Efficient Prediction Research Articles

Online variational Gaussian process for time series data

Gaussian processes (GPs) are a powerful and popular framework for addressing machine learning problems, particularly for time-dependent data such as that generated by the Internet of Things (IoT). GPs offer a compelling choice for constructing real-valued nonlinear models due to their inherent flexibility and ability to quantify uncertainty. However, traditional GP methods are often hindered by cubic computational complexity, making them impractical for the massive and potentially unbounded datasets commonly encountered in IoT applications. To address this issue, researchers have developed various sparse approximation methods that significantly reduce the computational burden of GPs. Among these, pseudo-point approximations have proven to be highly influential, leveraging a subset of the training data to represent the entire observation space. The variational sparse GP is a state-of-the-art approach that approximates the posterior distribution of GP models, enabling faster and more efficient predictions in real-time data series. However, integrating variational inference into the GP framework for sequentially arriving data remains a significant challenge, particularly when dealing with time series data where the underlying data distribution evolves over time. In this paper, we propose the OnLine Variational Gaussian Process (OLVGP) algorithm, which introduces a novel approach for dynamically managing the number of inducing points based on the concept of eigenfunction inducing features. Unlike traditional methods that rely on a fixed number of inducing points, OLVGP adaptively adjusts the number of inducing points as new data arrives and optimizes them from the model, ensuring that the model remains computationally efficient while maintaining high predictive accuracy. Our method capitalizes on the sophisticated design of the online variational inference framework, ensuring a technically robust derivation and implementation. We validate the effectiveness and efficiency of our approach through both synthetic examples and real-world experiments. The results demonstrate that OLVGP not only substantially reduces computational costs compared to traditional sparse GP methods but also dynamically adapts to the evolving data, delivering improved performance in time series prediction.

Spatio-Temporal Photovoltaic Power Prediction with Fourier Graph Neural Network

The strong development of distributed energy sources has become one of the most important measures for low-carbon development worldwide. With a significant quantity of photovoltaic (PV) power generation being integrated to the grid, accurate and efficient prediction of PV power generation is an essential guarantee for the security and stability of the electricity grid. Due to the shortage of data from PV stations and the influence of weather, it is difficult to obtain satisfactory performance for accurate PV power prediction. In this regard, we present a PV power forecasting model based on a Fourier graph neural network (FourierGNN). Firstly, the hypervariable graph is constructed by considering the electricity and weather data of neighbouring PV plants as nodes, respectively. The hypervariance graph is then transformed in Fourier space to capture the spatio-temporal dependence among the nodes via the discrete Fourier transform. The multilayer Fourier graph operator (FGO) can be further exploited for spatio-temporal dependence information. Experiments carried out at six photovoltaic plants show that the presented approach enables the optimal performance to be obtained by adequately exploiting the spatio-temporal information.

Prediction of Technical Efficiency of Aman Rice Farms in Satkhira District of Bangladesh: A Stochastic Frontier Approach

This paper aimed to assess the technical efficiency (TE) of aman rice farms and analyzed the major factors affecting inefficiency of aman rice farms. In doing so, a multistage random sampling method was used to collect primary data from a survey of 455 rice farmers between May and June in 2023 in Kaligonj sub-district of Satkhira district. Stochastic frontier approach (SFA) was employed to predict the efficiency of aman rice farms while the Tobit model was used to identify the factors that influence technical inefficiency. The findings of TE ranged from 0.98 to 0.51 with an average score of 0.8469. Technical inefficiency is largely affected by years of schooling, household size, salinity of land, agriculture policy and access to credit variables. The policy implications of this finding is that the government might provide the agricultural extension network so that the extension agent can better engage with targeted farmers rather than just recommendations. International Journal of Statistical Sciences, Vol. 24(2), November, 2024, pp 97-108

