Search

Aims/Introduction: Machine learning algorithms based on the artificial neural network (ANN), support vector machine, naive Bayesian or logistic regression model are commonly used to identify diabetes. This study investigated which approach performed the best and whether muscle strength provided any incremental benefit in identifying undiagnosed diabetes in Chinese adults. Methods: This cross‐sectional study enrolled 4,482 eligible participants from eight provinces in China, who were randomly divided into the training dataset (n = 3,586) and the testing dataset (n = 896). Muscle strength was assessed by handgrip strength and the number of chair stands in the 30‐s chair stand test. An oral glucose tolerance test was used to ascertain undiagnosed diabetes. The areas under the curve (AUCs) were calculated accordingly and compared with each other. Results: Of the included participants, 233 had newly diagnosed diabetes. All the four machine learning algorithms, which were developed based on nonlaboratory parameters, showed acceptable discriminative ability in identifying undiagnosed diabetes (all AUCs >0.70), with the ANN approach performing the best (AUC 0.806). Adding handgrip strength or the 30‐s chair stand test to this approach did not increase the AUC further (P = 0.39 and 0.26, respectively). Furthermore, compared with the New Chinese Diabetes Risk Score, the ANN approach showed a larger AUC in identifying undiagnosed diabetes (Pcomparison < 0.01), regardless of the addition of handgrip strength or the 30‐s chair stand test. Conclusions: The ANN approach performed the best in identifying undiagnosed diabetes in Chinese adults; however, the addition of muscle strength might not improve its efficacy. [ABSTRACT FROM AUTHOR]

A machine learning‐based optimized droop method is suggested here to simultaneously reduce the production cost (PC) and power line losses (PLL) for a class of direct current (DC) microgrids (MGs). Traditionally, a communication‐less technique known as the hybrid droop method has been employed to decrease PC and PLL in DC MGs. However, achieving the desired reduction in either PC or PLL requires arbitrary adjustments of weighting coefficients for each distributed generator in the conventional hybrid droop method. To address this challenge, this paper introduces a systematic approach that capitalizes on the benefits of artificial intelligence to accurately predict both the PC and PLL in a DC MG. Furthermore, an optimization technique relying on the gradient descendent method is employed to independently optimize both PC and PLL for each scenario. The effectiveness of the proposed method is confirmed through a comparative study with classical and hybrid droop coordination schemes under various scenarios such as rapid load changes. [ABSTRACT FROM AUTHOR]

Five‐phase permanent magnet synchronous machine (PMSM) can operate under open‐circuit faults with the appropriate current regulations. However, the traditional current regulations based on the five‐phase half‐bridge inverter have to satisfy the constraint of zero neutral point current, which limits the fault‐tolerant performance of the machine. Thus, this paper investigates the current regulation based on the five‐phase six‐leg (FPSL) inverter, which relieves the zero‐neutral point current limitation, and both current regulations considering the maximum torque (MT) and minimum copper loss (MC) are derived under different open‐circuit conditions. The cost of the system has increased, but with the new regulations, better fault‐tolerant operation capability of the machine can be obtained under all kinds of open‐circuit faults. Moreover, with the introduction of the neutral point current, the machine can work under triple‐phase open‐circuit faults. In conclusion, the proposed control scheme based on the FPSL inverter expands the fault‐tolerant operation capability of the five‐phase PMSM. The experiment results prove the effectiveness of the proposed current regulation on increasing average torque or reducing copper loss under fault‐tolerant operation. [ABSTRACT FROM AUTHOR]

