Common Prediction Models Research Articles

Short-Term Irradiance Prediction Based on Transformer with Inverted Functional Area Structure

Solar irradiance prediction is a crucial component in the application of photovoltaic power generation, playing a vital role in optimizing energy production, managing energy storage, and maintaining grid stability. This paper proposes an irradiance prediction method based on a functionally structured inverted transformer network, which maintains the channel independence of each feature in the model input and extracts the correlations between different features through an Attention mechanism, enabling the model to effectively capture the relevant information between various features. After the channel mixing of different features is completed through the Attention mechanism, a linear network is used to predict the irradiance sequence. A data processing method tailored to the prediction model used in this paper is designed, which employs a comprehensive data preprocessing approach combining mutual information, multiple imputation, and median filtering to optimize the raw dataset, enhancing the overall stability and accuracy of the prediction project. Additionally, a Dingo optimization algorithm suitable for the self-tuning of deep learning model hyperparameters is designed, improving the model’s generalization capability and reducing deployment costs. The artificial intelligence (AI) model proposed in this paper demonstrates superior prediction performance compared to existing common prediction models in irradiance data forecasting and can facilitate further applications of photovoltaic power generation in power systems.

Industrial water withdrawal prediction using multi-head attention encoder model

ABSTRACT Industrial water withdrawal prediction is the cornerstone of water resources monitoring and early warning, as well as a key task in implementing rigid constraints on water resources. Although many factors may influence water withdrawal, they are difficult to obtain. Extracting the features in the historical water withdrawal data itself is a more convenient alternative way to achieve accurate prediction. However, due to the lack of significant regularity and periodicity in industrial water data, feature extraction is challenging. In this paper, a multi-head attention encoder (MAEN) model consisting of multi-head attention mechanisms and feed-forward neural networks is proposed to enable more convenient and accurate forecasting. The multi-head attention mechanism allows to focus on different parts of the data simultaneously, detecting complex dependencies, and extracting key features from historical data to enable more efficient feature extraction. Applied to water withdrawal data from real factories, the proposed model outperforms common time series prediction models including artificial neural network, long short-term memory, and gate recurrent unit. Compared to the best-performing comparison model, MAEN shows a reduction of mean squared error by 3.2% for 1 day ahead predictions, and 8.9% for 7 day ahead predictions, illustrating its superior performance in industrial water withdrawal prediction.

Investigation of the Dominant Effects of Non-Spherical Particles on Particle–Wall Collisions

A deep understanding of the particle–wall collision (PWC) behaviors of non-spherical particles is important for managing gas–solid flows in industrial applications. It is important to identify the dominant parameters and to develop the common PWC prediction models for typical non-spherical particles. In this paper, different types of non-spherical particles were used to conduct the fundamental experiments. The effects of key parameters such as particle size, non-sphericity, wall roughness, and impact angle were analyzed. The results show that the trends of the collision coefficients with the impact angle for all non-spherical particles are similar. The dominant factors of particle–wall collisions are particle sphericity and wall roughness. A model with four parameters was fitted from the experimental data. The model can predict the collisions of non-spherical particles on rough steel walls with sizes ranging from 50 to 550 microns.

A common feature-driven prediction model for multivariate time series data

Multivariate time series data contain a variety of common features that are difficult to extract, among which the sudden irregular fluctuation trend, the trend feature of large fluctuation amplitude, and the long-term dependency relationship in the time series have an important impact on the accuracy of the prediction model. To predict non-stationary trends in large-scale data accurately using the common characteristics of multivariate time series. A novel generalised forecasting model NeA3L based on common features of time series is developed. The NeA3L model utilizes multiple independent parallel feature extraction modules to obtain the common features of multivariate time series. It utilizes the three-layer iterative structure to deal with sudden irregular fluctuation patterns. NeA3L optimizes the network structure to realize the heterogeneous codec structure. It applies the attention mechanism between the encoder and the decoder to accomplish the multivariate prediction of the multivariate time series, which has good stability for predicting various types of multivariate data. A comparison of the NeA3L model with nine current time series prediction methods on four publicly available datasets shows that the NeA3L model outperforms the current methods in various evaluation metrics. The RMSE is improved by 2.3 %, 26.5 %, 28.9 %, and 20.84 % on average, respectively. The NeA3L model can be universally applicable to the field of multivariate time series prediction, which is important for optimizing the intelligent management and decision-making.