Balance Strategy Prediction Model Based on Power Load Data Mining

To meet the purpose of a multi-objective solution, a scheme is introduced into the optimal strategy-intensive training process. It supports a multi-task-driven computing model and has good reasoning accuracy, which makes the hydropower management system have efficient collaborative strategy prediction ability. Aiming at the trade-off problem between the cost-benefit and energy load of the hydropower control system, based on the neural network model to improve the stacked sparse denoising auto encoder second-order cone programming (SSDAE-SOCP) algorithm, a low-level backtracking depth uncertainty optimization scheduling model is proposed to obtain the optimal scheduling strategy. It intends to improve the poor accuracy of the global optimal results caused by the lack of priority sampling in the traditional strategy. The feature space without boundary conditions is set to solve the optimal solution for global/local organizations. Further, the flexibility is transferred according to the single-core function of task decomposition for improving the calculation accuracy of the whole solution data and the dynamic double-mutation balance. Simulation results have shown that the proposed algorithm enhances the training quality and performance by 9.5% and 15.2% compared with the traditional MOPSO and MOIMPA algorithms. Gradient descent and convergence speed, as well as the stability and security of intensive training, are better than the comparison methods. The training features verify the stability of the balanced prediction model, showing its importance in enhancing the anti-noise ability of the matrix. The research results can further enhance the multiple dispatching and command capabilities of the hydropower projects, providing technical support for the sustainable development of maximizing the benefits for the systems.

A Lightweight Transformer-Based Spatiotemporal Analysis Prediction Algorithm for High-Dimensional Meteorological Data

High-dimensional meteorological data offer a comprehensive overview of meteorological conditions. Nevertheless, predicting regional high-dimensional meteorological data poses challenges due to the vast scale and rapid changes. Apart from slow conventional numerical weather prediction methods, recently developed deep learning methods often fail to fully integrate spatial information of the high-dimensional data and require a significant amount of computational resources. This paper presents the spatiotemporal analysis fitting prediction algorithm (SA-Fit), an approximation algorithm for regional high-dimensional meteorological data prediction. SA-Fit proposes two key designs to achieve efficient prediction of the high-dimensional data. SA-Fit introduces a lightweight Transformer-based spatiotemporal analysis network to encode spatiotemporal information, which can integrate the interaction information between different coordinates in the data. Furthermore, SA-Fit introduces explicit functions with a lasso penalty to fit variations in high-dimensional meteorological data, achieving the prediction of a large amount of data with minimal prediction values. We performed experiments using the ERA5 dataset from the Shanghai and Xi’an regions. The experimental results show that SA-Fit is comparable to other advanced deep learning prediction methods in overall prediction performance. SA-Fit shortens training time and significantly reduces model parameters while using the Transformer structure to ensure prediction accuracy.

Highly accurate, efficient, and fabrication tolerance-aware nanostructure prediction for high-performance optoelectronic devices

Despite extensive efforts to predict optimal nanostructures for enhancing optical devices, a more accurate, efficient, and practical method for nanostructure optimisation is required. In particular, fabrication tolerance is a promising avenue for significantly improving manufacturing efficiency; however, research in this area is limited. In this study, we introduce a practical approach for enhancing the performance of optoelectronic devices using an artificial intelligence (AI)-based nanostructure optimisation strategy. We optimised a support vector regression (SVR) model to capture the complex and nonlinear relationships between the transmittance and nanograting structure variables with the goal of improving optoelectronic devices. Our versatile model accurately predicted the continuous transmittance data with high precision (R2 = 0.995) using only 216 training data points. It can also make predictions under untrained conditions, thereby enabling the creation of a transmittance nanostructure contour map (R2 = 0.949). This method facilitates the design of nanostructures tailored to specific optical properties and provides valuable insights into fabrication tolerance. Through experimental validation, we identified an optimal nanograting structure with the highest transmittance in the visible-light spectrum. When integrated into optoelectronic devices such as organic light-emitting diodes (OLEDs) and organic solar cells (OSCs), their performance is significantly improved by increasing the light transmittance. Specifically, devices using the fabricated nanograting film exhibited a 17% improvement in external quantum efficiency (EQE) for solution-processed organic light-emitting diodes (SP-OLEDs) and a 10.7% improvement in power-conversion efficiency (PCE) for OSCs.

