Search

Economic growth, air pollution, and forest fires in some states in the United States have increased the concentration of particulate matter with a diameter less than or equal to 2.5 μm (PM2.5). Although previous studies have tried to observe PM2.5 both spatially and temporally using aerosol remote sensing and geostatistical estimation, they were limited in accuracy by coarse resolution. In this paper, the performance of machine learning models on predicting PM2.5 is assessed with linear regression (LR), decision tree (DT), gradient boosting regression (GBR), AdaBoost regression (ABR), XGBoost (XGB), k‐nearest neighbors (K‐NN), long short‐term memory (LSTM), random forest (RF), and support vector machine (SVM) using PM2.5 station data from 2017 to 2021. To compare the accuracy of all the nine machine learning models, the coefficient of determination (R2), root mean square error (RMSE), Nash‐Sutcliffe efficiency (NSE), root mean square error ratio (RSR), and percent bias (PBIAS) were evaluated. Among all nine models, the RF (100 decision trees with a max depth of 20) and support vector regression (SVR; nonlinear kernel, degree 3 polynomial) models were the best for predicting PM2.5 concentrations. Additionally, comparison of the PM2.5 performance metrics displayed that the models had better predictive behavior in the western United States than that in the eastern United States. Key Points: We present the prediction of PM2.5 concentrations over the United States using various machine learning (ML) algorithmsWe show ML as a new approach for analyzing large data sets due to the computational speed and easy implementation for massive amounts of dataThe study is important for improving our understanding of the differences among ML algorithms for Earth Science research [ABSTRACT FROM AUTHOR]

A phoneme is perceptually the smallest distinct sound unit distinguished among words in a particular language. Every language has its own set of phonemes, and all the words are ordered sequences of phonemes. Therefore, phoneme recognition is essential to automatic speech recognition (ASR) systems. Phonemes of a language can be classified together using a single machine learning (ML) model through the direct classification (also known as the baseline or flat classification) approach. However, it is observed that the performance of such phoneme recognition degrades with the increase in the number of phoneme classes. The challenge is pronounced in languages with a larger number of phoneme classes, like Hindi, which has 48 phonemes. In this paper, we propose a speaker‐independent hierarchical classification approach for 33 Hindi‐Devanagari consonants/phonemes using cepstral features with ML techniques like support vector machine (SVM), random forest (RF) and fully connected deep neural network (DNN). In this hierarchical approach, a given phoneme is classified into successive subgroups until the particular phoneme class is identified. To perform the classification task, a binary or multi‐class classifier is invoked for each internal (non‐leaf) node in the hierarchy tree. Our model identified pairs of Optimal Feature Sets (based on mutual information) and the best suitable ML classifier for each internal decision node in the hierarchy using 10‐fold cross‐validation to help in efficient classification. Our proposed hierarchical model leads to better accuracy and 57% improved performance for phoneme recognition compared with the non‐hierarchical, that is, the direct classification approach. [ABSTRACT FROM AUTHOR]

Pore structure impacts the capability of seepage pattern of subsurface fluid mineral and mineral exploitation efficiency. Because of the strong heterogeneity in carbonate reservoirs, the pore structure is nonlinearly varying and complex in reservoirs. It is necessary to establish a method for pore structure type (PST) prediction. Machine learning provides an efficient prediction method by finding the relationship between core test data and well‐logging data. In this paper, a reservoir identification method based on Gradient Boost Decision Trees (GBDT) is proposed for the pore structure characteristics of carbonate reservoirs integrating core test and logging data. Core testing data are utilized to form the training set for PST prediction. Then, we adopt the mutual information method to optimize the logging data as the input of the machine learning model. GBDT hyperparameters are optimized using the learning curve to make it have optimal performance. Finally, we compare the predicted result of GBDT with K‐Nearest Neighbor and support vector machines, demonstrating the superior performance of GBDT. The results indicate that the four PS are different in some properties, such as permeability, pore radius and shape of pore and throat. 20%, 10 and 0.15 are recommended as the optimal parameter values for Maximum feature, iteration number and Sub‐sample number to improve GBDT accuracy in carbonate reservoir PST prediction. Evaluation indicators of machine learning, including the Kappa coefficient, Heming distance, Jaccard similarity coefficient and Confusion matrices, indicate that GBDT has better performance. This research proves the high accuracy and applicability of machine learning technology in the carbonate reservoir and also provides a meaningful reference for the identification of the carbonate reservoirs in the central area of Iraq. [ABSTRACT FROM AUTHOR]