Here we present a method for using the spatial x–y coordinate of an image cropped from the cylindrical surface of digital 3D drill core images and demonstrate how this spatial metadata can be used to improve unsupervised machine learning performance. This approach is applicable to any data set with known spatial context, however, here it is used to classify 400 m of drillcore imagery into 12 distinct classes reflecting the dominant rock types and alteration features in the core. We modified two unsupervised learning models to incorporate spatial metadata and an average improvement of 25% was achieved over equivalent models that did not utilize metadata. Our semi‐supervised workflow involves unsupervised network training followed by semi‐supervised clustering where a support vector machine uses a subset of M expert labeled images to assign a pseudolabel to the entire data set. Fine‐tuning of the best performing model showed an f1 (macro average) of 90%, and its classifications were used to estimate bulk fresh and altered rock abundance downhole. Validation against the same information gathered manually by experts when the core was recovered during the Oman Drilling Project revealed that our automatically generated data sets have a significant positive correlation (Pearson's r of 0.65–0.72) to the expert generated equivalent, demonstrating that valuable geological information can be generated automatically for 400 m of core with only ∼24 hr of domain expert effort. Plain Language Summary: This work presents a novel method for using the spatial context of digital core images to improve the descriptive accuracy of unsupervised machine learning algorithms. The addition of spatial metadata improves model performance by an average of 25%, with the best performing model in this study achieving an accuracy score of 90%. The output of this model was then used to estimate the amount of fresh and altered rock within a 400 m long drill core, which was shown to be of comparable quality to the same estimations made by geologists on the cores themselves. Key Points: Use of spatial metadata improves state‐of‐the‐art unsupervised feature extractionSemi‐supervised methods using spatial metadata outperform supervised methods for the same expert labeling effortNew methods described enable the standardization of core‐logging processes and improve cross‐dataset comparisons [ABSTRACT FROM AUTHOR]

An accurate and trustworthy first break picking plays a key role in static correction calculations, velocity analysis, and deconvolution. First break traveltimes picking accuracy ensures correct and reliable seismic data processing results. Many methods are available to perform the first break pickings automatically. Most of these methods, however, are not robust when there is a low signal‐to‐noise ratio (SNR). In this study, to automatically determine the traveltimes of the first arrivals, we used the density‐based spatial clustering application with noise (DBSCAN) and the super‐virtual refraction interferometry (SVI). In the case of noisy data, using only DBSCAN for first break picking shows poor accuracy. To deal with this issue, SVI is employed to improve the SNR of the data, and then DBSCAN is applied again to the enhanced data for accurate picking. In the first step, DBSCAN is used to define a muting window for SVI. In the second step, SVI is employed to improve the first arrival SNR. In the third step, DBSCAN is applied to determine the final first arrival traveltime. The proposed approach is tested on synthetic and field data sets, where the manual and the cross‐correlation pickings are compared to the DBSCAN automatic pickings. We further test the proposed approach on a publicly available data set to benchmark our technique for first‐break accuracy with other established methods. Results show that the first arrival traveltime picks using the proposed approach are very accurate compared to manual picking. Plain Language Summary: Recorded seismic data goes through many processing steps to get a final image of the subsurface. One of the important processing steps is first break traveltime picking. Its accuracy is very important for accurate data processing outcomes. Many methods struggle to make an accurate automatic first break traveltime picking when the data is polluted with noise. In this research work, we used an unsupervised machine learning technique to perform automatic first break traveltime picking which produced good results even in the case of noisy data. The performance of the machine learning algorithm is improved by enhancing the signal‐to‐noise ratio of the data because of using the super‐virtual refraction interferometry (SVI) technique. The proposed methodology is tested using synthetic and field examples, and results show a better picking of the first breaks after using SVI as part of the working flowchart. Key Points: An unsupervised machine learning algorithm, the density‐based spatial clustering application with noise (DBSCAN), is used to automatically pick the first arrival traveltime of recorded seismic dataSuper‐virtual refraction interferometry is used to enhance signal‐to‐noise ratio of far‐offset traces then DBSCAN is used to pick the first breaks automatically and accurately [ABSTRACT FROM AUTHOR]