Trajectory prediction based on the dynamic characteristics and coupling relationships among vehicles in highway scenarios

In dynamic and highly interactive traffic scenarios, vehicle trajectory prediction has become a critical and complex problem in vehicle assistance systems due to the uncertainty of traffic participant behaviour. This study proposes a novel vehicle trajectory prediction method called the Dynamic Coupling-based Long and Short-Term Memory Network (DSKM-LSTM). The method innovatively combines a vehicle dynamics model with the dynamic coupling between vehicles by integrating the intrinsic motion laws of the vehicles with the correlation of the motion parameters (position, velocity, and acceleration) between the vehicles via Kalman filtering. Subsequently, this information is embedded into a Long Short-Term Memory (LSTM)-based encoder-decoder framework to encode and decode historical trajectories with the fused information in order to predict future driving trajectories. Additionally, this paper introduces a dynamic loss function that optimizes the generalization capability and iteration time of DSKM-LSTM by adjusting the threshold value in real time and dynamically updating the loss value. This approach effectively addresses the problem of insufficient objectivity and accuracy in existing vehicle trajectory prediction models and provides a theoretical foundation for generating objective and interpretable trajectories in the field of trajectory prediction. Validation results on three publicly available datasets show that DSKM-LSTM achieves efficient and accurate long-term (5-s) trajectory prediction in complex traffic scenarios (e.g., motorways).

Recent advances in machine learning and deep learning-enabled studies on transition metal dichalcogenides

Abstract The machine learning and deep learning (ML/DL) techniques have significantly advanced the understanding and utilization of TMDs by enabling efficient analysis, prediction, and optimization of their properties. ML/DL methods permit rapid screening, optimization and analysis of two-dimensional (2D) material candidates, potentially accelerating the discovery and development of TMDs with desired electronic, optoelectronic, and energy storage properties. This review provides a comprehensive review of machine learning and deep learning (ML/DL) methods to enhance 2D materials research via the optimization of synthesis conditions, interpretation of complex data sets, and the use of generative adversarial networks and variational autoencoders for innovative material design and image processing tasks. Furthermore, it highlights the potential of ML/DL techniques in predicting and tailoring the electronic, optical, and mechanical properties of 2D materials to meet specific application requirements.

A novel nomogram prediction model for postoperative atrial fibrillation in patients undergoing laparotomy

BackgroundPostoperative atrial fibrillation (POAF) is an ordinary complication of surgery, particularly cardiac surgery. It significantly increases in-hospital mortality and costs. This study aimed to establish a nomogram prediction model for POAF in patients undergoing laparotomy. The model is expected to identify individuals at a high risk of POAF before surgery in clinical practice.MethodsA retrospective observational case–control study involving 230 adult patients (60 patients with POAF, 120 patients in the control group, and 50 patients in the validation group) who underwent laparotomy was retrieved from two hospitals. Independent risk variables for POAF were investigated using logistic regression and the least absolute shrinkage and selection operator (LASSO) regression analysis. Subsequently, a nomogram model for POAF was constructed by multivariate logistic regression equations. The prediction model was internally validated by bootstrap method and externally validated with the validation group data. To assess the discriminative ability of the nomogram model, a receiver operating characteristic (ROC) curve was generated and a calibration curve was employed to assess the concentricity between the model’s probability curve and the ideal curve. Subsequently, decision curve analysis (DCA) was performed to assess the clinical effectiveness of the model.ResultsC-reactive protein (CRP), lymphocyte-to-monocyte ratio(LMR), blood urea nitrogen (BUN), and Macruz index were independent risk variables for POAF in patients who underwent laparotomy. A user-friendly and efficient prediction nomogram was visualized using R software. This nomogram exhibited strong discrimination, as evidenced by an area under the ROC curve (AUC) of 0.90 (95% CI 0.8509–0.9488) for the training set, 0.86 (95% CI 0.7142–1) for the test set, and 0.9792 (95% CI 0.9293–1) for the validation group data. The C-index of the bootstrap nomogram model was 0.8998. Furthermore, DCA revealed that this model displayed excellent fit and calibration, as well as positive net benefits.ConclusionsA nomogram prediction model was constructed for POAF in patients who underwent abdominal surgery. The nomogram prediction model is expected to identify individuals at high risk of POAF in clinical practice for prophylactic therapeutic intervention prior to surgery.

