Machine Learning Methods For Analysis Research Articles

Analysis of machine learning methods to improve efficiency of big data processing in Industry 4.0

The article considers the basic methods of machine learning applied by individual entrepreneurs within the framework of transition to digital production to improve the efficiency of data processing, classification of existing and would-be customers and their subsequent work with them. The main attention is paid to the problem of increasing the effectiveness of methods of machine learning applied for solving the current questions. Areas of application of technology are shown. The peculiarities of machine learning are briefly analyzed. The main features and prospects of the development of Machine Learning services are shown on the basis of the concept of a step-by-step combination of the methods under consideration. One of the main algorithms for working with data is analyzed; its main features, scope and procedure are described. Recommendations are given for the further use of machine learning algorithms. The role of machine learning in the development of modern science and industry is analyzed, the main tendencies of the industry development are determined, and the practical application of big data is shown. As part of the transition to Industry 4.0, the main areas of application of machine learning, big data, Artificial Intelligence and their relations with the corresponding fields of science and production are described. The article also offers a review of the application of Artificial Intelligence and machine learning in particular in the context of the transition to digitalization and the issues of individual entrepreneurship.

ARDIS: a Swedish historical handwritten digit dataset

This paper introduces a new image-based handwritten historical digit dataset named Arkiv Digital Sweden (ARDIS). The images in ARDIS dataset are extracted from 15,000 Swedish church records which were written by different priests with various handwriting styles in the nineteenth and twentieth centuries. The constructed dataset consists of three single-digit datasets and one-digit string dataset. The digit string dataset includes 10,000 samples in red–green–blue color space, whereas the other datasets contain 7600 single-digit images in different color spaces. An extensive analysis of machine learning methods on several digit datasets is carried out. Additionally, correlation between ARDIS and existing digit datasets Modified National Institute of Standards and Technology (MNIST) and US Postal Service (USPS) is investigated. Experimental results show that machine learning algorithms, including deep learning methods, provide low recognition accuracy as they face difficulties when trained on existing datasets and tested on ARDIS dataset. Accordingly, convolutional neural network trained on MNIST and USPS and tested on ARDIS provide the highest accuracies 58.80% and 35.44%, respectively. Consequently, the results reveal that machine learning methods trained on existing datasets can have difficulties to recognize digits effectively on our dataset which proves that ARDIS dataset has unique characteristics. This dataset is publicly available for the research community to further advance handwritten digit recognition algorithms.

Reflections on study abroad: a computational linguistics approach

Study abroad and the associated sociocultural experience has been a subject of substantial interest to social science scholars and university administrators. Shedding novel light on the phenomenon, we draw on a corpus of student-authored reflective essays and apply machine learning methods for analysis of text-as-data to examine the features and the determinants of salient themes emphasized by students in their study abroad reflections. Our analysis identifies 18 different topics spanning the domains of distinctly cultural cognition, interaction with people, physical environment, and personal change. Specifics of the experience such as duration and location, timing of reflections, and observable student characteristics including gender, major, academic performance, extracurricular involvement, and socioeconomic status are all important determinants of student’s reflections. Different factors, however, matter differently with respect to students’ emphases on particular topics, a finding indicative of the complex nature of the study abroad experience.

Дослідження та експериментальний аналіз методів машинного навчання в задачах електронної комерції

Дослідження та експериментальний аналіз методів машинного навчання в задачах електронної комерції

