Model Time Series Data Research Articles

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.

Long Short-Term Memory Parameter Optimization Based on Improved Sparrow Search Algorithm for Molten Iron Quality Prediction

Blast furnace (BF) ironmaking is a key process in iron and steel production. Because BF ironmaking is a dynamic time series process, it is more appropriate to use a recurrent neural network for modeling. The long short-term memory (LSTM) network is commonly used to model time series data. However, its model performance and generalization ability heavily depend on the parameter configuration. Therefore, it is necessary to study parameter optimization for the LSTM model. The sparrow search algorithm (SSA) holds advantages over traditional optimization algorithms in several aspects, such as no need for prior knowledge, fewer parameters, fast convergence, and high scalability. However, the algorithm still faces some challenges, such as the tendency to become trapped in the local optimum and the imbalance between global search ability and local search ability. Therefore, on the basis of SSA, this study examined the Levy flight strategy, sine search strategy, and step size factor adjustment strategy to improve it. This algorithm, improved by three strategies, is called the improved sparrow search algorithm (ISSA). Then, the ISSA-LSTM model was established. Furthermore, considering the limitations of SSA in dealing with multi-objective problems, the fast non-dominated sorting genetic algorithm (NSGAII) was introduced, and the ISSA-NSGAII model was established. Finally, experimental validation was performed using real blast furnace operation data, which demonstrated the proposed algorithm’s superiority in parameter optimization for the LSTM model and prediction for real industrial data.

Effective Forecasting of Key Features in Hospital Emergency Department

Efficiently forecasting the demands within a hospital’s Emergency Department (ED) is critical for optimal resource allocation and patient care management. This study focuses on leveraging deep learning techniques to predict various types of ED patient flows, facilitating informed decision-making by ED managers. The rising success of deep learning networks in modeling timeseries data makes them a compelling choice for patient flow forecasting. In this context, we investigate and compare seven deep learning models-Deep Belief Network (DBN), Restricted Boltzmann Machines (RBM), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), combined GRU and Convolutional Neural Networks (CNN-GRU), LSTM-CNN, and Generative Adversarial Network based on Recurrent Neural Networks (GAN-RNN)—to accurately forecast patient flow within a hospital’s emergency department. To enable traffic flow forecasting, a forecaster layer is introduced for each model. Real-world patient flow data spanning different ED services (biology, radiology, scanner, and echography) at Lille regional hospital in France serve as a case study to evaluate these models. Four effectiveness metrics are employed to assess and compare the forecasting methods. The outcomes demonstrate the superior performance of deep learning models in predicting ED patient flows compared to conventional shallow approaches like ridge regression and support vector regression. Significantly, the Deep Belief Network (DBN) stands out, achieving an averaged mean absolute percentage error of approximately 4.097.

Deep learning-enabled probing of irradiation-induced defects in time-series micrographs

Modeling time-series data with convolutional neural networks (CNNs) requires building a model to learn in batches as opposed to training sequentially. Coupling CNNs with in situ or operando techniques opens the possibility of accurately segmenting dynamic reactions and mass transport phenomena to understand how materials behave under the conditions in which they are used. In this article, in situ ion irradiation transmission electron microscopy (TEM) images are used as inputs into the CNN to assess the defect generation rate, defect cluster density, and saturation of defects. We then use the output segmentation maps to correlate with conventional TEM micrographs to assess the model’s ability to detail nanoscale interactions. Next, we discuss the implications of preprocessing and hyperparameters on model variability, accuracy when expanded to other datasets, and the role of regularization when controlling model variance. Ultimately, we eliminate human bias when extrapolating physical metrics, speed up analysis time, decouple reactions that happen at 100 ms intervals, and deploy models that are both accurate and transferable to similar experiments.

Comparison of simulation and predictive efficacy for hemorrhagic fever with renal syndrome incidence in mainland China based on five time series models.