Insulation for Rotating Low-Voltage Electrical Machines: Degradation, Lifetime Modeling, and Accelerated Aging Tests

The low-voltage electric machine (EM) is a core technology for transportation electrification, and features like high power density and compact volume are essential prerequisites. However, these requirements are usually in conflict with the reliability property of EM, especially in the safety-critical industry such as aviation. Therefore, an appropriate balance between high-performance and reliability needs to be found. Often, the over-engineering method is applied to ensure safety, although it might have a detrimental effect on the EM volume. To address this issue, the EM reliability assessment is included at the EM design stage through the physics of failure (PoF) theory. In EMs, the windings play a key role in electromechanical energy conversion, but their insulation system is subject to frequent failure and represents a reliability bottleneck. Therefore, in-depth research on the root causes of insulation breakdown is beneficial for EM reliability improvement purposes. Indeed, increasing awareness and knowledge on the mechanism of the insulation degradation process and the related lifetime modeling enables the growth of appropriate tools for achieving reliability targets since the first EM design steps. In this work, the main aspects of the insulation system, in terms of materials and manufacturing, are first reviewed. Then, the principal stresses experienced by the winding insulation system are deeply discussed with the purpose of building a profound understanding of the PoF. Finally, an overview of the most common insulation lifetime prediction models is presented, and their use for accomplishing the reliability-oriented design (RoD) and the remaining useful life (RUL) estimation are examined.

Fatigue Crack Propagation of 51CrV4 Steels for Leaf Spring Suspensions of Railway Freight Wagons.

Leaf springs are critical components for the railway vehicle safety in which they are installed. Although these components are produced in high-strength alloyed steel and designed to operate under cyclic loading conditions in the high-cyclic fatigue region, their failure is still possible, which can lead to economic and human catastrophes. The aim of this document was to precisely characterise the mechanical crack growth behaviour of the chromium-vanadium alloyed steel representative of leaf springs under cyclic conditions, that is, the crack propagation in mode I. The common fatigue crack growth prediction models (Paris and Walker) considering the effect of stress ratio and parameters such as propagation threshold, critical stress intensity factor and crack closure ratio were also determined using statistical methods, which resulted in good approximations with respect to the experimental results. Lastly, the fracture surfaces under the different test conditions were analysed using SEM, with no significant differences to declare. As a result of this research work, it is expected that the developed properties and fatigue crack growth prediction models can assist design and maintenance engineers in understanding fatigue behaviour in the initiation and propagation phase of cracks in leaf springs for railway freight wagons.

Dimensionality reduction and machine learning based model of software cost estimation

Software Cost Estimation (SCE) is one of the research priorities and challenges in the construction of cyber-physical-social systems (CPSSs). In CPSS, it is urge to process environmental and social information accurately and use it to guide social practice. Thus, in response to the problems of low prediction accuracy, poor robustness, and poor interpretability in SCE, this paper proposes a SCE model based on Autoencoder and Random Forest. First, preprocess the project data, remove outliers, and build regression trees to fill in missing attributes in the data. Second, construct a Autoencoder to reduce the dimensionality of factors that affect software cost. Subsequently, the performance of the model was trained and validated using the XGBoost framework on three datasets: COCOMO81, Albrecht, and Desharnais, and compared with common cost prediction models. The experimental results show that the MMRE, MdMRE, and PRED (0.25) values of the proposed model on the COCOMO81 dataset reached 0.21, 0.16, and 0.71, respectively. Compared with other models, the proposed model achieved significant improvements in accuracy and robustness.

