Existing Hybrid Models Research Articles

Hybrid hydrological modeling for large alpine basins: a semi-distributed approach

Abstract. Alpine basins are important water sources for human life, and reliable hydrological modeling can enhance the water resource management in alpine basins. Recently, hybrid hydrological models, coupling process-based models and deep learning (DL), have exhibited considerable promise in hydrological simulations. However, a notable limitation of existing hybrid models lies in their failure to incorporate spatial information within the basin and describe alpine hydrological processes, which restricts their applicability in hydrological modeling in large alpine basins. To address this issue, we develop a set of hybrid semi-distributed hydrological models by employing a process-based model as the backbone and utilizing embedded neural networks (ENNs) to parameterize and replace different internal modules. The proposed models are tested on three large alpine basins on the Tibetan Plateau. A climate perturbation method is further used to test the applicability of the hybrid models to analyze the hydrological sensitivities to climate change in large alpine basins. Results indicate that proposed hybrid hydrological models can perform well in predicting runoff processes and simulating runoff component contributions in large alpine basins. The optimal hybrid model with Nash–Sutcliffe efficiencies (NSEs) higher than 0.87 shows comparable performance to state-of-the-art DL models. The hybrid model also exhibits remarkable capability in simulating hydrological processes at ungauged sites within the basin, markedly surpassing traditional distributed models. In addition, the results also show reasonable patterns in the analysis of the hydrological sensitivities to climate change. Overall, this study provides a high-performance tool enriched with explicit hydrological knowledge for hydrological prediction and improves our understanding about the hydrological sensitivities to climate change in large alpine basins.

Enhanced prediction model of short-term sea surface wind speed: A multiscale feature extraction and selection approach coupled with deep learning technique

Accurate prediction of short-term sea surface wind speed is essential for maritime safety and coastal management. Most conventional studies encounter challenges simply in analyzing raw wind speed sequences and extracting multiscale features directly from the original received data, which result in lower efficiency. In this paper, an enhanced hybrid model based on a novel data assemble method for original received data, a multiscale feature extraction and selection approach, and a predictive network, is proposed for accurate and efficient short-term sea surface wind speed forecasting. Firstly, the received original data including wind speed are assembled into correlation matrices in order to uncover inherent associations over varied time spans. Secondly a novel Multiscale Wind-speed Feature-Enhanced Convolutional Network (MW-FECN) is designed for efficient and selective multiscale feature extraction, which can capture comprehensive characteristics. Thirdly, a Random Forest Feature Selection (RF-FS) is employed to pinpoint crucial characteristics for enhanced prediction of wind speed with higher efficiency than the related works. Finally, the proposed hybrid model utilized a Bidirectional Long Short-Term Memory (BiLSTM) network to achieve the accurate prediction of wind speed. Experimental data are collected in Weihai sea area, and a case study consist of five benchmarks and three ablation models is conducted to assess the proposed hybrid model. Compared with the conventional methods, experiment results illustrate the effectiveness of the proposed hybrid model and demonstrate effective balancing prediction accuracy and computational time. The proposed hybrid model achieves up to a 28.45% MAE and 27.27% RMSE improvement over existing hybrid models.

An integrated skip convolutional network with residual learning and feature extraction for point and interval prediction of solar radiation

Spinning reserve based on solar radiation prediction can ensure the secure operation of large-scale grid-connected photovoltaic systems, but irrational spinning reserve can lead to substantial economic losses and even grid collapse. Therefore, it is imperative to identify characteristic patterns of solar radiation and establish an effective solar radiation prediction model. However, existing hybrid models often struggle to efficiently recognize and leverage input features, compromising the robustness of the model. To address this limitation, this study proposes an integrated skip-convolutional network with residual learning and feature extraction (InSCNet), which enhances the capability to represent information data and thereby improves the stability and accuracy of solar radiation prediction by employing a series of feature extraction and prediction blocks with residual learning. InSCNet includes a sophisticated feature extraction module to effectively address the underutilization of feature information, and it incorporates residual learning, skip-convolution, and recursive networks in the prediction module, reducing the risk of gradient vanishing or gradient explosion while enhancing prediction accuracy. Additionally, an interval estimation method with adaptively chosen distributions is introduced, which extends the prediction interval estimation method. The proposed InSCNet is rigorously evaluated using datasets from three major cities in Pakistan. Experimental results demonstrate that InSCNet outperforms existing solutions in both point and interval predictions.