Hemorrhagic fever with renal syndrome (HFRS) is a zoonotic infectious disease commonly found in Asia and Europe, characterized by fever, hemorrhage, shock, and renal failure. China is the most severely affected region, necessitating an analysis of the temporal incidence patterns in the country. We employed Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Nonlinear AutoRegressive with eXogenous inputs (NARX), and a hybrid CNN-LSTM model to model and forecast time series data spanning from January 2009 to November 2023 in the mainland China. By comparing the simulated performance of these models on training and testing sets, we determined the most suitable model. Overall, the CNN-LSTM model demonstrated optimal fitting performance (with Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Error (MAE) of 93.77/270.66, 7.59%/38.96%, and 64.37/189.73 for the training and testing sets, respectively, lower than those of individual CNN or LSTM models). The hybrid CNN-LSTM model seamlessly integrates CNN's data feature extraction and LSTM's recurrent prediction capabilities, rendering it theoretically applicable for simulating diverse distributed time series data. We recommend that the CNN-LSTM model be considered as a valuable time series analysis tool for disease prediction by policy-makers.

Applications of Deep Learning Models for Forecasting and Modelling Rainwater in Moscow

To model and forecast complex time series data, machine learning has become a major field. This machine learning study examined Moscow rainfall data's future performance. The dataset is split into 65% training and 35% test sets to build and validate the model. We compared these deep learning models using the Root Mean Square Error (RMSE) statistic. The LSTM model outperforms the BILSTM and GRU models in this data series. These three models forecast similarly. This information could aid the creation of a complete Moscow weather forecast book. This material would benefit policymakers and scholars. We also believe this study can be used to apply machine learning to complex time series data, transcending statistical approaches.

Predictive Data Analysis: Leveraging RNN and LSTM Techniques for Time Series Dataset

Recurrent neural networks (RNNs) and long short-term memory (LSTM) models have demonstrated tremendous effectiveness in modeling time series data due to the ability they possess to capture temporal dependencies. Stock market data is an example of time series data. Stock price data is very volatile and dynamic therefore one of the most turbulent areas to invest in might be the stock market. The choice to buy or sell stocks is heavily influenced by external circumstances and statistical analysis of previous stock performance. Stock price index forecasting has been a major area of research for many years and many machine learning and deep learning methods have been proposed to simplify this hard process, but little success has been discovered so far.In this paper, the application of RNNs and LSTMs on a stock price dataset to predict future values is explored. We start with Recurrent neural networks (RNNs) to predict the values but one of the major challenges with it is the "vanishing gradient" problem, which makes it difficult for the network to learn long-term dependencies in the data. To overcome this long short-term memory (LSTM) was used which eliminates the vanishing gradient problem. Data were normalized and divided into time steps to determine the relationship between past values and future values to make accurate predictions. The outcomes show that the MLS LSTM method significantly outperforms existing algorithms, achieving a prediction accuracy of 98.1% on the training data set and a 91.97% accuracy on the testing data set.

Deep Geometric Learning With Monotonicity Constraints for Alzheimer's Disease Progression.

Alzheimer's disease (AD) is a devastating neurodegenerative condition that precedes progressive and irreversible dementia; thus, predicting its progression over time is vital for clinical diagnosis and treatment. For this, numerous studies have implemented structural magnetic resonance imaging (MRI) to model AD progression, focusing on three integral aspects: 1) temporal variability; 2) incomplete observations; and 3) temporal geometric characteristics. However, many pioneer deep learning-based approaches addressing data variability and sparsity have yet to consider inherent geometrical properties sufficiently. These properties are integral to modeling as they correlate with brain region size, thickness, volume, and shape in AD progression. The ordinary differential equation-based geometric modeling method (ODE-RGRU) has recently emerged as a promising strategy for modeling time-series data by intertwining a recurrent neural network (RNN) and an ODE in Riemannian space. Despite its achievements, ODE-RGRU encounters limitations when extrapolating positive definite symmetric matrices from incomplete samples, leading to feature reverse occurrences that are particularly problematic, especially within the clinical facet. Therefore, this study proposes a novel geometric learning approach that models longitudinal MRI biomarkers and cognitive scores by combining three modules: topological space shift, ODE-RGRU, and trajectory estimation. We have also developed a training algorithm that integrates the manifold mapping with monotonicity constraints to reflect measurement transition irreversibility. We verify our proposed method's efficacy by predicting clinical labels and cognitive scores over time in regular and irregular settings. Furthermore, we thoroughly analyze our proposed framework through an ablation study.

