HIM 650 Topic 8 Machine Learning Assignment
Introduction
The analysis or study of computer algorithms that automatically improve operational processes through the use of data and experience is referred to as machine learning. Machine learning is a subset of artificial intelligence. In machine learning, models’ algorithms are developed based on sample data collected from study participants over a set period of time. In machine learning, sample data is also known as “training data.” The data types are used to make decisions or forecasts without being explicitly programmed to do so (Choudhary & Gianey, 2017). The algorithms developed or produced by machine learning can be used in a variety of applications such as email filtering, computer vision, and medicine.
In the aforementioned cases, it is normally impractical or difficult to develop conventional algorithms to undertake or perform the required tasks. The subset of machine learning is directly associated with or related to computational statistics, which primarily focuses on predicting various situations using computers. However, not all machine learning is classified as statistical learning (Burkov, 2019).
The study and analysis of mathematical optimization produces theory, methods, and application domains in the field of machine learning. There is always exploratory data analysis and data mining in machine learning, which are done through unsupervised learning. Predictive analytics is another term for machine learning. This assignment’s goal is to describe and assess machine learning processes and techniques used in health care.
Data mining and machine learning are terms used to describe the examination and study of computer algorithms that automatically enhance operational processes via the use of data and experience. Artificial intelligence includes machine learning, which is a subset of artificial intelligence. When it comes to machine learning, algorithms for models are constructed based on sample data obtained from study participants over a specified period of time. Sample data is frequently referred to as “training data” in the context of machine learning. Without being specifically designed to do so, the data kinds are used to generate choices or forecasts without the need for additional programming (Choudhary & Gianey, 2017). A wide range of applications, including email filtering, computer vision, and medicine, can make use of the algorithms established or produced by machine learning.
The development of standard algorithms to undertake or complete the essential activities in the aforementioned situations is typically impracticable or difficult in the circumstances described above. The subset of machine learning that is directly associated with or related to computational statistics, which is largely concerned with forecasting various circumstances using computers, is known as computational statistics. Not all machine learning, on the other hand, is characterized as statistical learning (Burkov, 2019).
In the discipline of machine learning, the study and analysis of mathematical optimization results in the development of theory, methodologies, and application fields. When it comes to machine learning, there is no shortage of exploratory data analysis and data mining, which are accomplished through unsupervised learning. Machine learning is referred to as predictive analytics in some circles. The purpose of this assignment is to define and evaluate machine learning methods and techniques that are employed in the field of health care.
The contrast between data sets that have been categorized and those that have not
Whenever possible, machine learning takes into consideration both labeled and unlabeled datasets. The unlabeled data consists of samples of man-made or natural artifacts that can be obtained quickly and readily through any technique or collection method.
Examples of unlabeled data include films, photographs, audio recordings, articles, and other types of media. When unlabeled data is collected, there is never any labeling or description of the variables that were employed in the data gathering operations. Data that hasn’t been tagged consists just of data and nothing else (Uddin et al., 2019). A large portion of the labeled data is made up of previously unlabeled material that has been tagged. In other words, the labeled data consists of facts and figures that are accompanied with appropriately labeled variables. Labeled data also contains important information that can be used to Help readers in their decision-making process. In a nutshell, labeled data refers to sets of samples that have been marked with a certain label. It is customary for labeling processes to accept unlabeled data sets as well as arguments. Most of the time, data labeling is accomplished by requesting that individuals or humans make suitable judgments about a particular piece of unlabeled data.
Computer-Aided Design with Supervision
When employing supervised machine learning, systems or machines are trained based on data that has been collected over a specified period of time and saved in databases. In many cases, labeled data that has been collected and cleaned is used in supervised machine learning. Data that has tags or labels that can be read directly is referred to as labeled data.
The distinction between labeled and unlabeled data sets
Machine learning always takes into account both labeled and unlabeled datasets. The unlabeled data is made up of samples of man-made or natural artifacts that can be obtained easily through any process.
