Search

Introduction: Personality plays a crucial role in shaping an individual’s interactions with the world. The Big Five personality traits are widely used frameworks that help describe people’s psychological behaviours. These traits predict how individuals behave within an organizational setting. Methods: In this article, we introduce a virtual reality (VR) strategy for relatively scoring an individual’s personality to evaluate the feasibility of predicting personality traits from implicit measures captured from users interacting in VR simulations of different organizational situations. Specifically, eye-tracking and decision-making patterns were used to classify individuals according to their level in each of the Big Five dimensions using statistical machine learning (ML) methods. The virtual environment was designed using an evidence-centered design approach. Results: The dimensions were assessed using NEO-FFI inventory. A random forest ML model provided 83% accuracy in predicting agreeableness. A k-nearest neighbour ML model provided 75%, 75%, and 77% accuracy in predicting openness, neuroticism, and conscientiousness, respectively. A support vector machine model provided 85% accuracy for predicting extraversion. These analyses indicated that the dimensions could be differentiated by eye-gaze patterns and behaviours during immersive VR. Discussion: Eye-tracking measures contributed more significantly to this differentiation than the behavioural metrics. Currently, we have obtained promising results with our group of participants, but to ensure the robustness and generalizability of our findings, it is imperative to replicate the study with a considerably larger sample. This study demonstrates the potential of VR and ML to recognize personality traits. [ABSTRACT FROM AUTHOR]

Evaluating and mitigating the adverse effects of the ionosphere on communication, navigation, and other services, as well as fully utilizing the ionosphere, have become increasingly prominent topics in the academic community. To quantify the dynamical changes and improve the prediction accuracy of the ionospheric Total Electron Content (TEC), we propose a prediction model based on grid-optimized Support Vector Regression (SVR). This modeling processes include three steps: (1) dividing the dataset for training, validation, and testing; (2) determining the hyperparameters C and g by the grid search method through cross-validation using training and validation data; and (3) testing the trained model using the test data. Taking the Gakona station as an example, we compared the proposed model with the International Reference Ionosphere (IRI) model and a TEC prediction model based on Statistical Machine Learning (SML). The performance of the models was evaluated using the metrics of mean absolute error (MAE) and root mean square error (RMSE). The specific results are as follows: the MAE of the CCIR, URSI, SML, and SVR models compared to the observations are 1.06 TECU, 1.41 TECU, 0.7 TECU, and 0.54 TECU, respectively; the RMSE are 1.36 TECU, 1.62 TECU, 0.92 TECU, and 0.68 TECU, respectively. These results indicate that the SVR model has the most minor prediction error and the highest accuracy for predicting TEC. This method also provides a new approach for predicting other ionospheric parameters. [ABSTRACT FROM AUTHOR]

Estimating and controlling dynamical systems from observable time-series data are essential for understanding and manipulating nonlinear dynamics. This paper proposes a probabilistic framework for simultaneously estimating and controlling nonlinear dynamics under noisy observation conditions. Our proposed method utilizes the particle filter not only as a state estimator and a prior estimator for the dynamics but also as a controller. This approach allows us to handle the nonlinearity of the dynamics and uncertainty of the latent state. We apply two distinct dynamics to verify the effectiveness of our proposed framework: a chaotic system defined by the Lorenz equation and a nonlinear neuronal system defined by the Morris–Lecar neuron model. The results indicate that our proposed framework can simultaneously estimate and control complex nonlinear dynamical systems. [ABSTRACT FROM AUTHOR]

IntroductionTo reduce demands on expert time and improve clinical efficiency, we developed a framework to evaluate whether inexpensive, accessible data could accurately classify Alzheimer's disease (AD) clinical diagnosis and predict the likelihood of progression.MethodsWe stratified relevant data into three tiers: obtainable at primary care (low-cost), mostly available at specialty visits (medium-cost), and research-only (high-cost). We trained several machine learning models, including a hierarchical model, an ensemble model, and a clustering model, to distinguish between diagnoses of cognitively unimpaired, mild cognitive impairment, and dementia due to AD.ResultsAll models showed viable classification, but the hierarchical and ensemble models outperformed the conventional model. Classifier "error" was predictive of progression rates, and cluster membership identified subgroups with high and low risk of progression within 1.5 to 3 years.DiscussionAccessible, inexpensive clinical data can be used to guide AD diagnosis and are predictive of current and future disease states.HighlightsClassification performance using cost-effective features was accurate and robustHierarchical classification outperformed conventional multinomial classificationClassification labels indicated significant changes in conversion risk at follow-upA clustering-classification method identified subgroups at high risk of decline.

