Machine Learning in Studying the Organism’s Functional State of Clinically Healthy Individuals Depending on Their Immune Reactivity

Data Mining ◽

10.4018/978-1-4666-2455-9.ch046 ◽

2013 ◽

pp. 893-919

Author(s):

Tatiana V. Sambukova

Keyword(s):

Machine Learning ◽

Data Analysis ◽

Functional State ◽

Information Gain ◽

Decision Rules ◽

Interval Data ◽

Immune Reactivity ◽

Data Sets ◽

Numerical Attributes ◽

Learning Procedure

The work is devoted to the decision of two interconnected key problems of Data Mining: discretization of numerical attributes, and inferring pattern recognition rules (decision rules) from training set of examples with the use of machine learning methods. The method of discretization is based on a learning procedure of extracting attribute values’ intervals the bounds of which are chosen in such a manner that the distributions of attribute’s values inside of these intervals should differ in the most possible degree for two classes of samples given by an expert. The number of intervals is defined to be not more than 3. The application of interval data analysis allowed more fully than by traditional statistical methods of comparing distributions of data sets to describe the functional state of persons in healthy condition depending on the absence or presence in their life of the episodes of secondary deficiency of their immunity system. The interval data analysis gives the possibility (1) to make the procedure of discretization to be clear and controlled by an expert, (2) to evaluate the information gain index of attributes with respect to the distinguishing of given classes of persons before any machine learning procedure (3) to decrease crucially the machine learning computational complexity.

Download Full-text

A Comparison of Machine Learning Algorithms of Big Data for Time Series Forecasting Using Python

Open Source Software for Statistical Analysis of Big Data - Advances in Computer and Electrical Engineering ◽

10.4018/978-1-7998-2768-9.ch007 ◽

2020 ◽

pp. 197-218

Author(s):

Son Nguyen ◽

Anthony Park

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Time Series ◽

Big Data ◽

Data Analysis ◽

Big Data Analysis ◽

Time Series Forecasting ◽

Machine Learning Algorithms ◽

Time Series Models ◽

Data Sets

This chapter compares the performances of multiple Big Data techniques applied for time series forecasting and traditional time series models on three Big Data sets. The traditional time series models, Autoregressive Integrated Moving Average (ARIMA), and exponential smoothing models are used as the baseline models against Big Data analysis methods in the machine learning. These Big Data techniques include regression trees, Support Vector Machines (SVM), Multilayer Perceptrons (MLP), Recurrent Neural Networks (RNN), and long short-term memory neural networks (LSTM). Across three time series data sets used (unemployment rate, bike rentals, and transportation), this study finds that LSTM neural networks performed the best. In conclusion, this study points out that Big Data machine learning algorithms applied in time series can outperform traditional time series models. The computations in this work are done by Python, one of the most popular open-sourced platforms for data science and Big Data analysis.

Download Full-text

Investigation of Classifiers Algorithms of ML for Heart Disease Prediction

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.35686 ◽

2021 ◽

Vol 9 (VI) ◽

pp. 3025-3033

Author(s):

Ved Prakash Singh

Keyword(s):

Machine Learning ◽

Heart Disease ◽

Data Analysis ◽

Movement Disorders ◽

Learning Technologies ◽

The Body ◽

Data Sets ◽

K Nearest Neighbors ◽

Key Factor ◽

Ultimate Objective

A ML computer plays an important role in predicting the presence or absence of movement disorders and heart disease. The resting part of the body as compared to the Heart s, is the largest and most concentrated organ in the human body. Data analysis helps in predicting heart disease in the medical field is an important task. Machine learning is recycled in the medical industry throughout the world. The presence or absence of movement disorders and cardiac diseases is a key factor in machine learning. Data analysis helps predict more information and prevents various diseases in medical centers. The main impartial of the research paper is toward predict a patient cardiac disease using an algorithm for machine learning as a random forest is most predictable. A large number of patient data are kept every month. The data stored can be used to predict future diseases. Certain data mining and machine learning technologies are used to forecast heart disease, including artificial neural networks (ANN), decision trees, fuzzy logic, K-Nearest neighbors (KNN), naive bays and vector supporting equipment (SVM). The ultimate objective of this paper is to inspect the best logistic regression which signifies the machine's python learning. The UCI machine learning depot used the data sets of heart disease.

