crucial task for both academia and industry. Although some efforts have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal the real fashion trends. Towards insightful fashion trend forecasting, this work focuses on investigating fine-grained fashion element trends for specific user groups. We first contribute a large-scale fashion trend dataset (FIT) collected from social media with extracted time series fashion element records and user information. Furthermore, to effectively model the time series data of fashion elements with rather complex patterns, we propose a Machine Learning which takes advantage of the capability in modeling time series data. Moreover, it leverages internal and external knowledge in fashion domain that affects the time-series patterns of fashion element trends. Such incorporation of domain knowledge further enhances the deep learning model in capturing the patterns of specific fashion elements and predicting the future trends. Extensive experiments demonstrate that the proposed ML model can effectively capture the complicated patterns of objective fashion elements, therefore making preferable fashion trend forecast.

Dynamic community detection algorithm based on hyperbolic graph convolution

PurposeCommunity detection is a key factor in analyzing the structural features of complex networks. However, traditional dynamic community detection methods often fail to effectively solve the problems of deep network information loss and computational complexity in hyperbolic space. To address this challenge, a hyperbolic space-based dynamic graph neural network community detection model (HSDCDM) is proposed.Design/methodology/approachHSDCDM first projects the node features into the hyperbolic space and then utilizes the hyperbolic graph convolution module on the Poincaré and Lorentz models to realize feature fusion and information transfer. In addition, the parallel optimized temporal memory module ensures fast and accurate capture of time domain information over extended periods. Finally, the community clustering module divides the community structure by combining the node characteristics of the space domain and the time domain. To evaluate the performance of HSDCDM, experiments are conducted on both artificial and real datasets.FindingsExperimental results on complex networks demonstrate that HSDCDM significantly enhances the quality of community detection in hierarchical networks. It shows an average improvement of 7.29% in NMI and a 9.07% increase in ARI across datasets compared to traditional methods. For complex networks with non-Euclidean geometric structures, the HSDCDM model incorporating hyperbolic geometry can better handle the discontinuity of the metric space, provides a more compact embedding that preserves the data structure, and offers advantages over methods based on Euclidean geometry methods.Originality/valueThis model aggregates the potential information of nodes in space through manifold-preserving distribution mapping and hyperbolic graph topology modules. Moreover, it optimizes the Simple Recurrent Unit (SRU) on the hyperbolic space Lorentz model to effectively extract time series data in hyperbolic space, thereby enhancing computing efficiency by eliminating the reliance on tangent space.

Inventory Prediction Using a Modified Multi-Dimensional Collaborative Wrapped Bi-Directional Long Short-Term Memory Model

Inventory prediction is concerned with the forecasting of future demand for products in order to optimize inventory levels and supply chain management. The challenges include demand volatility, data quality, multi-dimensional interactions, lead time variability, seasonal trends, and dynamic pricing. Nevertheless, these models suffer from numerous shortcomings, and in this research, we propose a new model, MMCW-BiLSTM (modified multi-dimensional collaboratively wrapped BiLSTM), for inventory prediction. The MMCW-BiLSTM model reflects a considerable leap in inventory forecasting by combining a number of components in order to consider intricate temporal dependencies and incorporate feature interactions. The MMCW-BiLSTM makes use of BiLSTM layers, collaborative attention mechanisms, and a multi-dimensional attention approach to learn from augmented datasets consisting of the original features and the extracted time series data. Moreover, adding a Taylor series transformation allows for a more precise description of the features in the model, thus improving the prediction precision. The results show that the models make the least mistakes when they use the AV demand forecasting dataset, with MAE values of 1.75, MAPE values of 2.89, MSE values of 6.76, and RMSE values of 2.6. Similarly, when utilizing the product demand dataset, the model also achieves the lowest error values for these metrics at 1.97, 3.91, 8.76, and 2.96. Likewise, when utilizing the dairy goods sales dataset, the model also achieves the lowest error values for these metrics at 2.54, 3.69, 10.39, and 3.22.

An improved transformer‐based model for long‐term 4D trajectory prediction in civil aviation

AbstractFour‐dimensional trajectory prediction is a crucial component of air traffic management, and its accuracy is closely related to the efficiency and safety of air transportation. Although long short‐term memory (LSTM) or its variants have been widely used in recent studies, they may produce unacceptable results in long‐term prediction due to the iterative output that accumulates error. To address this issue, a transformer‐based long‐term trajectory prediction model is proposed here, which utilizes the self‐attention mechanism to extract time series features from historical trajectory data. For long‐term prediction scenarios, we a trajectory stabilization module is introduced to ensure the stationarity of the time series for better predictability. Additionally, the transformer output strategy is improved to generate the prediction sequence by a single step instead of serial dynamic decoding, thus effectively enhancing the precision and inference speed. The proposed model is validated using real data obtained from China's Southwest Air Traffic Management Bureau. The experimental results demonstrate that this model outperforms the benchmark model. Further ablation experiments and visualizations are performed to analyze the impact of trajectory stabilization and one‐step inference strategy.