In the study titled Research on English Translation Optimization Algorithm Based on Statistical Machine Learning: IAAM-NN (Integrating Advanced Attention Mechanisms with Neural Networks), we explore the fusion of advanced attention mechanisms with neural networks to enhance English translation accuracy. This research delves into the intersection of statistical machine learning and language processing, presenting a novel approach termed IAAM-NN. This method capitalizes on the strengths of neural networks in learning complex patterns and the refined attention mechanisms' ability to accurately map contextual relationships within text. The core objective is to address the challenges faced in traditional translation algorithms - primarily context misinterpretation and semantic inaccuracies. By harnessing the power of advanced attention mechanisms, the IAAM-NN algorithm effectively deciphers nuanced linguistic structures, ensuring more accurate and contextually relevant translation outputs. This study demonstrates the potential of combining neural network models with enhanced attention processes, illustrating significant improvements in translation quality compared to standard machine learning approaches. The implementation of IAAM-NN marks a step forward in the realm of machine translation, offering insights into developing more sophisticated and reliable translation tools in the future. [ABSTRACT FROM AUTHOR]

One field of research that is gathering attention today is statistical machine learning that aims to apply analytical data to realworld problems. Conventional analysis has mainly used methods that manually set the scale and parameters of a statistical model or training model based on the data given and that involve costly tuning. These methods, however, incur massive amounts of time and labor, so using them to analyze data that will only continue to expand from here on is difficult. To solve this problem, there is a strong demand for a new technique that automatically adjusts model scale and parameters according to the quality and volume of data. In this article, we talked with NTT Distinguished Researcher Masahiro Nakano about his research on Bayesian nonparametric methods for solving problems faced by today's data society. [ABSTRACT FROM AUTHOR]

As the new generation of artificial intelligence (AI) continues to evolve, weather big data and statistical machine learning (SML) technologies complement each other and are deeply integrated to significantly improve the processing and forecasting accuracy of fishery weather. Accurate fishery weather services play a crucial role in fishery production, serving as a great safeguard for economic benefits and personal safety, enabling fishermen to carry out fishery production better, and contributing to the sustainable development of the fishery industry. The objective of this paper is to offer an understanding of the present state of research and development in SML technology for simulating and forecasting fishery weather. Specifically, we analyze the current state of research and technical features of SML in weather and summarize the applications of SML in simulation and forecasting of fishery weather, which mainly include three aspects: fishery weather scenario generation, fishery weather forecasting, and fishery extreme weather warning. We also illustrate the main technical means and principles of SML technology. Finally, we summarize the most advanced SML fields and provide an outlook on their application value in the field of fishery weather.

Computational Medicine encompasses the application of Statistical Machine Learning and Artificial Intelligence methods on several traditional medical approaches, including biochemical testing which is extremely valuable both for early disease prognosis and long-term individual monitoring, as it can provide important information about a person's health status. However, using Statistical Machine Learning and Artificial Intelligence algorithms to analyze biochemical test data from Electronic Health Records requires several preparatory steps, such as data manipulation and standardization. This study presents a novel approach for utilizing Electronic Health Records from large, real-world databases to develop predictive precision medicine models by exploiting Artificial Intelligence. Furthermore, to demonstrate the effectiveness of this approach, we compare the performance of various traditional Statistical Machine Learning and Deep Learning algorithms in predicting individuals' future biochemical test outcomes. Specifically, using data from a large real-world database, we exploit a longitudinal format of the data in order to predict the future values of 15 biochemical tests and identify individuals at high risk. The proposed approach and the extensive model comparison contribute to the personalized approach that modern medicine aims to achieve. [ABSTRACT FROM AUTHOR]

IntroductionPersonality plays a crucial role in shaping an individual’s interactions with the world. The Big Five personality traits are widely used frameworks that help describe people’s psychological behaviours. These traits predict how individuals behave within an organizational setting.MethodsIn this article, we introduce a virtual reality (VR) strategy for relatively scoring an individual’s personality to evaluate the feasibility of predicting personality traits from implicit measures captured from users interacting in VR simulations of different organizational situations. Specifically, eye-tracking and decision-making patterns were used to classify individuals according to their level in each of the Big Five dimensions using statistical machine learning (ML) methods. The virtual environment was designed using an evidence-centered design approach.ResultsThe dimensions were assessed using NEO-FFI inventory. A random forest ML model provided 83% accuracy in predicting agreeableness. A k-nearest neighbour ML model provided 75%, 75%, and 77% accuracy in predicting openness, neuroticism, and conscientiousness, respectively. A support vector machine model provided 85% accuracy for predicting extraversion. These analyses indicated that the dimensions could be differentiated by eye-gaze patterns and behaviours during immersive VR.DiscussionEye-tracking measures contributed more significantly to this differentiation than the behavioural metrics. Currently, we have obtained promising results with our group of participants, but to ensure the robustness and generalizability of our findings, it is imperative to replicate the study with a considerably larger sample. This study demonstrates the potential of VR and ML to recognize personality traits.