A feature-recombinant asynchronous deep reservoir computing for modeling time series data

Modeling time series data is an important issue in many areas. Reservoir computing (RC) is a promising tool to build time series model due to its dynamic characteristic and simple training way. Asynchronous deep reservoir computing (ADRC) is an improvement version of the traditional RC. It solves time-dependent tasks more efficiently than traditional RC because of its rich dynamics and flexible short-term memory (STM). Nevertheless, it has been an open issue to design RC’s or ADRC’s reservoir topology owing to large amounts of random factors. To promote the solution of this problem, the paper proposes a feature-recombinant ADRC (FR-ADRC) for modeling time series data. In the FR-ADRC scheme, the first sub-reservoir is designed as the feature-adaptive layer, and a trainable matrix C is introduced into this layer. By learning C, the singular value (SV) distribution of the first layer could be adjusted. Further, the principal components of the reservoir topology can be extracted by the principal component analysis (PCA). Then a new temporary reservoir is constructed by recombining these extracted components. The subsequent information processing is carried out based on the recombinant reservoir, which can be adaptive to the input signals. The validity of the FR-ADRC is tested by modeling some numerical and real-life time series data. Experimental results show that the proposed approach is better than the traditional ADRC in modeling precision, generalization ability and stability.

Enhancing accuracy and interpretability in EEG-based medical decision making using an explainable ensemble learning framework application for stroke prediction

Medical decision making increasingly relies on machine learning algorithms to analyze complex patient data and provide recommendations. However, the lack of interpretability in “black box” models has limited their adoption in clinical practice, which demands transparency and justification. Echo State Networks (ESNs), a recurrent neural network architecture, have shown promise for medical Decision Support Systems (DSS) applications due to their accuracy in modeling time series data, such as physiological signals. However, conventional ESNs suffer from a lack of interpretability, which limits their usefulness for clinical decisions. This study proposes a multi-level framework to optimize both accuracy and interpretability for improved medical decision support. The framework is specifically designed for EEG data, which represents a non-invasive and continuous recording of brain activity. EEG data is ideal for recording information about the internal state of the brain, which is not always translated by perceptible external manifestations. The framework consists of four components: (1) data preprocessing and optimized feature selection utilizing a filter-based feature importance algorithm, (2) ensemble learning via Ensemble ESNs (E-ESNs) that combines the predictions of multiple ESNs to reduce variance and improve accuracy, (3) Global and Local model explanation techniques to allow users to understand the decision-making process and identify the most influential features for each prediction, and (4) decision-making for presenting diagnoses and recommendations. The framework was evaluated on an EEG dataset for stroke prediction, a valuable use case for informed clinical decisions and resource allocation. The results showed that the framework significantly outperformed baseline related works with an accuracy of 96.5% and provides insights into the E-ESN model's predictions. This transparency enhances trust and comprehension among healthcare practitioners. These findings suggest that the proposed framework can be a valuable tool for medical DSS applications.

Multi-oscillations Detection for Process Variables Based on K-Nearest Neighbor

In the process industry, a control system is important to ensure the process runs smoothly and keeps the product under predetermined specifications. Oscillations in process variables can affect the decreasing profitability of the plant. It is important to detect the oscillation before it becomes a problem for profitability. Various methods have been developed; however, the methods still need to improve when implemented online for multi-oscillation. Therefore, this research uses a machine learning-based method with the K-Nearest Neighbour (KNN) algorithm to detect multi-oscillation in the control loop, and the detection methods are made to carry out online detection from real plants. The developed method simulated the Tennessee Eastman Process (TEP), and it used Python programming to create a KNN model and extract time series data into the frequency domain. The Message Queuing Telemetry Transport (MQTT) communication protocol has been used to implement as an online system. The result of the implementation showed that two KNN models were made with different window size variations to get the best performance model. The best model for multi-oscillation detection was obtained with an F1 score of 76% for detection.