MicroIRC: Instance-level Root Cause Localization for Microservice Systems

The use of microservice architecture is gaining popularity in the development of web applications. However, identifying the root cause of a failure can be challenging due to the complexity of interconnected microservices, long service invocation links, dynamic changes in service states, and the abundance of service deployment nodes. Furthermore, as each microservice may have multiple instances, it can be difficult to identify instance-level failures promptly and effectively when the microservice topology and failure types change dynamically. To address this issue, we propose MicroIRC (Instance-level Root Cause Localization for Microservice Systems), a novel metrics-based approach that localizes root causes at the instance level while exhibiting robustness to adapt to dynamic changes in topology and new types of anomalies. We begin by training a graph neural network to fit different root cause types based on extracted time series features of microservice system metrics. Next, we construct a heterogeneous weighted topology (HWT) of microservice systems and execute a personalized random walk to identify root cause candidates. These candidates, along with real-time metrics from the anomalous time window, are then fed into the trained graph neural network to generate a ranked root cause list. Experiments conducted on five real-world datasets demonstrate that MicroIRC can accurately locate the root cause of microservices at the instance level, achieving a precision rate of 93.1% for the top five results. Furthermore, compared to the state-of-the-art methods, MicroIRC can improve the accuracy of root cause localization by more than 17% at the service level and more than 11.5% at the instance level. Remarkably, it exhibits robustness in scenarios involving new failure types, achieving an accuracy of 84.2% for the top result amid dynamic topological changes.

Herding behaviour towards high order systematic risks and the contagion Effect—Evidence from BRICS stock markets

This paper investigates the existence of herding movements towards several systematic risk factors derived from the Capital Asset Pricing Model (CAPM) and its extensions. The measure of herding is estimated using the dispersion of the risk factor loadings. The state space model is employed to extract time series of herding dynamics. We empirically survey the herding behaviors in the BRICS stock markets (i.e., Brazil, Russia, India, China, and South Africa) using monthly stock index data from 2006 to 2022, and identify various herding patterns towards specific factors. We also examine the impact of unanticipated shocks in crucial macroeconomic variables on the degree of herding measure in these countries. Lastly, we test the contagion hypothesis of herding across markets using correlation analysis. The results show that the level of herding linkages increases significantly in periods of market stress, casting doubt on the effectiveness of asset allocation in these markets for the sake of diversity.

Causal Forest Machine Learning Analysis of Parkinson's Disease in Resting-State Functional Magnetic Resonance Imaging.

In recent years, Artificial Intelligence has been used to assist healthcare professionals in detecting and diagnosing neurodegenerative diseases. In this study, we propose a methodology to analyze functional Magnetic Resonance Imaging signals and perform classification between Parkinson's disease patients and healthy participants using Machine Learning algorithms. In addition, the proposed approach provides insights into the brain regions affected by the disease. The functional Magnetic Resonance Imaging from the PPMI and 1000-FCP datasets were pre-processed to extract time series from 200 brain regions per participant, resulting in 11,600 features. Causal Forest and Wrapper Feature Subset Selection algorithms were used for dimensionality reduction, resulting in a subset of features based on their heterogeneity and association with the disease. We utilized Logistic Regression and XGBoost algorithms to perform PD detection, achieving 97.6% accuracy, 97.5% F1 score, 97.9% precision, and 97.7%recall by analyzing sets with fewer than 300 features in a population including men and women. Finally, Multiple Correspondence Analysis was employed to visualize the relationships between brain regions and each group (women with Parkinson, female controls, men with Parkinson, male controls). Associations between the Unified Parkinson's Disease Rating Scale questionnaire results and affected brain regions in different groups were also obtained to show another use case of the methodology. This work proposes a methodology to (1) classify patients and controls with Machine Learning and Causal Forest algorithm and (2) visualize associations between brain regions and groups, providing high-accuracy classification and enhanced interpretability of the correlation between specific brain regions and the disease across different groups.