Sentiment-electroencephalogram fusion for efficient product review prediction using correlation-based deep learning neural network

<span lang="EN-US">Various techniques have been proposed and implemented in previous work for sentiment analysis prediction. However, achieving satisfactory quality of description and fault prediction remains a challenging task. To overcome these limitations, this study proposes an efficient prediction technique that utilizes sentiment analysis of product reviews and electroencephalogram (EEG) signals using correlation-based deep learning neural network (CDNN). The study employs two types of datasets: EEG signals and Amazon product reviews. During the pre-processing phase, EEG signals undergo normalization, while Amazon product reviews undergo tokenization, stop word removal, and weighting factor application to convert unstructured data into a structured format. Subsequently, the pre-processed EEG signals and reviews are analyzed to extract features like emotion, demographic information, personality traits, and sentiment. These features are then employed in sentiment analysis via an entropy-based deep-learning neural network. The proposed CDNN utilizes the grasshopper optimization algorithm (EGOA) to optimize hyperparameters for each layer. Comparative performance assessment against established methods like convolutional neural network (CNN), <a name="_Hlk167111148"></a>long short-term memory (LSTM), multiclass <a name="_Hlk175651957"></a>support vector machine (M-SVM), and bidirectional encoder representations from transformers (BERT) is conducted, and the results are evaluated. Experimental result reveal that the proposed system outperforms traditional approaches.</span>

Machine learning predictive model to estimate the photo-degradation performance of stannates and hydroxystannates photocatalysts on a variety of waterborne contaminants

In this work, a comprehensive machine learning (ML) methodology was used to predict the degradation efficiency of different stannate and hydroxystannate photocatalysts on a wide range of waterborne pollutants. The structural, atomic features along with molecular fingerprints (MF) were used as descriptors of the crystalline phase of the photocatalysts and the organic compounds, respectively. The encoded features of the photocatalysts and contaminants along with the experimental variables of the degradation process are input to two ML models, named as RF (random forest) and KNN (K nearest neighbor). The RF model has achieved a very good prediction of the photocatalytic degradation efficiency (%) by different photocatalysts over a wide range of organic contaminants. The RF model performance was investigated by applying two different training strategies. The effects of different factors on photocatalytic degradation performance are further evaluated by feature importance analyses. Two illustrative applications on the use of the ML model for optimal photocatalyst selection and for assessing other types of photocatalysts for different environmental applications were provided.

Reliable Prediction of Solar Photovoltaic Power and Module Efficiency using Bayesian Surrogate Assisted Explainable Data-Driven Model

This study proposes a Bayesian surrogate-driven explainable deep neural network model to predict and interpret the module efficiency and maximum output power of three commercially available photovoltaic modules: monocrystalline silicon, polycrystalline silicon, and amorphous silicon during the winter season. In addition, the influence of the photovoltaic material and ambient conditions on the predicted power and module efficiency is investigated. The model inputs include solar irradiance, module material (monocrystalline, polycrystalline, and amorphous silicon), season of the year (months), and time of day (morning to evening). Experiments were conducted on these three modules during the winter using data from Rawalpindi, Pakistan. These data were then fed into the deep neural network model to train and yield predictions. Several preprocessing techniques such as logarithmic transformation, square root, cube root, reciprocal, and exponential transformations are employed to improve the linearity of distributed data. For hyper-parameters optimization, Gaussian process, gradient boost regression trees, and random forest are used. The results show that the optimal deep neural network using random forest surrogate model along with square root and exponential transformation is able to predict the maximum power output and module efficiency of the considered photovoltaic modules for the entire investigated period with a correlation coefficient, R2 = 0.998. The least accurate model (R2=0.991) is a Gaussian process using simple data distribution. These results hold valuable insights for predicting and optimizing the performance of other solar photovoltaic modules in various climates and different seasons of the year.

