Machine Learning Methods For Prediction Research Articles

Designing and modeling of a new MSMA vibration energy transducer

The conversion of mechanical vibrational energy into electrical energy to power wireless electronic devices using the smart material magnetic shape memory alloy (MSMA) has garnered substantial attention. This paper presents a vibration energy transducer founded on the inverse effect of MSMA, elucidating the principle of power generation. The variations in martensite and magnetic domain characteristics within MSMA were analyzed, and a constitutive model was established for the MSMA vibration energy transducer, integrating the thermodynamic theory of the Gibbs free energy function. Although this model performs well in predicting experimental outcomes, it falls short in capturing all features of the experimental data. To comprehensively encompass these features, the PSO-XGBoost machine learning approach was introduced to train the experimental data by incorporating factors such as stress, magnetic field, and induced voltage. An experimental prototype of the MSMA vibration energy transducer is fabricated, and the predictions of both models are compared with the collected experimental data, validating the accuracy of the model and indicating the enhanced effectiveness of machine learning methods in prediction. This research not only validates the correctness of the models but also emphasizes the potential for more precise predictions using machine learning methods, thereby establishing a robust foundation for the thorough study and broader application of MSMA vibration energy transducers.

The application of machine learning methods for prediction of heavy metal by activated carbons, biochars, and carbon nanotubes

Carbonaceous materials are commonly used as adsorbents for heavy metals. The determination of the adsorption capacity needs time and energy, and the key factors affecting the adsorption capacity have not been determined. Therefore, a new and efficient method is needed to predict the adsorption capacity and explore the decisive factors in the adsorption process. In this study, three tree-based machine learning models (i.e., random forest, gradient boosting decision tree, and extreme gradient boosting) were developed to predict the adsorption capacity of eight heavy metals (i.e., As, Cd, Cr, Cu, Hg, Ni, Pb, and Zn) on activated carbons, biochars, and carbon nanotubes using 3674 data points extracted from 151 journal articles. After a comprehensive comparison, the gradient boosting decision tree had the best performance for a combined model based on all data (R2 = 0.9707, RMSE = 0.1420). Moreover, independent models were developed for three datasets classified by the adsorbent and eight datasets classified by the heavy metals. In addition, a graphical user interface was built to predict the adsorption capacity of heavy metals. This study provides a novel strategy and convenient tool for the removal of heavy metals and can help to improve the removal efficiency of heavy metals to build a healthier world.

A fusion gas load prediction model with three-way residual error amendment

Accurately predicting gas load is crucial for optimal planning and scheduling of natural gas production. Existing machine learning or deep learning-based prediction methods primarily aim to improve accuracy. However, these methods face challenges such as overlapped features, significant background noise, and residual errors. In response to these challenges, we proposed a fusion prediction model, known as the Double Temporal Convolutional Network (TCN) and Light Gradient Boosting Machine (LightGBM) with Three-way Residual Error Amendment (DT-LGBM-3WREA). To address the overlapped feature issue in time series data, we utilize the STL module for data decomposition. To handle background noise, the network incorporates a double TCN module specifically designed for trend and seasonal components. Thus, it can better avoid the transmission of noise between modules. To address residual error, we introduce three-way decision methodology and develop the 3WREA module, which aims to avoid local optima and random factors from perturbing the prediction accuracy. This approach mitigates the influence of remainder item on overall prediction performance. Experimental results demonstrate that the DT-LGBM-3WREA model excels in gas load prediction scenarios, surpassing state-of-the-art methods.

