Traditional Prediction Methods Research Articles

The role of news sentiment in salmon price prediction using deep learning

The role of news sentiment in salmon price prediction using deep learning

Reactive Load Pre-measurement for Large Industrial Users Based on Improved GBDT Regression Algorithm

Abstract With the development of intelligence and marketization of power system, reactive load prediction is the key technology applied to the intelligent technical means of power grid. For large industrial users, the management of reactive power is one of the key factors to maintain the voltage stability. Therefore, the accurate prediction of the reactive load of large industrial users is of great significance to optimize the operation of the power system and reduce energy waste. To this end, this paper realizes the prediction set date based on the improved gradient lifting tree (Gradient Boosting Decision Tree, GBDT) regression algorithm, selects the whole data as the historical data for training, and compares the data with the traditional prediction method. The experiments show that the improved GBDT regression algorithm is 28.9% more accurate than the time series algorithm MA, which predicts only from historical data.

Short-Term Prognostic Risk Factors and Nomogram Predictive Model Construction for Acute Ischaemic Stroke after Endovascular Treatment.

To investigate the factors influencing the severity of acute ischaemic stroke (AIS) and short-term prognosis after endovascular treatment. Observational study. Place and Duration of the Study: Department of Cerebrovascular Diseases, The First People's Hospital of Qujing City, Yunnan Province, China, from June 2020 to December 2022. An analysis was conducted on 160 AIS patients undergoing endovascular treatment, classified into atherosclerosis subtype (AS) and cardioembolic subtype (CE) based on the Trial of ORG 10172 in Acute Stroke Treatment (TOAST) classification, each comprising 80 cases. The association among baseline and endovascular treatment parameters, clinical characteristics, postoperative complications, and short-term outcomes (risks of mortality and poor prognosis) was tested. Univariate analysis revealed significant positive correlations between increased fasting glucose, diastolic pressure, and the number of thrombectomy procedures with the frequency of cerebral haemorrhage in CE-type stroke. The time from femoral artery puncture to vessel opening was positively associated with the degree of brain oedema. In the AS subtype, univariate regression analysis demonstrated a significant association between heart rate, fasting glucose, cholesterol, time from femoral artery puncture to vessel opening, and degree of brain oedema with short-term prognosis. Fasting glucose and the number of thrombectomy procedures were significantly linked to short-term prognosis in CE-type AIS. A predictive model using line charts was developed for factors associated with postoperative complications and short-term prognosis, achieving predictive accuracies of 95.5% for the risk of death and 92.7% for poor prognosis (mRS >2), notably surpassing traditional prediction methods. Clinical characteristics and endovascular treatment-related factors are important for the short-term prognosis of AIS patients. Development of predictive models can efficiently identify high-risk patients at an early stage. Acute ischaemic stroke, Atherosclerosis, Cardioembolic, Severity, Prognosis.

Prediction of Solar Radiation using Deep LSTM-based Machine Learning Algorithm

Solar radiation, a critical parameter for various applications such as solar energy systems and weather forecasting, exhibits complex temporal patterns influenced by numerous environmental factors. In the quest to enhance the accuracy of solar radiation predictions, this study introduces a novel approach utilizing Deep Long Short-Term Memory (Deep LSTM) networks, a type of recurrent neural network (RNN) known for its capability to model sequential data. Traditional prediction methods often struggle to capture these intricacies, leading to sub-optimal performance. This investigation is based on a Deep LSTM-based machine learning algorithm designed to predict solar radiation with elevated exactitude. The model is meticulously trained on copious datasets encompassing historical meteorological data, including temperature, humidity, wind velocity, and antecedent solar radiation metrics. Pivotal stages encompass data preprocessing, judicious feature selection, and hyperparameter optimization to enhance the model’s predictive efficacy. Empirical results clearly illustrate that the Deep LSTM model surpasses traditional methodologies, attaining superior accuracy and resilience across diverse meteorological scenarios. The ramifications of this endeavor portend significant advancements in the strategic planning and administration of solar energy resources, thereby contributing to more dependable and efficacious renewable energy systems.

Analytical time-coordinated entry guidance for multi-hypersonic vehicles within three-dimensional corridor

Analytical time-coordinated entry guidance for multi-hypersonic vehicles within three-dimensional corridor

Wfold: A new method for predicting RNA secondary structure with deep learning

Precise estimations of RNA secondary structures have the potential to reveal the various roles that non-coding RNAs play in regulating cellular activity. However, the mainstay of traditional RNA secondary structure prediction methods relies on thermos-dynamic models via free energy minimization, a laborious process that requires a lot of prior knowledge. Here, RNA secondary structure prediction using Wfold, an end-to-end deep learning-based approach, is suggested. Wfold is trained directly on annotated data and base-pairing criteria. It makes use of an image-like representation of RNA sequences, which an enhanced U-net incorporated with a transformer encoder can process effectively. Wfold eventually increases the accuracy of RNA secondary structure prediction by combining the benefits of self-attention mechanism's mining of long-range information with U-net's ability to gather local information. We compare Wfold's performance using RNA datasets that are within and across families. When trained and evaluated on different RNA families, it achieves a similar performance as the traditional methods, but dramatically outperforms the state-of-the-art methods on within-family datasets. Moreover, Wfold can also reliably forecast pseudoknots. The findings imply that Wfold may be useful for improving sequence alignment, functional annotations, and RNA structure modeling.