The data acquired in civil engineering tasks often involve high acquisition costs, and the available datasets tend to have a limited number of samples and are highly biased. To estimate the performance of machine learning models, k‐fold cross‐validation (k‐CV) is widely used. However, if only limited data are available and the data distribution is biased, k‐CV tends to overestimate the performance for practical applications. This study proposed a new estimator, leave one reference out and k‐CV (LORO‐k‐CV), to determine the practical performance of machine learning models, that is, the generalization performance for population data in the target task, in case data are collected by multiple references resulting in biased data. LORO‐k‐CV is a combination of a new concept, LORO‐CV, that estimates the performance in the extrapolation region of the training data without human intervention and k‐CV, considering the ratio of the interpolation and extrapolation regions. The efficacy of LORO‐k‐CV was validated with its application to the regression task for the chloride‐ion concentration of concrete structures. To more specifically demonstrate the advantages of LORO‐k‐CV in model construction, the feature selections were conducted using both k‐CV and LORO‐k‐CV methods. These results revealed that LORO‐k‐CV can effectively construct a model with improved generalization performance even from the same data in cases where data are collected by multiple references, resulting in biased data. [ABSTRACT FROM AUTHOR]

Induction machines are the working horses in a lot of industries. Inter‐turn short‐circuit (ITSC) fault is one of the most common failure modes taking place in them. It can generate large fault currents that lead to a local temperature rise in the faulty stator slot, which deteriorates the working performance of the machine or even cascades to a complete machine breakdown. This article focuses on developing transient thermal models for an induction machine under ITSC faults. The aim of these thermal models is to understand the thermal behaviour of the induction machine at different ITSC fault propagation stages. The first thermal model is based on finite element method (FEM) simulation that includes a physics‐based model for the thermal contact resistance. The second thermal model is a lumped parameter thermal network that models the stator as inter‐connected slot‐number parts. They are both capable of modelling the characteristic of non‐uniform temperature along the circumferential direction for the induction machine operating under ITSC fault conditions. After area‐weighted averaging the results of the FEM simulation, it is found they are quantitatively consistent, with an average relative error magnitude of 5%, as well. [ABSTRACT FROM AUTHOR]

There is a widely held view that visual representations (images) do not depict negation, for example, as expressed by the sentence, "the train is not coming." The present study focuses on the real‐world visual representations of photographs and comic (manga) illustrations and empirically challenges the question of whether humans and machines, that is, modern deep neural networks, can recognize visual representations as expressing negation. By collecting data on the captions humans gave to images and analyzing the occurrences of negation phrases, we show some evidence that humans recognize certain images as expressing negation. Furthermore, based on this finding, we examined whether or not humans and machines can classify novel images as expressing negation. The humans were able to correctly classify images to some extent, as expected from the analysis of the image captions. On the other hand, the machine learning model of image processing was only able to perform this classification at about the chance level, not at the same level of performance as the human. Based on these results, we discuss what makes humans capable of recognizing negation in visual representations, highlighting the role of the background commonsense knowledge that humans can exploit. Comparing human and machine learning performances suggests new ways to understand human cognitive abilities and to build artificial intelligence systems with more human‐like abilities to understand logical concepts. [ABSTRACT FROM AUTHOR]

Machine learning has been facing significant challenges over the last years, much of which stem from the new characteristics of machine learning problems, such as learning from streaming data or incorporating human feedback into existing datasets and models. In these dynamic scenarios, data change over time and models must adapt. However, new data do not necessarily mean new patterns. The main goal of this paper is to devise a method to predict a model's performance metrics before it is trained, in order to decide whether it is worth it to train it or not. That is, will the model hold significantly better results than the current one? To address this issue, we propose the use of meta‐learning. Specifically, we evaluate two different meta‐models, one built for a specific machine learning problem, and another built based on many different problems, meant to be a generic meta‐model, applicable to virtually any problem. In this paper, we focus only on the prediction of the root mean square error (RMSE). Results show that it is possible to accurately predict the RMSE of future models, event in streaming scenarios. Moreover, results also show that it is possible to reduce the need for re‐training models between 60% and 98%, depending on the problem and on the threshold used. [ABSTRACT FROM AUTHOR]