A joint multi-model machine learning prediction approach based on confidence for ship stability

Since the traditional ship stability failure probability assessment method has many input parameters and cumbersome intermediate calculation process, this paper proposes a joint multi-model machine learning prediction method based on confidence. The method calculates the confidence of each machine learning model for the current prediction result, selects the top n models among them, and takes the average of their prediction results as the output. The confidence is calculated by a method inspired by semi-supervised learning. To reduce the number of ship features that need to be input for assessment, a sensitivity analysis is used to reject irrelevant features. Eight machine learning models that have good performance and are widely used in other fields, including Radial Basis Function Neural Network, Random Forest, eXtreme Gradient Boosting, and so on, are used as component learners in this study. The hyperparameters of each model are obtained by cross-validation and grid search. The advancedness of the proposed method is verified by comparing it with other models on a small self-built ship stability failure probability dataset. By conducting experiments that simply average the results of the component learners, it is confirmed that simple superposition different models does not necessarily improve the accuracy. At the same time, after pre-processing the input features in different ways, the comparison of the prediction performance was conducted, and the experimental results showed that the proposed method is not affected by the way the input features are preprocessed and therefore has some robustness.

An initial investigation into the use of machine learning methods for prediction of carcass component yields in F2 broiler chickens

Context As evaluation of carcass components is costly and time consuming, models for prediction of broiler carcass components are useful. Aims The aim was to investigate the feasibility of machine learning methods in the prediction of carcass components from measurements on live birds during the rearing period. Methods Three machine learning methods, including regression tree, random forest and gradient-boosting trees, were applied to predict carcass yields, and benchmarked against classical linear regression. Two scenarios were defined for prediction. In the first scenario, carcass yields were predicted by live bodyweight, shank length and shank diameter features, recorded at 2, 3 and 4 weeks of age. In the second scenario, predictor features recorded at 5, 6 and 7 weeks of age were used. The two scenarios were reanalysed by including effective single-nucleotide polymorphisms associated with bodyweight, shank length and shank diameter as new predictor features. Key results The correlation coefficient between predicted and observed values for predicting weight of carcass traits ranged from 0.50 for wing to 0.59 for thigh in the first scenario, and from 0.63 for wing to 0.74 for carcass in the second scenario. These predictions for the percentage of carcass components ranged from 0.30 for wing to 0.39 for carcass and breast in the first scenario, and from 0.34 for thigh to 0.43 for carcass in the second scenario when random forest was used. Conclusions Predictive accuracy in the first scenario was lower than in the second scenario for all prediction methods. Including single-nucleotide polymorphisms as predictor features in either scenario did not increase the accuracy of the prediction. Implications In general, random forest had the best performance among machine learning methods, and classical linear regression in two scenarios, suggesting that it may be considered as an alternative to conventional linear models for prediction of carcass traits in broiler chickens.

FRP-XGBoost: Identification of ferroptosis-related proteins based on multi-view features

Ferroptosis represents a novel form of programmed cell death. Pan-cancer bioinformatics analysis indicates that identifying and modulating ferroptosis offer innovative approaches for preventing and treating diverse tumor pathologies. However, the precise detection of ferroptosis-related proteins via conventional wet-laboratory techniques remains a formidable challenge, largely due to the constraints of existing methodologies. These traditional approaches are not only labor-intensive but also financially burdensome. Consequently, there is an imperative need for the development of more sophisticated and efficient computational tools to facilitate the detection of these proteins. In this paper, we presented a XGBoost and multi-view features-based machine learning prediction method for predicting ferroptosis-related proteins, which was referred to as FRP-XGBoost. In this study, we explored four types of protein feature extraction methods and evaluated their effectiveness in predicting ferroptosis-related proteins using six of the most commonly used traditional classifiers. To enhance the representational power of the hybrid features, we employed a two-step feature selection technique to identify the optimal subset of features. Subsequently, we constructed a prediction model using the XGBoost algorithm. The FRP-XGBoost achieved an accuracy of 96.74 % in 10-fold cross-validation and a further accuracy of 91.52 % in an independent test. The implementation source code of FRP-XGBoost is available at https://github.com/linli5417/FRP-XGBoost.