Hybrid black-box classification for customer churn prediction with segmented interpretability analysis

Customer retention management relies on advanced analytics for decision making. Decision makers in this area require methods that are capable of accurately predicting which customers are likely to churn and that allow to discover drivers of customer churn. As a result, customer churn prediction models are frequently evaluated based on both their predictive performance and their capacity to extract meaningful insights from the models. In this paper, we extend hybrid segmented models for customer churn prediction by incorporating powerful models that can capture non-linearities. To ensure the interpretability of such segmented hybrid models, we introduce a novel model-agnostic approach that extends SHAP. We extensively benchmark the proposed methods on 14 customer churn datasets on their predictive performance. The interpretability aspect of the new model-agnostic approach for interpreting hybrid segmented models is illustrated using a case study. Our contributions to decision making literature are threefold. First, we introduce new hybrid segmented models as powerful tools for decision makers to boost predictive performance. Second, we provide insights in the relative predictive performance by an extensive benchmarking study that compares the new hybrid segmented methods with their base models and existing hybrid models. Third, we propose a model-agnostic tool for segmented hybrid models that provide decision makers with a tool to gain insights for any hybrid segmented model and illustrate it on a case study. Although we focus on customer retention management in this study, this paper is also relevant for decision makers that rely on predictive modeling for other tasks.

A hybrid neural network based solar PV power classification with time series data for bend, Oregon

ABSTRACT Photovoltaic (PV) power classification model has become a significant alternative to PV power point forecasting model in which classes of future PV powers are estimated. In this work, a novel PV power classification model which could be realized using feed forward neural network (FFNN) trained with a hybrid meta-heuristic approach is proposed to forecast the classes of future PV powers. The insisted classification model is implemented to classify three classes of PV power for the location Oregon city of United States of America (USA) with latitude 43.8041 0 N , longitude 120.5542 0 W , and altitude of 1124 m. The meta-heuristic approach comprising of Levy Flight (Levy)-Sine Cosine Algorithm (SCA)-Particle Swarm Optimization (PSO) is utilized for training the parameters of FFNN by minimizing the root mean square error RMSE . The results disclose that the proposed approach attained the most accurate prediction of PV power with % MAPE = 2.38 for the month of November as well as high classification accuracy with PCA = 94.96 % in the month of April. Based on the obtained results, the proposed LF-SCA-PSO trained FFNN outperformed the existing hybrid models in both prediction and classification and hence possess the potential to be a new alternative to assist engineers in predicting the PV power of solar systems at short- and long-time horizons.

Interactive Hybrid Model for Remaining Useful Life Prediction With Uncertainty Quantification of Bearing in Nuclear Circulating Water Pump

Journal bearings are the key components of the nuclear circulating water pump (NCWP), and accurate remaining useful life (RUL) prediction is of great significance for improving the reliability, safety, and maintenance planning of NCWP. However, it is difficult to quantify the uncertainty of bearing RUL based on the current deep learning (DL) model, resulting in a lack of credibility and effective convincing for RUL predicted by the model. Meanwhile, all existing hybrid models are basically simple combinations, and they cannot solve the uncertainty quantification problem of RUL predicted by DL. Hence, the bearing RUL prediction method based on a dynamic interactive hybrid model is proposed. Firstly, a degradation model based on a nonlinear enhanced generalized Wiener process (EGWP) is proposed, which combines gated neural networks and time-varying drift coefficients to describe the nonlinear degradation process of bearing. Then, a corrective gated recurrent unit (CGRU) network is designed to learn and predict real-time degradation increments, and the parameters of the degradation model are dynamically updated through the history and prediction of degradation increments. Finally, the bearing RUL prediction is given by the CGRU network, and the probability density function (PDF) of RUL is given by the proposed hybrid model. The performance of the proposed method is evaluated using the PHM 2012 bearing dataset and the NCWP journal bearing dataset. The results show that our proposed method can effectively predict bearing RUL and its uncertainty.