Analysis of Machine Learning Methods in EtherCAT-Based Anomaly Detection

Today, the use of Ethernet-based protocols in industrial control systems (ICS) communications has led to the emergence of attacks based on information technology (IT) on supervisory control and data acquisition systems. In addition, the familiarity of Ethernet and TCP/IP protocols and the diversity and success of attacks on them raises security risks and cyber threats for ICS. This issue is compounded by the absence of encryption, authorization, and authentication mechanisms due to the development of industrial communications protocols only for performance purposes. Recent zero-day attacks, such as Triton, Stuxnet, Havex, Dragonfly, and Blackenergy, as well as the Ukraine cyber-attack, are possible because of the vulnerabilities of the systems; these attacksare carried by the protocols used in communication between PLC and I/O units or HMI and engineering stations. It is evident that there is a need for robust solutions that detect and prevent protocol-based cyber threats. In this paper, machine learning methods are evaluated for anomaly detection, particularly for EtherCAT-based ICS. To the best of the author's knowledge, there has been no research focusing on machine learning algorithms for anomaly detection of EtherCAT. Before testing anomaly detection, an EtherCAT-based water level control system testbed was developed. Then, a total of 16 events were generated in four categories and applied on the testbed. The dataset created was used for anomaly detection. The results showed that the k-nearest neighbors (k-NN) and support vector machine with genetic algorithm (SVM GA) models perform best among the 18 techniques applied. In addition to detecting anomalies, the methods are able to flag the attack types better than other techniques and are applicable in EtherCAT networks. Also, the dataset and events can be used for further studies since it is difficult to obtain data for ICS due to its critical infrastructure and continuous real-time operation.

Empirical Asset Pricing Via Machine Learning

We perform a comparative analysis of machine learning methods for the canonical problem of empirical asset pricing: measuring asset risk premia. We demonstrate large economic gains to investors using machine learning forecasts, in some cases doubling the performance of leading regression-based strategies from the literature. We identify the best performing methods (trees and neural networks) and trace their predictive gains to allowance of nonlinear predictor interactions that are missed by other methods. All methods agree on the same set of dominant predictive signals which includes variations on momentum, liquidity, and volatility. Improved risk premium measurement through machine learning simplifies the investigation into economic mechanisms of asset pricing and highlights the value of machine learning in financial innovation.

Machine Learning Methods for Analysis of Metabolic Data and Metabolic Pathway Modeling.

Machine learning uses experimental data to optimize clustering or classification of samples or features, or to develop, augment or verify models that can be used to predict behavior or properties of systems. It is expected that machine learning will help provide actionable knowledge from a variety of big data including metabolomics data, as well as results of metabolism models. A variety of machine learning methods has been applied in bioinformatics and metabolism analyses including self-organizing maps, support vector machines, the kernel machine, Bayesian networks or fuzzy logic. To a lesser extent, machine learning has also been utilized to take advantage of the increasing availability of genomics and metabolomics data for the optimization of metabolic network models and their analysis. In this context, machine learning has aided the development of metabolic networks, the calculation of parameters for stoichiometric and kinetic models, as well as the analysis of major features in the model for the optimal application of bioreactors. Examples of this very interesting, albeit highly complex, application of machine learning for metabolism modeling will be the primary focus of this review presenting several different types of applications for model optimization, parameter determination or system analysis using models, as well as the utilization of several different types of machine learning technologies.

Empirical Asset Pricing via Machine Learning

We perform a comparative analysis of machine learning methods for the canonical problem of empirical asset pricing: measuring asset risk premia. We demonstrate large economic gains to investors using machine learning forecasts, in some cases doubling the performance of leading regression-based strategies from the literature. We identify the best performing methods (trees and neural networks) and trace their predictive gains to allowance of nonlinear predictor interactions that are missed by other methods. All methods agree on the same set of dominant predictive signals which includes variations on momentum, liquidity, and volatility. Improved risk premium measurement through machine learning simplifies the investigation into economic mechanisms of asset pricing and highlights the value of machine learning in financial innovation.

Аналіз методів машинного навчання для раннього детектування та прогнозування епілептичних нападів

The comparative analysis of machine learning methods has performed to solve the problem of early detection and prediction of epileptic seizures using electroencephalographic signals. Recent studies has shown that it is possible to predict seizures in prior of its physical appearance. Our goal is to present and analyse different approaches of seizure prediction techniques, particulary in machine learning and deep learning. Seizure prediction has made important advances over the last decade, nevertheless it is still a problem to provide steady algorithm of seizure early detection. Also, within individual patients exhibit distinctive dynamics, is it cruicial to find algorithms providing greater clinical utility. This article focuses of the problem of features development from electroencephalography signals in order to provide the accurate pattern recognition techniques for detection and classification of epilepsy seizures in advance. The mathematical model of the algorithms is constructed and quantitative data presented for estimating the methods efficiency.