Comparison of different machine learning methods for prediction of ultrasonic pulse velocity

Deneysel sonuçlardan elde edilen basınç dayanımı sonuçlarına bağlı olarak ultrases dalgası hızı sonuçlarının tahmin edilmesi amacıyla, farklı oranlarda mineral katkı içeren on iki (12) farklı çimento harcı üretilmiştir. Üretilen harç numunelerinin 1, 3, 7, 28 ve 90 günlük kür yaşları için hem basınç dayanımı hem de ultrases dalgası hızı sonuçları deneysel olarak elde edilmiştir. Farklı kür koşulları için harç numunelerinden elde edilen basınç dayanımı deneysel verileri Aşırı Öğrenme Makinesi, Destek Vektör Makinesi ve Grup Veri İşleme Yöntemi olmak üzere üç farklı regresyon yöntemi kullanılarak ultrases dalgası hızı değerlerinin tahmininde kullanılmıştır. Regresyon yöntemlerinin uygulanmasında iki farklı yaklaşım izlenmiştir. İlk yaklaşımda, farklı kür yaşları için ultrases dalgası hızı sonuçları, basınç dayanımı değerleri göz ardı edilerek tahmin edilmiştir. Diğer yaklaşımda ise ultrases dalgası hızı sonuçlarını tahmin etmek için basınç dayanımı değerleri dikkate alınmıştır. Böylece hem basınç dayanımı hem de ultrases dalgası hızı değerleri ile regresyon modelleri ile elde edilen başarı sonuçları arasındaki ilişki belirlenip, karşılaştırılmıştır. Bu çalışmada, Yöntem 1'deki Grup Veri İşleme Yöntemi modeli ile en iyi test performansları (yani R2 ve MSE için) sırasıyla 0.856 ve 0.037; Yöntem 2'de ise Grup Veri İşleme Yöntemi modeli ile en iyi test performansları sırasıyla 0.977 ve 0.003 olarak bulunmuştur. Elde edilen sonuçlar dikkate alındığında, ultrases dalgası hızı değerleri seçilen regresyon modelleri ile yüksek başarı oranlarıyla elde edilmiştir.

Machine learning based biomarker discovery for chronic kidney disease-mineral and bone disorder (CKD-MBD).

Chronic kidney disease-mineral and bone disorder (CKD-MBD) is characterized by bone abnormalities, vascular calcification, and some other complications. Although there are diagnostic criteria for CKD-MBD, in situations when conducting target feature examining are unavailable, there is a need to investigate and discover alternative biochemical criteria that are easy to obtain. Moreover, studying the correlations between the newly discovered biomarkers and the existing ones may provide insights into the underlying molecular mechanisms of CKD-MBD. We collected a cohort of 116 individuals, consisting of three subtypes of CKD-MBD: calcium abnormality, phosphorus abnormality, and PTH abnormality. To identify the best biomarker panel for discrimination, we conducted six machine learning prediction methods and employed a sequential forward feature selection approach for each subtype. Additionally, we collected a separate prospective cohort of 114 samples to validate the discriminative power of the trained prediction models. Using machine learning under cross validation setting, the feature selection method selected a concise biomarker panel for each CKD-MBD subtype as well as for the general one. Using the consensus of these features, best area under ROC curve reached up to 0.95 for the training dataset and 0.74 for the perspective dataset, respectively. For the first time, we utilized machine learning methods to analyze biochemical criteria associated with CKD-MBD. Our aim was to identify alternative biomarkers that could serve not only as early detection indicators for CKD-MBD, but also as potential candidates for studying the underlying molecular mechanisms of the condition.

