关键词： Metal matrix composites   Powder metallurgy   Wear   ANOVA   Machine learning methods  

摘要： In this study, 7075 - Al2O3 (5 wt%) composites with a particle size of 0.3 mu m, 2 mu m, and 15 mu m were developed by hot pressing. The dry sliding wear performance of the specimens was evaluated under loads of 5 N, 10 N, 20 N, 30 N, and at sliding speeds of 80 mm/s, 110 mm/s, 140 mm/s by reciprocating wear tests. The wear tests showed that 7075 5 - Al2O3 (15 mu m) exhibited the best wear performance. The volume loss of 7075 5 - Al2O3 (15 mu m) under load of 30 N for sliding speed of 140 mm/s was 37.1% lower than the unreinforced 7075 alloy. The volume loss (mm(3)) of composites reinforced with the particle size of 0.3 mu m, 2 mu m, and 15 mu m was 11.62, 9.87, and 8.07, respectively, for load of 30 N and sliding speed of 140 mm/s. An increase in the applied load and sliding speed increased the wear severity by changing the wear mechanism from abrasion to delamination. The analysis of variance (ANOVA) showed that the load was the most significant parameter on the volume loss. The linear regression (LR), support vector regression (SVR), artificial neural network (ANN), and extreme learning machine (ELM) were used for the prediction of volume loss. The determination coefficient (R-2) of the LR, SVR, ANN, and ELM was 0.814, 0.976, 0.935, and 0.989, respectively. The ELM model has the highest success. Thus, the ELM model has significant potential for the prediction of wear behaviour for Al matrix composites. (c) 2020 The Society of Powder Technology Japan. Published by Elsevier B.V. and The Society of Powder Technology Japan. All rights reserved.

关键词： Beam-column joints   Prediction model   Failure mode   Machine learning method   SHAP value  

摘要： Beam-column joints are important components that control the performance of reinforced concrete frame structures under seismic loads. Beam-column joint failures may induce partial or overall collapses of the structures. Brittle failure is joint shear failure before beam yielding, and ductile failure is joint shear failure after beam yielding or beam yielding without joint failure. In this study, based on the collected 580 test data of interior beam-column joints, nine features were constructed to reflect the characteristics of the joints' design parameters. Twelve machine learning methods are applied to predict failure modes of beam-column joints. After comparing the prediction performance and comparing the results from four design codes, the prediction model provided by the XGBoost algorithm is recommended in this study for its excellent classification results of the failure modes of beam-column joints. Moreover, the SHAP method was used to explain the features' effects in the prediction models. Accordingly, the interior beam-column joints' failure mode can be accurately predicted, and the suggestions for changing the failure mode from brittle failure to ductility failure can be offered for the beam-column joints.

关键词： predictive modeling   machine learning models   water demand prediction   Beijing-Tianjin-Hebei Region  

摘要： Predicting water demand helps decision-makers allocate regional water resources efficiently, thereby preventing water waste and shortage. The aim of this study is to predict water demand in the Beijing-Tianjin-Hebei region of North China. The explanatory variables associated with economy, community, water use, and resource availability were identified. Eleven statistical and machine learning models were built, which used data covering the 2004-2019 period. Interpolation and extrapolation scenarios were conducted to find the most suitable predictive model. The results suggest that the gradient boosting decision tree (GBDT) model demonstrates the best prediction performance in the two scenarios. The model was further tested for three other regions in China, and its robustness was validated. The water demand in 2020-2021 was provided. The results show that the identified explanatory variables were effective in water demand prediction. The machine learning models outperformed the statistical models, with the ensemble models being superior to the single predictor models. The best predictive model can also be applied to other regions to help forecast water demand to ensure sustainable water resource management.

关键词： acoustic sensor   acoustic event detection   corpora   feature extraction   machine learning  

摘要： Acoustic event detection and analysis has been widely developed in the last few years for its valuable application in monitoring elderly or dependant people, for surveillance issues, for multimedia retrieval, or even for biodiversity metrics in natural environments. For this purpose, sound source identification is a key issue to give a smart technological answer to all the aforementioned applications. Diverse types of sounds and variate environments, together with a number of challenges in terms of application, widen the choice of artificial intelligence algorithm proposal. This paper presents a comparative study on combining several feature extraction algorithms (Mel Frequency Cepstrum Coefficients (MFCC), Gammatone Cepstrum Coefficients (GTCC), and Narrow Band (NB)) with a group of machine learning algorithms (k-Nearest Neighbor (kNN), Neural Networks (NN), and Gaussian Mixture Model (GMM)), tested over five different acoustic environments. This work has the goal of detailing a best practice method and evaluate the reliability of this general-purpose algorithm for all the classes. Preliminary results show that most of the combinations of feature extraction and machine learning present acceptable results in most of the described corpora. Nevertheless, there is a combination that outperforms the others: the use of GTCC together with kNN, and its results are further analyzed for all the corpora.