Advancements in Satellite Remote Sensing for Predicting Large-Scale Wildfire Risks: An Image Processing Algorithmic Framework

With the escalation of global warming and human activities, large-scale wildfires have become increasingly frequent, posing significant threats to both ecological environments and human societal safety. Satellite remote sensing technology plays a pivotal role in wildfire monitoring and risk assessment, providing extensive geographical coverage and continuous monitoring capabilities. Traditional methods for predicating wildfire risk, however, face limitations in processing large-scale remote sensing data, especially in cloud detection and temporal information analysis. In response to this challenge, a novel set of image processing algorithms has been developed to enhance the efficiency and accuracy of wildfire risk prediction. Initially, a cloud detection and removal algorithm based on deep learning is introduced. This algorithm effectively identifies and eliminates cloud interference in remote sensing images, thereby significantly improving the quality and usability of image data. Subsequently, a temporal information capturing technique is proposed, capable of processing vast amounts of remote sensing data and extracting time series features. This technique provides robust data support for wildfire risk prediction. The application of these technologies not only improves the efficiency of the data processing workflow but also enhances the timeliness and accuracy of the prediction model, holding significant practical importance for guiding actual wildfire prevention and response measures.

From Sensors to Insights: An Original Method for Consumer Behavior Identification in Appliance Usage

In light of the energy crisis, extensive research is being conducted to enhance load forecasting, optimize the targeting of demand response programs, and advise building occupants on actions to enhance energy performance. Cluster analysis is increasingly applied to usage data across all consumer types. More accurate consumer identification translates to improved resource planning. In the context of Industry 4.0, where comprehensive data are collected across various domains, we propose using existing sensor data from household appliances to extract the usage patterns and characterize the resource demands of consumers from residential households. We propose a general pipeline for extracting features from raw sensor data alongside global features for clustering device usages and classifying them based on extracted time series. We applied the proposed method to real data from three different types of household devices. We propose a strategy to identify the number of existent clusters in real data. We employed the label data obtained from clustering for the classification of consumers based on data recorded on different time ranges and achieved an increase in accuracy of up to 15% when we expanded the time range for the recorded data on the entire dataset, obtaining an accuracy of over 99.89%. We further explore the data meta-features for a minimal dataset by examining the necessary time interval for the recorded data, dataset dimensions, and the feature set. This analysis aims to achieve an effective trade-off between time and performance.

Detecting abnormal cell behaviors from dry mass time series

The prediction of pathological changes on single cell behaviour is a challenging task for deep learning models. Indeed, in self-supervised learning methods, no prior labels are used for the training and all of the information for event predictions are extracted from the data themselves. We present here a novel self-supervised learning model for the detection of anomalies in a given cell population, StArDusTS. Cells are monitored over time, and analysed to extract time-series of dry mass values. We assessed its performances on different cell lines, showing a precision of 96% in the automatic detection of anomalies. Additionally, anomaly detection was also associated with cell measurement errors inherent to the acquisition or analysis pipelines, leading to an improvement of the upstream methods for feature extraction. Our results pave the way to novel architectures for the continuous monitoring of cell cultures in applied research or bioproduction applications, and for the prediction of pathological cellular changes.

Transformer enhanced by local perception self-attention for dynamic soft sensor modeling of industrial processes

The use of dynamic soft sensor modeling methods to mine the time-varying and dynamic characteristics of industrial process data is of great significance for improving production efficiency and quality, given the rapid development of industrial processes and the increasing prominence of dynamic changes in the production process. However, existing dynamic soft sensor methods have limited long-term memory capacity, making it difficult to capture the long dynamic dependence, which can severely affect the results of the soft sensor model. To address this issue, we propose a dynamic soft sensor model based on local perception transformer, where the transformer is applied to achieve global perception of the variables. Through the application of the self-attention mechanism in the transformer encoder, the dynamic tracking and prediction of parameters can be realized by assigning different weights to the process variables and quality variables at different time steps, thereby adapting to the time-varying nature of the process. Additionally, convolution is used to generate a Query and Key in the self-attention mechanism, thereby enhancing local information learning. The proposed dot product self-attention calculation method effectively utilizes local information, thereby reducing the potential impact of abnormal data at a certain moment. Furthermore, by utilizing LSTM to extract time series information, the final prediction result was obtained. In soft sensor modeling experiments of the sulfur recovery unit and debutanizer tower, our proposed model demonstrated higher prediction accuracy compared to other methods, such as SVR, MLP, LSTM, CNN + LSTM, and vanilla transformer.