Advanced Machine Learning Methods for Prediction of Blast-Induced Flyrock Using Hybrid SVR Methods

Advanced Machine Learning Methods for Prediction of Blast-Induced Flyrock Using Hybrid SVR Methods

Machine learning for prediction of transcatheter mitral valve repair outcomes: A systematic review

BackgroundTranscatheter mitral valve repair (TMVR) has evolved as a minimally invasive alternative to traditional mitral valve surgery. Meanwhile, machine learning (ML) offers a promising tool for TMVR risk stratification due to the lack of established risk scores specifically tailored for TMVR patients. To address the absence of consensus on its efficacy, we conducted a systematic review of primary studies that have utilized ML to predict the success of TMVR. MethodsEmbase, MEDLINE, Scopus, Web of Science, PubMed, Google Scholar, and the Cochrane Library were systematically searched from inception through April 2024. We included primary studies that used TMVR as the sole interventional technique for adult MR patients. These studies also had to employ at least one ML model to predict the success of TMVR. Results244 publications were screened, with seven eventually included in this review. Two studies employed clustering techniques, two utilized extreme gradient boosting, and three used multiple ML algorithms to predict TMVR outcomes. Of the four studies that compared the accuracy of ML with traditional regression models, all four demonstrated higher accuracy with ML, and this difference was statistically significant in three of the four studies. ConclusionsTo our knowledge, we conducted the first systematic review of ML methods for prediction of TMVR success in MR treatment. ML outperformed established risk scores, demonstrating promising potential in interventional cardiology. Future ML models, trained on larger patient datasets, may further improve predictive accuracy, and enhance risk stratification in this population.

ACCURATE PREDICTION OF DRILL BIT PENETRATION RATE IN ROCK USING SUPERVISED MACHINE LEARNING TECHNIQUES BASE ON LABORATORY TEST DATA

Knowing the rate of penetration of a drill bit in rocks is among the most important parameters in their behaviour measurement. However, the direct measurement of ROP in rocks is a high-cost and time-intensive process. Therefore, obtaining the ROP parameter through a method other than direct measurement can be very useful and effective. Predictive machine learning methods are among the strong and precise techniques for the indirect measurement of ROP. To this end, 492 samples were tested under different UCS, µ, WOB, and ω conditions to obtain the corresponding ROP. To achieve an accurate model, three methods of linear regression analysis, lasso regression, and ridge regression were compared in terms of prediction accuracy. These models were compared through performance criteria of the prediction process and error-based charts. The performance criteria were measured using three measures: mean absolute percentage error, D-squared pinball score, and mean Poisson deviance error. For the MAPE index, the Lasso and Ridge models performed the best with values of 0.2557. Concerning the D2PS index, the linear regression model and Ridge performed better with values of 0.4083 and 0.4025, respectively. Finally, for the MPDE index, the Ridge model provided a more accurate performance with a value of 0.0105. For a better comparison, an objective function was created and calculated by combining these three indicators. The results showed the best rank for the Ridge model with an estimated value of 659.475. Finally, it was concluded that the Ridge model is a reliable and accurate model for predicting the ROP.

Comparison between multiple logistic regression and machine learning methods in prediction of abnormal thallium scans in type 2 diabetes

Comparison between multiple logistic regression and machine learning methods in prediction of abnormal thallium scans in type 2 diabetes

Predicting risk of obesity in overweight adults using interpretable machine learning algorithms.

To screen for predictive obesity factors in overweight populations using an optimal and interpretable machine learning algorithm. This cross-sectional study was conducted between June 2011 and January 2012. The participants were randomly selected using a simple random sampling technique. Seven commonly used machine learning methods were employed to construct obesity risk prediction models. A total of 5,236 Chinese participants from Ningde City, Fujian Province, Southeast China, participated in this study. The best model was selected through appropriate verification and validation and suitably explained. Subsequently, a minimal set of significant predictors was identified. The Shapley additive explanation force plot was used to illustrate the model at the individual level. Machine learning models for predicting obesity have demonstrated strong performance, with CatBoost emerging as the most effective in both model validity and net clinical benefit. Specifically, the CatBoost algorithm yielded the highest scores, registering 0.91 in the training set and an impressive 0.83 in the test set. This was further corroborated by the area under the curve (AUC) metrics, where CatBoost achieved 0.95 for the training set and 0.87 for the test set. In a rigorous five-fold cross-validation, the AUC for the CatBoost model ranged between 0.84 and 0.91, with an average AUC of ROC at 0.87 ± 0.022. Key predictors identified within these models included waist circumference, hip circumference, female gender, and systolic blood pressure. CatBoost may be the best machine learning method for prediction. Combining Shapley's additive explanation and machine learning methods can be effective in identifying disease risk factors for prevention and control.