We propose in this paper a novel reliable detection method to recognize forged inpainting images. Detecting potential forgeries and authenticating the content of digital images is extremely challenging and important for many applications. The proposed approach involves developing new probabilistic support vector machines (SVMs) kernels from a flexible generative statistical model named “bounded generalized Gaussian mixture model”. The developed learning framework has the advantage to combine properly the benefits of both discriminative and generative models and to include prior knowledge about the nature of data. It can effectively recognize if an image is a tampered one and also to identify both forged and authentic images. The obtained results confirmed that the developed framework has good performance under numerous inpainted images.

We propose in this paper a novel reliable detection method to recognize forged inpainting images. Detecting potential forgeries and authenticating the content of digital images is extremely challenging and important for many applications. The proposed approach involves developing new probabilistic support vector machines (SVMs) kernels from a flexible generative statistical model named "bounded generalized Gaussian mixture model". The developed learning framework has the advantage to combine properly the benefits of both discriminative and generative models and to include prior knowledge about the nature of data. It can effectively recognize if an image is a tampered one and also to identify both forged and authentic images. The obtained results confirmed that the developed framework has good performance under numerous inpainted images. [ABSTRACT FROM AUTHOR]

In recent years, the field of precision medicine has seen many advancements. Significant focus has been placed on creating algorithms to estimate individualized treatment rules (ITRs), which map from patient covariates to the space of available treatments with the goal of maximizing patient outcome. Direct learning (D‐Learning) is a recent one‐step method which estimates the ITR by directly modeling the treatment–covariate interaction. However, when the variance of the outcome is heterogeneous with respect to treatment and covariates, D‐Learning does not leverage this structure. Stabilized direct learning (SD‐Learning), proposed in this paper, utilizes potential heteroscedasticity in the error term through a residual reweighting which models the residual variance via flexible machine learning algorithms such as XGBoost and random forests. We also develop an internal cross‐validation scheme which determines the best residual model among competing models. SD‐Learning improves the efficiency of D‐Learning estimates in binary and multi‐arm treatment scenarios. The method is simple to implement and an easy way to improve existing algorithms within the D‐Learning family, including original D‐Learning, Angle‐based D‐Learning (AD‐Learning), and Robust D‐learning (RD‐Learning). We provide theoretical properties and justification of the optimality of SD‐Learning. Head‐to‐head performance comparisons with D‐Learning methods are provided through simulations, which demonstrate improvement in terms of average prediction error (APE), misclassification rate, and empirical value, along with a data analysis of an acquired immunodeficiency syndrome (AIDS) randomized clinical trial. [ABSTRACT FROM AUTHOR]

Herein, a historical analytical survey of work of "Discrete Modelling of Pattern Recognition" (DM-Lab) research group in Armenia is presented. The group is since 1973, supervised by worldwide recognized scientist Yurii Ivanovich Zhuravlev and lead by his former student Levon Aslanyan. The general start of attention to computational mathematics and computational systems in Armenia is concerned with the times of cybernetics as a research direction, and the names of great scientists and policy makers, such as Andranik Iosifyan and Sergei Mergelyan. In early 1950's a large number of HighTech and defense related organizations were established in area, and their theoretical, scientific cluster was formed around the Yerevan Research Institute of Mathematical Machines, and Computer Center of Academy of Sciences and Yerevan State University. This was the time for intensive stuff and student exchanges inside the larger country USSR. Rimma Podlovchenko, Rafik Tonoyan, Igor' Zaslavski, Yuri Shoukourian started teaching at Yerevan State University in 70's, a number of students were delegated to the recognized cybernetical centers, in Moscow, Kiev, Novosibirsk. And one of the results of these developments was appearance of DM-Lab in Armenia, composed by alumnus of Novosibirsk and Moscow State Universities, led by Levon Aslanyan, and supervised globally by RF Academician Yuri Ivanovich Zhuravlev. Further research and education activities lead to defenses of candidate and doctoral dissertations, in Armenia, and at the council of Computer Center of Academy of Sciences of Russian Federation. The initial stuff of DM-Lab group included Gevorg Tonoyan, Levon Asatryan, Vilik Karakhanyan. Local members of the group were Hasmik Sahakyan, Vladimir Sahakyan, Irina Arsenyan, Levon Kazaryan and large number of young PhD students. Research directions at the DM-Lab were and are related to the pattern recognition theory – to mathematical models of forming and analyzing learning sets, studying their properties such as the class compactness hypothesis, in terms of isoperimetry; to forming the logic of interrelations of classes, in terms of logic separation; setting up new approaches in data mining area, etc. All these studies involve intensive research over the years, addressing topics related to the geometry of n-dimensional unite cube and lattices in general, Boolean function minimization, discrete optimization problems, and algorithmic studies coming from data science and artificial intelligence. International relations and activities of the group includes: long term representation of Armenia in the ISO technical groups, representation of Armenia in ICT research programmes of European Council, membership at the ITHEA virtual research institute with its conferences and publishing house. 10's of research projects were implemented during these years. Projects were funded by UNDP, NATO Research, INTAS, EC Esprit, IST and Horizone, RFBR, and other international and local sources. 16 candidate and 2 doctoral theses were defended by the group members. [ABSTRACT FROM AUTHOR]