Download Full-text

Data Science Methods for Psychology

Psychology ◽

10.1093/obo/9780199828340-0259 ◽

2020 ◽

Author(s):

Jeffrey Stanton

Keyword(s):

Machine Learning ◽

Big Data ◽

Data Analysis ◽

Data Collection ◽

Data Science ◽

Large Data ◽

Large Data Sets ◽

Predictive Analysis ◽

Data Sets ◽

The Impact

The term “data science” refers to an emerging field of research and practice that focuses on obtaining, processing, visualizing, analyzing, preserving, and re-using large collections of information. A related term, “big data,” has been used to refer to one of the important challenges faced by data scientists in many applied environments: the need to analyze large data sources, in certain cases using high-speed, real-time data analysis techniques. Data science encompasses much more than big data, however, as a result of many advancements in cognate fields such as computer science and statistics. Data science has also benefited from the widespread availability of inexpensive computing hardware—a development that has enabled “cloud-based” services for the storage and analysis of large data sets. The techniques and tools of data science have broad applicability in the sciences. Within the field of psychology, data science offers new opportunities for data collection and data analysis that have begun to streamline and augment efforts to investigate the brain and behavior. The tools of data science also enable new areas of research, such as computational neuroscience. As an example of the impact of data science, psychologists frequently use predictive analysis as an investigative tool to probe the relationships between a set of independent variables and one or more dependent variables. While predictive analysis has traditionally been accomplished with techniques such as multiple regression, recent developments in the area of machine learning have put new predictive tools in the hands of psychologists. These machine learning tools relax distributional assumptions and facilitate exploration of non-linear relationships among variables. These tools also enable the analysis of large data sets by opening options for parallel processing. In this article, a range of relevant areas from data science is reviewed for applicability to key research problems in psychology including large-scale data collection, exploratory data analysis, confirmatory data analysis, and visualization. This bibliography covers data mining, machine learning, deep learning, natural language processing, Bayesian data analysis, visualization, crowdsourcing, web scraping, open source software, application programming interfaces, and research resources such as journals and textbooks.

Download Full-text

Artificial Intelligence

Manual of Digital Earth ◽

10.1007/978-981-32-9915-3_10 ◽

2019 ◽

pp. 357-385

Author(s):

Eric Guérin ◽

Orhun Aydin ◽

Ali Mahdavi-Amiri

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Virtual Reality ◽

Data Analysis ◽

Generative Models ◽

Geospatial Data ◽

Great Promise ◽

Data Sets ◽

Digital Earth ◽

Data Analysis Methods

Abstract In this chapter, we provide an overview of different artificial intelligence (AI) and machine learning (ML) techniques and discuss how these techniques have been employed in managing geospatial data sets as they pertain to Digital Earth. We introduce statistical ML methods that are frequently used in spatial problems and their applications. We discuss generative models, one of the hottest topics in ML, to illustrate the possibility of generating new data sets that can be used to train data analysis methods or to create new possibilities for Digital Earth such as virtual reality or augmented reality. We finish the chapter with a discussion of deep learning methods that have high predictive power and have shown great promise in data analysis of geospatial data sets provided by Digital Earth.

Download Full-text

Machine learning, artificial neural networks and social research

Quality & Quantity ◽

10.1007/s11135-020-01037-y ◽

2020 ◽

Author(s):

Giovanni Di Franco ◽

Michele Santurro

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Artificial Neural Networks ◽

Data Analysis ◽

Social Research ◽

Heterogeneous Data ◽

Data Sets ◽

Artificial Neural ◽

Analysis Models ◽

The Impact

Abstract Machine learning (ML), and particularly algorithms based on artificial neural networks (ANNs), constitute a field of research lying at the intersection of different disciplines such as mathematics, statistics, computer science and neuroscience. This approach is characterized by the use of algorithms to extract knowledge from large and heterogeneous data sets. In addition to offering a brief introduction to ANN algorithms-based ML, in this paper we will focus our attention on its possible applications in the social sciences and, in particular, on its potential in the data analysis procedures. In this regard, we will provide three examples of applications on sociological data to assess the impact of ML in the study of relationships between variables. Finally, we will compare the potential of ML with traditional data analysis models.

Download Full-text

FCA-Based Data Analysis for Discovering Association Rules in Social Network Service

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.764-765.910 ◽

2015 ◽

Vol 764-765 ◽

pp. 910-914

Author(s):

Jeong Dong Kim ◽

Suk Hyung Hwang ◽

Doo Kwon Baik

Keyword(s):

Machine Learning ◽

Data Analysis ◽

Association Rules ◽

Formal Concept Analysis ◽

Methodological Approach ◽

Mining Machine ◽

Formal Concept ◽

Data Sets ◽

Social Network Service ◽

Conceptual Structures

Recently, Formal Concept Analysis (FCA) have been widely used for various purposes in many different domains such as data mining, machine learning, knowledge management and so on. In this paper, we introduce FCA as the basis for a practical and well founded methodological approach for data analysis which identifies conceptual structures among data sets. As well as, we propose a FCA-based data analysis for discovering association rules by using polarity from social contents. Additionally, we show the experiments that demonstrate how our data analysis approaches can be applied for knowledge discovery by using association rules.

Download Full-text