MAFNet: Multimodal Asymmetric Fusion Network for Radar Echo Extrapolation

Radar echo extrapolation (REE) is a crucial method for convective nowcasting, and current deep learning (DL)-based methods for REE have shown significant potential in severe weather forecasting tasks. Existing DL-based REE methods use extensive historical radar data to learn the evolution patterns of echoes, they tend to suffer from low accuracy. This is because data of radar modality face difficulty adequately representing the state of weather systems. Inspired by multimodal learning and traditional numerical weather prediction (NWP) methods, we propose a Multimodal Asymmetric Fusion Network (MAFNet) for REE, which uses data from radar modality to model echo evolution, and data from satellite and ground observation modalities to model the background field of weather systems, collectively guiding echo extrapolation. In the MAFNet, we first extract overall convective features through a global shared encoder (GSE), followed by two branches of local modality encoder (LME) and local correlation encoders (LCEs) that extract convective features from radar, satellite, and ground observation modalities. We employ an multimodal asymmetric fusion module (MAFM) to fuse multimodal features at different scales and feature levels, enhancing radar echo extrapolation performance. Additionally, to address the temporal resolution differences in multimodal data, we design a time alignment module based on dynamic time warping (DTW), which aligns multimodal feature sequences temporally. Experimental results demonstrate that compared to state-of-the-art (SOTA) models, the MAFNet achieves average improvements of 1.86% in CSI and 3.18% in HSS on the MeteoNet dataset, and average improvements of 4.84% in CSI and 2.38% in HSS on the RAIN-F dataset.

Prediction of regional water resources carrying capacity based on stochastic simulation: A case study of Beijing-Tianjin-Hebei Urban Agglomeration

Prediction of regional water resources carrying capacity based on stochastic simulation: A case study of Beijing-Tianjin-Hebei Urban Agglomeration

Prediction of the internal corrosion rate for oil and gas pipelines and influence factor analysis with interpretable ensemble learning

Prediction of the internal corrosion rate for oil and gas pipelines and influence factor analysis with interpretable ensemble learning

BioPathNet: Enhancing Link Prediction in Biomedical Knowledge Graphs through Path Representation Learning.

Understanding complex interactions in biomedical networks is crucial for advancements in biomedicine, but traditional link prediction (LP) methods are limited in capturing this complexity. Representation-based learning techniques improve prediction accuracy by mapping nodes to low-dimensional embeddings, yet they often struggle with interpretability and scalability. We present BioPathNet, a novel graph neural network framework based on the Neural Bellman-Ford Network (NBFNet), addressing these limitations through path-based reasoning for LP in biomedical knowledge graphs. Unlike node-embedding frameworks, BioPathNet learns representations between node pairs by considering all relations along paths, enhancing prediction accuracy and interpretability. This allows visualization of influential paths and facilitates biological validation. BioPathNet leverages a background regulatory graph (BRG) for enhanced message passing and uses stringent negative sampling to improve precision. In evaluations across various LP tasks, such as gene function annotation, drug-disease indication, synthetic lethality, and lncRNA-mRNA interaction prediction, BioPathNet consistently outperformed shallow node embedding methods, relational graph neural networks and task-specific state-of-the-art methods, demonstrating robust performance and versatility. Our study predicts novel drug indications for diseases like acute lymphoblastic leukemia (ALL) and Alzheimer's, validated by medical experts and clinical trials. We also identified new synthetic lethality gene pairs and regulatory interactions involving lncRNAs and target genes, confirmed through literature reviews. BioPathNet's interpretability will enable researchers to trace prediction paths and gain molecular insights, making it a valuable tool for drug discovery, personalized medicine and biology in general.

