Machine Learning Theory Research Articles

Retracted: Relevance of Ancient Chinese Wine Ware Representation Design and Cultural Characteristics Based on Machine Learning and Semiotic Theory

Retracted: Relevance of Ancient Chinese Wine Ware Representation Design and Cultural Characteristics Based on Machine Learning and Semiotic Theory

Investigating Machine Learning and Control Theory Approaches for Process Fault Detection: A Comparative Study of KPCA and the Observer-Based Method.

The paper focuses on the importance of prompt and efficient process fault detection in contemporary manufacturing industries, where product quality and safety protocols are critical. The study compares the efficiencies of two techniques for process fault detection: Kernel Principal Component Analysis (KPCA) and the observer method. Both techniques are applied to observe water volume variation within a hydraulic system comprising three tanks. PCA is an unsupervised learning technique used for dimensionality reduction and pattern recognition. It is an extension of Principal Component Analysis (PCA) that utilizes kernel functions to transform data into higher-dimensional spaces, where it becomes easier to separate classes or identify patterns. In this paper, KPCA is applied to detect faults in the hydraulic system by analyzing the variation in water volume. The observer method originates from control theory and is utilized to estimate the internal states of a system based on its output measurements. It is commonly used in control systems to estimate the unmeasurable or hidden states of a system, which is crucial for ensuring proper control and fault detection. In this study, the observer method is applied to the hydraulic system to estimate the water volume variations within the three tanks. The paper presents a comparative study of these two techniques applied to the hydraulic system. The results show that both KPCA and the observer method perform similarly in detecting faults within the system. This similarity in performance highlights the efficacy of these techniques and their potential adaptability in various fault diagnosis scenarios within modern manufacturing processes.

Comparative study on risk prediction model of type 2 diabetes based on machine learning theory: a cross-sectional study

ObjectivesTo compare the prediction effects of six models based on machine learning theories, which can provide a methodological reference for predicting the risk of type 2 diabetes mellitus (T2DM).Setting and...

Prediction and theoretical investigation of dehydrogenation enthalpy of V–Ti–Cr–Fe alloy using machine learning and density functional theory

The dehydrogenation enthalpy, a crucial thermodynamic parameter, determines the difficulty of hydrogen desorption in V–Ti–Cr–Fe alloy, but it is unaffordable to predict and modify the dehydrogenation enthalpy and investigate the synergistic effects of structural and chemical parameters relying on conventional experimental methods. In this paper, an extreme gradient boosting (Xgboost) model with feature selection is developed, which can obtain a relative error under 15% in prediction on most of the data. Moreover, the genetic algorithm is utilized for optimizing alloy composition having suitable dehydrogenation enthalpy. The accuracy of prediction and optimization is demonstrated by the subsequent experimental validation, where the error between calculation and experiment is within 4.5%. Density function theory (DFT) is used to analyze the key features provided by machine learning, with results suggesting that the volumes, valence electrons, and bulk module factors have a significant impact. This research supplies an efficient way of using machine learning to predict and optimize the dehydrogenation enthalpy. In addition, DFT calculation also validates the feature importance outputted by machine learning and reveals the principle of feature effects at the microscopic aspect.

Theory of Machine Learning Assisted Structural Optimization Algorithm and Its Application

The machine learning assisted structural optimization (MLASO) algorithm has recently been proposed to expedite topology optimization. In the MLASO algorithm, the machine learning model learns and predicts the update of the chosen optimization quantity in routine and prediction iterations. The routine and prediction iterations are activated with a predefined learning and predicting scheme; and in the prediction iterations, the design variable can be updated using the predicted quantity without running a finite element analysis and sensitivity analysis, and thus the computational time can be saved. Based on the MLASO algorithm, this work first proposes a novel generic criterion-driven learning and predicting (CDLP) scheme that allows the algorithm to autonomously activate prediction iterations in the solution procedure. Second, this work presents the convergence analysis and the computational efficiency analysis of the MLASO algorithm with the CDLP scheme. The MLASO algorithm is then embedded within the solid isotropic material with penalization topology optimization method to solve two-dimensional and three-dimensional problems. Numerical examples and results demonstrate the prediction accuracy and the computational efficiency of the MLASO algorithm, and that the CDLP scheme can remarkably improve the computational efficiency of the MLASO algorithm.

Computational Materials Design for Ceramic Nuclear Waste Forms Using Machine Learning, First-Principles Calculations, and Kinetics Rate Theory.

