Hybrid Model Research Articles

Solar irradiation forecast enhancement using clustering based CNN-BiLSTM-attention hybrid architecture with PSO

Accurate solar irradiation forecasting is essential for optimising solar energy use. This paper presents a novel forecasting approach: the ‘Clustering-based CNN-BiLSTM-Attention Hybrid Architecture with PSO’. It combines clustering, attention mechanisms, Convolutional Neural Networks (CNN), Bidirectional Long-Short Term Memory (BiLSTM) networks, and Particle Swarm Optimisation (PSO) into a unified framework. Clustering categorises days into groups, improving predictive capabilities. The CNN-BiLSTM model captures spatial and temporal features, identifying complex patterns. PSO optimises the hybrid model’s hyperparameters, while an attention mechanism assigns probability weights to relevant information, enhancing performance. By leveraging spatial and temporal patterns in solar data, the proposed model improves forecasting accuracy in univariate and multivariate analyses with multi-step predictions. Extensive tests on real-world datasets from various locations show the model’s effectiveness. For example, with NASA power data, the model achieves a Mean Absolute Error (MAE) of 24.028 W/m2, Root Mean Square Error (RMSE) of 43.025 W/m2, and an R 2 score of 0.984 for 1-hour ahead forecasting. The results show significant improvements over conventional methods.

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.

Rapid Classification of Milk Using a Cost-Effective Near Infrared Spectroscopy Device and Variable Cluster-Support Vector Machine (VC-SVM) Hybrid Models.

Removing fat from whole milk and adding water to milk to increase its volume are among the most common food fraud practices that alter the characteristics of milk. Usually, deviations from the expected fat content can indicate adulteration. Infrared spectroscopy is a commonly used technique for distinguishing pure milk from adulterated milk, even when it comes from different animal species. More recently, portable spectrometers have enabled in situ analysis with analytical performance comparable to that of benchtop instruments. Partial Least Square (PLS) analysis is the most popular tool for developing calibration models, although the increasing availability of portable near infrared spectroscopy (NIRS) has led to the use of alternative supervised techniques, including support vector machine (SVM). The aim of this study was to develop and implement a method based on the combination of a compact and low-cost Fourier Transform near infrared (FT-NIR) spectrometer and variable cluster-support vector machine (VC-SVM) hybrid model for the rapid classification of milk in accordance with EU Regulation EC No. 1308/2013 without any pre-treatment. The results obtained from the external validation of the VC-SVM hybrid model showed a perfect classification capacity (100% sensitivity, 100% specificity, MCC = 1) for the radial basis function (RBF) kernel when used to classify whole vs. not-whole and skimmed vs. not-skimmed milk samples. A strong classification capacity (94.4% sensitivity, 100% specificity, MCC = 0.95) was also achieved in discriminating semi-skimmed vs. not-semi-skimmed milk samples. This approach provides the dairy industry with a practical, simple and efficient solution to quickly identify skimmed, semi-skimmed and whole milk and detect potential fraud.

Validation of MEWS, NEWS, NEWS-2 and qSOFA for different infection foci at the emergency department, the acutelines cohort.

Sepsis is a leading cause of morbidity and mortality globally. The lack of specific prognostic markers necessitates tools for early risk identification in patients with suspected infections in emergency department (ED). This study evaluates the prognostic accuracy of various Early Warning Scores (EWS)-MEWS, NEWS, NEWS-2, and qSOFA-for in-hospital mortality, 30-day mortality, and ICU admission, considering the site of infection. A retrospective analysis was conducted using data from the Acutelines cohort, which included data collected from patients admitted to the University Medical Centre Groningen ED between September 2020 and July 2023. Patients were included if they had an ICD-10 code for infection. EWS were calculated using clinical data within 8h post-admission. Predictive performance was assessed using AUC-ROC, calibration by the Hosmer-Lemeshow test and calibration curves, and operative characteristics like sensitivity and specificity. A total of 1661 patients were analyzed, with infections distributed as follows: lower respiratory tract (32.9%), urinary tract (30.7%), abdominal (12.5%), skin and soft tissue (9.5%), and others (8.2%). The overall in-hospital mortality was 6.7%, and ICU admission was 7.1%. The highest AUC-ROC for in-hospital mortality prediction was observed with NEWS and NEWS-2 in abdominal infections (0.86), while the lowest was for qSOFA in skin and soft tissue infections (0.57). Predictive performance varied by infection site. The study highlights the variability in EWS performance based on infection site, emphasizing the need to consider the source of infection in EWS development for sepsis prognosis. Tailored or hybrid models may enhance predictive accuracy, balancing simplicity and specificity.