Prediction method of condition degradation for network-level bridges based on U-Net++ convolutional neural network

Prediction method of condition degradation for network-level bridges based on U-Net++ convolutional neural network

Remaining useful life prediction based on time-series features and conformalized quantile regression

Abstract The remaining useful life (RUL) prediction is a key task in the field of prognostics and health management (PHM) and plays a crucial role in preventive maintenance tasks. Traditional prediction methods have mostly focused on point prediction issues, neglecting the uncertain factors in the prediction task, thus failing to ensure the credibility of the prediction. In light of this, this paper focuses on improving the accuracy of point prediction models for RUL and interval prediction issues, proposing the introduction of multi-scale convolutional neural networks (MCNN), decomposed time-sequential linear layers (DL), and conformal quantile regression (CQR) techniques into the RUL prediction task of aero-engines. The aim is to provide timely and accurate failure warnings for aero engines, effectively ensure their reliability and safety, and reduce maintenance costs throughout their life cycle. In response to the limitations of current point prediction models in capturing the temporal features of life data, a MCNN-DL-based RUL prediction model is proposed to capture life data's long-term trends and local variations for precise point predictions. Furthermore, an interval estimation approach for RUL is presented, which integrates the MCNN-DL model with CQR to account for prediction uncertainty. Finally, the method in this paper is verified using the CMAPSS dataset, and the results show that the method has achieved excellent results in both RUL point prediction and interval prediction tasks.

Prediction of Human Microbe-Drug Association based on Layer Attention Graph Convolutional Network.

In this paper, we have proposed a novel model of layer attention graph convolutional network for microbe-drug association prediction. First, multiple biological data have been integrated into a heterogeneous network. Then, the heterogeneous network has been incorporated into a graph convolutional network to determine the embedded microbe and drug. Finally, the microbe-drug association scores have been obtained by decoding the embedding of microbe and drug based on the layer attention mechanism. To evaluate the performance of our proposed model, leave-one-out crossvalidation (LOOCV) and 5-fold cross-validation have been implemented on the two datasets of aBiofilm and MDAD. As a result, based on the aBiofilm dataset, our proposed model has attained areas under the curve (AUC) of 0.9178 and 0.9022 on global LOOCV and local LOOCV, respectively. Based on aBiofilm dataset, the proposed model has attained an AUC value of 0.9018 and 0.8902 on global LOOCV and local LOOCV, respectively. In addition, the average AUC and standard deviation of the proposed model for 5- fold cross-validation on the aBiofilm and MDAD datasets were 0.9141±6.8556e-04 and 0.8982±7.5868e-04, respectively. Also, two kinds of case studies have been further conducted to evaluate the proposed models. Traditional methods for microbe-drug association prediction are timeconsuming and laborious. Therefore, the computational model proposed was used to predict new microbe-drug associations. Several evaluation results have shown the proposed model to achieve satisfactory results and that it can play a role in drug development and precision medicine.

Enhancing Flight Delay Predictions Using Network Centrality Measures

Accurately predicting flight delays remains a significant challenge in the aviation industry due to the complexity and interconnectivity of its operations. The traditional prediction methods often rely on meteorological conditions, such as temperature, humidity, and dew point, as well as flight-specific data like departure and arrival times. However, these predictors frequently fail to capture the nuanced dynamics that lead to delays. This paper introduces network centrality measures as novel predictors to enhance the binary classification of flight arrival delays. Additionally, it emphasizes the use of tree-based ensemble models, specifically random forest, gradient boosting, and CatBoost, which are recognized for their superior ability to model complex relationships compared to single classifiers. Empirical testing shows that incorporating centrality measures improves the models’ average performance, with random forest being the most effective, achieving an accuracy rate of 86.2%, surpassing the baseline by 1.7%.

Artificial Intelligence in Predicting the Mode of Delivery: A Systematic Review.

The integration of artificial intelligence (AI) into obstetric care offers significant potential to enhance clinical decision-making and optimize maternal and neonatal outcomes. Traditional prediction methods for mode of delivery often rely on subjective clinical judgment and limited statistical models, which may not fully capture complex patient data. This systematic review aims to evaluate the current state of research on AI applications in predicting the mode of delivery, comparing the performance of AI models with traditional methods, and identifying gaps for future research. A comprehensive literature search was conducted across PubMed, Google Scholar, Web of Science, and Scopus databases, covering publications from January 2010 to July 2024. Inclusion criteria were studies employing AI techniques to predict the mode of delivery, published in peer-reviewed journals, and involving human subjects. Studies were assessed for quality using the Prediction Model Risk of Bias Assessment Tool (PROBAST), and data were synthesized narratively due to heterogeneity. In total, 18 studies met the inclusion criteria, employing various AI models such as logistic regression, random forest, gradient boosting, and neural networks. Sample sizes ranged from 40 to 94,480 participants across diverse geographic settings. AI models demonstrated high accuracy rates, often exceeding 90%, and strong predictive metrics (area under the curve (AUC) values from 0.745 to 0.932). Key predictors included maternal age, gravidity, parity, gestational age, labor induction type, and fetal weight. Notable models like the Adana Systemand Categorical Boosting (CatBoost, Yandex LLC, Moscow, Russia) highlighted the effectiveness of AI in enhancing prediction accuracy and supporting clinical decisions. AI models significantly outperform traditional statistical methods in predicting the mode of delivery, providing a robust tool for obstetric care. Future research should focus on standardizing data collection, improving model interpretability, addressing ethical concerns, and ensuring fairness in AI predictions to enhance clinical trust and application.