Further study on oil/water relative permeability ratio model and waterflooding performance prediction model for high water cut oilfields sustainable development

The accuracy of predicting waterflooding performance is crucial in determining the scale of investment for oilfield development. However, existing common waterflooding prediction models often relies on assumptions that may not apply universally or lack theoretical derivation through statistical analysis. This has led to unsatisfactory prediction accuracy and multiple potential solutions. To address these limitations, it is proposed to incorporate the oil/water relative permeability ratio model into the derivation process of waterflooding prediction models. Initially, an evaluation of prevalent oil/water relative permeability ratio models is conducted, along with an analysis of their primary constraints. Additionally, the applicability of the analytical relative permeability model is thoroughly examined. Building upon the analytical relative permeability model and a modified Welge equation, a new waterflooding model is formulated, encompassing all pertinent physical coefficients. Notably, this model aligns seamlessly with the commonly used Arps’ decline curve, while extending its applicability to a broader range of conditions. Moreover, it can be simplified to generate typical water drive curves under suitable circumstances. The semi-log relationship between oil/water relative permeability ratio and water saturation is further simplified into a linear relationship or a multi-term formula. Compared with the traditional waterflooding model, the new model proposed in this research has a wider application range and can be applied to oilfield at high water cut. At the same time, the new model clarifies the coefficient of waterflooding curve A and the physical meaning of parameter 7.5 in Tong’s chart method for the first time. The new model proposed in this research further enriches the connotation of waterflooding theory and has certain application significance.

Identifying primary aldosteronism patients who require adrenal venous sampling: a multi-center study

Adrenal venous sampling (AVS) is crucial for subtyping primary aldosteronism (PA) to explore the possibility of curing hypertension. Because AVS availability is limited, efforts have been made to develop strategies to bypass it. However, it has so far proven unsuccessful in applying clinical practice, partly due to heterogeneity and missing values of the cohorts. For this purpose, we retrospectively assessed 210 PA cases from three institutions where segment-selective AVS, which is more accurate and sensitive for detecting PA cases with surgical indications, was available. A machine learning-based classification model featuring a new cross-center domain adaptation capability was developed. The model identified 102 patients with PA who benefited from surgery in the present cohort. A new data imputation technique was used to address cross-center heterogeneity, making a common prediction model applicable across multiple cohorts. Logistic regression demonstrated higher accuracy than Random Forest and Deep Learning [(0.89, 0.86) vs. (0.84, 0.84), (0.82, 0.84) for surgical or medical indications in terms of f-score]. A derived integrated flowchart revealed that 35.2% of PA cases required AVS with 94.1% accuracy. The present model enabled us to reduce the burden of AVS on patients who would benefit the most.

Development of comprehensive calibration models for pulp traits by near infrared spectroscopy (NIRS) for pure species and hybrids of Corymbia and Eucalyptus