Unlabeled data examples include videos, photos, audio recordings, articles, and so on. There is never any labeling or explanation of variables used in the data collection processes for unlabeled data. The unlabeled data consists of only the data and nothing else (Uddin et al., 2019). The labeled data is primarily composed of unlabeled data that has been tagged. In other words, the labeled data contains facts and figures with well-labeled variables. Labeled data also contains informative information that can help readers make decisions. Labeled data, in a nutshell, refers to groups of samples that have been labeled. Labeling processes typically take unlabeled data sets as well as arguments. Data labeling is typically obtained by asking people or humans to make appropriate judgments on a given piece of unlabeled data.
Machine Learning with Supervision
In supervised machine learning, systems or machines are trained using data collected over a set period of time and stored in databases. Supervised machine learning frequently makes use of labeled data that has been collected and cleaned. Labeled data is data that has tags or labels that can be read directly.
There is a close relationship between supervised learning and actual learning that occurs in the classroom (Osisanwo et al., 2017). In supervised machine learning, various analytics tools are used.
Depending on the type of data or variables considered in the study, these tools are always used. For example, Accord.net is one of the tools used in supervised machine learning to analyze data.
Accord.net frequently includes both audio and image packages. These packages help with model training as well as the development of interactive applications. TensorFlow and Scikit-Learn are two other tools that can be used. TensorFlow is an open-source framework that is always useful for numerical ML.
Click here to ORDER an A++ paper from our Verified MASTERS and DOCTORATE WRITERS: HIM 650 Topic 8 Machine Learning Assignment
The above tools were chosen based on the types of data that are typically used in the supervised machine learning approach. The tools can recognize labels or tags in the dataset provided to improve information analysis via the machine learning process. Accord.net is one of the tools used in supervised machine learning to analyze data (Zhang, 2020). Accord.net frequently includes both audio and image packages.
Depending on the type of data or information that needs to be analyzed, the tools can be used singly or in combination. TensorFlow is an open-source framework that is always useful for numerical ML.
Machine Learning Methodology
In machine learning, artificial intelligence provides various devices with the capability or ability to learn from experiences and improve without the use of coding or actual program development. Machine learning is expected to make life or various processes easier. Machine learning processes primarily involve computers that are not explicitly programmed.
The Use of Machine Learning in Healthcare
The use of machine learning has significantly altered healthcare processes. Machine learning enables or facilitates clinicians’ ability to identify, diagnose, and treat various types of complications or diseases.
Machine learning can also be used to automate various healthcare tasks and improve surgical planning.
HIM 650 Topic 8 Machine Learning Assignment
The purpose of this assignment is to describe and evaluate machine learning processes and techniques used in health care. In a 750-1,000 word essay, address the following:
Pick either supervised or unsupervised machine learning and discuss the type analytic tool that is used to analyze the data sets.
Describe the difference between labeled data sets and unlabeled data sets.
Discuss the rationale for selecting the analytic tool that was selected to analyze supervised vs. unsupervised machine learning.
Discuss the machine learning process?
Provide examples of the uses of machine learning in health care.
RUBIC
Machine Learning
No of Criteria: 10 Achievement Levels: 5
Criteria
Achievement Levels
DescriptionPercentage
1: Unsatisfactory
0.00 %
2: Less Than Satisfactory
74.00 %
3: Satisfactory
79.00 %
4: Good
87.00 %
5: Excellent
100.00 %
Criteria
100.0
Difference Between Labeled and Unlabeled Data Sets
14.0
The description of the difference between labeled and unlabeled data sets is not present.
The description of the difference between labeled and unlabeled data sets is present but lacks detail or is incomplete.
The description of the difference between labeled and unlabeled data sets is present.
The description of the difference between labeled and unlabeled data sets is detailed.
The description of the difference between labeled and unlabeled data sets is thorough.
Discussion of Supervised vs. Unsupervised Machine Learning and Type of Analytic Tools Used to Analyze Data Sets
14.0
The discussion of supervised vs. unsupervised machine learning and the type of analytic tools used to analyze the data sets is not present.
The discussion of supervised vs. unsupervised machine learning and the type of analytic tools used to analyze the data sets is present but lacks detail or is incomplete.
The discussion of supervised vs. unsupervised machine learning and the type of analytic tools used to analyze the data sets is present.
The discussion of supervised vs. unsupervised machine learning and the type of analytic tools used to analyze the data sets is detailed.