Prediction of stock price leveraging Arima model

In today`s world, more and more machine learning methods and prediction methods have been proposed. There are also lots of investors who choose the more difficult and complex models to use as technical analysis tools to predict stock prices. However, Rome wasn't built in a day. So, it`s necessary to learn the traditional models penetratingly. To have a more thorough understanding of classic models in the past, this paper provides a great way to analyze the ARIMA model. It explains the methods of fitting the ARIMA model step by step and improves the ARIMA model by adding seasonal parameters to fit the SARIMA model, enabling readers to better understand the advantages and disadvantages of this model. Although the results of the ARIMA model are unfortunately similar, and difficult to demonstrate its predictive power in images, the SARIMA model presents a trend prediction that conforms to people's imagine. As of today, the change in the price of Netflix's stock has been visible, which is different from the predicted price. Therefore, while making technical predictions, investors also need to combine fundamental analyses like the supply and demand balance, changes in interest rates, government regulations, macroeconomic indicators, and unique features of the industry in question, among others. Rather than relying solely on a model.

A machine learning method for prediction of remaining useful life of supercapacitors with multi-stage modification

Stable and accurate prediction of the remaining useful life (RUL) of supercapacitors is of great significance for the safe operation and economic maximization of the energy storage system based on supercapacitors. For the phenomenon of unstable discharge capacity of supercapacitor during the cycling, a multi-stage (MS) prediction model based on empirical mode decomposition (EMD) and gated recurrent unit (GRU) neural network is proposed. The prediction model is based on multi-feature inputs with high correlation, and the final output is obtained through EMD reconstruction. The modification process ensures the stability of the model to predict the discharge capacity during the cycling of the supercapacitor. Compared with the traditional seven prediction models, the root mean square error is reduced by 80 %, and the goodness of fit is increased by 6 %. Our method has higher stability and prediction accuracy, while satisfying the high compatibility between the features and models, and provides a feasible strategy for the application of supercapacitors in energy storage systems.

Evaluation of various machine learning prediction methods for particulate matter $$PM_{10}$$ in Kuwait

Evaluation of various machine learning prediction methods for particulate matter $$PM_{10}$$ in Kuwait

Integrated MOVES model and machine learning method for prediction of CO2 and NO from light-duty gasoline vehicle

With rapid urbanization and industrialization, the number of light-duty gasoline vehicles (LDGVs) in China has continued to grow rapidly, leading to a significant increase in traffic pollution. Therefore, it is essential to accurately calculate the emission of LDGVs for air quality monitoring and management. Fortunately, Motor Vehicle Emission Simulator (MOVES) is a sophisticated model for estimating mobile source emissions with good prediction accuracy. However, the parameters of MOVES are based on the field tests in the US, which is worth exploring whether MOVES can be applied to other countries. Hence, in this paper, we used the portable emission measurement system (PEMS) to conduct real driving emission (RDE) tests of LDGVs, aiming to explore the possibility of the MOVES application in China. Based on the field tests, we modified basic parameters in the MOVES model, but unsatisfactory prediction performance was obtained. Existing research on improving MOVES performance mainly involved new binning of operating modes, but these methods had limited improvements. Though studies have also used machine learning methods for predicting LDGV emissions, they lacked comparison and integration with the MOVES model. To further improve the prediction accuracy, we proposed a novel road vehicle emission model that integrated the machine learning method and the MOVES to predict the road-level emission rates of NO and CO2 emissions of LDGVs. In addition, we employed the Boruta algorithm to capture the key influencing factors and promote prediction performance. The enhanced model outperformed MOVES and achieved higher R2 values. On average, the improvement for CO2 was 0.132, and for NO, it was 0.261. This work will provide references for MOVES improvements in practical scenarios and better predict pollutant emissions for LDGVs using limited resources of field tests in cities outside the US.