Fractional‐slot concentrated‐windings are appreciated for their simple construction, short end‐winding length, high copper fill factor, low cogging torque, good field‐weakening capability and fault‐tolerant ability. However, in comparison to the conventional distributed windings, the fractional‐slot concentrated‐windings are characterised with high space magnetomotive force (MMF) harmonics, which results in undesirable effects on the machine performance, such as localised core saturation, eddy current loss in the rotor and noise and vibration. In order to improve winding characteristics, several techniques have been developed recently. This manuscript introduces the 5 new winding topologies by using the general concept of stator slot shifting. It means that, in order to cancel undesirable MMF harmonics, by doubling (or tripling or even multiplying) the slot number and dividing the winding and then relatively shifting the winding by one (or more) slots, the undesirable harmonics have been eliminated effectively. The best choice is chosen according to the lowest amount of the MMF harmonic, highest value of winding factor and torque desirable characteristics. At the end, comprehensive comparisons for the designed synchronous reluctance motor (SynRel) equipped with proposed windings and also distributed winding are presented. The analytical study and 2D FEM analysis results show that it is possible to get an ideal low space‐harmonic winding topology, and consequently, a low torque ripple for these motors. [ABSTRACT FROM AUTHOR]

A novel DC‐Excited Flux‐Switching Linear Motor (DC‐FSLM) is investigated in this paper, where a simple secondary is used as the machine stator. The phases and excitation windings are placed on the primary, which contributes to a low‐cost and simple structure linear motor with acceptable dynamic performance. The motor operation under dynamic load is analysed by a parametric Magnetic Equivalent Circuit (MEC), and the core saturation is modelled by the non‐linear reluctance of the flux tubes. Moreover, the end‐effect is considered by virtual zones at both entrance and exit ends of the primary. In the considered MEC, the model accuracy can be selected as desired as well as different DC‐FSLMs with various properties can be modelled. Finally, the machine capabilities and performance characteristics are discussed by simulation results, and validation is performed by the Finite Element Method (FEM). [ABSTRACT FROM AUTHOR]

Multi air‐gap tubular linear machines usually take the form of a double‐sided tubular linear machine (DSTLM). Such machines have a higher space utilisation and higher power density than their single air‐gap counterparts, but at the same time the structure is more complex. It is traditionally very difficult to mechanically implement a movement between two slotted stators, whilst maintaining an even air gap distribution. Thermally, the inner stator is another complex aspect of a DSTLM. However, very little understanding of these two aspects and how they influence the performances of tubular machines exists today. Therefore in this paper, the aim is to accurately analyse the influence of temperature rise and eccentricity fault on the performances of DSTLM. A two‐way electromagnetic‐fluid‐thermal multi‐physics coupling model of the DSTLM is established. The variations of electromagnetic, fluid and thermal characteristics with the eccentricity are systematically analysed. A physical prototype is manufactured and the analysed results are verified by the experiments. [ABSTRACT FROM AUTHOR]

This paper develops a new model with adjustable accuracy to evaluate performance of permanent magnet Vernier machine (PMVM) based on flexible magnetic equivalent circuit (MEC) method. The desired machine parameters such as number of flux modulation poles (FMPs), winding pole‐pairs, and geometrical dimensions can be chosen in the presented model. By utilizing nonlinear core magnetization curve, saturation effect is taken into account. There are two main contributions in this study. First, the flexible MEC model is developed to predict the machine performance accurately. The second contribution is that the developed model can be used to evaluate the performance of the machine under no‐load and loading conditions at the same time. The results of MEC model under no‐load and loading conditions are compared with 2D‐finite element method (FEM) and 3D‐FEM in terms of accuracy and simulation time. The results indicate acceptable accuracy and suitable processing time of the proposed MEC model. [ABSTRACT FROM AUTHOR]