Ceramic waste forms are designed to immobilize radionuclides for permanent disposal in geological repositories. One of the principal criteria for the effective incorporation of waste elements is their compatibility with the host material. In terms of performance under environmental conditions, the resistance of the waste forms to degradation over long periods of time is a critical concern when they are exposed to natural environments. Due to their unique crystallographic features and behavior in nature environment as exemplified by their natural analogues, ceramic waste forms are capable of incorporating problematic nuclear waste elements while showing promising chemical durability in aqueous environments. Recent studies of apatite- and hollandite-structured waste forms demonstrated an approach that can predict the compositions of ceramic waste forms and their long-term dissolution rate by a combination of computational techniques including machine learning, first-principles thermodynamics calculations, and modeling using kinetic rate equations based on critical laboratory experiments. By integrating the predictions of elemental incorporation and degradation kinetics in a holistic framework, the approach could be promising for the design of advanced ceramic waste forms with optimized incorporation capacity and environmental degradation performance. Such an approach could provide a path for accelerated ceramic waste form development and performance prediction for problematic nuclear waste elements.

In vivo ephaptic coupling allows memory network formation.

It is increasingly clear that memories are distributed across multiple brain areas. Such "engram complexes" are important features of memory formation and consolidation. Here, we test the hypothesis that engram complexes are formed in part by bioelectric fields that sculpt and guide the neural activity and tie together the areas that participate in engram complexes. Like the conductor of an orchestra, the fields influence each musician or neuron and orchestrate the output, the symphony. Our results use the theory of synergetics, machine learning, and data from a spatial delayed saccade task and provide evidence for in vivo ephaptic coupling in memory representations.

Information-Theoretic Analysis of Minimax Excess Risk

Two main concepts studied in machine learning theory are generalization gap (difference between train and test error) and excess risk (difference between test error and the minimum possible error). While information-theoretic tools have been used extensively to study the generalization gap of learning algorithms, the information-theoretic nature of excess risk has not yet been fully investigated. In this paper, some steps are taken toward this goal. We consider the frequentist problem of minimax excess risk as a zero-sum game between the algorithm designer and the world. Then, we argue that it is desirable to modify this game in a way that the order of play can be swapped. We then prove that, under some regularity conditions, if the world and designer can play randomly the duality gap is zero and the order of play can be changed. In this case, a Bayesian problem surfaces in the dual representation. This makes it possible to utilize recent information-theoretic results on minimum excess risk in Bayesian learning to provide bounds on the minimax excess risk. We demonstrate the applicability of the results by providing information theoretic insight on two important classes of problems: classification when the hypothesis space has finite VC-dimension, and regularized least squares.

Нелинейная фильтрация сигналов распределенной движущейся цели при траекторной обработке

This paper introduces a novel algorithm for multi–extended object tracking, which is based on probabilistic–statistical modelling, machine learning, and optimization theory. The proposed approach encompasses methods for modelling the state of extended objects, data association, and predicting and updating the state of extended objects at each time step. The performance of the algorithm was assessed and compared with other existing algorithms using simulation modelling in MATLAB. This simulation emulates scenarios in which extended objects are tracked while moving under various noise levels. Simulation results demonstrate that the algorithm can effectively detect and track the trajectories of multiple extended objects under different noise levels, utilizing both linear and non–linear measurements from an array of sensors. Furthermore, the algorithm estimates not only the number and kinematic states of the targets but also provides an approximate evaluation of their size.

Similar connectivity of gut microbiota and brain activity networks is mediated by animal protein and lipid intake in children from a Mexican indigenous population.

The gut microbiota-brain axis is a complex communication network essential for host health. Any long-term disruption can affect higher cognitive functions, or it may even result in several chronic neurological diseases. The type and diversity of nutrients an individual consumes are essential for developing the gut microbiota (GM) and the brain. Hence, dietary patterns might influence networks communication of this axis, especially at the age that both systems go through maturation processes. By implementing Mutual Information and Minimum Spanning Tree (MST); we proposed a novel combination of Machine Learning and Network Theory techniques to study the effect of animal protein and lipid intake on the connectivity of GM and brain cortex activity (BCA) networks in children from 5-to 10 years old from an indigenous community in the southwest of México. Socio-ecological conditions in this nonwestern lifestyle community are very homogeneous among its inhabitants but it shows high individual heterogeneity in the consumption of animal products. Results suggest that MST, the critical backbone of information flow, diminishes under low protein and lipid intake. So, under these nonwestern regimens, deficient animal protein and lipid consumption diets may significantly affect the GM-BCA connectivity in crucial development stages. Finally, MST offers us a metric that unifies biological systems of different nature to evaluate the change in their complexity in the face of environmental pressures or disturbances. Effect of Diet on gut microbiota and brain networks connectivity.

