Materials Innovation at Argonne

 New looks at innovation with AI and HPC at Argonne.

Automatic Database Creation for Materials Discovery: Innovation From Frustration

Argonne National Laboratory  by John Spizzirri

Scientists at the U.S. Department of Energy's Argonne National Laboratory and the U.K.'s University of Cambridge have developed a method that generates automatic databases to support specific scientific disciplines, using artificial intelligence and high-performance computing (HPC). The technique can assemble databases via natural language processing (NLP) and HPC, most of which was performed at the Argonne Leadership Computing Facility. The team built a database on both material structures and material properties, using the NLP ChemDataExtractor data-mining application. Cambridge's Jacqueline Cole said, "It's probably the first such compilation of a database on such a massive scale, with 5,380 like-for-like pairs of experimental and calculated data. And because it's such a large amount, it serves as a repository in its own right and really opens the door to predicting new materials."

Matching for Identification of Antibiotics

Refreshing here is that there is no claim for AI.  We need all kinds of analytics to enhance our skills.

Computational 'Match Game' Identifies Potential Antibiotics
Carnegie Mellon News    By Byron Spice

Carnegie Mellon University (CMU) computational biologists collaborated with researchers at seven other institutions to develop a software tool that identifies bioactive molecules and the microbial genes that generate them, for assessment as potential antibiotics. The team demonstrated that MetaMiner can detect such molecules at least 100 times faster than was possible with previous techniques. MetaMiner applies genome mining methodology, analyzing gene clusters to deduce molecules the genes produce. CMU's Hosein Mohimani and Liu Cao bypassed genome mining's high susceptibility to error by building an error-tolerant search engine that finds matches between databases of microbial DNA and databases that classify molecular products according to mass spectra. With MetaMiner, the researchers identified 31 known and seven previously unknown ribosomally synthesized and post-translationally modified peptides in about 14 days; Mohimani said obtaining those results manually likely would have taken decades. ... "

Data Mining and Advertising Targets

How Data Mining Can Help Advertisers Hit Their Targets?

Wharton's Shawndra Hill discusses her research on TV ads and online search.

Podcast and text: 

Shawndra Hill, a senior fellow at the Wharton Customer Analytics Initiative, likes to dig into the details. As someone who studies data mining, she looks for new ways to apply what she finds to solve business problems. Hill’s latest research paper, “Television and Digital Advertising: Second Screen Response and Coordination with Sponsored Search,” focuses on TV ads, online search and the connections between them. The paper was co-authored with Gordon Burtch from the University of Minnesota and Michael Barto, a data scientist at Microsoft. Hill recently spoke with Knowledge@Wharton about what she found.  ... " 

Plotting Analytics Terminology

An interesting article in the SAS blog on the evolution of 'data mining', actually a term less used these days.   They quote the image below about how a number of capabilities overlap, which was published by SAS in 1998.  

The terms all still exist today,  are understood.  But how they overlap and refer to specific available methods is still very debatable.    Some are narrow, some very broad. I am involved in designing a course that addresses just this confusion today.     Worth thinking about each of the terms.

A History of Data Mining

In Dataconomy.  Quite a few things left out based on my own experience.  A little too much emphasis paid to neural methods.    Patterns of all sort were being driven by statistics since regression and Bayesian.    Still a good reminder of where we have come from.

EU's Robotic Nose for Aroma Sensory Data

A long time challenge, a system that can detect and recognize aroma.   We experimented in the area of coffee beans and blend classification, linked to optimizing machine learning.  But the existing systems could not capture the ppm variances involved.

At the time it was suggested that such a system could 'sniff out' changes in blends or even manufacturing results or emerging issues in real time.  At least the system could gather large quantities of data that could be mined for subtle, or not not so subtle changes.   We have done that in the dimension of imagery, now how about scent? Would this system take us closer to that idea?

See also  Inhalio.com

In the CACM: 
The European Union's BIOMACHINELEARNING project has created a neuromorphic network for odor recognition, running on neuromorphic hardware, which can receive real-time input from electrical gas sensors.

The project's researchers say the technology could lead to the development of a cost-effective, portable, and fully functional robotic nose.