Forecasting Construction Cost Indices: Methods, Trends, and Influential Factors

The Construction Cost Index (CCI) is an important tool that is widely used in construction cost management to monitor cost fluctuations over time. Numerous studies have been conducted on CCI development and forecasting models, including time series, artificial intelligence, machine learning, and hybrid models. Therefore, this study seeks to reveal the complexity of CCI forecasting and identify the leading indicators, trends, and techniques for CCI prediction. A bibliometric analysis was conducted to explore the landscape in the CCI literature, focusing on co-occurrence, co-authorship, and citation analysis. These analyses revealed the frequent keywords, the most cited authors and documents, and the most productive countries. The research topics and clusters in the CCI forecasting process were presented, and directions for future research were suggested to enhance the prediction models. A case study was conducted to demonstrate the practical application of a forecasting model to validate its prediction reliability. Furthermore, this study emphasizes the need to integrate advanced technologies and sustainable practices into future CCI forecasting models. The findings are useful in enhancing the knowledge of CCI prediction techniques and serve as a base for future research in construction cost estimation.

Optimizing H2 production from biomass: A machine learning-enhanced model of supercritical water gasification dynamics

Supercritical water gasification (SCWG) is recognized as an efficient technology for biomass conversion, demonstrating substantial potential in the sustainable energy sector. This paper focuses on the H2 production by SCWG of biomass. The objective is to develop an accurate gasification kinetic model that can facilitate the optimization of industrial reactor designs. A series of SCWG experiments is conducted in a batch reactor system under temperature of 500–600 °C and residence time of 1–20 min. Based on the experimental results, a hybrid-driven model for SCWG reaction is established. Firstly, experimental data is utilized to delineate SCWG reaction mechanistic model and forecast gas yields with an acceptable error margin. Subsequently, a Wasserstein Generative Adversarial Network Gradient Boosting Regression Grid Search (WGAN-GBR-GRID) model is applied to acquire knowledge of the predictive errors from the mechanistic model and to develop a hybrid model. The hybrid-driven model significantly enhances the average relative prediction error from 15.56 % to 0.02 % when compared to the mechanistic model. This result underscores the potential of the hybrid model in optimizing SCWG technology and the Shapley Additive exPlanations (SHAP) values in feature analysis shows the possible shortcomings of mechanistic model, thereby providing a new perspective for SCWG reaction dynamics modeling.

Sustainable separation of molybdenum from mixed mineral acids generated as semiconductor industry waste streams using tributyl phosphate (TBP) by effects of hybrid machine learning models