Multivariate quality prediction of thin-walled parts machining using multi-task parallel deep transfer learning

Multivariate machining quality prediction of thin-walled parts with multiple machining features is a complex problem due to different data distribution between training and unlabelled test samples. Traditional quality prediction methods ignore the correlation of multiple quality labels and do not consider changes in data distribution, resulting in low accuracy of multivariate quality prediction. Therefore, a multivariate quality prediction method using multi-task parallel deep transfer learning is proposed to solve this problem. Specifically, a multi-output quality prediction model of cross-machining features is constructed through the joint design of multi-task parallel learning and deep transfer learning. Furthermore, a domain matcher is designed to form multiple transfer strategies, which can be used for dynamic matching of multi-source and multi-target machining features with multiple quality labels. The domain invariant data features through dynamic domain adaptation are extracted to deal with data distribution discrepancy between the source and target domains. Finally, the results of multiple comparison experiments show that the proposed method can effectively achieve the accurate quality prediction of the target domain with unlabelled labels and different distributions. Compared with the traditional methods, the proposed method has improved by 8.34%, 7.14%, and 9.09%, respectively, in MAE, RMSE, and score on average.

Productivity Prediction Model of Tight Oil Reservoir Based on Particle Swarm Optimization–Back Propagation Neural Network

Single-well productivity is a crucial metric for assessing the effectiveness of petroleum reservoir development. The accurate prediction of productivity is essential for achieving the efficient and economical development of oil–gas reservoirs. Traditional productivity prediction methods (empirical formulae and numerical simulation) are limited to specific reservoir types. There are few influencing factors, and a large number of ideal assumptions are made for the assumed conditions when predicting productivity. The application scenario is ideal. However, in tight oil reservoirs, numerous factors affect productivity, and their interactions exhibit significant complexity. Continuing to use traditional reservoir productivity prediction methods may result in significant calculation errors and lead to economic losses in oilfield development. To enhance the accuracy of tight reservoir productivity predictions and achieve economical and efficient development, this paper investigates the tight reservoir in the WZ block of the Beibuwan area, considering the impact of geological and engineering factors on productivity; the random forest tree and Spearman correlation coefficient are used to analyze the main influencing factors of productivity. The back propagation neural network optimized by particle swarm optimization was employed to develop a productivity prediction model (PSO-BP model) for offshore deep and ultra-deep tight reservoirs. The actual test well data of the oilfield are substituted into this model. The analysis results of the example application yielded an RMSE of 0.032, an MAE of 1.209, and an R2 value of 0.919. Compared with traditional productivity prediction methods, this study concludes that the model is both reasonable and practical. The calculation speed is faster and the calculation result is more accurate, which can greatly reduce productivity errors. The model constructed in this paper is well suited for predicting the productivity of tight reservoirs within the WZ block. It offers substantial guidance for predicting the productivity of similar reservoirs and supports the economical and efficient development of petroleum reservoirs.

Random projection ensemble conformal prediction for high-dimensional classification

Random projection ensemble conformal prediction for high-dimensional classification

Implementing machine learning techniques for customer retention and churn prediction in telecommunications

This review paper explores the application of machine learning techniques in predicting customer churn and enhancing customer retention within the telecommunications industry. The paper begins by discussing the significance of customer churn, its causes, and the limitations of traditional churn prediction methods. It then delves into machine learning algorithms, including decision trees, support vector machines, and ensemble methods. It highlights their effectiveness in handling large and complex datasets typical of the telecom sector. The discussion extends to the challenges faced in data quality, model selection, implementation, and ethical considerations in using customer data for predictive analytics. The paper also compares machine learning models with traditional methods, emphasizing the advantages of scalability, accuracy, and real-time processing. Furthermore, it identifies potential innovations, such as improved data integration, interpretable models, and personalized retention strategies. Finally, the paper reflects on future trends, predicting the growing role of AI and machine learning in telecommunications, particularly in customer service automation and network optimization. The review underscores the importance of adopting machine learning to reduce churn and improve customer retention while considering the field's ethical implications and future opportunities. Keywords: Customer Churn Prediction, Machine Learning, Telecommunications, Customer Retention, Predictive Analytics, AI in Telecom

Droplet volume prediction methods in electrohydrodynamic jet printing based on multi-source data fusion

Droplet volume prediction methods in electrohydrodynamic jet printing based on multi-source data fusion