When studying how to improve the accuracy and speed of odor detection and identification, the researchers found they could use bio-inspired signal processing to enhance the signals from sensors and resolve variations in gas concentrations resulting from of a phenomenon called "turbulence." Rapid concentration changes associated with turbulence can be resolved with inexpensive, off-the-shelf gas sensors and appropriate signal processing, according to the researchers. .... " 

Data Mining and Reporting Blog

Brought to my attention,  The Data Mining Reporting Blog, by Rosaria Silipo, Principal Data Scientist at KNIME.com AG.  The blog covers data analytics in general and not only KNIME.  Have added it to my reading list, looks to have some excellent technology value.  See the latest post:  Anomaly Detection for Predictive Maintenance with Time Series Analysis  ... of particular interest.

Cross Industry Standard Process for Data Mining

CRISP-DM ( Cross Industry Standard Process for Data Mining) which we plugged into as far back as 07, seems to have disappeared, along with its web site.  Data mining also appears to have been folded into the study and methods of data science.  In particular the decision tree aspects.  That is too bad, because the decision oriented pieces were particularly understandable to executives.    We found the tree methods indispensable.  A WP article still covers the basics . The six fundamental aspects of the process are:

  1.) Business Understanding
  2.) Data Understanding
  3.) Data Preparation
  4.) Modeling
  5.) Evaluation
  6.) Deployment

With lots of details included in each segment. Each element makes excellent points about what is to be done, what resources are needed, who is responsible and where the results go.    I see that SPSS Modeler (formerly Clementine) still embraces the concept.   Does anyone still teach this?

Free Data Mining Books and Distinction Advice

From Data On Focus.  A list of links to free data mining resources. Nicely done.  No excuse these days for not getting lots of information on the subject.  Likely lots of variance in value and need for preparatory information.    Is it data mining or machine learning or data analytics?   There is great overlap, depending upon if you are talking to an engineer, computer scientist, statistician or marketer. Each can learn from the other, and sometimes even does.   Still hoping to get more executives involved.

Python Packages for Data Mining

A good overview of the topic: Why Python?   and a number of examples of its availability.   While I have done data mining and analytics for many years, I have never used Python.  But from the few examples I have seen, as a former coder, Python appears easily learnable.  The Dataconomy site is also a good resource.

Facial Emotion Analysis

Well known work by Paul Ekman is covered in the WSJ. " ...  The Technology that Unmasks Your Hidden Emotions ... Using Psychology and Data Mining to Discern Emotions as People Shop, Watch Ads; Breeding Privacy Concerns .... Companies are amassing an enormous database of human emotions using technology that relies on algorithms to analyze people’s faces and potentially discover their deepest feelings. While the evolving technology has many potential benefits, it's also raising privacy concerns .... " .  The big databases analytics aspects of this is also interesting.

Mining Search Trends for Ad Buys

In Adage: Google mines search trends.    " ....  Two years ago, WPP's Mindshare created a tool for its client Kleenex that used Google search data to see where in the United Kingdom people were searching for things related to the flu. Based on that data, Kleenex was able to shift its TV ad spend to make sure people in those areas saw its spots. ... Now Mindshare has developed the tool into a full-fledged search-trend analyzer with Google. Called Search As Signal, the tool tracks what people are searching on Google, where around the world they're doing those searches and on what device and identifies trends. ... "  

See also Mindshare's Loop Room, which futher looks at the delivery mechanism for this kind of data. Similarities to P&G's Business Sphere.  Get the right data to the right people, in real-time.

Popular Slideshare Presentations on Data Mining

In KDNuggets:  A list of the most popular Slideshare presentations on data mining.   Slideshare can be a nice way to get an overview of a method, or even basic training for the self-motivated, or filling in your own understanding of an area of technology.