Corymbia hybrid has emerged as a complimentary pulpwood in India along with Eucalyptus camaldulensis and eucalypt hybrids for enhancing the profitability of the industry and the income of farmers. Near infrared spectroscopy (NIRS) offers a rapid non-destructive method for estimating wood and pulp traits of short rotation trees. Development of NIR calibration models in Corymbia is essential for quick selection and rapid advancement of pulp wood traits. A study was carried out to develop a combined calibration curve for pure E. camaldulensis and Corymbia species and their interspecific hybrids. Wood samples were extracted from four-year-old 300 trees of Corymbia torelliana (CT), C. citriodora (CC), C. variegata (CV) and E. camaldulensis (EC) and their interspecific hybrids from progeny evaluation trials at three different locations in south India. The wood logs and powdered core samples were analyzed for kraft pulp yield (KPY), lignin and S|G ratio by wet chemistry and NIRS method. The KPY values of CC and CV ranged from 44 to 52%, whereas CT, a maternal parent in CT x CC|CV hybrids, had a narrow range of 38-46.5%. However, the interspecific hybrids of CT x CC|CV exhibited a range with higher values from 48.5 to 50.5%, indicating a narrow scope for predicting hybrids from that of parent’s standard calibration curves. The estimated values in pure species of Corymbia for lignin content ranged from 22.7 to 29.2 % and 1.9 to 3.1 for S|G ratio, while in hybrids it was 25.6 to 29.4 for lignin. The correlation coefficients for cross-validation of KPY in CC, CV, CT and their hybrids were 0.8, 0.81, 0.89 and 0.72, respectively, and root mean square errors (RMS) were 0.8, 0.55, 0.73 and 0.31, respectively. When CC and CV samples were pooled to generate a common prediction model, the correlation coefficients were 0.8 for KPY, 0.75 for lignin and 0.83 for S|G ratio, with RMS of 0.68 for both KPY and lignin, and 0.12 for S|G ratio. Corymbia hybrids were evaluated with 99% accuracy using a combined prediction model of pure Corymbia species and hybrids. The method was validated with 80 samples of pure species and hybrids with a RMS of less than 1.0. We also attempted in developing a combined prediction model for different species of Corymbia, Eucalyptus, and their hybrids with minimum prediction errors.

Common Predictive Model for PMSM Drives With Interturn Fault Considering Torque Ripple Suppression

Common Predictive Model for PMSM Drives With Interturn Fault Considering Torque Ripple Suppression

Risk prediction models for mortality and readmission in patients with acute heart failure: A protocol for systematic review, critical appraisal, and meta-analysis.

A considerable number of risk models, which predict outcomes in mortality and readmission rates, have been developed for patients with acute heart failure (AHF) to help stratify patients by risk level, improve decision making, and save medical resources. However, some models exist in a clinically useful manner such as risk scores or online calculators, while others are not, providing only limited information that prevents clinicians and patients from using them. The reported performance of some models varied greatly when predicting at multiple time points and being validated in different cohorts, which causes model users uncertainty about the predictive accuracy of these models. The foregoing leads to users facing difficulties in the selection of prediction models, and even sometimes being reluctant to utilize models. Therefore, a systematic review to assess the performance at multiple time points, applicability, and clinical impact of extant prediction models for mortality and readmission in AHF patients is essential. It may facilitate the selection of models for clinical implementation. Four databases will be searched from their inception onwards. Multivariable prognostic models for mortality and/or readmission in AHF patients will be eligible for review. Characteristics and the clinical impact of included models will be summarized qualitatively and quantitatively, and models with clinical utility will be compared with those without. Predictive performance measures of included models with an analogous clinical outcome appraised repeatedly, will be compared and synthesized by a meta-analysis. Meta-analysis of validation studies for a common prediction model at the same time point will also be performed. We will also provide an overview of critical appraisal of the risk of bias, applicability, and reporting transparency of included studies using the PROBAST tool and TRIPOD statement. PROSPERO registration number CRD42021256416.

Community evolution prediction based on a self-adaptive timeframe in social networks

The prediction of community evolution events in dynamic social networks is of great importance for network security alerts. Currently, most of the common prediction models use a fixed timeframe division strategy to divide the dynamic social network, such as the disjoint timeframe division strategy and overlapping timeframe division strategy. However, these frameworks cannot change once they are selected, and are not suitable for the prediction of network evolution with strong variability in real-world applications. In this paper, a new community evolution model is developed from the perspective of the universality of the timeframe, and a new optimized timeframe partitioning algorithm is proposed. Compared with the traditional fixed timeframe partitioning algorithm, this method adaptively adjusts the size and number of time windows according to the information fluctuations of the specific network at an acceptable extra computational cost. Based on the analysis of several real-world networks, we found that the proposed self-adaptive timeframe partitioning algorithm improved the quality of community tracking of the network and ensured the accuracy of prediction events.

Development and validation of common data model-based fracture prediction model using machine learning algorithm.