Species distribution modeling (SDM) is widely used in ecology and conservation. Currently, the most available data for SDM are species presence‐only records (available through digital databases). There have been many studies comparing the performance of alternative algorithms for modeling presence‐only data. Among these, a 2006 paper from Elith and colleagues has been particularly influential in the field, partly because they used several novel methods (at the time) on a global data set that included independent presence–absence records for model evaluation. Since its publication, some of the algorithms have been further developed and new ones have emerged. In this paper, we explore patterns in predictive performance across methods, by reanalyzing the same data set (225 species from six different regions) using updated modeling knowledge and practices. We apply well‐established methods such as generalized additive models and MaxEnt, alongside others that have received attention more recently, including regularized regressions, point‐process weighted regressions, random forests, XGBoost, support vector machines, and the ensemble modeling framework biomod. All the methods we use include background samples (a sample of environments in the landscape) for model fitting. We explore impacts of using weights on the presence and background points in model fitting. We introduce new ways of evaluating models fitted to these data, using the area under the precision‐recall gain curve, and focusing on the rank of results. We find that the way models are fitted matters. The top method was an ensemble of tuned individual models. In contrast, ensembles built using the biomod framework with default parameters performed no better than single moderate performing models. Similarly, the second top performing method was a random forest parameterized to deal with many background samples (contrasted to relatively few presence records), which substantially outperformed other random forest implementations. We find that, in general, nonparametric techniques with the capability of controlling for model complexity outperformed traditional regression methods, with MaxEnt and boosted regression trees still among the top performing models. All the data and code with working examples are provided to make this study fully reproducible. [ABSTRACT FROM AUTHOR]

It is a long‐term goal in external insulation studies to determine the discharge voltages of complicated engineering gaps by simulation methods. Based on the one‐to‐one correspondence between air gap structure and the static electric field (EF) distribution, this paper characterizes the transmission tower gap configuration by spatial EF features, which were used for machine learning to achieve switching impulse discharge voltage prediction. An interelectrode path and a conical zone between the energized sub‐conductor and the crossarm or the tower window were considered as EF regions strongly associated with gap breakdown, where 73 parameters were extracted to construct a feature set. Taking 15 extra‐high voltage (EHV) transmission tower gaps as training samples, with different gap distances and tower configurations, their EF features were input to a support vector machine (SVM) for model training to establish the relationships with discharge voltages. The trained SVM model was used to predict the impulse discharge voltages of 20 EHV and ultra‐high voltage (UHV) transmission tower gaps. The prediction results with different feature dimensions and various sizes of conical zones were compared to the experimental values, which demonstrate similar variation trends and acceptable errors. This study contributes to realize insulation strength calculation of engineering gaps. [ABSTRACT FROM AUTHOR]