METHODS FOR DETERMINING SIMILARITY OF CATEGORICAL ORDERED DATA

Context. The development of effective distance metrics and similarity measures for categorical features is an important task in data analysis, machine learning, and decision theory since a significant portion of object properties is described by non-numerical values. Typically, the dependence between categorical features may be more complex than simply comparing them for equality or inequality. Such attributes can be relatively similar, and to construct an effective model, it is necessary to consider this similarity when calculating distance or similarity measures.
 Objective. The aim of the study is to improve the efficiency of solving practical data analysis problems by developing mathematical tools for determining the similarity of objects based on categorical ordered features.
 Method. A distance based on weighted Manhattan distance and a similarity measure for determining the similarity of objects based on categorical ordinal features (i.e. a linear order with scales of preference considering the problem domain can be specified on the attribute value set) are proposed. It is proven that the distance formula satisfies the axioms of non-negativity, symmetry, triangle inequality, and upper bound, and therefore is a distance metric in the space of ranked categorical features. It is also proven that the similarity measure presented in the study satisfies the axioms of boundedness, symmetry, maximum and minimum similarity, and is described by a decreasing function.
 Results. The developed approach has been implemented in an applied problem of determining the degree of similarity between objects described by ordered categorical features.
 Conclusions. In this study, mathematical tools were developed to determine similarity between structured data described by categorical attributes that can be ordered based on a specific priority in the form of a ranking system with preferences. Their properties were analyzed. Experimental studies have shown the convenience and “intuitive understanding” of the logic of data processing in solving practical problems. The proposed approach can provide the opportunity to conduct new meaningful research in data analysis. Prospects for further research lie in the experimental use of the proposed tools in practical tasks and in studying their effectiveness.

Retracted: Validity Analysis Based on Multidimensional Pattern Analysis and Machine Learning Theory in Educational Teaching Assessment

Retracted: Validity Analysis Based on Multidimensional Pattern Analysis and Machine Learning Theory in Educational Teaching Assessment

Retracted: An Analysis of the Effectiveness of Machine Learning Theory in the Evaluation of Education and Teaching

Retracted: An Analysis of the Effectiveness of Machine Learning Theory in the Evaluation of Education and Teaching

Learning and Planning under Uncertainty for Conservation Decisions

My research focuses on new techniques in machine learning and game theory to optimally allocate our scarce resources in multi-agent settings to maximize environmental sustainability. Drawing scientific questions from my close partnership with conservation organizations, I have advanced new lines of research in learning and planning under uncertainty, inspired by the low-data, noisy, and dynamic settings faced by rangers on the frontlines of protected areas.

Physics-informed recurrent neural network modeling for predictive control of nonlinear processes

In this work, we present a physics-informed recurrent neural network (PIRNN) modeling approach, and a PIRNN-based predictive control scheme for a general class of nonlinear dynamic systems. Specifically, we first develop a hybrid data-driven and physics-guided modeling framework that integrates measurement data and mechanistic mathematical models to construct high-fidelity RNN models. Then, we derive a generalization error bound of the PIRNN model based on a nominal system model via the Rademacher complexity technique from statistical machine learning theory. Subsequently, the PIRNN model is utilized in Lyapunov-based model predictive controllers and applied to a chemical reactor example with Gaussian measurement noise to demonstrate its improved noise rejection and generalization performance in comparison to the purely data-driven and the purely physics-guided RNN-based predictive control schemes.

A review of traffic behaviour and intelligent driving at roundabouts based on a microscopic perspective

Abstract The contradiction between increasing traffic and the relatively poor roundabout infrastructure is getting stronger. The control and optimization of the macroscopic traffic flow needs to be improved to resolve congestion and safety problems at roundabouts and the connected road network. In order to better understand the gaps and trends in this field, we have systematically reviewed the main research and developments in traffic phenomena, driving behaviour, autonomous vehicles (AVs), intelligent connected vehicles and real vehicle trajectory data sets at roundabouts. The study is based on 388 papers about roundabouts, selected through a comprehensive literature search. The review demonstrates that based on a microscopic perspective, sensing, prediction, decision-making, planning and control aspects of AVs and intelligent connected vehicles can be designed and optimized to fundamentally and significantly improve traffic capacity and driving safety at roundabouts. However, the generation mechanism of traffic conflicts among traffic participants at roundabouts is complex, which is a tremendous challenge for the systematic design of AVs. Therefore, based on naturalistic driving data and machine learning theory, it is an important research direction to build driver models by learning and imitating human driver decision-making and driving behaviours.