Estimation of conventional and innovative models for Rwanda's GDP per capita: A comparative analysis of artificial neural networks and Box–Jenkins methodologies

This study aims to model the time series data of Rwanda's GDP per capita using the Box–Jenkins (BJ) approach as a conventional approach and artificial neural networks (ANNs) as an innovative approach. The BJ technique, which utilizes autoregressive moving average - ARMA or an integrated version of ARMA - ARIMA, has been applied, and it is found that the ARIMA (0,2,1) model is the best fit for Rwanda's GDP per capita. Moreover, three ANNs models (the long short-term model- LSTM, the generalized regression neural network- GRNN, and the multilayer perception - MLP) have been utilized for the dataset. It is shown that the MLP and GRNN models have outperformed the LSTM model and BJ approach in terms of statistical criteria. In addition, the LSTM model is not superior to the BJ model, except for the Mean Absolute Percentage Error (MAPE) value. Therefore, any inference that ANNs models will always be superior to traditional approaches would be misleading. It is necessary to evaluate the results cumulatively using both traditional and innovative methods and then come to a conclusion. Additionally, the study provides insights into the use of both BJ and ANNs approaches for modeling time series data of GDP per capita and highlights the potential of ANNs models for improving the prediction accuracy of GDP per capita. Decision-makers and policymakers may benefit in the future from these analyses and results including recommendations.

PREDIKSI JUMLAH PEMAKAIAN AIR BERSIH MENGGUNAKAN METODE HYBRID SINGULAR SPECTRUM ANALYSIS (SSA) DAN SARIMA DI PDAM TIRTANADI SIBOLANGIT

Clean water is one of the basic human needs that is needed on an ongoing basis. Water has an important role in human life. As the population increases, the use of clean water also increases, resulting in the need for demand for the availability of clean water to continue to increase, this is explained by data from the Central Statistics Agency (2022) that the population growth rate in Sibolangit District from 2021-2022 is 0.25% and that This is also explained by data on the amount of clean water consumption by PDAM Tirtanadi Sibolangit which has increased by 6.5%. The purpose of this study is to apply the SSA-SARIMA hybrid model to predict the amount of clean water consumption in the coming period at PDAM Tirtandi Sibolangit so that there is no shortage and wastage of clean water. Hybrid SSA-SARIMA is a combination of two data analysis methods that take advantage of the advantages of each method, namely Singular Spectrum Analysis (SSA) and Seasonal Autoregressive Moving Average (SARIMA). SSA is a technique used to separate signals into periodic and non-periodic components while SARIMA is used to model time series data with trend and seasonal patterns and make predictions for future periods. SARIMA cannot separate periodic and non-periodic signals in data like SSA did. The data used in this study is monthly data on clean water usage from January 2018 to December 2022. The prediction results for the amount of clean water consumption in PDAM Tirtanadi Sibolangit in 2024 use the SSA-SARIMA(1,1,0)(1,0,0) hybrid model. )12 experienced a decrease in the use of clean water with a level of forecasting accuracy having a MAPE value of 6.920446%.

A point mass proposal method for Bayesian state-space model fitting

State-space models (SSMs) are commonly used to model time series data where the observations depend on an unobserved latent process. However, inference on the model parameters of an SSM can be challenging, especially when the likelihood of the data given the parameters is not available in closed-form. One approach is to jointly sample the latent states and model parameters via Markov chain Monte Carlo (MCMC) and/or sequential Monte Carlo approximation. These methods can be inefficient, mixing poorly when there are many highly correlated latent states or parameters, or when there is a high rate of sample impoverishment in the sequential Monte Carlo approximations. We propose a novel block proposal distribution for Metropolis-within-Gibbs sampling on the joint latent state and parameter space. The proposal distribution is informed by a deterministic hidden Markov model (HMM), defined such that the usual theoretical guarantees of MCMC algorithms apply. We discuss how the HMMs are constructed, the generality of the approach arising from the tuning parameters, and how these tuning parameters can be chosen efficiently in practice. We demonstrate that the proposed algorithm using HMM approximations provides an efficient alternative method for fitting state-space models, even for those that exhibit near-chaotic behavior.