A comparative analysis of machine learning methods for classification type decision problems in healthcare

Abstract Advanced analytical techniques are gaining popularity in addressing complex classification type decision problems in many fields including healthcare and medicine. In this exemplary study, using digitized signal data, we developed predictive models employing three machine learning methods to diagnose an asthma patient based solely on the sounds acquired from the chest of the patient in a clinical laboratory. Although, the performances varied slightly, ensemble models (i.e., Random Forest and AdaBoost combined with Random Forest) achieved about 90% accuracy on predicting asthma patients, compared to artificial neural networks models that achieved about 80% predictive accuracy. Our results show that non-invasive, computerized lung sound analysis that rely on low-cost microphones and an embedded real-time microprocessor system would help physicians to make faster and better diagnostic decisions, especially in situations where x-ray and CT-scans are not reachable or not available. This study is a testament to the improving capabilities of analytic techniques in support of better decision making, especially in situations constraint by limited resources.

Automatic machine learning methods for analysis of signals from accelerometers: Classification of human activity and walking–running speed estimation

Automatic machine learning methods for analysis of signals from accelerometers: Classification of human activity and walking–running speed estimation

From Data Processing to Multivariate Validation - Essential Steps in Extracting Interpretable Information from Metabolomics Data

In metabolomics studies there is a clear increase of data. This indicates the necessity of both having a battery of suitable analysis methods and validation procedures able to handle large amounts of data. In this review, an overview of the metabolomics data processing pipeline is presented. A selection of recently developed and most cited data processing methods is discussed. In addition, commonly used chemometric and machine learning analysis methods as well as validation approaches are described.

A Synergistic Combination of Supervised Machine Learning Methods for Analysis of White Matter Lesions in Neuropsychiatric Systemic Lupus Erythematosus

A Synergistic Combination of Supervised Machine Learning Methods for Analysis of White Matter Lesions in Neuropsychiatric Systemic Lupus Erythematosus

Comparative Analysis of Machine Learning Methods in Ligand-Based Virtual Screening of Large Compound Libraries

Machine learning methods have been explored as ligand-based virtual screening tools for facilitating drug lead discovery. These methods predict compounds of specific pharmacodynamic, pharmacokinetic or toxicological properties based on their structure-derived structural and physicochemical properties. Increasing attention has been directed at these methods because of their capability in predicting compounds of diverse structures and complex structure-activity relationships without requiring the knowledge of target 3D structure. This article reviews current progresses in using machine learning methods for virtual screening of pharmacodynamically active compounds from large compound libraries, and analyzes and compares the reported performances of machine learning tools with those of structure-based and other ligand-based (such as pharmacophore and clustering) virtual screening methods. The feasibility to improve the performance of machine learning methods in screening large libraries is discussed.

Improved machine learning method for analysis of gas phase chemistry of peptides

BackgroundAccurate peptide identification is important to high-throughput proteomics analyses that use mass spectrometry. Search programs compare fragmentation spectra (MS/MS) of peptides from complex digests with theoretically derived spectra from a database of protein sequences. Improved discrimination is achieved with theoretical spectra that are based on simulating gas phase chemistry of the peptides, but the limited understanding of those processes affects the accuracy of predictions from theoretical spectra.ResultsWe employed a robust data mining strategy using new feature annotation functions of MAE software, which revealed under-prediction of the frequency of occurrence in fragmentation of the second peptide bond. We applied methods of exploratory data analysis to pre-process the information in the MS/MS spectra, including data normalization and attribute selection, to reduce the attributes to a smaller, less correlated set for machine learning studies. We then compared our rule building machine learning program, DataSqueezer, with commonly used association rules and decision tree algorithms. All used machine learning algorithms produced similar results that were consistent with expected properties for a second gas phase mechanism at the second peptide bond.ConclusionThe results provide compelling evidence that we have identified underlying chemical properties in the data that suggest the existence of an additional gas phase mechanism for the second peptide bond. Thus, the methods described in this study provide a valuable approach for analyses of this kind in the future.