关键词： Machine learning   Market basket analysis   Factor analysis   Topic models   Restricted Boltzmann machine   Deep learning  

摘要： We compare several unsupervised probabilistic machine learning methods for market basket analysis, namely binary factor analysis, two topic models (latent Dirichlet allocation and the correlated topic model), the restricted Boltzmann machine and the deep belief net. After an overview of previous applications of unsupervised probabilistic machine learning methods to market basket analysis we shortly present the methods which we investigate and outline their estimation. Performance is measured by tenfold cross-validated log likelihood values. Binary factor analysis vastly outperforms topic models. The restricted Boltzmann machine attains a similar performance advantage over binary factor analysis. Overall, a deep belief net with 45 variables in the first and 15 variables in the second hidden layers turns out to be the best model. We also compare the investigated machine learning methods with respect to ease of interpretation and runtimes. In addition, we show how to interpret the relationships between hidden variables and observed category purchases. To demonstrate managerial implications we estimate the effect of promoting each category both on purchase probability increases of other product categories and the relative increase of basket size. Finally, we indicate several possibilities to extend restricted Boltzmann machines and deep belief nets for market basket analysis.

关键词： Indoor air   PM2.5   Households   Prediction model   Random forest  

摘要： People typically spend most of their time indoors. It is of importance to establish prediction models to estimate PM2.5 concentration in indoor environments (e.g., residential households) to allow accurate assessments of exposure in epidemiological studies. This study aimed to develop models to predict PM2.5 concentration in residential households. PM2.5 concentration and related parameters (e.g., basic information about the households and ventilation settings) were collected in 116 households during the winter and summer seasons in Hong Kong. Outdoor PM2.5 concentration at households was estimated using a land-use regression model. The random forest machine learning algorithm was then applied to develop indoor PM2.5 prediction models. The results show that the random forest model achieved a promising predictive accuracy, with R-2 and cross-validation R-2 values of 0.93 and 0.65, respectively. Outdoor PM2.5 concentration was the most important predictor variable, followed in descending order by the household marked number, outdoor temperature, outdoor relative humidity, average household area and air conditioning. The external validation result using an independent dataset confirmed the potential application of the random forest model, with an R-2 value of 0.47. Overall, this study shows the value of a combined land-use regression and machine learning approach in establishing indoor PM2.5 prediction models that provide a relatively accurate assessment of exposure for use in epidemiological studies. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： machine learning   pacemaker implantation   prediction   random forest   TAVR  

摘要： Background An accurate assessment of permanent pacemaker implantation (PPI) risk following transcatheter aortic valve replacement (TAVR) is important for clinical decision making. The aims of this study were to investigate the significance and utility of pre- and post-TAVR ECG data and compare machine learning approaches with traditional logistic regression in predicting pacemaker risk following TAVR. Methods Five hundred fifity seven patients in sinus rhythm undergoing TAVR for severe aortic stenosis (AS) were included in the analysis. Baseline demographics, clinical, pre-TAVR ECG, post-TAVR data, post-TAVR ECGs (24 h following TAVR and before PPI), and echocardiographic data were recorded. A Random Forest (RF) algorithm and logistic regression were used to train models for assessing the likelihood of PPI following TAVR. Results Average age was 80 +/- 9 years, with 52% male. PPI after TAVR occurred in 95 patients (17.1%). The optimal cutoff of delta PR (difference between post and pre TAVR PR intervals) to predict PPI was 20 ms with a sensitivity of 0.82, a specificity of 0.66. With regard to delta QRS, the optimal cutoff was 13 ms with a sensitivity of 0.68 and a specificity of 0.59. The RF model that incorporated post-TAVR ECG data (AUC 0.81) more accurately predicted PPI risk compared to the RF model without post-TAVR ECG data (AUC 0.72). Moreover, the RF model performed better than logistic regression model in predicting PPI risk (AUC: 0.81 vs. 0.69). Conclusions Machine learning using RF methodology is significantly more powerful than traditional logistic regression in predicting PPI risk following TAVR.