This study explores the separation and optimization of molybdenum (Mo) from mixed mineral acids derived from semiconductor industry waste streams with tributyl phosphate (TBP) by implementing machine learning (ML) models. Considerable experimental tests were performed to evaluate the impact of various operational variables on the effectiveness of Mo extraction and stripping. The support vector regression (SVR) paired with harmony search algorithm (HSA), genetic algorithm (GA), and shuffled frog leaping algorithm (SFLA) were employed for enhancement in the separation process and structural optimization. The SVR-SFLA model yielded the most meticulous predictions, identifying optimal extraction conditions with a TBP concentration, mixing time, temperature, and O/A ratio of 50%, 30 min, 25 °C, and 1, respectively, achieving 77.8% efficiency. The derived results from the SVR-SFLA model, in tandem with the McCabe-Theil diagram, indicated a four-stage counter-current extraction process required to achieve a yield exceeding 99%. For the stripping process, the hybrid model indicated optimal conditions with 3 M NH4OH and an A/O ratio of 0.5 at 50 °C for 20 min, requiring two counter-current stages for nearly complete stripping. Feature importance analysis using a random forest algorithm (RFA) highlighted the NH4OH concentration and phase ratio as the most significant factors, contributing 40.3% and 29.1%, respectively, to the stripping from the loaded TBP phase. The final product, obtained after crystallization and thermal decomposition of the strip solutions, was characterized by X-ray diffraction (XRD), thermogravimetric analysis (TGA), scanning electron microscopy (SEM), and energy-dispersive X-ray spectroscopy (EDS), revealing 99.74% purity for molybdenum trioxide.

Contextual embedded text summarizer system: A hybrid approach

AbstractSelecting crucial sentences from a document is a pivotal task in automatic text summarization systems. Abstractive summarization involves rephrasing key content through advanced natural language techniques, generating a concise, new text conveying critical information. Conversely, extractive summarization reproduces important material from the original text. In the proposed method, a hybrid ensemble approach combines BERTsum for extractive summarization and Longformer2Roberta for abstractive summarization for generating a contextual semantic rich summary for a huge collection of text. These proposed system‐generated summaries were evaluated against reference summaries using the ROUGE package at three rouge levels (Rouge‐1, Rouge‐2, and Rouge‐L). The Proposed contextual embedded hybrid text summarization model has shown significant performance improvement in multiple levels of Rouge score and word mover distance (WMD) of generated summary with a reference summary. The proposed hybrid model demonstrates superior performance over existing state‐of‐the‐art summarizing models on three distinct datasets CNN dataset, WikiSum, and Gigaword dataset. The proposed hybrid model as a text summarizer involves leveraging its capabilities to process longer sequences of text with domain‐specific contextual summaries. This transformers‐based text summarization model has great potential in developing expert systems in various research domains such as health decision support systems, the education sector, customer support chatbots, financial analysis investment recommendations, and financial assistance.

Unifying Principles of Generalization: Past, Present, and Future.

Generalization, defined as applying limited experiences to novel situations, represents a cornerstone of human intelligence. Our review traces the evolution and continuity of psychological theories of generalization, from its origins in concept learning (categorizing stimuli) and function learning (learning continuous input-output relationships) to domains such as reinforcement learning and latent structure learning. Historically, there have been fierce debates between approaches based on rule-based mechanisms, which rely on explicit hypotheses about environmental structure, and approaches based on similarity-based mechanisms, which leverage comparisons to prior instances. Each approach has unique advantages: Rules support rapid knowledge transfer, while similarity is computationally simple and flexible. Today, these debates have culminated in the development of hybrid models grounded in Bayesian principles, effectively marrying the precision of rules with the flexibility of similarity. The ongoing success of hybrid models not only bridges past dichotomies but also underscores the importance of integrating both rules and similarity for a comprehensive understanding of human generalization.

Trade Policy Space, Aid for Trade and, Intra-African and External African Manufactured Exports

Boosting intra-African manufactured exports is a critical objective of African leaders. The present analysis examines whether trade policy space and Aid for Trade (AfT) flows can contribute to achieving this objective. The analysis covers an unbalanced sample of 36 African countries over the period from 2004 to 2020, and uses estimators that allow obtaining the short-term (i.e., within-country effect) and long-term (i.e., between-country effect) effects of each regressor. The estimators are the combination of the feasible generalized least squares estimator on the one hand, and the Seemingly Unrelated Regression on the other hand, in the context of a hybrid model. The findings indicate that both trade policy space and AfT flows can help promote - including in a complementary way - African manufactured exports, especially intra-African manufactured exports. In this regard, trade policy space and AfT flows are instrumental in meeting African leaders’ objectives of promoting intra-African trade. The implications of the findings are discussed.