Public interest and seasonal peaks for wisdom teeth related web inquiries - A google trends analysis.

With the help of the online search query tool, Google Trends, the public interest in the primary search term "wisdom teeth" for the timeframe between January 1st, 2004 and September 31st, 2021 was analyzed. To do so, a country-specific search was conducted in English-speaking countries (the USA, the UK, Canada, and Australia) in the northern and southern hemispheres. The extracted time series was examined for reliability, and a Cosinor analysis evaluated the statistical significance of seasonal interest peaks. The reliability of averaged time series data on the search term "wisdom teeth" was excellent in all examined countries. In all countries analyzed, "wisdom teeth removal" was one of the most common related search terms. Significant interest peaks for wisdom teeth-related search terms were found in Canada and the USA during summer (p < .001). In Canada and the USA, significant seasonal patterns with the highest interest during the summer months, could be displayed. This phenomenon could be caused by increased wisdom teeth-related complaints induced by seasonal climate changes.

Automated Extraction of Satellite-Derived Shoreline Changes along the Ongole Coast of Andhra Pradesh from 2000 to 2023 Using CoastSat

This paper presents a fully automated methodology for extracting time-series of monthly shoreline changes along the sandy beaches of the Ongole coast in Andhra Pradesh, India, from 2000 to 2023 using publicly available satellite imagery. The methodology involves the identification of sandy coastline sections within the region of interest, creating cross shore transects automatically at each site, and utilizing the open-source global shoreline mapping toolbox called CoastSat. The CoastSat tool is employed to extract time-series of shoreline change at each transect. To account for variations in tide levels among satellite images, the final step includes tidally correcting the shoreline change time-series using predicted tide levels and an image-derived estimation of the average intertidal beach slope. Keywords: - satellite imagery, shoreline change, Ongole coast, Andhra Pradesh, CoastSat, automated methodology, time- series analysis, and tide correction.

A domain adaptation network with feature scale preservation for remaining useful life prediction of rolling bearings under variable operating conditions

Transfer learning and domain adaptation (DA) methods have been utilized in bearing prognostic and health management, but most of the current DA methods do not take into account the feature scale change of degraded features when aligning the feature distribution, and these methods are more suitable for the classification problem, which is more robust to the feature scale change. However, they perform poorly in regression problems. In addition, most of the remaining useful life (RUL) prediction methods require preprocessing such as statistical feature extraction on the signal, which makes the prediction process complicated. To solve the above problems, a DA method based on the representation subspace distance (RSD) is proposed for predicting the bearing RUL under different operating conditions. First, the proposed convolutional neural network (CNN) self-attention (SA) long short term memory network model is utilized to extract the deep features from the original signal, which overcomes the limitations of the CNN in extracting time series. Then, the RSD in the Riemannian geometry of the Grassmann manifold is proposed as a domain transfer loss to learn domain invariant features. The modified method can align the feature distribution of the source domain and the target domain without changing the feature scale. At the same time, the bases mismatch penalization is introduced to avoid destroying the semantic information of the features in the process of domain alignment. Finally, the effectiveness of the proposed method is verified by experiments on four types of transfer tasks, and its superiority is also demonstrated by comparison with other advanced methods.

Passenger flow forecast of tourist attraction based on MACBL in LBS big data environment

Abstract The existing scenic spot passenger flow prediction models have poor prediction accuracy and inadequate feature extraction ability. To address these issues, a multi-attentional convolutional bidirectional long short-term memory (MACBL)-based method for predicting tourist flow in tourist scenic locations in a location-based services big data environment is proposed in this study. First, a convolutional neural network is employed to identify local features and reduce the dimension of the input data. Then, a bidirectional long short-term memory network is utilized to extract time-series information. Second, the multi-head attention mechanism is employed to parallelize the input data and assign weights to the feature data, which deepens the extraction of important feature information. Next, the dropout layer is used to avoid the overfitting of the model. Finally, three layers of the above network are stacked to form a deep conformity network and output the passenger flow prediction sequence. In contrast to the state-of-the-art models, the MACBL model has enhanced the root mean square error index by at least 2.049, 2.926, and 1.338 for prediction steps of 24, 32, and 60 h, respectively. Moreover, it has also enhanced the mean absolute error index by at least 1.352, 1.489, and 0.938, and the mean absolute percentage error index by at least 0.0447, 0.0345, and 0.0379% for the same prediction steps. The experimental results indicate that the MACBL is better than the existing models in evaluating indexes of different granularities, and it is effective in enhancing the forecasting precision of tourist attractions.