The applicability of a hybrid framework for automated phishing detection

Phishing attacks are a critical and escalating cybersecurity threat in the modern digital landscape. As cybercriminals continually adapt their techniques, automated phishing detection systems have become essential for safeguarding Internet users. However, many current systems rely on single-analysis models, making them vulnerable to sophisticated bypass attempts by hackers. This research delves into the potential of hybrid approaches, which combine multiple models to enhance both the robustness and effectiveness of phishing detection. It highlights existing hybrid models' limitations that focus primarily on effectiveness while ignoring broader applicability. To address these gaps, we introduce a novel framework explicitly designed for applicability in the real world, which poses the foundation for practical and robust phishing detection architectures. We develop a proof of concept to evaluate its effectiveness, robustness, and detection speed. Additionally, we introduce an innovative methodology for simulating bypass attacks on single-analysis base models. Our experiments demonstrate that the proposed hybrid framework outperforms individual models, displaying higher effectiveness, robustness against bypassing attempts, and real-time detection capabilities. Our proof of concept achieves an accuracy of 97.44% thereby outperforming the current state-of-the-art approach while requiring less computational time. The results provide insights into the multifaceted factors of hybrid models, extending beyond mere effectiveness, and emphasize the importance of holistic applicability in hybrid approaches to address the critical need for robust defenses against phishing attacks.

Enhancing Load Forecasting Accuracy in Smart Grids: A Novel Parallel Multichannel Network Approach Using 1D CNN and Bi‐LSTM Models

Load forecasting plays a pivotal role in the efficient energy management of smart grid. However, the complex, intermittent, and nonlinear smart grids and the complexity of large dataset handling pose difficulty in accurately forecasting loads. The important issue is considering the cyclic features, which have not yet been adequately addressed through the trigonometric transformations. Furthermore, using long short‐term memory (LSTM) or 1D convolution neural network (1D CNN) and existing hybrid models involve stacked CNN‐LSTM architectures, employing 1D convolutions as a preprocessing step to downsample sequences and extract high‐ and low‐level spatial features. However, these models often overlook temporal features, emphasizing higher‐level features processed by the subsequent recurrent neural network layer. Therefore, this study considers a novel approach to independently process features for spatial and temporal characteristics using a parallel multichannel network comprising 1D CNN and bidirectional‐LSTM (Bi‐LSTM) models. The proposed model evaluated the National Transmission and Dispatch Company (NTDC) load dataset, with additional assessment on two datasets, American Electric Power and Commonwealth Edison, to ensure its generalizability. Performance evaluation on the NTDC dataset yields results of 3.4% mean absolute percentage error (MAPE), 513.95 mean absolute error (MAE), and 623.78 root mean square error (RMSE) for day‐ahead forecasting, and 0.56% MAPE, 94.84 MAE, and 115.67 RMSE for hour‐ahead load forecast. The experimental results demonstrate that the proposed model outperforms stacked CNN‐LSTM models, particularly in forecasting hour‐ and day‐ahead loads. Moreover, a comparative analysis with previous studies reveals superior performance in reducing the error gap between predicted and actual values.