Advanced facial recognition with LBP-URIGL hybrid descriptors

AbstractFacial recognition technology is transformative in security and human-machine interaction, reshaping societal interactions. Robust descriptors, essential for high precision in machine learning tasks like recognition and recall, are integral to this transformation. This paper presents a hybrid model enhancing local binary pattern descriptors for facial representation. By integrating rotation-invariant local binary pattern with uniform rotation-invariant grey-level co-occurrence, employing linear discriminant analysis for feature space optimization, and utilizing an artificial neural network for classification, the model achieves exceptional accuracy rates of 100% for Olivetti Research Laboratory, 99.98% for Maastricht University Computer Vision Test, and 99.17% for Extended Yale B, surpassing traditional methods significantly.

An Improved Hybrid Model Based on Ensemble Features and Regularization Selection for Classification

Feature selection is a pivotal process in machine learning, essential for enhancing model performance by reducing dimensionality, improving generalization, and mitigating overfitting. By eliminating irrelevant or redundant features, simpler and more interpretable models are achieved, which generally perform better. In this study, we introduce an advanced hybrid method combining ensemble feature selection and regularization techniques, designed to optimize model accuracy while significantly reducing the number of features required. Applied to a customer satisfaction dataset, our method was first tested without feature selection, where the model achieved a ROC AUC value of 0.946 on the test set using all 369 features. However, after applying our proposed feature selection method, the model achieved a higher ROC AUC value of 0.954, utilizing only 12 key features and completing the task in approximately 43% less time. These findings demonstrate the effectiveness of our approach in producing a more efficient and superior-performing model.

Pi Class – A Revolutionary Step Forward in Hybrid Class Management System

The COVID-19 pandemic has caused widespread disruptions globally, resulting in a state of health emergency with numerous deaths reported and an overall implementation of quarantine and isolation. Strict lockdowns have been implemented to curb the spread of the virus, requiring social distancing and limiting physical interactions. These measures had far-reaching impacts on all aspects of life, including education. Education was one of the most affected sectors, with difficulty delivering quality education in schools, colleges, and universities. It was hard to provide quality education, a basic need of humanity. In this research paper, we propose an adequate solution to overcome the difficulties of maintaining educational quality during and after the COVID-19 pandemic and its multiple variants. The proposed solution is a hybrid model for an autonomous lecture recording system that facilitates students to attend physical classes and attend lectures virtually. The solution proposed is a cost-effective and convenient way for students to access lectures. The application involves hardware and software components that record and preserve lectures' audio and visual aspects. The system will allow lectures to be delivered directly to the students' devices. The major modules of the project include Python scripting, model training, UI/UX design, and app development.

Estimating the individual stillborn rate from easy-to-collect sow data on farm: an application of the bayesian network model

BackgroundA high number of stillborn piglets has a negative impact on production and animal welfare. It is an important contributor to piglet mortality around farrowing and continues to rise with the increase of prolificacy. The objective of this study was to build a predictive model of the stillborn rate.ResultsThis study was performed on two farrow-to-finish farms and one farrow-to-wean farm located in Brittany, France. At each farm, the number of total born (TB), born alive (BA), stillborn piglets (S), the same data at the previous farrowing (TBn− 1, BAn− 1 and Sn− 1), backfat thickness just before farrowing and at previous weaning and parity rank were recorded in our dataset of 3686 farrowings. Bayesian networks were used as an integrated modelling approach to investigate risk factors associated with stillbirth using BayesiaLab® software. Our results suggest the validity of a hybrid model to predict the percentage of stillborn piglets. Three significant risk factors were identified by the model: parity rank (percentage of total mutual information: MI = 64%), Sn− 1 (MI = 25%) and TBn− 1 (MI = 11%). Additionally, backfat thickness just before farrowing was also identified for sows of parity five or more (MI = 0.4%). In practice, under optimal conditions (i.e., low parity rank, less than 8% of stillborn piglets, and a prolificacy lower than 14 piglets at the previous farrowing), our model predicted a stillborn rate almost halved, from 6.5% (mean risk of our dataset) to 3.5% for a sow at the next farrowing. In contrast, in older sows with a backfat thickness less than 15 mm, more than 15% of stillborn and a prolificacy greater than 18 piglets at the previous farrowing, the risk is multiplied by 2.5 from 6.5 to 15.7%.ConclusionOur results highlight the impact of parity, previous prolificacy and stillborn rate on the probability of stillborn. Moreover, the importance of backfat thickness, especially in old sows, must be considered. This information can help farmers classify and manage sows according to their risk of giving birth to stillborn piglets.