Estimating and controlling dynamical systems from observable time-series data are essential for understanding and manipulating nonlinear dynamics. This paper proposes a probabilistic framework for simultaneously estimating and controlling nonlinear dynamics under noisy observation conditions. Our proposed method utilizes the particle filter not only as a state estimator and a prior estimator for the dynamics but also as a controller. This approach allows us to handle the nonlinearity of the dynamics and uncertainty of the latent state. We apply two distinct dynamics to verify the effectiveness of our proposed framework: a chaotic system defined by the Lorenz equation and a nonlinear neuronal system defined by the Morris–Lecar neuron model. The results indicate that our proposed framework can simultaneously estimate and control complex nonlinear dynamical systems.

Evaluating and mitigating the adverse effects of the ionosphere on communication, navigation, and other services, as well as fully utilizing the ionosphere, have become increasingly prominent topics in the academic community. To quantify the dynamical changes and improve the prediction accuracy of the ionospheric Total Electron Content (TEC), we propose a prediction model based on grid-optimized Support Vector Regression (SVR). This modeling processes include three steps: (1) dividing the dataset for training, validation, and testing; (2) determining the hyperparameters C and g by the grid search method through cross-validation using training and validation data; and (3) testing the trained model using the test data. Taking the Gakona station as an example, we compared the proposed model with the International Reference Ionosphere (IRI) model and a TEC prediction model based on Statistical Machine Learning (SML). The performance of the models was evaluated using the metrics of mean absolute error (MAE) and root mean square error (RMSE). The specific results are as follows: the MAE of the CCIR, URSI, SML, and SVR models compared to the observations are 1.06 TECU, 1.41 TECU, 0.7 TECU, and 0.54 TECU, respectively; the RMSE are 1.36 TECU, 1.62 TECU, 0.92 TECU, and 0.68 TECU, respectively. These results indicate that the SVR model has the most minor prediction error and the highest accuracy for predicting TEC. This method also provides a new approach for predicting other ionospheric parameters.

At a worldwide scale, artificial intelligence (AI) is now an intrinsic part of various sectors and a significant strategic element in the business agendas of several industries including health care, finance and retail. Machine learning, an statistical paradigm of AI, is one of the most preferred technologies to achieve AI. Machine learning-oriented approaches exploit massive sized, unstructured and complicated dataset instances to learn from previous experiences and find insightful patterns. A range of statistical, probabilistic and optimization approaches are used to achieve this task. Early detection of chronic diseases is critical in the realm of biomedical research and healthcare communities, where it is pivotal to primarily diagnose the particular disease at probabilistically early stage in order to lower the death rate. Pneumonia mainly affects a huge number of people, particularly children and adults, in the developing and undeveloped nations that are characterized as overcrowding, inadequate sanitation, malnutrition, lack of suitable medical services and other risk factors. It is critical to detect pneumonia at its early stage in order to properly treat the infection. This paper presents an approach, i.e. DPUD (Disease Prediction for Unstructured Data). The proposed framework consists of an statistically novel and fine-tuned algorithmic procedure to address certain pain points of categorization problem such as selection of an optimal set of model hyperparameters and attain an improved statistical performance metrics with multichannel shared activation function and cost function. In experimental evaluation, our approach capitulates state-of-the-art computational achievement on Chest X-Ray Images for the Pneumonia Classification dataset, while being considerably much faster at specifically test time. The methodology presented in this chapter has an empirical scope for societal improvement, modernization and progress. [ABSTRACT FROM AUTHOR]