The prevalence of musculoskeletal and neurological diseases such as knee osteoarthritis (KOA) and Parkinson's disease (PD) has grown speedily in recent years. The direct impact of these disorders on a person's gait has evoked many researchers to perform their analysis using gait because of its greater feasibility. In this paper, we proposed a framework to accurately classify abnormal considering KOA and PD and normal (NM) gait using a vision‐based (VB) approach. The aim of this study is four‐fold: firstly, a novel VB gait dataset is created and presented; secondly, the segmentation of the region of interest (ROIs) is performed using an improved technique; thirdly gait parameters, that is, spatiotemporal (SPT), linear kinematic (KNM) and additional body motion features are evaluated using statistical methods; fourthly, the classification of KOA, PD and NM subjects has been done based on artificial intelligence or a machine learning technique (MLT), that is, k‐nearest neighbour (KNN) at three severity levels and a comparison is performed with other methods namely support vector machine (SVM), random forest (RF) and linear regression (LR). The results reveal the relevance of considered gait features in this investigation. For classification purposes, the highest results are obtained by our proposed method in classifying the subjects with severity also, achieving an overall accuracy = 0.9006, sensitivity = 0.8554, specificity = 0.9044, and precision = 0.8966 respectively. This study thus successfully presents KOA, PD, and NM gait classification method based on the MLT which may be beneficial for clinicians to perform early diagnosis of such disorders objectively. [ABSTRACT FROM AUTHOR]

In most data assimilation and numerical weather prediction systems, the Gaussian assumption is prevalent for the behavior of the random variables/errors that are involved. At the Cooperative Institute for Research in the Atmosphere theory has been developed for different forms of variational data assimilation schemes that enables the Gaussian assumption to be relaxed. For certain variable types, a lognormally distributed random variable can be combined in a mixed Gaussian‐lognormal distribution to better capture the interactions of the errors of different distributions. However, assuming that a distribution can change in time, then developing techniques to know when to switch between different versions of the data assimilation schemes becomes very important. By dynamically changing the formulation of the data assimilation system we are able to assimilate observations in a way that reflects the flow‐dependent variability of their distribution. In this paper, we present results with a machine learning technique (the support vector machine) to switch between data assimilation methods based on the detection of a change in the Lorenz 1963 model's z component's probability distribution. Given the machine learning technique's detection/prediction of a change in the distribution, then either a Gaussian or a mixed Gaussian‐lognormal 3DVar based cost function is used to minimize the errors in this period of time. It is shown that switching from a Gaussian 3DVar to a lognormal 3DVar at lognormally distributed parts of the attractor improves the data assimilation analysis error compared to using one distribution type for the entire attractor. Key Points: Machine learning can be used to detect non‐Gaussian distributionsGiven the machine learning detection, we can switch between optimal data assimilation schemesData assimilation can be improved using machine learning techniques [ABSTRACT FROM AUTHOR]

Pandemic novel Coronavirus (Covid‐19) is an infectious disease that primarily spreads by droplets of nose discharge when sneezing and saliva from the mouth when coughing, that had first been reported in Wuhan, China in December 2019. Covid‐19 became a global pandemic, which led to a harmful impact on the world. Many predictive models of Covid‐19 are being proposed by academic researchers around the world to take the foremost decisions and enforce the appropriate control measures. Due to the lack of accurate Covid‐19 records and uncertainty, the standard techniques are being failed to correctly predict the epidemic global effects. To address this issue, we present an Artificial Intelligence (AI)‐based meta‐analysis to predict the trend of epidemic Covid‐19 over the world. The powerful machine learning algorithms namely Naïve Bayes, Support Vector Machine (SVM) and Linear Regression were applied on real time‐series dataset, which holds the global record of confirmed, recovered, deaths and active cases of Covid‐19 outbreak. Statistical analysis has also been conducted to present various facts regarding Covid‐19 observed symptoms, a list of Top‐20 Coronavirus affected countries and a number of coactive cases over the world. Among the three machine learning techniques investigated, Naïve Bayes produced promising results to predict Covid‐19 future trends with less Mean Absolute Error (MAE) and Mean Squared Error (MSE). The less value of MAE and MSE strongly represent the effectiveness of the Naïve Bayes regression technique. Although, the global footprint of this pandemic is still uncertain. This study demonstrates the various trends and future growth of the global pandemic for a proactive response from the citizens and governments of countries. This paper sets the initial benchmark to demonstrate the capability of machine learning for outbreak prediction. [ABSTRACT FROM AUTHOR]