关键词： Temperature distribution  

摘要： The pattern formation and spatial-temporal chaos are interesting issues in nonlinear dynamics. A novel model based on machine learning methods is designed to learn and imitate the pattern evolution in Benard-Marangoni convection (BM convection). There is a supercritical process, which is an inevitable and unique experimental phenomenon, on the way to chaos in BM convection. A single layer of fluid uniformly heated at the bottom is used as the experimental system. During the experiment, the temperature difference between top and bottom of the liquid layer is increased first to make the system enter the supercritical convection state and then decreased after a while;surface temperature distribution of the liquid layer is measured in real time with an infrared thermal imager, which visualized the formation and re-organization of cellular convection during the supercritical state. The temperature data are used as the material that meets the conditions of machine learning and then the machine learning method in charge of predicting the picture of temperature distribution that it never has seen before in two steps. The experimental data are used to train an auto-encoder model based on convolutional neural networks and an RNN-CNN joint model, in which the former is used for extracting low-dimensional features of the temperature field, and the latter is used for predicting evolution results of the low-dimensional features and recovering them back to the temperature field. The models have finally achieved the objectives of supplementing the missing experimental data and correcting actual experimental data by comparing the actual experimental results with the prediction results of the machine learning approach and theoretical analysis results. On the other hand, active exploration has been undertaken in predicting physical experimental results that have never happened before.

关键词： artificial neural network   fertility traits   genomic selection   random forest   support vector regression  

摘要： This study aimed to assess the predictive ability of different machine learning (ML) methods for genomic prediction of reproductive traits in Nellore cattle. The studied traits were age at first calving (AFC), scrotal circumference (SC), early pregnancy (EP) and stayability (STAY). The numbers of genotyped animals and SNP markers available were 2342 and 321 419 (AFC), 4671 and 309 486 (SC), 2681 and 319 619 (STAY) and 3356 and 319 108 (EP). Predictive ability of support vector regression (SVR), Bayesian regularized artificial neural network (BRANN) and random forest (RF) were compared with results obtained using parametric models (genomic best linear unbiased predictor, GBLUP, and Bayesian least absolute shrinkage and selection operator, BLASSO). A 5-fold cross-validation strategy was performed and the average prediction accuracy (ACC) and mean squared errors (MSE) were computed. The ACC was defined as the linear correlation between predicted and observed breeding values for categorical traits (EP and STAY) and as the correlation between predicted and observed adjusted phenotypes divided by the square root of the estimated heritability for continuous traits (AFC and SC). The average ACC varied from low to moderate depending on the trait and model under consideration, ranging between 0.56 and 0.63 (AFC), 0.27 and 0.36 (SC), 0.57 and 0.67 (EP), and 0.52 and 0.62 (STAY). SVR provided slightly better accuracies than the parametric models for all traits, increasing the prediction accuracy for AFC to around 6.3 and 4.8% compared with GBLUP and BLASSO respectively. Likewise, there was an increase of 8.3% for SC, 4.5% for EP and 4.8% for STAY, comparing SVR with both GBLUP and BLASSO. In contrast, the RF and BRANN did not present competitive predictive ability compared with the parametric models. The results indicate that SVR is a suitable method for genome-enabled prediction of reproductive traits in Nellore cattle. Further, the optimal kernel bandwidth parameter in the SV

关键词： Medical imaging   Retinal vessels   Segmentation   Machine learning   Deep learning   Review  

摘要： The eye affords a unique opportunity to inspect a rich part of the human microvasculature non-invasively via retinal imaging. Retinal blood vessel segmentation and classification are prime steps for the diagnosis and risk assessment of microvascular and systemic diseases. A high volume of techniques based on deep learning have been published in recent years. In this context, we review 158 papers published between 2012 and 2020, focussing on methods based on machine and deep learning (DL) for automatic vessel segmentation and classification for fundus camera images. We divide the methods into various classes by task (segmentation or artery-vein classification), technique (supervised or unsupervised, deep and non-deep learning, hand-crafted methods) and more specific algorithms (e.g. multiscale, morphology). We discuss advantages and limitations, and include tables summarising results at-a-glance. Finally, we attempt to assess the quantitative merit of DL methods in terms of accuracy improvement compared to other methods. The results allow us to offer our views on the outlook for vessel segmentation and classification for fundus camera images. (c) 2020 Elsevier B.V. All rights reserved.