Teen mothers experience disadvantage across a wide range of outcomes. However, previous research is equivocal with respect to possible long-term mental health consequences of teen motherhood and has not adequately considered the possibility that effects on mental health may be heterogeneous. Drawing on data from the 1970 British Birth Cohort Study, this article applies a novel statistical machine-learning approach--Bayesian Additive Regression Trees--to estimate the effects of teen motherhood on mental health outcomes at ages 30, 34, and 42. We extend previous work by estimating not only sample-average effects but also individual-specific estimates. Our results show that sample-average mental health effects of teen motherhood are substantively small at alltime points, apart from age 30 comparisons to women who first became mothers at age 25-30. Moreover, we find that these effects are largely homogeneous for allwomen in the sample--indicating that there are no subgroups in the data who experience important detrimental mental health consequences. We conclude that there are likely no mental health benefits to policy and interventions that aim to prevent teen motherhood. [ABSTRACT FROM AUTHOR]

Genomic selection (GS) is revolutionizing plant breeding. However, because it is a predictive methodology, a basic understanding of statistical machine-learning methods is necessary for its successful implementation. This methodology uses a reference population that contains both the phenotypic and genotypic information of genotypes to train a statistical machine-learning method. After optimization, this method is used to make predictions of candidate lines for which only genotypic information is available. However, due to a lack of time and appropriate training, it is difficult for breeders and scientists of related fields to learn all the fundamentals of prediction algorithms. With smart or highly automated software, it is possible for these professionals to appropriately implement any state-of-the-art statistical machine-learning method for its collected data without the need for an exhaustive understanding of statistical machine-learning methods and programing. For this reason, we introduce state-of-the-art statistical machine-learning methods using the Sparse Kernel Methods (SKM) R library, with complete guidelines on how to implement seven statistical machine-learning methods that are available in this library for genomic prediction (random forest, Bayesian models, support vector machine, gradient boosted machine, generalized linear models, partial least squares, feed-forward artificial neural networks). This guide includes details of the functions required to implement each of the methods, as well as others for easily implementing different tuning strategies, cross-validation strategies, and metrics to evaluate the prediction performance and different summary functions that compute it. A toy dataset illustrates how to implement statistical machine-learning methods and facilitate their use by professionals who do not possess a strong background in machine learning and programing. [ABSTRACT FROM AUTHOR]

Seated postural limit defines the boundary of a region such that for any excursions made outside this boundary a subject cannot return the trunk to the neutral position without additional external support. The seated postural limits can be used as a reference to provide assistive support to the torso by the Trunk Support Trainer (TruST). However, fixed boundary representations of seated postural limits are inadequate to capture dynamically changing seated postural limits during training. In this study, we propose a conceptual model of dynamic boundary of the trunk center by assigning a vector that tracks the postural-goal direction and trunk movement amplitude during a sitting task. We experimented with 20 healthy subjects. The results support our hypothesis that TruST intervention with an assist-as-needed force controller based on dynamic boundary representation could achieve more significant sitting postural control improvements than a fixed boundary representation. The second contribution of this paper is that we provide an effective approach to embed deep learning into TruST’s real-time controller design. We have compiled a 3D trunk movement dataset which is currently the largest in the literature. We designed a loss function capable of solving the gate-controlled regression problem. We have proposed a novel deep-learning roadmap for the exploration study. Following the roadmap, we developed a deep learning architecture, modified the widely used Inception module, and then obtained a deep learning model capable of accurately predicting the dynamic boundary in real-time. We believe that this approach can be extended to other rehabilitation robots towards designing intelligent dynamic boundary-based assist-as-needed controllers.

Abstract The development of distributed renewable energy, such as photovoltaic power and wind power generation, makes the energy system cleaner, and is of great significance in reducing carbon emissions. However, weather can affect distributed renewable energy power generation, and the uncertainty of output brings challenges to uncertainty planning for distributed renewable energy. Energy systems with high penetration of distributed renewable energy involve the high-dimensional, nonlinear dynamics of large-scale complex systems, and the optimal solution of the uncertainty model is a difficult problem. From the perspective of statistical machine learning, the theory of planning of distributed renewable energy systems under uncertainty is reviewed and some key technologies are put forward for applying advanced artificial intelligence to distributed renewable power uncertainty planning.