Deep learning‐based robust hybrid approaches for brain tumor classification in magnetic resonance images

AbstractThe classification of brain images is an immensely challenging task and one of the most valuable and frequently employed procedures in the field of medical diagnostics. Deep Learning (DL), which falls under the umbrella of artificial intelligence, has introduced novel techniques for automated analysis of medical images. The objective of this study was to develop two hybrid DL models for the segmentation and classification of brain magnetic resonance imaging (MRI) data. The first hybrid model combines fully convolutional networks (FCNs) and residual networks (ResNets) for both segmentation and classification purposes. The second model is a hybrid of SegNet for segmentation and MobileNet for classification. Rest assured, it will provide you with a dependable and promising performance. The analysis was conducted on a labeled dataset comprising images of glioma, meningioma, pituitary, and no‐tumor cases. Python was utilized to implement the aforementioned hybrid models. The proposed models achieved remarkable accuracies of 93.9% and 91.3%, respectively, when evaluated on a brain tumor MRI dataset. Additionally, a comprehensive evaluation of the proposed models was conducted, comparing them with other existing hybrid models in terms of metrics such as the dice score, Jaccard index, positive predictive value (PPV), false predictive value (FPV), testing time, precision, recall, specificity, and F1 score. The results demonstrated that the proposed DL technique can significantly assist doctors and radiologists in the early detection of brain tumor cells.

A Review on Neural Network Based Models for Short Term Solar Irradiance Forecasting

The accuracy of solar energy forecasting is critical for power system planning, management, and operation in the global electric energy grid. Therefore, it is crucial to ensure a constant and sustainable power supply to consumers. However, existing statistical and machine learning algorithms are not reliable for forecasting due to the sporadic nature of solar energy data. Several factors influence the performance of solar irradiance, such as forecasting horizon, weather classification, and performance evaluation metrics. Therefore, we provide a review paper on deep learning-based solar irradiance forecasting models. These models include Long Short-Term Memory (LTSM), Gated Recurrent Unit (GRU), Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), Generative Adversarial Networks (GAN), Attention Mechanism (AM), and other existing hybrid models. Based on our analysis, deep learning models perform better than conventional models in solar forecasting applications, especially in combination with some techniques that enhance the extraction of features. Furthermore, the use of data augmentation techniques to improve deep learning performance is useful, especially for deep networks. Thus, this paper is expected to provide a baseline analysis for future researchers to select the most appropriate approaches for photovoltaic power forecasting, wind power forecasting, and electricity consumption forecasting in the medium term and long term.

HPnet: Hybrid Parallel Network for Human Pose Estimation.

Hybrid models which combine the convolution and transformer model achieve impressive performance on human pose estimation. However, the existing hybrid models on human pose estimation, which typically stack self-attention modules after convolution, are prone to mutual conflict. The mutual conflict enforces one type of module to dominate over these hybrid sequential models. Consequently, the performance of higher-precision keypoints localization is not consistent with overall performance. To alleviate this mutual conflict, we developed a hybrid parallel network by parallelizing the self-attention modules and the convolution modules, which conduce to leverage the complementary capabilities effectively. The parallel network ensures that the self-attention branch tends to model the long-range dependency to enhance the semantic representation, whereas the local sensitivity of the convolution branch contributes to high-precision localization simultaneously. To further mitigate the conflict, we proposed a cross-branches attention module to gate the features generated by both branches along the channel dimension. The hybrid parallel network achieves 75.6% and 75.4%AP on COCO validation and test-dev sets and achieves consistent performance on both higher-precision localization and overall performance. The experiments show that our hybrid parallel network is on par with the state-of-the-art human pose estimation models.

Hybrid Optimized GRU-ECNN Models for Gait Recognition with Wearable IOT Devices.

With the advent of the Internet of Things (IoT), human-assistive technologies in healthcare services have reached the peak of their application in terms of diagnosis and treatment process. These devices must be aware of human movements to provide better aid in clinical applications as well as the user's daily activities. In this context, real-time gait analysis remains to be key catalyst for developing intelligent assistive devices. In addition to machine and deep learning algorithms, gait recognition systems have significantly improved in terms of high accuracy recognition. However, most of the existing models are focused on improving gait recognition while ignoring the computational overhead that affects the accuracy of detection and even remains unsuitable for real-time implementation. In this research paper, we proposed a hybrid gated recurrent unit (GRU) based on BAT-inspired extreme convolutional networks (BAT-ECN) for the effective recognition of human activities using gait data. The gait data are collected by implanting the wearable Internet of Things (WIoT) devices invasively. Then, a novel GRU and ECN networks are employed to extract the spatio-temporal features which are then used for classification to realize gait recognition. Extensive and comprehensive experimentations have been carried out to evaluate the proposed model using real-time datasets and also other benchmarks such as whuGait and OU-ISIR datasets. To prove the excellence of the proposed learning model, we have compared the model's performance with the other existing hybrid models. Results demonstrate that the proposed model has outperformed the other learning models in terms of high gait classification and less computational overhead.

