We read an interesting article on the Internet recently which succinctly describes how data analytics can easily lead to wrong conclusions.
The illustration was simple and eye-opening: A man with only two hours’ sleep the previous night rear-ends a car at a red light. Based on the data thus far, we conclude that his lack of sleep caused a lack of attention.
This is an example of a wrong conclusion drawn from data analysis. The deficiency of the analysis is that the data did not log all possible factors that had a bearing on the mishap. For instance, was the man busy tweeting from his phone at the time? Was there a defect in the road? Did the brakes fail?
The lesson here is that prior to embarking on a data analysis project, we should make sure the data is comprehensive. If it isn’t, either draw conclusions with a rider mentioning which factors were not considered, or declare that the data is insufficient for the task (this might cost you additional revenue, but will preserve your reputation).
Read the article we read
One of the most powerful tools of humankind, Big Data Analytics, is being used to locate Malaysia Airlines’ Flight 370, the plane that vanished without a trace on March 8, 2014.
DigitalGlobe is a company that has satellites take pictures of global terrain. It has taken more than 400,000 photographs of the oceans around Malaysia after March 8th and put them up for free public study on the Tomnod.com website. Go to Tomnod.com to look at the pictures and help find the aircraft.
DigitalGlobe keeps track of the locations mentioned by the public, then uses cluster analysis on the location data to find hot spots. These hotspots can then be handed over to search and rescue teams so that they can physically fly over the spot.
If this process leads discovery of the missing airliner, it will indeed be a crowning glory for Big Data Analytics.
Read more on the web: http://www.eweek.com/innovation/how-big-data-analytics-is-aiding-search-for-flight-370.html
Related posts on this blog:
A Database of Cancer-Linked Gene Mutations
Databases vs Cancer Cells: A Clash of Titans
3D printing has a good future and a bad future. On the bad side, there are 3D printers which can print working guns (read our post on that); on the good side, there are 3D printers which have started printing body parts. This post is about the good side (and it will be updated as the technology progresses).
Please note that in this post we are not talking about prosthesis that remain made out of metal or plastic after implantation: we are describing objects that morph into living tissue once they are in you.
3D printing used to rebuild British man’s face
17 March 2014
Hopefully people who have had their faces disfigured by accidents or surgery now have hope for near 100% restoration. How this accident victim’s face was reconstructed.
Californian Company Prints Liver Cells
30 December 2013
They haven’t printed a full liver (yet). At the rate at which things are going, it will happen (with FDA approval) in about 10 years. Read about it here.
Printing Ears and Noses in China
Aug 29, 2013
Researchers in China devise a 3D printer that prints from a container of cell material:
Printing body parts in China
TMG cannot create the input files for a body part printer (yet!) but can certainly create the files needed for complex mechanical parts and other solid objects. Have a look at what we can do and message us from our page on modeling for 3D printers.
Have a great day,
Our regular study of Big Data unearthed this entertaining infographic that encapsulates the state of the discipline. View it, be entertained and informed! (click on it if you need to enlarge)
Via: Wikibon Big Data
Yes, the term may soon go the way of “fantabulous”, “far out” and other conversational fossils. Big Data, ie voluminous, non-homogenous data, will soon be the norm, and therefore soon cease to be differentiated from “data” .
Here is a diagram that shows the various phases of uniqueness of several software-related firms:
Diagram source: Gartner
Right now the term is in the honeymoon period, described in the above diagram as “the peak of inflated expectations.” The diagram also indicated that in 2 – 5 years, the term will slide into the “trough of disillusionment”, along with “cloud computing” and “augmented reality.”
Also take a look at how subjects in the above trough can subsequently ramp at a low angle into the plateau of realistic significance (shown as the “plateau of productivity.”
Read more on the web here.