HOW TO BUY
Announcing GeoTime 5.6 For Cell Site Analysis
FCIAA 2014 and new AppleTV prize winner!
GeoTime 5.5.4 Update Release Ready For Download
GeoTime Regional Training Classes - Spring 2014 Schedule
GeoTime 5.5 Update Release
Houston HIDTA: Using Cell Phone Records In Narcotics Investigations
GeoTime Regional Trainings - Fall 2013 Schedule
New iPod Touch Winners
GeoTime 5.5 Now Shipping
UK based SmartWater using GeoTime to assist police with commercial crimes
Announcing Oculus GeoTime 5.5 for Law Enforcement
ArcNews Article on LA Clear's use of GeoTime for cell site analysis
Law and Order Magazine features GeoTime in November issue.
Introducing GeoTime 5.4: GeoTime for Law Enforcement
GeoTime iPod Draw Winner from ISS World Americas Conference
LA Clear analyst presents cell site analysis using GeoTime at the 2012 ESRI International User Conference
Police Chief Magazine Feature on 3D Visualization for Law Enforcement
GeoTime Media Library is now live
5KM RunTime Results and Winner [VIDEO]
New GeoTime Customer Case Study
ESRI UC 5KM Fun Run/Walk Route
Look, Listen, Learn, and Connect at this year’s ESRI International User Conference
Working With Device Extraction Data From Cellebrite’s UFED Logical Device
5KM RunTime Project
GeoTime: Bi-directional Workflows with ESRI ArcGIS10
2012 Olympic Torch Relay Route in CSV
Microsoft's GeoLife Project
New Webinar Schedule Posted: 4 Upcoming Presentations Added
US Geological Survey - Wildlife Tracking Analysis Webinar
Oculus GeoTime 5.3 - What’s New Overview Webinar Recording is now live
Down hill skiing GPS data now available
Cupid Strikes Again: Time Series + GIS: Together at last.
New Webinar Schedule And Registration Page Now Live
Analysis of GPS Data From A Downhill Skier - New Feature Sneak Peek
Santa's voyage if he used global population ranking to plan his route
Interactive Timeline: Michael Jackson’s Billboard Rankings
Looking At Time Series Data From ArcGIS 10
Crisis Mappers Webinar Series
Upstream Data Mining And Data Viz Go Hand In Hand
20 Visualizations to Help You Understand Crime
Investigating Money Laundering Cases: How The Who/Where/When Make All The Difference
Mapping the Mexican Drug War
Choosing Clarity over Style: World Food Prices
A Periodic Table of Visualization Methods
7 Billion: How Did we Get So Big So fast - Dynamic Visualizations and Metaphors
Announcing the new GeoTme(s) Blog
Upstream Data Mining And Data Viz Go Hand In Hand
18/11/2011 2:05:14 PM
by Sebastian Schweigert
A worthwhile read by Enrico Bertini on "Why Visualization Cannot Afford Ignoring Data Mining and Vice Versa".
Here are a few notable exerpts that we really enjoyed from his article:
- Data is full of rubbish: I repeated it several times in this blog. Data never comes for free, you have to manipulate it in order to accommodate the needs you have for your project. The most classical things you will need to deal with are: missing values, outliers detection, normalization, aggregation, sampling, etc., but every project comes with its own bag of necessary data wrangling. Each one of these requires robust and solid techniques, it is not something you can improvise. And no matter how skilled a data visualization expert you are, you will need to borrow solid techniques from dataminers, otherwise you are an amateur.
- Humans don’t scale, machines do: There is no way to visualize a billion items. really believe me, there’s no way to do that effectively. If you assign every item to one single pixel (known as pixel-based visualization), which is the maximum scalability available, you will need either a huge screen or very tiny pixels. In both cases our body has limitations. With a huge screen your perception is hampered by the maximum field of view, that is, there’s no way to embrace the whole screen with your eyes. With tiny pixels the human eye is limited by its maximum resolution. On the other hand machines do scale and can crunch monstrous amounts of data. Add a number of machines to your cluster and you have more power.
- You cannot trust black boxes. The issue of trust is very well known among dataminers: the models data mining algorithms build are often arcane and even if something seems to work, there’s no way to really understand why and how it works. Visualization has the power to shorten this gap and help model builders gain better confidence on the babies they build.
- There’s no right answer. Data Mining has a long tradition for providing tools to build models that give clear cut answers automatically: “should I give the loan to this customer or not?“. This is fine and useful and it’s been a very successful model for data mining so far. But many of the modern inquiries on data are not so clear-cut. Data analysis is often exploratory and and there’s no right answer. When mining is used for this purpose it necessarily needs a certain level of flexibility: ask a question, produce some initial results, visualize them, understand better the problem, change the parameters, use another algorithm, compare alternative results etc … and how do you do that without visualization?
Well worth the time for a full reading:
Copyright © 2014 Oculus Info Inc. All Rights Reserved.
Registered trade-marks and trade-marks are owned by Oculus Info Inc.