CO2 Emissions, Health Expenditures, and Economic Growth Nexus in Pakistan

Climate change has an impact on human health, and it is generally known that environmental degradation and climate change are related. The utilization of fossil fuels results in more CO2 emissions into the atmosphere, a greenhouse gas that dramatically raises global temperatures. By replacing oxygen in the atmosphere, CO2 emissions have an impact on human health. While CO2 emissions hurt human health, sometimes economic expansion has a favorable impact on public health and vice versa. Using the Autoregressive Distributive Lag model (ARDL) and annual time series data from 1985 to 2020, this study aims to investigate the relationship between CO2 emissions, health spending, and economic growth in Pakistan. The empirical findings of this study demonstrate a substantial long-run and short-run relationship. To use technologies that cause emissions, the government must increase its investment in renewable energy sources and implement carbon taxes.

A novel model for runoff prediction based on the ICEEMDAN-NGO-LSTM coupling.

Prediction of runoff trends is a critical topic in hydrological forecasting. Accurate and reliable prediction models are important for the rational use of water resources. This paper proposes a new coupled model, ICEEMDAN-NGO-LSTM, for runoff prediction in the middle reaches of the Huai River. This model combines the excellent nonlinear processing capability of the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) algorithm, the perfect optimization strategy of the Northern Goshawk Optimization (NGO) algorithm, and the advantages of the Long Short-Term Memory (LSTM) algorithm in modeling time series data. The results show that the ICEEMDAN-NGO-LSTM model predicts the monthly runoff trend with higher accuracy compared to the actual data variation. The average relative error is 5.95% within 10%, and the Nash Sutcliffe (NS) is 0.9887. These results indicate that the ICEEMDAN-NGO-LSTM coupled model has superior prediction performance and provides a new method for short-term runoff forecasting.

Optimizing BiLSTM Network Attack Prediction Based on Improved Gray Wolf Algorithm

Aiming at the problems of low accuracy of network attack prediction and long response time of attack detection, bidirectional long short-term memory (BiLSTM) was used to predict network attacks. However, BiLSTM has the problems of difficulty in parameter setting and low accuracy of the prediction model. This paper first proposes the Improved Grey Wolf algorithm (IGWO) to optimize the BiLSTM (IGWO-BiLSTM). First, IGWO uses Dimension Learning Hunting (DLH) strategy to construct the wolf neighborhood. In the established wolf neighborhood, the BiLSTM parameters are iteratively optimized to obtain a prediction model with fast convergence speed and small reconstruction error. Secondly, the dataset is preprocessed, and the IP packet statistical signature (IPDCF) is defined according to the characteristics of denial of service (DOS) and distributed denial of service (DDOS) attacks. IPDCF was used to establish the time series model and network traffic time series data were input into IGWO-BiLSTM to get the prediction results. Finally, the DOS and DDOS network packets were input into the trained prediction model to obtain the prediction results of attack data. By comparing the predicted values of IGWO-BiLSTM normal network packets and attack packets, a reasonable threshold is set to provide the basis for the subsequent attack prediction. Experiments show that the IGWO-BiLSTM can reach 99.05% of the fitting degree and accurately distinguish network attacks from normal network demand increases.