Concrete carbonation depth prediction model based on a gradient-boosting decision tree and different metaheuristic algorithms

Carbonation is a significant factor contributing to the instability of concrete structures. This study proposes two prediction models based on the gradient boosting decision tree (GBDT) to address the challenge of predicting concrete carbonation depth. This study integrates GBDT with two metaheuristic algorithms, particle swarm optimization algorithm (PSO) and sparrow search optimization algorithm (SSA), forming two hybrid models, PSO-GBDT and SSA-GBDT, aimed at enhancing prediction accuracy. Six influencing parameters (FA, t, w/b, B, RH, and CO2) were selected as input features to train and evaluate the hybrid models, with the concrete carbonation depth was used as the output. A database containing 883 groups of cases was established. Finally, three classic models, GBDT, ANN and SVR, were compared against the two hybrid models. To enhance model generalization, all models were subjected to five-fold cross validation. Four evaluation indicators (RMSE, R2, MAE, and VAF) and Taylor diagrams were employed to comprehensively assess these models. The results indicated that the two hybrid models exhibited superior prediction performance in the dataset (training set: R2, VAF>0.98, testing set: R2, VAF>0.96). The SSA-GBDT model achieved the highest prediction performance (RMSE= 2.7008, R2= 0.9639, MAE= 1.7691, VAF= 0.9627). Additionally, the SSA-GBDT model identified exposure time (t) as the feature with the greatest impact. This study demonstrates the applicability of the SSA-GBDT models in predicting concrete carbonation depth, offering a novel approach for improving accuracy in such predictions.

Development of novel computational models based on artificial intelligence technique to predict liquids mixtures separation via vacuum membrane distillation

The fundamental objective of this paper is to use Machine Learning (ML) methods for building models on temperature (T) prediction using input features r and z for a membrane separation process. A hybrid model was developed based on computational fluid dynamics (CFD) to simulate the separation process and integrate the results into machine learning models. The CFD simulations were performed to estimate temperature distribution in a vacuum membrane distillation (VMD) process for separation of liquid mixtures. The evaluated ML models include Support Vector Machine (SVM), Elastic Net Regression (ENR), Extremely Randomized Trees (ERT), and Bayesian Ridge Regression (BRR). Performance was improved using Differential Evolution (DE) for hyper-parameter tuning, and model validation was performed using Monte Carlo Cross-Validation. The results clearly indicated the models’ effectiveness in temperature prediction, with SVM outperforming other models in terms of accuracy. The SVM model had a mean R2 value of 0.9969 and a standard deviation of 0.0001, indicating a strong and consistent fit to the membrane data. Furthermore, it exhibited the lowest mean squared error, mean absolute error, and mean absolute percentage error, signifying superior predictive accuracy and reliability. These outcomes highlight the importance of selecting a suitable model and optimizing hyperparameters to guarantee accurate predictions in ML tasks. It demonstrates that using SVM, optimized with DE improves accuracy and consistency for this specific predictive task in membrane separation context.

Stock Price Prediction Research Based on CNN-LSTM

In recent years, neural network technology has been widely used in the field of stock forecasting, especially in the aspect of LSTM, which has become a research hotspot because of its unique advantages in dealing with time series problems in stock forecasting. By analyzing and summarizing the recent research literature based on LSTM and its extended model, this paper aims to deeply explore the effect and potential limitations of LSTM in capturing the dynamic and nonlinear characteristics of the stock market. By constructing different combination models combining LSTM and CNN, the paper uses normalization to preprocess the split data and realize the generalization prediction of stock price. Compared with the experimental results, a suitable combination model of LSTM and CNN is found. This hybrid model can significantly improve the accuracy and stability of prediction, and also shows the advantages in multi-input data processing. The results of this study not only provide a new technical means for the direction of stock prediction, but also explore a new direction for the further application of deep learning technology in the financial field.

