Annotation and Cluster Analysis
Q1. Read Chapter 9 in the textbook: Cluster Analysis
Textbook: Tan, Pang-Ning. Introduction to Data Mining
- What are the characteristics of anomaly detection?
- What are the detection problems and methods?
- What are the statistical approaches when there is an anomaly found?
- Compare and contrast proximity and clustering based approaches.
Follow APA7 guidelines and answer in Q&A format. There should be headings to each of the questions and include an introduction and conclusion. Ensure there are at least two-peer reviewed sources to support your work. The paper should be at least 2-3 pages of content (this does not include the cover page or reference page).
Q2. Read ch. 8 in the textbook: Annotation
Textbook: Kirk, Andy. Data Visualization: A Handbook for Data Driven Design
Select any example of a visualization or infographic. The task is to undertake a deep, detailed ‘forensic’ like assessment of the design choices made across each of the five layers of the chosen visualization’s anatomy. In each case your assessment is only concerned with one design layer at a time. For this task, take a close look at the annotation choices:
- Start by identifying all the annotation features deployed, listing them under the headers of either project or chart annotation.
- How suitable are the choices and deployment of these annotation features? If they are not, what do you think they should have been?
- Go through the set of ‘Influencing factors’ from the latter section of the book’s chapter to help shape your assessment and to possibly inform how you might tackle this design layer differently.
- Also, considering the range of potential annotation features, what would you do differently or additionally?
Be sure to show the visualization first and then thoroughly answer the above questions.
Answer in a Q&A format in 2-3 pages. Ensure that there are at least two-peer reviewed sources utilized this week to support your work.