In this paper, we present a hybrid approach for credit scoring, and the classification performance of this approach is compared with 4 base learners in machine learning. A large credit default swap dataset covering the period from 2006 to 2016 is used to build classifiers and test their performances. The results from this empirical study indicate that the bagging ensemble method can substantially improve individual base learners such as decision tree, multilayer perceptron, and k‐nearest neighbours. The performance of support vector machine does not change after applying bagging ensemble. The overall results demonstrate that k‐nearest neighbour is more suitable than any other method when dealing with large unbalanced datasets in credit scoring. [ABSTRACT FROM AUTHOR]

Thyroid hormones are essential for all the metabolic and reproductive activities with significance to growth, and neuron development in the human body. The thyroid hormone dysfunction has many ill consequences, affecting the human population; thereby being a global epidemic. It is noticed that every one in 10 persons suffer from different thyroid disorders in India. In recent years, many researchers have implemented various disease predictive models based on Information and Communications Technology (ICT). Increasing the accuracy of disease classification is a critical and challenging task. To increase the accuracy of classification, in this paper, we propose a hybrid optimization algorithm‐based feature selection design for thyroid disease classifier with rough type‐2 fuzzy support vector machine. This work uses the hybrid optimization algorithm, which combines the firefly algorithm (FA) and butterfly optimization algorithm (BOA) to select the top‐n features. The proposed hybrid firefly butterfly optimization‐rough type‐2 fuzzy support vector machine (HFBO‐RT2FSVM) is evaluated with several key metrics such as specificity, accuracy, and sensitivity. We compare our approach with well‐known benchmark methods such as improved grey wolf optimization linear support vector machine (IGWO Linear SVM) and mixed‐kernel support vector machine (MKSVM) methods. From the experimental evaluations, we justify that our technique improves the accuracy by large thereby precise in identifying the thyroid disease. HFBO‐RT2FSVM model attained an accuracy of 99.28%, having specificity and sensitivity of 98 and 99.2%, respectively. [ABSTRACT FROM AUTHOR]

Marine renewable energy has made significant progress in the last few decades. Even after making substantial progress, the cost of electricity produced by tidal turbines is high. Therefore, the current paper concentrated on reducing the cost of transportation and installation of the turbine by performing a model. Extreme Learning Machine and Support Vector Machines as well as Genetic Programming were applied to predict the performance of the turbine model by creating short‐term, multistep‐ahead prediction models to compute the performance of the H‐rotor vertical axis Folding Tidal turbine. The performance of the turbine was verified by a numerical study using the three‐dimensional approach for the viscous model with the unsteady flow. Statistical evaluation of the outcomes pointed out that advanced Extreme Learning Machine simulation made the assurance in formulating an innovative forecasting strategy for investigating the performances of the tidal turbine. This study shows that the application of the new procedure resulted in confident generality performance and learns faster than orthodox learning algorithms. In conclusion, the assessment indicated that the advanced Extreme Learning Machine simulation was capable as a promising alternative to existing numerical methods for computing the coefficient of performance for turbines. [ABSTRACT FROM AUTHOR]

Aim: To investigate whether activity-monitors and machine learning models could provide accurate information about physical activity performed by children and adolescents with cerebral palsy (CP) who use mobility aids for ambulation.Method: Eleven participants (mean age 11y [SD 3y]; six females, five males) classified in Gross Motor Function Classification System (GMFCS) levels III and IV, completed six physical activity trials wearing a tri-axial accelerometer on the wrist, hip, and thigh. Trials included supine rest, upper-limb task, walking, wheelchair propulsion, and cycling. Three supervised learning algorithms (decision tree, support vector machine [SVM], random forest) were trained on features in the raw-acceleration signal. Model-performance was evaluated using leave-one-subject-out cross-validation accuracy.Results: Cross-validation accuracy for the single-placement models ranged from 59% to 79%, with the best performance achieved by the random forest wrist model (79%). Combining features from two or more accelerometer placements significantly improved classification accuracy. The random forest wrist and hip model achieved an overall accuracy of 92%, while the SVM wrist, hip, and thigh model achieved an overall accuracy of 90%.Interpretation: Models trained on features in the raw-acceleration signal may provide accurate recognition of clinically relevant physical activity behaviours in children and adolescents with CP who use mobility aids for ambulation in a controlled setting.What This Paper Adds: Machine learning may assist clinicians in evaluating the efficacy of surgical and therapy-based interventions. Machine learning may help researchers better understand the short- and long-term benefits of physical activity for children with more severe motor impairments. [ABSTRACT FROM AUTHOR]