Osteoporotic fractures are substantial health and economic burden. Therefore, the need for an accurate real-world-based fracture prediction model is increasing. We aimed to develop and validate an accurate and user-friendly model to predict major osteoporotic and hip fractures using a common data model database. The study included 20,107 and 13,353 participants aged ≥ 50years with data on bone mineral density using dual-energy X-ray absorptiometry from the CDM database between 2008 and 2011 from the discovery and validation cohort, respectively. The main outcomes were major osteoporotic and hip fracture events.DeepHit and Cox proportional hazard models were used to identify predictors of fractures and to build scoring systems, respectively. The mean age was 64.5years, and 84.3% were women. During a mean of 7.6years of follow-up, 1990 major osteoporotic and 309 hip fracture events were observed. In the final scoring model, history of fracture, age, lumbar spine T-score, total hip T-score, and cardiovascular disease were selected as predictors for major osteoporotic fractures. For hip fractures, history of fracture, age, total hip T-score, cerebrovascular disease, and diabetes mellitus were selected. Harrell's C-index for osteoporotic and hip fractures were 0.789 and 0.860 in the discovery cohort and 0.762 and 0.773 in the validation cohort, respectively. The estimated 10-year risks of major osteoporotic and hip fractures were 2.0%, 0.2% at score 0 and 68.8%, 18.8% at their maximum scores, respectively. We developed scoring systems for osteoporotic fractures from hospital-based cohorts and validated them in an independent cohort. These simple scoring models may help predict fracture risks in real-world practice.

Photovoltaic power prediction based on sliced bidirectional long short term memory and attention mechanism

Solar photovoltaic power generation has the characteristics of intermittence and randomness, which makes it a challenge to accurately predict solar power generation power, and it is difficult to achieve the desired effect. Therefore, by fully considering the relationship between power generation data and climate factors, a new prediction method is proposed based on sliced bidirectional long short term memory and the attention mechanism. The prediction results show that the presented model has higher accuracy than the common prediction models multi-layer perceptron, convolution neural network, long short term memory and bidirectional long short term memory. The presented sliced bidirectional cyclic network has high prediction accuracy by low root mean square error and mean absolute error of 1.999 and 1.159 respectively. The time cost is only 24.32% of that of long short term memory network and 13.76% of that of bidirectional long short term memory network.

Convolutional Neural Network Knowledge Graph Link Prediction Model Based on Relational Memory.

A knowledge graph is a collection of fact triples, a semantic network composed of nodes and edges. Link prediction from knowledge graphs is used to reason about missing parts of triples. Common knowledge graph link prediction models include translation models, semantics matching models, and neural network models. However, the translation models and semantic matching models have relatively simple structures and poor expressiveness. The neural network model can easily ignore the overall structural characteristics of triples and cannot capture the links between entities and relations in low-dimensional space. In response to the above problems, we propose a knowledge graph embedding model based on a relational memory network and convolutional neural network (RMCNN). We encode triple embedding vectors using a relational memory network and decode using a convolutional neural network. First, we will obtain entity and relation vectors by encoding the latent dependencies between entities and relations and some critical information and keeping the translation properties of triples. Then, we compose a matrix of head entity encoding embedding vector, relation encoding embedding vector, and tail entity embedding encoding vector as the input of the convolutional neural network. Finally, we use a convolutional neural network as the decoder and a dimension conversion strategy to improve the information interaction capability of entities and relations in more dimensions. Experiments show that our model achieves significant progress and outperforms existing models and methods on several metrics.

Response observation of a full-scale geosynthetic-reinforced pile-supported system to environmental actions

The collected field data from well-instrumented reinforced embankments in the framework of a real project for the extension of the inner-city area at HafenCity in Hamburg is used to study the effect of environmental changes on the load transfer process over the structure lifetime. A particular focus is put to improve the understanding of the load transfer mechanism from the soil embankment to pile foundations through the reinforced geosynthetic layer and to investigate the corresponding long-term settlements. The time-dependent stress and strain distribution of the reinforced load transfer platform has been focused to investigate the process of soil arching on top of the piles and examine the overall settlement of the embankment. Finally, the most common available prediction models in European design guidelines are applied to estimate the loads on structural components and the results are compared with the measurements.