Achieving enhanced diagnostic precision in endometrial lesion analysis through a data enhancement framework.

The aim of this study was to enhance the precision of categorization of endometrial lesions in ultrasound images via a data enhancement framework based on deep learning (DL), through addressing diagnostic accuracy challenges, contributing to future research. Ultrasound image datasets from 734 patients across six hospitals were collected. A data enhancement framework, including image features cleaning and soften label, was devised and validated across multiple DL models, including ResNet50, DenseNet169, DenseNet201, and ViT-B. A hybrid model, integrating convolutional neural network and transformer architectures for optimal performance, to predict lesion types was developed. Implementation of our novel strategies resulted in a substantial enhancement in model accuracy. The ensemble model achieved accuracy and macro-area under the receiver operating characteristic curve values of 0.809 of 0.911, respectively, underscoring the potential for use of DL in endometrial lesion ultrasound image classification. We successfully developed a data enhancement framework to accurately classify endometrial lesions in ultrasound images. Integration of anomaly detection, data cleaning, and soften label strategies enhanced the comprehension of lesion image features by the model, thereby boosting its classification capacity. Our research offers valuable insights for future studies and lays the foundation for creation of more precise diagnostic tools.

A Novel Neural Network Prediction Model for Mineral Content Based on the Data of Elemental Logging and Well Logging

The mineral content of shale plays an important role in the study of reservoir characteristics. Obtaining high-precision mineral content data from a simple and straightforward method is helpful for the study of reservoir properties. Due to the complex and varied elemental combination of minerals and the lithological diversity in different formations, there are limitations in the traditional statistical methods for predicting mineral content. In this study, a multi-source fusion dataset is constructed first using a detailed workflow to process multi-source data from elemental logging and conventional well logging from the Funing shale formations in China. A hybrid neural network model consisting of a back-propagation artificial neural network (BP-ANN) and gated recurrent unit (GRU) structure, with a custom constraint loss function, is developed to predict the mineral contents. The results show that the predictive performance of this hybrid multi-source model performs statistically significantly better than that of the BP-ANN and GRU models using single source data. In addition, the accuracy of the hybrid model is further improved by using the custom constraint loss function. This method provides high-resolution distributions of mineral content compared to the X-ray powder diffraction testing method. It will help enhance the understanding of the formation.

Ejection of Real-Time Malicious Intrusion and Attacks in IoT Empowered Infrastructure

The project recognizes the pervasive threat of computer viruses, malware, and hostile attacks on computer networks, highlighting the critical role of intrusion detection as a proactive defense technology. The project introduces a novel approach based on deep learning to identify and mitigate cybersecurity vulnerabilities and breaches in IoT-driven cyber-physical systems, aiming for enhanced security measures. The project's objective is to elevate intrusion detection beyond the limitations of traditional systems by addressing issues like accuracy, detection effectiveness, and reducing false positives. This emphasizes the advancement and innovation in cybersecurity. To achieve the project's goals, the method employs a generative adversarial network, a cutting-edge deep learning technique. Additionally, it distinguishes itself by contrasting unsupervised and deep learning-based discriminative approaches, showcasing a comprehensive and effective approach to cybersecurity. In our project, we successfully implemented an ensemble method to boost predictive accuracy by integrating multiple individual models. Particularly noteworthy is the inclusion of a hybrid architecture, combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), denoted as CNN+LSTM. This hybrid model achieved an impressive accuracy of 99% when applied to the KDD-Cup dataset, underscoring the efficacy of our ensemble technique for intrusion detection in IoT- based cybersecurity infrastructures.