In this paper, we propose a machine‐learning‐based approach to automatically detect a satellite oscillator anomaly. A major challenge is to differentiate an oscillator anomaly from ionospheric scintillation. Although both scintillation and oscillator anomalies cause phase disturbances, their underlying physics are different and, therefore, show different carrier‐frequency dependency. By using triple‐frequency signals, distinct features are extracted from the disturbed signals and applied to the radial basis function (RBF) support vector machine (SVM) classifier to identify an oscillator anomaly. The results show that the proposed RBF SVM displays superior performance and outperforms several other classification methods. The proposed approach is applied to an extensive GNSS database to conduct automatic satellite oscillator anomaly detection. Preliminary detection results validate the effectiveness of the proposed method. On average, one‐to‐three satellite oscillator anomaly events are detected daily at each receiver location. [ABSTRACT FROM AUTHOR]

This paper presents a rule-based adaptive protection scheme using machine-learning methodology for microgrids in extensive distribution automation (DA). The uncertain elements in a microgrid are first analysed quantitatively by Pearson correlation coefficients from data mining. Then, a so-called hybrid artificial neural network and support vector machine (ANN-SVM) model is proposed for state recognition in microgrids, which utilises the growing massive data streams in smart grids. Based on the state recognition in the algorithm, adaptive reconfigurations can be implemented with enhanced decision-making to modify the protective settings and the network topology to ensure the reliability of the intelligent operation. The effectiveness of the proposed methods is demonstrated on a microgrid model in Aalborg, Denmark and an IEEE 9 bus model, respectively. [ABSTRACT FROM AUTHOR]

This paper presents a rule‐based adaptive protection scheme using machine‐learning methodology for microgrids in extensive distribution automation (DA). The uncertain elements in a microgrid are first analysed quantitatively by Pearson correlation coefficients from data mining. Then, a so‐called hybrid artificial neural network and support vector machine (ANN‐SVM) model is proposed for state recognition in microgrids, which utilises the growing massive data streams in smart grids. Based on the state recognition in the algorithm, adaptive reconfigurations can be implemented with enhanced decision‐making to modify the protective settings and the network topology to ensure the reliability of the intelligent operation. The effectiveness of the proposed methods is demonstrated on a microgrid model in Aalborg, Denmark and an IEEE 9 bus model, respectively. [ABSTRACT FROM AUTHOR]

Abstract: Data stream is a sequence of data that has unique features. In many data streams, data from one concept is available, and detection of other types of data in data stream is an essential task. One‐class classification is a famous approach to data classification when data from one class is accessible. The principal task of one‐class classification is separating input data in two different parts: target and outlier data. One of the main challenges concerning data classification on the stationary data streams is the response time, which causes negative effects on effective runtime. Most classifiers, that have been proposed on Rd feature space, solve a quadratic problem for classification that leads to extreme runtime increase. In this paper, an incremental one‐class classification on stationary data streams is proposed using two‐quarter sphere (IOCTQ) in order to achieve lower computation cost of classification time, and a linear optimization problem is solved. IOCTQ divides one data classification problem into two data classifiers, and each data point will be individually classified in one‐quarter sphere. The two‐quarter spheres can be run parallel. The results of the experiments have been compared with state‐of‐the‐art methods and show superiority of the IOCTQ method in classification accuracy and time complexity. [ABSTRACT FROM AUTHOR]