Prediction of Soil Erodibility by Diffuse Reflectance Spectroscopy in a Neotropical Dry Forest Biome

The USLE and the RUSLE are two common erosion prediction models that are used worldwide, and soil erodibility (K-factor) is one parameter used to calculate them. The objectives of this study were to investigate the variability of soil-erodibility factors under different soil-texture classes and evaluate the efficiency of diffuse reflectance spectroscopy (DRS) in the near-infrared range at predicting the USLE and RUSLE K-factors using a partial least squares regression analysis. The study was conducted in Fluvisols in dry tropical forest (the Caatinga). Sampling was undertaken in the first 20 cm of soil at 80 sites distributed 15 m apart on a 70 m × 320 m spatial grid. Results show that the clay fraction is represented mainly by 2:1 phyllosilicates. Soil organic matter content is low (<0.2%), which is typical of tropical dry forests, and this is reflected in the high values of the calculated USLE and RUSLE K-factors. An empirical semivariogram was used to investigate the spatial dependence of both K-factors. Pedometric modeling showed that DRS can be used to predict both USLE (R2adj = 0.53; RMSE = 8.37 10−3 t h MJ−1 mm−1) and RUSLE (R2adj = 0.58; RMSE = 6.78 10−3 t h MJ−1 mm−1) K-factors.

A Comparative Study on Traffic Modeling Techniques for Predicting and Simulating Traffic Behavior

The significant advancements in intelligent transportation systems (ITS) have contributed to the increased development in traffic modeling. These advancements include prediction and simulation models that are used to simulate and predict traffic behaviors on highway roads and urban networks. These models are capable of precise modeling of the current traffic status and accurate predictions of the future status based on varying traffic conditions. However, selecting the appropriate traffic model for a specific environmental setting is challenging and expensive due to the different requirements that need to be considered, such as accuracy, performance, and efficiency. In this research, we present a comprehensive literature review of the research related to traffic prediction and simulation models. We start by highlighting the challenges in the long-term and short-term prediction of traffic modeling. Then, we review the most common nonparametric prediction models. Lastly, we look into the existing literature on traffic simulation tools and traffic simulation algorithms. We summarize the available traffic models, define the required parameters, and discuss the limitations of each model. We hope that this survey serves as a useful resource for traffic management engineers, researchers, and practitioners in this domain.

Machine learning outperformed logistic regression classification even with limit sample size: A model to predict pediatric HIV mortality and clinical progression to AIDS.

Logistic regression (LR) is the most common prediction model in medicine. In recent years, supervised machine learning (ML) methods have gained popularity. However, there are many concerns about ML utility for small sample sizes. In this study, we aim to compare the performance of 7 algorithms in the prediction of 1-year mortality and clinical progression to AIDS in a small cohort of infants living with HIV from South Africa and Mozambique. The data set (n = 100) was randomly split into 70% training and 30% validation set. Seven algorithms (LR, Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naïve Bayes (NB), Artificial Neural Network (ANN), and Elastic Net) were compared. The variables included as predictors were the same across the models including sociodemographic, virologic, immunologic, and maternal status features. For each of the models, a parameter tuning was performed to select the best-performing hyperparameters using 5 times repeated 10-fold cross-validation. A confusion-matrix was built to assess their accuracy, sensitivity, and specificity. RF ranked as the best algorithm in terms of accuracy (82,8%), sensitivity (78%), and AUC (0,73). Regarding specificity and sensitivity, RF showed better performance than the other algorithms in the external validation and the highest AUC. LR showed lower performance compared with RF, SVM, or KNN. The outcome of children living with perinatally acquired HIV can be predicted with considerable accuracy using ML algorithms. Better models would benefit less specialized staff in limited resources countries to improve prompt referral in case of high-risk clinical progression.