Brain morphology varies across the ageing trajectory and the prediction of a person's age using brain features can aid the detection of abnormalities in the ageing process. Existing studies on such "brain age prediction" vary widely in terms of their methods and type of data, so at present the most accurate and generalisable methodological approach is unclear. Therefore, we used the UK Biobank data set (N = 10,824, age range 47–73) to compare the performance of the machine learning models support vector regression, relevance vector regression and Gaussian process regression on whole‐brain region‐based or voxel‐based structural magnetic resonance imaging data with or without dimensionality reduction through principal component analysis. Performance was assessed in the validation set through cross‐validation as well as an independent test set. The models achieved mean absolute errors between 3.7 and 4.7 years, with those trained on voxel‐level data with principal component analysis performing best. Overall, we observed little difference in performance between models trained on the same data type, indicating that the type of input data had greater impact on performance than model choice. All code is provided online in the hope that this will aid future research. [ABSTRACT FROM AUTHOR]

Limited labelled data is a challenge in the field of medical imaging and the need for a large number of them is paramount for the training of machine learning algorithms, as well as measuring the performance of image processing algorithms. The purpose of this study is to construct synthetic and labelled optical coherence tomography (OCT) data to solve the problems of having access to accurately labelled data and evaluating the processing algorithms. In this study, a modified active shape model is used which considers the anatomical features of available images such as the number and thickness of the layers as well as their associated brightness, the location of retinal blood vessels and shadow information with respect to speckle noise. The algorithm is also able to provide different data sets with the varying noise level. The validity of the proposed method for the synthesis of retinal images is measured by two methods (qualitative assessment and quantitative analysis). [ABSTRACT FROM AUTHOR]

Rotor excited flux‐switching permanent magnet machines (REFSPMs) have been recently introduced exhibiting high power density and low permanent magnet consumption. Despite the advantages, 12/8 configuration of REFSPM has an intrinsic unbalanced voltage waveform due to the existence of even‐order harmonics. Aiming to improve the machine voltage THD, using notches on the rotor segments is proposed. To study the effects of the rotor notch on machine performance with low computational time, the non‐linear magnetic equivalent circuit is developed taking into account the effects of fringing fluxes, iron saturation, and rotor transition. An optimisation procedure based on Taguchi method is applied to minimise the voltage THD value taking the effects of uncontrollable factors into account. Finally, the REFSPM is prototyped and the measured results are compared with the analytical and numerical results. [ABSTRACT FROM AUTHOR]

Premise: High‐resolution cameras are very helpful for plant phenotyping as their images enable tasks such as target vs. background discrimination and the measurement and analysis of fine above‐ground plant attributes. However, the acquisition of high‐resolution images of plant roots is more challenging than above‐ground data collection. An effective super‐resolution (SR) algorithm is therefore needed for overcoming the resolution limitations of sensors, reducing storage space requirements, and boosting the performance of subsequent analyses. Methods: We propose an SR framework for enhancing images of plant roots using convolutional neural networks. We compare three alternatives for training the SR model: (i) training with non‐plant‐root images, (ii) training with plant‐root images, and (iii) pretraining the model with non‐plant‐root images and fine‐tuning with plant‐root images. The architectures of the SR models were based on two state‐of‐the‐art deep learning approaches: a fast SR convolutional neural network and an SR generative adversarial network. Results: In our experiments, we observed that the SR models improved the quality of low‐resolution images of plant roots in an unseen data set in terms of the signal‐to‐noise ratio. We used a collection of publicly available data sets to demonstrate that the SR models outperform the basic bicubic interpolation, even when trained with non‐root data sets. Discussion: The incorporation of a deep learning–based SR model in the imaging process enhances the quality of low‐resolution images of plant roots. We demonstrate that SR preprocessing boosts the performance of a machine learning system trained to separate plant roots from their background. Our segmentation experiments also show that high performance on this task can be achieved independently of the signal‐to‐noise ratio. We therefore conclude that the quality of the image enhancement depends on the desired application. [ABSTRACT FROM AUTHOR]