Condition Monitoring Method for the Gearboxes of Offshore Wind Turbines Based on Oil Temperature Prediction

Traditional machine learning prediction methods usually only predict input parameters through a single model, so the problem of low prediction accuracy is common. Different predictive models extract different information for input, and combining different predictive models can make as much use as possible of all the information contained in the inputs. Therefore, this paper improves the existing oil temperature prediction method of offshore wind turbine gearboxes, and for the actual prediction effect of Supervisory Control And Data Acquisition (SCADA) data in this paper, Bayesian-optimized Light Gradient Boosting Machine (LightGBM) and eXtreme Gradient Boosting(XGBoost) machine learning models are selected to be combined. A method based on the Induced Ordered Weighted Average (IOWA) operator combination prediction model is thus proposed, with simulation results showing that the proposed model improves the accuracy of gearbox condition monitoring. The innovation of this article lies in considering the various negative impacts faced by actual offshore wind turbines and adopting a combination prediction model to improve the accuracy of gearbox condition monitoring.

Shaping the concentration of petroleum hydrocarbon pollution in soil: A machine learning and resistivity-based prediction method

A new method relying on machine learning and resistivity to predict concentrations of petroleum hydrocarbon pollution in soil was proposed as a means of investigation and monitoring. Currently, determining pollutant concentrations in soil is primarily achieved through costly sampling and testing of numerous borehole samples, which carries the risk of further contamination by penetrating the aquifer. Additionally, conventional petroleum hydrocarbon geophysical surveys struggle to establish a correlation between survey results and pollutant concentration. To overcome these limitations, three machine learning models (KNN, RF, and XGBOOST) were combined with the geoelectrical method to predict petroleum hydrocarbon concentrations in the source area. The results demonstrate that the resistivity-based prediction method utilizing machine learning is effective, as validated by R-squared values of 0.91 and 0.94 for the test and validation sets, respectively, and a root mean squared error of 0.19. Furthermore, this study confirmed the feasibility of the approach using actual site data, along with a discussion of its advantages and limitations, establishing it as an inexpensive option to investigate and monitor changes in petroleum hydrocarbon concentration in soil.

HERG agonists pose challenges to web-based machine learning methods for prediction of drug-hERG channel interaction

Pharmacological blockade of the IKr channel (hERG) by diverse drugs in clinical use is associated with the Long QT Syndrome that can lead to life threatening arrhythmia. Various computational tools including machine learning models (MLM) for the prediction of hERG inhibition have been developed to facilitate the throughput screening of drugs in development and optimise thus the prediction of hERG liabilities. The use of MLM relies on large libraries of training compounds for the quantitative structure-activity relationship (QSAR) modelling of hERG inhibition. The focus on inhibition omits potential effects of hERG channel agonist molecules and their associated QT shortening risk. It is instructive, therefore, to consider how known hERG agonists are handled by MLM. Here, two highly developed online computational tools for the prediction of hERG liability, Pred-hERG and HergSPred were probed for their ability to detect hERG activator drug molecules as hERG interactors. In total, 73 hERG blockers were tested with both computational tools giving overall good predictions for hERG blockers with reported IC50s below Pred-hERG and HergSPred cut-off threshold for hERG inhibition. However, for compounds with reported IC50s above this threshold such as disopyramide or sotalol discrepancies were observed. HergSPred identified all 20 hERG agonists selected as interacting with the hERG channel. Further studies are warranted to improve online MLM prediction of hERG related cardiotoxicity, by explicitly taking into account channel agonism as well as inhibition.