Abstract: We propose an approach to image segmentation that views it as one of pixel classification using simple features defined over the local neighborhood. We use a support vector machine for pixel classification, making the approach automatically adaptable to a large number of image segmentation applications. Since our approach utilizes only local information for classification, both training and application of the image segmentor can be done on a distributed computing platform. This makes our approach scalable to larger images than the ones tested. This article describes the methodology in detail and tests it efficacy against 5 other comparable segmentation methods on 2 well‐known image segmentation databases. Hence, we present the results together with the analysis that support the following conclusions: (i) the approach is as effective, and often better than its studied competitors; (ii) the approach suffers from very little overfitting and hence generalizes well to unseen images; (iii) the trained image segmentation program can be run on a distributed computing environment, resulting in linear scalability characteristics. The overall message of this paper is that using a strong classifier with simple pixel‐centered features gives as good or better segmentation results than some sophisticated competitors and does so in a computationally scalable fashion. [ABSTRACT FROM AUTHOR]

Intelligent system (IS) using synchronous phasor measurements for transient stability assessment (TSA) has received continuous interests recently. For post-disturbance TSA, one pivotal concern is the response time, which was reported in the literature as a fixed value ranging from 4 cycles to 3 s after fault clearance. Since transient instability can develop very fast, there is a pressing need for faster response speed. This paper develops a novel IS to balance the response speed and accuracy requirements. A set of classifiers are sequentially organised, each is an ensemble of extreme learning machines (ELMs), whose inputs are post-disturbance generator voltage trajectories and outputs are the classification on the stable/unstable status of the post-disturbance system and an evaluation of the credibility of the classification. A self-adaptive TSA decision-making mechanism is designed to progressively adjust the response time, such that the IS can do the classification faster, thereby allowing more time for emergency controls. The ELM ensemble classifiers can also be updated by on-line pre-disturbance TSA results due to its very fast learning speed. Case studies on the New England system and IEEE 50-machine system have validated the high efficiency and accuracy of the IS. [ABSTRACT FROM AUTHOR]

Boosting has been shown to improve the predictive performance of unstable learners such as decision trees, but not of stable learners like Support Vector Machines (SVM), k-nearest neighbors and Naive Bayes classifiers. In addition to the model stability problem, the high time complexity of some stable learners such as SVM prohibits them from generating multiple models to form an ensemble for large data sets. This paper introduces a simple method that not only enables Boosting to improve the predictive performance of stable learners, but also significantly reduces the computational time to generate an ensemble of stable learners such as SVM for large data sets that would otherwise be infeasible. The method proposes to build local models, instead of global models; and it is the first method, to the best of our knowledge, to solve the two problems in Boosting stable learners at the same time. We implement the method by using a decision tree to define local regions and build a local model for each local region. We show that this implementation of the proposed method enables successful Boosting of three types of stable learners: SVM, k-nearest neighbors and Naive Bayes classifiers. [ABSTRACT FROM AUTHOR]

Gender recognition has been playing a very important role in various applications such as human–computer interaction, surveillance, and security. Nonlinear support vector machines (SVMs) were investigated for the identification of gender using the Face Recognition Technology (FERET) image face database. It was shown that SVM classifiers outperform the traditional pattern classifiers (linear, quadratic, Fisher linear discriminant, and nearest neighbour). In this context, this paper aims to improve the SVM classification accuracy in the gender classification system and propose new models for a better performance. We have evaluated different SVM learning algorithms; the SVM‐radial basis function with a 5% outlier fraction outperformed other SVM classifiers. We have examined the effectiveness of different feature selection methods. AdaBoost performs better than the other feature selection methods in selecting the most discriminating features. We have proposed two classification methods that focus on training subsets of images among the training images. Method 1 combines the outcome of different classifiers based on different image subsets, whereas method 2 is based on clustering the training data and building a classifier for each cluster. Experimental results showed that both methods have increased the classification accuracy. [ABSTRACT FROM AUTHOR]