Mean-field update in the JAM microscopic transport model: Mean-field effects on collective flow in high-energy heavy-ion collisions atsNN=2–20 GeV energies

The beam energy dependence of the directed flow is a sensitive probe for the properties of strongly interacting matter. Hybrid models that simulate dense (core) and dilute (corona) parts of the system by combining the fluid dynamics and hadronic cascade model describe well the bulk observables, strangeness productions, and radial and elliptic flows in high-energy heavy-ion collisions in the high baryon density region. However, the beam energy dependence of the directed flow cannot be described in existing hybrid models. We focus on improving the corona part, i.e., the nonequilibrium evolution part of the system, by introducing the mean-field potentials into a hadronic cascade model. For this purpose, we consider different implementations of momentum-dependent hadronic mean fields in the relativistic quantum molecular dynamics (RQMD) framework. First, Lorentz scalar implementation of a Skyrme type potential is examined. Then, full implementation of the Skyrme type potential as a Lorentz vector in the RQMD approach is proposed. We find that scalar implementation of the Skyrme force is too weak to generate repulsion explaining observed data of sideward flows at $\sqrt{{s}_{NN}}<10$ GeV, while vector implementation gives collective flows compatible with the data for a wide range of beam energies $2.7<\sqrt{{s}_{NN}}<20$ GeV. We show that our approach reproduces the negative proton directed flow at $\sqrt{{s}_{NN}}>10$ GeV discovered by experiments. We discuss the dynamical generation mechanisms of the directed flow within a conventional hadronic mean field. A positive slope of proton directed flow is generated predominantly during compression stages of heavy-ion collisions by the strong repulsive interaction due to high baryon densities. In contrast, at the expansion stages of the collision, the negative directed flow is generated more strongly than the positive one by the tilted expansion and shadowing by the spectator matter. At lower collision energies $\sqrt{{s}_{NN}}<10$ GeV, the positive flow wins against the negative flow because of a long compression time. On the other hand, at higher energies $\sqrt{{s}_{NN}}>10$ GeV, negative flow wins because of shorter compression time and longer expansion time. A transition beam energy from positive to negative flow is highly sensitive to the strength of the interaction.

A Hybrid Prediction Model Integrating GARCH Models With a Distribution Manipulation Strategy Based on LSTM Networks for Stock Market Volatility

Accurate prediction of volatility is one of the most important tasks in financial decision making. Recently, the hybrid models integrating artificial neural networks with GARCH-type models have been developed, and performance gains from the models have been found to be outstanding. However, there have been few studies of hybrid models considering the nature of the distribution of financial data. Distribution of volatility time-series is highly concentrated near zero, and such aspect can cause low prediction performance on the whole domain of probability density function because weights in the networks can be trained to obtain accurate prediction only for the high frequency region, that is, near zero. To overcome the challenge, we propose a new hybrid model with GARCH-type models based on a novel non-linear filtering method to mitigate concentration property of volatility. For the filtering, we utilize root-type functions that transform extremely left-biased and pointed distribution of original volatility to a volume-upped (VU) distribution shifted to the right. Long short-term memory (LSTM) is employed as the basic implementation model, and the realized volatility of S&P 500 is predicted using the proposed models. It is found that the proposed hybrid model (VU-GARCH-LSTM) obtains 21.03% performance gain with respect to the root mean square error (RMSE) against the mean performances of the existing hybrid models integrating LSTM with GARCH-type models. Furthermore, the proposed model improves prediction performance in the right domain region of label probability density by making the prediction distribution comparable to the label distribution.