The discussion of supervised vs. unsupervised machine learning and the type of analytic tools used to analyze the data sets is thorough.
Rationale for Selecting Analytic Tool to Analyze Supervised vs. Unsupervised Machine Learning
14.0
The discussion of the rationale for selecting the analytic tool to analyze supervised vs. unsupervised machine learning is not present.
The discussion of the rationale for selecting the analytic tool to analyze supervised vs. unsupervised machine learning is present but lacks detail or is incomplete.
The discussion of the rationale for selecting the analytic tool to analyze supervised vs. unsupervised machine learning is present.
The discussion of the rationale for selecting the analytic tool to analyze supervised vs. unsupervised machine learning is detailed.
The discussion of the rationale for selecting the analytic tool to analyze supervised vs. unsupervised machine learning is thorough.
Machine Learning Process
14.0
The discussion of the machine learning process is not present.
The discussion of the machine learning process is present but lacks detail or is incomplete.
The discussion of the machine learning process is present.
The discussion of the machine learning process is detailed.
The discussion of the machine learning process is thorough.
Examples of the Uses of Machine Learning in Health Care
14.0
The discussion of examples of the uses of machine learning in health care is not present.
The discussion of examples of the uses of machine learning in health care is present but lacks detail or is incomplete.
The discussion of examples of the uses of machine learning in health care is present.
The discussion of examples of the uses of machine learning in health care is detailed.
The discussion of examples of the uses of machine learning in health care is thorough.
Thesis Development and Purpose
7.0
Paper lacks any discernible overall purpose or organizing claim.
Thesis is insufficiently developed or vague. Purpose is not clear.
Thesis is apparent and appropriate to purpose.
Thesis is clear and forecasts the development of the paper. Thesis is descriptive and reflective of the arguments and appropriate to the purpose.
Thesis is comprehensive and contains the essence of the paper. Thesis statement makes the purpose of the paper clear.
Argument Logic and Construction
8.0
Statement of purpose is not justified by the conclusion. The conclusion does not support the claim made. Argument is incoherent and uses noncredible sources.
Sufficient justification of claims is lacking. Argument lacks consistent unity. There are obvious flaws in the logic. Some sources have questionable credibility.
Argument is orderly, but may have a few inconsistencies. The argument presents minimal justification of claims. Argument logically, but not thoroughly, supports the purpose. Sources used are credible. Introduction and conclusion bracket the thesis.
Argument shows logical progressions. Techniques of argumentation are evident. There is a smooth progression of claims from introduction to conclusion. Most sources are authoritative.
Clear and convincing argument that presents a persuasive claim in a distinctive and compelling manner. All sources are authoritative.
Criteria 2Mechanics of Writing (includes spelling, punctuation, grammar, language use)
5.0
Surface errors are pervasive enough that they impede communication of meaning. Inappropriate word choice or sentence construction is used.
Frequent and repetitive mechanical errors distract the reader. Inconsistencies in language choice (register) or word choice are present. Sentence structure is correct but not varied.
Some mechanical errors or typos are present, but they are not overly distracting to the reader. Correct and varied sentence structure and audience-appropriate language are employed.
Prose is largely free of mechanical errors, although a few may be present. The writer uses a variety of effective sentence structures and figures of speech.
Writer is clearly in command of standard, written, academic English.
Paper Format (use of appropriate style for the major and assignment)
5.0
Template is not used appropriately or documentation format is rarely followed correctly.
Appropriate template is used, but some elements are missing or mistaken. A lack of control with formatting is apparent.
Appropriate template is used. Formatting is correct, although some minor errors may be present.
Appropriate template is fully used. There are virtually no errors in formatting style.
All format elements are correct.
Documentation of Sources (citations, footnotes, references, bibliography, etc., as appropriate to assignment and style)
5.0
Sources are not documented.
Documentation of sources is inconsistent or incorrect, as appropriate to assignment and style, with numerous formatting errors.
Sources are documented, as appropriate to assignment and style, although some formatting errors may be present.
Sources are documented, as appropriate to assignment and style, and format is mostly correct.
Sources are completely and correctly documented, as appropriate to assignment and style, and format is free of error.
Total Percentage 100