Imbalanced learning problems typically consist of data with skewed class distributions, coupled with large misclassification costs for the rare events. For binary classification, logistic regression is a common supervised learning technique chosen to perform this task. Unfortunately, the model performs poorly on classification tasks when class distributions are highly imbalanced. To improve this generalization, we implement a novel instance-level weighting methodology for the minority class in the loss function. We build our method from a recently published, locally weighted log-likelihood objective function, where each of the minority class weights are learned from the data. We improve upon this previous approach by creating a convex and hyperparameter-free loss function that improves generalization performance for datasets exhibiting extreme class imbalance. [ABSTRACT FROM AUTHOR]

This paper introduces the subgraph nomination inference task, in which example subgraphs of interest are used to query a network for similarly interesting subgraphs. This type of problem appears time and again in real world problems connected to, for example, user recommendation systems and structural retrieval tasks in social and biological/connectomic networks. We formally define the subgraph nomination framework with an emphasis on the notion of a user-in-the-loop in the subgraph nomination pipeline. In this setting, a user can provide additional post-nomination light supervision that can be incorporated into the retrieval task. After introducing and formalizing the retrieval task, we examine the nuanced effect that user-supervision can have on performance, both analytically and across real and simulated data examples. [ABSTRACT FROM AUTHOR]

The National Heart, Lung and Blood Institute Growth and Health Study (NGHS) is a large longitudinal study of childhood health. A main objective of the study is to estimate the joint distributions of cardiovascular risk outcomes at any two time points conditioning on a large number of covariates. Existing multivariate longitudinal methods are not suitable for outcomes at multiple time points. We present a dynamic copula approach for estimating an outcome's joint distributions at two time points given a large number of time-varying covariates. Our models depend on the outcome's time-varying distributions at one time point, the bivariate copula densities and the functional copula parameters. We develop a three-step procedure for variable selection and estimation, which selects the influential covariates using a machine learning procedure based on spline Lasso-regularized least squares, computes the outcome's single-time distribution using splines, and estimates the functional copula parameter of the dynamic copula models. Pointwise confidence intervals are constructed through the resampling-subject bootstrap. We apply our procedure to the NGHS cardiovascular risk data and illustrate the clinical interpretations of the conditional distributions of a set of risk outcomes. We demonstrate the statistical properties of the dynamic models and estimation procedure through a simulation study. [ABSTRACT FROM AUTHOR]

Seated postural limit defines the boundary of a region such that for any excursions made outside this boundary a subject cannot return the trunk to the neutral position without additional external support. The seated postural limits can be used as a reference to provide assistive support to the torso by the Trunk Support Trainer (TruST). However, fixed boundary representations of seated postural limits are inadequate to capture dynamically changing seated postural limits during training. In this study, we propose a conceptual model of dynamic boundary of the trunk center by assigning a vector that tracks the postural-goal direction and trunk movement amplitude during a sitting task. We experimented with 20 healthy subjects. The results support our hypothesis that TruST intervention with an assist-as-needed force controller based on dynamic boundary representation could achieve more significant sitting postural control improvements than a fixed boundary representation. The second contribution of this paper is that we provide an effective approach to embed deep learning into TruST’s real-time controller design. We have compiled a 3D trunk movement dataset which is currently the largest in the literature. We designed a loss function capable of solving the gate-controlled regression problem. We have proposed a novel deep-learning roadmap for the exploration study. Following the roadmap, we developed a deep learning architecture, modified the widely used Inception module, and then obtained a deep learning model capable of accurately predicting the dynamic boundary in real-time. We believe that this approach can be extended to other rehabilitation robots towards designing intelligent dynamic boundary-based assist-as-needed controllers. [ABSTRACT FROM AUTHOR]

Twin support vector machine (TSVM) has attracted much attention in the field of machine learning with good generalization ability and computational performance. However, the conventional grid search method is very time-consuming to obtain the optimal regularization parameter. To address this problem, we develop a novel fast regularization parameter tuning algorithm for TSVM, named TSVMPath. After transforming the models of two sub-optimization problems, we divide the two classes of samples into different sets. Lagrangian multipliers are then proved to be piecewise linear concerning the corresponding regularization parameters, greatly extending the search space of the solution. By proving that the Lagrangian multipliers of two sub-optimization models are 1 when the regularization parameters approach infinity, we design a simple yet effective initialization. As a result, the entirely regularized solution path can be obtained without solving quadratic programming problems. Four types of events are finally defined to update the solution path. Experiments on 8 UCI datasets show that the prediction accuracy of TSVMPath is superior to the best competing methods, with up to four orders of magnitude speed-up for the computational overhead compared with the grid search method. [ABSTRACT FROM AUTHOR]

Abstract New energy integration and flexible demand response make smart grid operation scenarios complex and changeable, which bring challenges to network planning. If every possible scenario is considered, the solution to the planning can become extremely time-consuming and difficult. This paper introduces statistical machine learning (SML) techniques to carry out multi-scenario based probabilistic power flow calculations and describes their application to the stochastic planning of distribution networks. The proposed SML includes linear regression, probability distribution, Markov chain, isoprobabilistic transformation, maximum likelihood estimator, stochastic response surface and center point method. Based on the above SML model, capricious weather, photovoltaic power generation, thermal load, power flow and uncertainty programming are simulated. Taking a 33-bus distribution system as an example, this paper compares the stochastic planning model based on SML with the traditional models published in the literature. The results verify that the proposed model greatly improves planning performance while meeting accuracy requirements. The case study also considers a realistic power distribution system operating under stressed conditions.

