'Data smashing' could unshackle automated discovery
From recognizing speech to identifying unusual stars, new discoveries often begin with comparison of data streams to find connections and spot outliers.
But most data comparison algorithms today have one major weakness – somewhere, they rely on a human expert to specify what aspects of the data are relevant for comparison, and what aspects aren't. But experts aren't keeping pace with the growing amounts and complexities of big data.
Cornell computing researchers have come up with a new principle they call “data smashing” for estimating the similarities between streams of arbitrary data without human intervention, and without access to the data sources. Hod Lipson, associate professor of mechanical engineering and computing and information science, and Ishanu Chattopadhyay, a former postdoctoral associate with Lipson and now at the University of Chicago, have described their method in Royal Society Interface, Oct. 1.
Data smashing is based on a new way to compare data streams. The process involves two steps. First, the data streams are algorithmically “smashed” to “annihilate” the information in each other. Then, the process measures what information remained after the collision. The more information remained, the less likely the streams originated in the same source.
Data smashing principles may open the door to understanding increasingly complex observations, especially when experts do not know what to look for, according to the researchers.
The authors demonstrated the application of their principle to data from real-world problems, including the disambiguation of electroencephalograph patterns from epileptic seizure patients; detection of anomalous cardiac activity from heart recordings; and classification of astronomical objects from raw photometry.
In all cases and without access to original domain knowledge, the researchers demonstrated performance on par with the accuracy of specialized algorithms and heuristics devised by experts.
The work in the paper, “Data smashing: Uncovering lurking order in data,” was supported by the Defense Advanced Research Projects Agency and the U.S. Army Research Office.
Study: http://rsif.royalsocietypublishing.org/content/11/101/20140826.full
Media Contact
More Information:
http://www.cornell.eduAll latest news from the category: Studies and Analyses
innovations-report maintains a wealth of in-depth studies and analyses from a variety of subject areas including business and finance, medicine and pharmacology, ecology and the environment, energy, communications and media, transportation, work, family and leisure.
Newest articles
Tackling Life-Threatening Fungal Infections Using RNA Modifications
Importance of RNA modifications for the development of resistance in fungi raises hope for more effective treatment of fungal infections. An often-overlooked mechanism of gene regulation may be involved in…
Unraveling Aphasia: Global Study Breaks Down Patients’ Struggle with Verb Tenses
An international team of researchers, including scientists from the HSE Centre for Language and Brain, has identified the causes of impairments in expressing grammatical tense in people with aphasia. They discovered…
Facing the Storm: A Prepped Up Future Against Extreme Climatic and Weather Changes
From the persistent droughts of southern Africa and Central America in the early part of the year to the more recent devastating extreme rainfall in Spain and the deadly Hurricane…