Forecasting hourly PM[formula omitted] based on deep temporal convolutional neural network and decomposition method

For hourly PM2.5 concentration prediction, accurately capturing the data patterns of external factors that affect PM2.5 concentration changes, and constructing a forecasting model is one of efficient means to improve forecasting accuracy. In this study, a novel hybrid forecasting model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and deep temporal convolutional neural network (DeepTCN) is developed to predict PM2.5 concentration, by modeling the data patterns of historical pollutant concentrations data, meteorological data, and discrete time variables’ data. Taking PM2.5 concentration of Beijing as the sample, experimental results showed that the forecasting accuracy of the proposed CEEMDAN-DeepTCN model is verified to be the highest when compared with the statistics-based models, traditional machine learning models, the popular deep learning models and several existing hybrid models. The new model has improved the capability to model the PM2.5-related factor data patterns, and can be used as a promising tool for forecasting PM2.5 concentrations.

A Hybrid Approach of Bayesian Structural Time Series With LSTM to Identify the Influence of News Sentiment on Short-Term Forecasting of Stock Price

In the financial sector, the stock market and its trends are highly volatile in nature. Recent studies have shown that news articles and social media analysis can have an immense impact on investors’ opinion toward financial markets. Thus, the purpose of this study is to explore the relationship between news sentiment and stock market movement using information from different news agencies, business magazines, and financial portals. This study offers an application of the Bayesian structural time (BST) series model that is more transparent and facilitates better handling of uncertainty than the autoregressive integrated moving average (ARIMA) model and the vector autoregression (VAR) method by using prior information about the structure of the model. One of the main pitfalls of this model is the presumption of linearity. The long short-term memory (LSTM) model is a nonlinear model that can capture various nonlinear structures present in the data set. We propose a hybrid model, which combines the LSTM model with the BST model along with the regression component that captures information from different news sources to identify market predictors. The proposed model detects unusual behavior or anomalous pattern of the stock price movement, which makes our model superior compared to the traditional methods. Our new hybrid model accumulates error with lower rates (3.5%) and shows a remarkable performance over some of the other existing hybrid models, such as AR-MLP, ARIMA-LSTM, and VAR-LSTM model.

Hybrid deep neural model for hourly solar irradiance forecasting

Owing to integrating photovoltaic solar systems into power networks, accurate prediction of solar irradiance plays an increasingly significant role in electric energy planning and management. However, the existing hybrid models ignore the influence of other factors except for the irradiance time series and adopt a single branch independent network structure, which may lead to decrease prediction accuracy. In this paper, a novel multivariate hybrid deep neural model named WPD–CNN–LSTM-MLP for 1-h-ahead solar irradiance forecasting is proposed. The novel WPD–CNN–LSTM-MLP model is based on a sophisticated multi-branch hybrid structure with multi-variable inputs, which the multi-branch hybrid structure combines wavelet packet decomposition (WPD), convolutional neural network (CNN), long short-term memory (LSTM) networks, and multi-layer perceptron network (MLP), and the multi-variable inputs include hourly solar irradiance and three climate variables, namely: temperature, relative humidity, and wind speed and their combination. The new model extracts the inherent characteristics of multi-layer inputs sufficiently, overcomes the shortcomings of traditional models, and achieves more accurate forecasting results. The performance of the model is verified by actual data from Denver, Clark, and Folsom, the United States. Comparative studies of traditional individual back propagation neural network, support vector machine, recurrent neural network, LSTM, the climatology–persistence reference forecasts method and the proposed LSTM-MLP model, CNN-LSTM-MLP model, and WPD–CNN–LSTM model reveal that the proposed WPD–CNN–LSTM-MLP deep learning model has better prediction accuracy in hourly irradiance forecasting.