The development of distributed renewable energy, such as photovoltaic power and wind power generation, makes the energy system cleaner, and is of great significance in reducing carbon emissions. However, weather can affect distributed renewable energy power generation, and the uncertainty of output brings challenges to uncertainty planning for distributed renewable energy. Energy systems with high penetration of distributed renewable energy involve the high-dimensional, nonlinear dynamics of large-scale complex systems, and the optimal solution of the uncertainty model is a difficult problem. From the perspective of statistical machine learning, the theory of planning of distributed renewable energy systems under uncertainty is reviewed and some key technologies are put forward for applying advanced artificial intelligence to distributed renewable power uncertainty planning. [ABSTRACT FROM AUTHOR]

Genomic selection (GS) changed the way plant breeders select genotypes. GS takes advantage of phenotypic and genotypic information to training a statistical machine learning model, which is used to predict phenotypic (or breeding) values of new lines for which only genotypic information is available. Therefore, many statistical machine learning methods have been proposed for this task. Multi-trait (MT) genomic prediction models take advantage of correlated traits to improve prediction accuracy. Therefore, some multivariate statistical machine learning methods are popular for GS. In this paper, we compare the prediction performance of three MT methods: the MT genomic best linear unbiased predictor (GBLUP), the MT partial least squares (PLS) and the multi-trait random forest (RF) methods. Benchmarking was performed with six real datasets. We found that the three investigated methods produce similar results, but under predictors with genotype (G) and environment (E), that is, E + G, the MT GBLUP achieved superior performance, whereas under predictors E + G + genotype × environment (GE) and G + GE, random forest achieved the best results. We also found that the best predictions were achieved under the predictors E + G and E + G + GE. Here, we also provide the R code for the implementation of these three statistical machine learning methods in the sparse kernel method (SKM) library, which offers not only options for single-trait prediction with various statistical machine learning methods but also some options for MT predictions that can help to capture improved complex patterns in datasets that are common in genomic selection. [ABSTRACT FROM AUTHOR]

Culture and language evolve together. With respect to Tamil, the form of the language that people use nowadays has come a long way from its origins. These days, the old literary form of Tamil is used commonly for writing and the contemporary colloquial Tamil is used for speaking. Human–computer interaction applications require colloquial Tamil (CT) to make it more accessible and easy for the everyday user and, it requires literary Tamil (LT) when information is needed in a formal written format. Continuing the use of LT alongside CT in computer-aided language learning applications will both preserve LT, and provide ease of use via CT, at the same time. Hence, there is a need for the conversion between LT and CT dialects, which demands as a first step, dialect identification. Dialect identification (DID) of LT and CT is an unexplored area of research. There is a considerable research potential in this area, because, (i) LT is standardized while CT is not fully standardized and, (ii) they have only subtle differences. Five methods are explored in our work, which originated from the preliminary work using Gaussian mixture model (GMM) for dialect identification of LT and CT, which offered a motivation with an identification accuracy of 87%. In the current work, keeping the nuances of both these dialects in mind, one other implicit method—convolutional neural network (CNN); two explicit methods—Parallel Phone Recognition (PPR) and Parallel Large Vocabulary Continuous Speech Recognition (P-LVCSR); two versions of the proposed explicit unified phone recognition method (UPR-1 and UPR-2), are explored. These methods vary based on: the need for annotated data, the size of the unit, the way in which modelling is carried out, and the way in which the final decision is made. Even though the average duration of the test utterances is less—4.9 s for LT and 2.5 s for CT—the systems performed well, offering the following identification accuracies: 87.72% (GMM), 93.97% (CNN), 89.24% (PPR), 94.21% (P-LVCSR), 88.57 (UPR-1), 93.53% (UPR-1 with P-LVCSR), 94.55 (UPR-2) and 95.61% (UPR-2 with P-LVCSR). [ABSTRACT FROM AUTHOR]