To explore the potential of machine learning-based cooperative spectrum sensing (CSS) in training time, classification speed and classification performance, this study mainly focuses on studying the problem of the feature vectors selecting for machine learning-based CSS. First, a new machine learning-based CSS framework is presented, in which, energy vector forming module, feature vector conversion module, training module, classification module and training sample database are included. Second, a new two-dimensional distance vector is developed, and it is converted by an m-dimensional energy vector according to the distance measurement between vectors. Furthermore, six combination modes are obtained by combining three feature vectors (energy, probability and distance vectors) with two supervised machine learning methods, which are support vector machine (SVM) and weighted K-nearest-neighbour, respectively. From the proposed experimental simulations, the authors can find that the distance vector is obviously superior to the probability vector in computation time. Moreover, the probability vector and distance vector are superior to the energy vector in training time except for the case of poor signal and fewer users, and obviously superior to the energy vector in classification speed. At last, the probability vector and distance vector with SVM classifier show the best classification performance in six combination modes. [ABSTRACT FROM AUTHOR]

Brushless doubly-fed induction machine (BDFIM) has recently gained considerable research interests due to its promising features when incorporated as wind generator or variable speed drive. The BDFIM has two three-phase stator windings with different pole-pair numbers and excitation frequencies. The performance of the machine is based on the magnetic cross-coupling of rotating fields produced by the stator windings through a special squirrel cage rotor. Contrary to the conventional induction machine (IM), the rotor slip and frequency are high throughout the operating speed range. Hence, the rotor core loss cannot be ignored in the steady-state analysis. Although the core loss components have much more study of BDFIM. In this study, analytical expressions are individually derived for a number of core loss components caused by the complicated nature than those of an IM, the precise calculation of these components is important especially on the efficiency each stator winding field. Then, the modified steady-state electric equivalent model is developed by considering the components. The experiments and finite element analysis based on a 3 kW prototype BDFIM verify the accuracy of the proposed model. [ABSTRACT FROM AUTHOR]

V‐shape interior permanent‐magnet machines (IPMs) have been widely utilised in the industry due to their high‐power density, high efficiency, and low manufacturing cost. There has been growing interest in applying multi‐objective optimisation to the design of electric machines. In the context of V‐shape IPM designs, it is important to include stress analysis in the optimisation design analysis as the steel bridges in the IPM rotor are structural weak points, where high stresses develop. However, traditional finite element analysis (FEA) that is normally used to compute bridge stresses becomes cumbersome due to its high computational cost. In this study, a computationally efficient analytical method is proposed to compute the mechanical stresses developed within the steel bridges in a V‐shape IPM. The proposed method is shown to yield accurate predictions compared with FEA while reducing computational cost. A design study is conducted that demonstrates that the machine performance can be improved by incorporating the proposed structural analysis in a multi‐objective optimisation‐based‐design environment. [ABSTRACT FROM AUTHOR]

This study illustrates the design of a low‐torque ripple ferrite‐assisted synchronous reluctance machine. The design strategy initially adopts a simplified analytical model in order to select the optimal values for the flux barrier angles that mainly affects the torque ripple. Then, synchronous reluctance rotor geometries selected on the basis of analytical results are analysed by finite elements (FEs) simulations. The simulated geometries are provided by ferrite permanent magnets (PMs) to enhance machine performance. The optimisation steps are properly coordinated in order to realise the maximum reduction of the torque ripple, taking into account the PM quantity and the flux barrier shape as well as the demagnetisation risk. Two optimal rotor geometries are presented and compared in terms of torque ripple by FEs simulations. Then, the comparison have been extended to other machine characteristics (as high‐frequency saliency and demagnetisation tolerance) to the aim of selecting the more promising one. Available measurements on prototypes are reported to confirm the simulation results and the design approach. [ABSTRACT FROM AUTHOR]