A hybrid wind power prediction model based on seasonal feature decomposition and enhanced feature extraction

Efficient and accurate wind power prediction is crucial for enhancing the reliability and safety of power system. The data-driven forecasting methods are regarded as an effective solution. However, the inherent randomness and nonlinearity of wind power systems, along with the abundance of redundant information in measurement data, present challenges to forecasting methods. The integration of precise and efficient techniques for data feature decomposition and extraction is essential in conjunction with advanced data-driven forecasting models. Focus on the seasonal variation characteristics of wind energy, a hybrid wind power prediction model based on seasonal feature decomposition and enhanced feature extraction is proposed. The effectiveness and superiority of the proposed method in predictive accuracy are demonstrated through comprehensive multi-model experiment comparisons.

Genetic basis analysis and genome prediction of swimming performance traits in juvenile spotted sea bass (Lateolabrax maculatus)

The swimming performance of fish is crucial for their survival, playing a significant role in enhancing disease resistance and facilitating stress recovery, particularly in aquaculture fish. Understanding the genetic basis of fish swimming performance is essential for its integration as a key trait in selection breeding programs, especially for deeper offshore aquaculture. Spotted sea bass, an economically important aquaculture fish species in China, exhibits euryhaline and eurythermic characteristics and has demonstrated substantial potential for deep-sea aquaculture. Therefore, in our study, the absolute critical swimming speed (a.Ucrit) of juvenile spotted sea bass were assessed, ranging form 24.50 cm s−1 to 65.00 cm s−1, and this range enabled the identification of individuals with superior and inferior swimming abilities within the test population. Based on whole-genome resequencing, genome-wide association studies (GWAS) were conducted for three phenotypes of swimming performance, identifying 25 associated SNPs and 85 candidate genes, indicating that it is a polygenetic trait influenced by multiple biological processes. The heritability estimates for a.Ucrit and relative critical swimming speed (r.Ucrit) were 0.21 ± 0.08 and 0.22 ± 0.08, respectively. Furthermore, the impact of various genomic selection (GS) models and SNP densities on prediction accuracy of swimming performance was evaluated using genomic prediction (GP). The SVM model is recommended for continuous trait prediction of swimming performance, especially when SNP densities ranges between 500 and 50 K, as it provides more accurate, efficient and stable predictions. Our research further enhances the understanding of the genetic basis of fish swimming performance and holds promise for improving productivity in deep-sea aquaculture through genomic selection.

Multi-model fusion method for predicting CO2 concentration in greenhouse tomatoes

With the rapid development of greenhouse agriculture, accurate prediction of environmental parameters such as temperature, humidity, and carbon dioxide concentration is crucial for optimal crop growth. Traditional forecasting models struggle with the nonlinear and complex nature of greenhouse data, leading to challenges in model robustness. This study addresses these issues by proposing a multi-model fusion strategy for predicting CO2 concentration in greenhouse tomatoes. The proposed method integrates wavelet denoising (WT), variational mode decomposition (VMD), and long short-term memory networks (LSTM). This innovative nonlinear ensemble model effectively extracts key time series features and removes noise, while an introduced attention mechanism enhances the model’s focus on essential time steps, improving prediction accuracy. Experimental results demonstrate that the multi-model fusion approach significantly outperforms single models in terms of accuracy and stability, achieving mean absolute error (MAE) and root mean square error (RMSE) of 0.0117 and 0.0194, respectively. The proposed method offers significant advantages for CO2 prediction in greenhouse crops, providing a theoretical basis and technical support for optimizing and controlling greenhouse parameters. This contributes to the advancement of smart agriculture by offering an efficient environmental monitoring and prediction tool. Additionally, the study presents new ideas and technical solutions for addressing similar agricultural environment prediction challenges, optimizing greenhouse environment control strategies, and improving crop production efficiency.

Ensemble stacking classifier model for prediction of diabetes

Diabetes, being a chronic condition, possesses the capacity to instigate a global healthcare catastrophe. This condition can be managed and potentially cured with prompt diagnosis and treatment. Integrating machine learning technology with medical science enables precise prognosis of an individual’s susceptibility to diabetes. The proposed work presents the ensemble stacking classifier model. This efficient and effective diabetes prediction model predicts a patient’s diabetes risk by combining the output of multiple machine-learning techniques into a single model. The performance parameters of four distinct machine learning classification algorithms K-nearest neighbors (KNN), random forest (RF), support vector machine (SVM), and decision tree (DT) are compared in this study with those of the proposed stacked classifier model. The suggested model is developed using ensemble methods, where the previously discussed algorithms are integrated to create the base classifier layer of the stack classifier. The meta-classifier is implemented in the form of the logistic regression (LR) algorithm. Upon evaluating the performance of both the developed model and its algorithms, it is proved that the proposed model attains a testing accuracy of 88.5%, surpassing the accuracy of all baseline classification algorithms. As a result, this work determines that the ensemble stacking classifier model exhibits higher prediction accuracy than the base classifier algorithms. This finding underscores the model’s potential as a viable instrument for predicting diabetes in individuals.