The goal of Multi-Source Domain Adaptation (MSDA) is to train a model (e.g. , neural network) with minimal target loss, utilizing training data from multiple source domains (source joint distributions) and a target domain (target joint distribution). The challenge in this problem is that the multiple source joint distributions are different from the target joint distribution. In this paper, we develop a theory that shows a neural network's target loss is upper bounded by both its source mixture loss (i.e. , the loss concerning the source mixture joint distribution) and the Pearson χ 2 divergence between the source mixture joint distribution and the target joint distribution. Here, the source mixture joint distribution is the mixture of multiple source joint distributions with mixing weights. Accordingly, we propose an algorithm that optimizes both the mixing weights and the neural network to minimize the estimated source mixture loss and the estimated Pearson χ 2 divergence. To estimate the Pearson χ 2 divergence, we rewrite it as the maximal value of a quadratic functional, exploit a linear-in-parameter function as the functional's input, and solve the resultant optimization problem with an analytic solution. This analytic solution allows us to explicitly express the estimated divergence as a loss of the mixing weights and the network's feature extractor. Finally, we conduct experiments on popular image classification datasets, and the results show that our algorithm statistically outperforms the comparison algorithms. PyTorch code is available at https://github.com/sentaochen/Mixture-of-Joint-Distributions. • The target loss is bounded by the source mixture loss and Pearson χ 2 divergence. • Our algorithm optimizes the mixing weights and network to minimize the two losses. • The divergence is estimated by analytically solving a maximization problem. • Experiments are conducted to verify the effectiveness of our algorithm. [ABSTRACT FROM AUTHOR]

New energy integration and flexible demand response make smart grid operation scenarios complex and changeable, which bring challenges to network planning. If every possible scenario is considered, the solution to the planning can become extremely time-consuming and difficult. This paper introduces statistical machine learning (SML) techniques to carry out multi-scenario based probabilistic power flow calculations and describes their application to the stochastic planning of distribution networks. The proposed SML includes linear regression, probability distribution, Markov chain, isoprobabilistic transformation, maximum likelihood estimator, stochastic response surface and center point method. Based on the above SML model, capricious weather, photovoltaic power generation, thermal load, power flow and uncertainty programming are simulated. Taking a 33-bus distribution system as an example, this paper compares the stochastic planning model based on SML with the traditional models published in the literature. The results verify that the proposed model greatly improves planning performance while meeting accuracy requirements. The case study also considers a realistic power distribution system operating under stressed conditions. [ABSTRACT FROM AUTHOR]

We propose a dust‐event detection and tracking procedure based on air quality data from the ground monitoring network by detecting temporal and spatial change‐points in PM10 concentration. It supplements the existing remote sensing based approach with high temporal resolution and better weather adaptivity. Applications of the procedure on the labeled data showed its having high discriminating power for dust events, pollution events, and clean periods. Our study finds changing correlation patterns between PM10 and other air pollutants at the start of the dust events, which are utilized to enhance the discriminating power of the dust‐event detection procedure. The detection and tracking procedure allows the construction of transport networks of the dust‐events as well as the identification of the source regions and the transportation pattern, and assess the intensity and severity of the dust‐events in North China. Our analysis find the dust‐events contributed to 23.3%–34.6% for PM10 and 18.2–33.2% for PM2.5 in the source regions and 2.0%–7.3% and 0.8%–4.0%, respectively, in the down‐stream provinces in the spring season from 2015 to 2020. Plain Language Summary: Dust storm can be tracked via the air quality monitoring network via a statistical semi‐supervised learning algorithm. Key Points: Develop a dust event detection procedure based on air quality data with finer spatial‐temporal resolution and better weather adaptationConstruct dust transport networks and find altering dependence between PM10 and CO, SO2 and NO2 at the start of dust eventsDust‐events contributed to 23.3%–34.6% for PM10 and 18.2–33.2% for PM2.5 in the source regions and 2.0%–7.3% and 0.8%–4.0%, respectively, in the down‐stream provinces in spring in North China [ABSTRACT FROM AUTHOR]

Although the Lasso method has been popular for variable selection in regression modeling, it has been known to yield very different model structures with minor perturbations of the training data. A consequence is that, when cross-validation (CV) is used to determine the hyperparameter λ , seemingly heterogeneous model structures among the CV-folds are resulted for the same λ. In this paper, we propose a new stable Lasso method for model structure learning of static and dynamic models. We begin with building consensus Lasso models with a grid of λ values using all training data. Then the CV-fold models are optimized to conform with the consensus model structures with a modified Lasso objective. In addition, we propose a stable criterion that uses CV errors jointly with a stability measure to select the most stable model with near minimum CV errors. The proposed method is applied to inferential modeling of a chemical plant at DOW Chemical and dynamic modeling of an industrial boiler. • A stable Lasso algorithm is proposed to select variables for inferential sensor modeling. • The algorithm enhances consistent structures in the cross-validation step. • A stable selection criterion of MSE jointly the Jaccard stability measure is proposed. • Successful case studies are presented on inferential modeling of two industrial processes. [ABSTRACT FROM AUTHOR]