Research on the Application of Machine Learning Technology in Intelligent Stock Selection

With the development of big data era and artificial intelligence, intelligent investment has gradually replaced artificial investment consultants for consulting and financial services. Robo-advisor can also be called robot investment, intelligent financial management, automated financial management and so on. The traditional quantitative investment model mostly depends on the indicators designed by the financial knowledge and experience of the researchers and cooperates with the economic model or strategy. Financial knowledge and experience play a major role in the construction of the quantitative investment model, so the efficiency of model development and updating is low and the human influence factors are large. The quantitative model is established through big data and intelligent algorithms, and the market is judged according to the risk preference of investors, intelligent allocation and investment of assets are carried out, and automatic strategic trading services are implemented. Based on machine learning theory, this paper studies the two types of investment in quantitative investment: quantitative timing and quantitative stock selection, and puts forward corresponding quantitative investment models. Through testing the models, it is verified that they have good profitability and risk control ability, which is a quantitative investment model that can provide guidance for investors.

A Self-Attention-Based Imputation Technique for Enhancing Tabular Data Quality

Recently, data-driven decision-making has attracted great interest; this requires high-quality datasets. However, real-world datasets often feature missing values for unknown or intentional reasons, rendering data-driven decision-making inaccurate. If a machine learning model is trained using incomplete datasets with missing values, the inferred results may be biased. In this case, a commonly used technique is the missing value imputation (MVI), which fills missing data with possible values estimated based on observed values. Various data imputation methods using machine learning, statistical inference, and relational database theories have been developed. Among them, conventional machine learning based imputation methods that handle tabular data can deal with only numerical columns or are time-consuming and cumbersome because they create an individualized predictive model for each column. Therefore, we have developed a novel imputational neural network that we term the Denoising Self-Attention Network (DSAN). Our proposed DSAN can deal with tabular datasets containing both numerical and categorical columns; it considers discretized numerical values as categorical values for embedding and self-attention layers. Furthermore, the DSAN learns robust feature expression vectors by combining self-attention and denoising techniques, and can predict multiple, appropriate substituted values simultaneously (via multi-task learning). To verify the validity of the method, we performed data imputation experiments after arbitrarily generating missing values for several real-world tabular datasets. We evaluated both imputational and downstream task performances, and we have seen that the DSAN outperformed the other models, especially in terms of category variable imputation.

A combination of machine learning model and density functional theory method to predict corrosion inhibition performance of new diazine derivative compounds

This study proposes a novel approach that combines machine learning (ML) and density functional theory (DFT) methods to construct a quantitative structure-properties relationship (QSPR) model for diazine derivatives as anti-corrosion inhibitors. A dataset is constructed by combining three existing diazine isomer datasets to represent diazine compounds. Thirty-two different ML algorithms were implemented on the dataset, and the gradient boosting regressor (GBR) model was identified as the best predictive model for diazine and each isomer dataset based on the coefficient of determination (R2) and root mean square error (RMSE) metric values. This consistency was also observed when the GBR model was implemented on four other diazine derivatives, resulting in high corrosion inhibition efficiency (CIE) values ranging from 85.02 % to 94.99 %. The DFT calculations for these derivatives also showed strong adsorption energies ranging from − 4.41 to − 6.09 eV, in line with the CIE trend obtained from the ML prediction. This novel approach can provide insights into the properties of prospective organic corrosion inhibitors prior to experimental investigations, which could accelerate the development of new and effective organic corrosion inhibitors.

Learning from fuzzy labels: Theoretical issues and algorithmic solutions

In this article we study the problem of learning from fuzzy labels (LFL), a form of weakly supervised learning in which the supervision target is not precisely specified but is instead given in the form of possibility distributions, that express the imprecise knowledge of the annotating agent. While several approaches for LFL have been proposed in the literature, including generalized risk minimization (GRM), instance-based methods and pseudo label-based learning, both their theoretical properties and their empirical performance have scarcely been studied. We address this gap by: first, presenting a review of the previous results relative to the sample complexity and generalization bounds for GRM and instance-based methods; second, studying both their computational complexity, by proving in particular the impossibility of efficiently solving LFL using GRM, as well as impossibility theorems. We then propose a novel pseudo label-based learning method, called Random Resampling-based Learning (RRL), which directly draws from ensemble learning and possibility theory and study its learning- and complexity-theoretic properties, showing that it achieves guarantees similar to those for GRM while being computationally efficient. Finally, we study the empirical performance of several state-of-the-art LFL algorithms on wide set of synthetic and real-world benchmark datasets, by which we confirm the effectiveness of the proposed RRL method. Additionally, we describe directions for future research, and highlight opportunities for further interaction between machine learning and uncertainty representation theories.