Ensem_SLDR: Classification of Cybercrime using Ensemble Learning Technique

With the advancement of technology, cybercrimes are surging at an alarming rate as miscreants pour into the world's modern reliance on the virtual platform. Due to the accumulation of an enormous quantity of cybercrime data, there is huge potential to analyze and segregate the data with the help of Machine Learning. The focus of this research is to construct a model, Ensem_SLDR which can predict the relevant sections of IT Act 2000 from the compliant text/subjects with the aid of Natural Language Processing, Machine Learning, and Ensemble Learning methods. The objective of this paper is to implement a robust technique to categorize cybercrime into two sections, 66 and 67 of IT Act 2000 with high precision using ensemble learning technique. In the proposed methodology, Bag of Words approach is applied for performing feature engineering where these features are given as input to the hybrid model Ensem_SLDR. The proposed model is implemented with the help of model stacking, comprising Support Vector Machine (SVM), Logistic Regression, Decision Tree, and Random Forest and gave better performance by having 96.55 % accuracy, which is higher and reliable than the past models implemented using a single learning algorithm and some of the existing hybrid models. Ensemble learning techniques enhance model performance and robustness. This research is beneficial for cyber-crime cells in India, which have a repository of detailed information on cybercrime including complaints and investigations. Hence, there is a need for model and automation systems empowered by artificial intelligence technologies for the analysis of cybercrime and their classification of its sections.

An inquiry into the structure and dynamics of crude oil price using the fast iterative filtering algorithm

Abstract The identification of the temporal scales related to market activities is crucial for understanding the dynamics of international crude oil prices. Standard analysis techniques fail in producing consistently good results due to the non-linear behaviour of the oil market. In this paper we propose an innovative approach based on the concurring application of a new non-linear data analysis method, Fast Iterative Filtering (FIF), and a multi-scale statistical analysis (Standardized Mean Test). This approach proves to be able to separate automatically crude oil price data into three components: a long term trend, an intermediate or middle period behaviour, and a transitory or short-run behaviour. The economic meaning of each component is clearly identified as: high frequency variations, caused by normal supply-demand disequilibrium; medium term fluctuations, driven by geopolitical, financial, and technological shocks; a low frequency trend reflecting the global business cycle. All these results make the proposed approach a more performing tool for analysing oil price data structure and dynamics. Such a method, if coupled with different prediction techniques (e.g., ARIMA, ARCH, etc., or ANN, SVM, etc.), can potentially show higher performance than existing hybrid models in forecasting crude oil prices.

Parallel hybridization of series (PHOS) models for time series forecasting

Literature indicates that many efforts have been conducted toward the development of forecasting models with a high degree of accuracy. Combining different models is known as a powerful alternative to access more reliable and more accurate results than single models. Given the great importance of hybridization theory, various hybrid models have been proposed in the literature of time series forecasting. Series hybrid approaches are one of the most well study and the most widely used hybridization models, in which components are sequentially applied. However, according to the modeling essence of this hybrid structure, the performance of the series hybrid models is directly dependent on the order of using components and modeling sequence. Besides, selecting the best modeling order that can yield the best performance in all situations is a problematic theoretical as well as practical task. Thus, the main purpose of this paper is to eliminate the drawback of series models, regarding modeling order selection using a parallel hybridization schema, which is addressed for the first time. The core principle of the proposed parallel hybridization of series (PHOS) models is to improve the series hybrid model’s forecasting accuracy by integrating two hybrid structures in contrast to existing hybrid models, which emphasize only the combination of individual models. The proposed model decomposes the original time series into two linear and nonlinear parts and uses the autoregressive integrated moving average (ARIMA) and multilayer perceptron neural network (MLP) models to model underlying patterns, incorporating two series models including ARIMA–MLP and MLP–ARIMA. Finally, the series models are integrated as components of the parallel hybridization scheme. Moreover, an ordinary least square algorithm is developed to determine the optimal weights of these two components. Three benchmark data sets, including the closing of the DAX index, the closing of the Nikkei 225 index (N225), and the opening of the Dow Jones Industrial Average Index, are used for empirical analysis and verifying the effectiveness of the PHOS model. The empirical analysis indicates that the PHOS model can improve the forecasting performance of both series ARIMA–MLP and MLP–ARIMA models as well as individual models and some parallel hybrid models.