Mining Massive Datasets

Coursera course from Stanford on Mining Massive Data Sets.  " ... This class teaches algorithms for extracting models and other information from very large amounts of data. The emphasis is on techniques that are efficient and that scale well. ...  "

Hospitals Mining Your Credit Card Behavior

In Businessweek.  This scenario has been much in the news. It is starting to happen:
" ... Imagine getting a call from your doctor if you let your gym membership lapse, make a habit of buying candy bars at the checkout counter, or begin shopping at plus-size clothing stores. For patients of Carolinas HealthCare System, which operates the largest group of medical centers in North and South Carolina, such a day could be sooner than they think. Carolinas HealthCare, which runs more than 900 care centers, including hospitals, nursing homes, doctors’ offices, and surgical centers, has begun plugging consumer data on 2 million people into algorithms designed to identify high-risk patients so that doctors can intervene before they get sick. The company purchases the data from brokers who cull public records, store loyalty program transactions, and credit card purchases. ... " 

List of Visualization and Data Mining Resources

Good list of resources regarding big data and analytics.  Nicely done.  Visualization and data mining topics, a number I had not heard of,  worth knowing about.

KDNuggets for Analytics

Long before Big Data there was KDNuggets.  Well worth the follow.   Which is a  " ... Data Mining Community Top Resource for Analytics, Data Mining, and Data Science Software, Companies, Data, Jobs, Education, News, and more ... "   Run by my new colleague: Gregory Piatetsky-Shapiro, Ph.D. is the President of KDnuggets, which provides analytics and data mining consulting. Gregory is a founder of KDD (Knowledge Discovery and Data mining conferences) and is one of the leading experts in the field.  

Data Mining Day

I am planning to attend:

The Center for Business Analytics in the Carl H. Lindner College of Business at the University of Cincinnati is pleased to announce

Data Mining Day
Wednesday, February 12, 2014
Tangeman University Center
University of Cincinnati

The day will kick off with a networking breakfast where attendees will get to meet fellow analytics professionals as well as master's students from the University of Cincinnati programs in Information Systems and Business Analytics.

Our ​keynote ​speaker ​ will ​be ​John ​Elder,  ​PhD, ​of ​Elder ​Research, ​Inc. ​Dr. ​Elder ​is ​an ​international ​ expert ​and author on ​data ​mining ​as well as ​a ​well-known ​speaker ​on ​this ​subject. In addition to our keynote speaker, we will also have presentations from other leading experts on data mining. Nick Street, PhD, Professor and Department Executive Officer of the Management Sciences Department at the University of Iowa, will discuss data mining applications in healthcare. Randy Collica, Sr. Solutions Architect at SAS, will present on using text analytics to determine customers' future monetary values and future risk.

You may choose to attend only the morning sessions (including breakfast, keynote and other presentations plus lunch) or the morning plus afternoon sessions which also gives you access to the data mining software demonstrations where you will be able to choose two of three sessions offered by SAS Enterprise Miner, RapidMiner and Frontline System's XLMiner (limited number of seats available in each session).

For more information and to register, please visit: https://www.regonline.com/DataMiningDay

For more information on the Center for Business Analytics at the University of Cincinnati:
 http://business.uc.edu/centers/analytics-center.html
___________________________________________________________
Michael J. Fry, PhD
Associate Professor and Lindner Research Fellow
Assistant Director, Center for Business Analytics
Department of Operations, Business Analytics
      & Information Systems
Carl H. Lindner College of Business
University of Cincinnati
Cincinnati, OH
mike.fry@uc.edu
(513) 556 0404

Data Mining Techniques that Create Business Value

Nice summary of common techniques.  For a good start, review your business and decide which of these discoveries would give the most value.  Their definition:  " ... Data mining is a buzzword that often is used to describe the entire range of big data analytics, including collection, extraction, analysis and statistics. This however, is too broad as data mining especially refers to the discovery of previously unknown interesting patterns, unusual records or dependencies. When developing your big data strategy it is important to have a clear understanding of what data mining is and how it can help you. ... " 

Applying Data to the Education Landscape

Involved in just such a project.  How do you understand how well education is working under alternative conditions?  And how will education be adapted to changes?  A very big challenge with new support.  Via Walter Riker.  From AllthingsD:

" ... There are so many things that could be done to make schools better — improving teaching methods, curbing dropout rates, cutting down on bullying.
Panorama product shots“But there’s no way to understand what’s going on, because there’s not enough data analysis, not enough data being collected, and nobody there to analyze it,” according to Panorama Education co-founder Aaron Feuer. “This would never be acceptable at a company, because nobody would know what’s going on.” ... "