SeaConvNeXt: A Lightweight Two-Branch Network Architecture for Efficient Prediction of Specific IHC Proteins and Antigens on Hematoxylin and Eosin (H&E) Images

SeaConvNeXt: A Lightweight Two-Branch Network Architecture for Efficient Prediction of Specific IHC Proteins and Antigens on Hematoxylin and Eosin (H&E) Images

TPE-xgboost for explainable predictions of concrete compressive strength considering compositions, and mechanical and microstructure properties of testing samples

The use of machine learning (ML) for predicting concrete compressive strength (CCS) has shown promising and accurate results, making it a valuable tool in the field. However, efficient prediction requires not only a robust ML approach but also a comprehensive and well-curated dataset. This study addresses this challenge by investigating an extensive and integrated dataset of (1) concrete compositions (mixture proportions) and (2) testing conditions (mechanical and microstructure properties of concrete testing samples), containing 1525 observations relating to 39 parameters. On algorithms side, this research proposes novel tree-structured parzen estimator based extreme gradient boosting (TPE-xgboost) for accurate and confident CCS predictions. Moreover, SHapley Additive exPlanations (SHAP) analysis was performed to provide a comprehensive understanding of feature importance, dependencies, and interactions. Compared to prior research, this study demonstrates significant improvements in CCS prediction accuracy for separate investigations on concrete compositions (3.77%) and mechanical and microstructure properties (28.57%), while maintaining reasonable accuracy for the integrated dataset despite its complexity and sparseness. SHAP analysis reveals key influential factors, including age and water-to-binder ratio in concrete composition, and peak load and height of testing samples, as well as microstructural characteristics such as mean values of global autocorrelation length and its integral range. This research provides valuable insights into model optimization, predictive performance, and feature dependencies and interactions, contributing to the development of more accurate and reliable CCS prediction models.

DR-Z2AN: dual-recurrent neural network with a tri-channel attention mechanism for financial management prediction

Financial management prediction, often known as financial forecasting, is the act of estimating future financial outcomes using past data and present trends. It is an essential component of financial analysis and planning that aids businesses in making well-informed decisions and preparing for potential future events. In the healthcare domain, financial management prediction is a crucial task that helps patients track and predict the expenses required for their medical services. The established methods for financial management prediction have some flaws, such as the requirement of labeled data, data quality, time complexity, under fitting problems, and longer execution times. Therefore, in order to resolve these limitations; a deep learning-based model is developed in this study for efficient financial management prediction. Specifically, this research proposes a dual-recurrent neural network with a tri-channel attention mechanism (DR-Z2AN) for accurate prediction. The proposed DR-Z2AN model combines the tri-channel attention mechanism with dual-RNN and multi-head attention, which enhances the robustness and interpretability of the systems. The multi-head attention learns the complex relationships between the data, which develops the generalization capability of the model in prediction tasks. The combined model efficiently processes the sequence data, and the tri-channel attention improves the model's capacity to extract meaningful characteristics from the input. The integration of the incentive learning approach helps the model improve the learning parameters to get better results with the minimum error. The experimental results demonstrate that the DR-Z2AN model attains minimal error in terms of MAE, MAPE, MSE, and RMSE of 1.46, 3.83, 4.32, and 2.08, respectively; thus, the proposed approach gives better results than the other traditional methods. Overall, the DR-Z2AN model offers accurate predictions with reduced computational time and improved interpretability.

An efficient plant disease prediction model based on machine learning and deep learning classifiers

An efficient plant disease prediction model based on machine learning and deep learning classifiers