A WOA-CNN-BiLSTM-based multi-feature classification prediction model for smart grid financial markets

Introduction: Smart grid financial market forecasting is an important topic in deep learning. The traditional LSTM network is widely used in time series forecasting because of its ability to model and forecast time series data. However, in long-term time series forecasting, the lack of historical data may lead to a decline in forecasting performance. This is a difficult problem for traditional LSTM networks to overcome.Methods: In this paper, we propose a new deep-learning model to address this problem. This WOA-CNN-BiLSTM model combines bidirectional long short-term memory network BiLSTM and convolution Advantages of Neural Network CNN. We replace the traditional LSTM network with a bidirectional long short-term memory network, BiLSTM, to exploit its ability in capturing long-term dependencies. It can capture long-term dependencies in time series and is bidirectional modelling. At the same time, we use a convolutional neural network (CNN) to extract features of time series data to better represent and capture patterns and regularity in the data. This method combining BiLSTM and CNN can learn the characteristics of time series data more comprehensively, thus improving the accuracy of prediction. Then,to further improve the performance of the CNN-BiLSTM model, we optimize the model using the whale algorithm WOA. This algorithm is a new optimization algorithm, which has good global search ability and convergence speed, and can complete the optimization of the model in a short time.Results: Optimizing the CNN-BiLSTM model through the WOA algorithm can reduce its calculation and training speed, improve the prediction accuracy of the smart grid financial market, and improve the prediction ability of the smart grid financial market. Experimental results show that our proposed CNN-BiLSTM model has better prediction accuracy than other models and can effectively deal with the problem of missing historical data in long-term sequence forecasting.Discussion: This provides necessary help for the development of smart grid financial markets and risk management services, and can promote the development and growth of the smart grid industry. Our research results are of great significance in deep learning, and provide an effective method and idea for solving the financial market forecasting problem of smart grid.

PEMODELAN INDEKS HARGA PERDAGANGAN BESAR (IHPB) SEKTOR EKSPOR MENGGUNAKAN ARFIMA-GARCH

Indonesia's price index serves as a barometer for the nation's economic condition. One of the Indonesia’s price index is Wholesale Price Index (WPI). WPI is a price index that tracks the average change in wholesale prices over time. Time series analysis can be used for forecasting because WPI is one of the time series data. WPI is long memory, which is a condition in which data from different time periods have a high link despite being separated by a large amount of time. The Autoregressive Fractional Integrated Moving Average (ARFIMA) model can be used to overcome this feature when modeling time series data. The assumption of constant error variance is not fulfilled in the IHPB data analysis, indicating that the data is heteroscedastic. The GARCH (Generalized Auto Regressive Conditional Heteroscedasticity) model is one of the models used to overcome heteroscedasticity. The data used is the export sector of WPI from January 2003 to June 2021. The best model for forecasting WPI is ARFIMA(1,b,2) – GARCH(1,1) with b=0,7345333, and MAPE value is 3,150875%.

PERBANDINGAN MODEL ARIMA DENGAN MODEL NONPARAMETRIK POLINOMIAL LOKAL DAN SPLINE TRUNCATED UNTUK PERAMALAN HARGA MINYAK MENTAH WEST TEXAS INTERMEDIATE (WTI) DILENGKAPI GUI R

Crude oil as one of the most important natural resources experiences price fluctuations from time to time, even the spot price of West Texas Intermediate (WTI) world crude oil on 20th April 2020 reached -36,98 USD/barrel due to the Covid-19 pandemic. WTI oil price data was modeled using the ARIMA method, local polynomial, and spline truncated nonparametric regression then compared and obtained the best model and formed R Graphical User Interface (GUI). The ARIMA model and nonparametric time series models can be used to model time series data, but in the ARIMA model there are assumptions that must be fulfilled. Nonparametric time series models, which include local polynomial model and truncated spline do not need to fulfill these assumptions. The ARIMA model obtained did not fulfilled the assumptions of normality and residual homoscedasticity, so the modeling was stopped and modeling was only carried out using nonparametric regression methods. Based on the minimum MSE criteria, the best nonparametric model was obtained, namely nonparametric truncated spline model with degrees 3 and 3 knot points which was categorized as a strong model based on R-squared in sample value and having a very good forecasting ability based on MAPE out sample value.