Browse Prior Art Database

Cognitive Computing in Internet of Things (IoT) Disclosure Number: IPCOM000249286D
Publication Date: 2017-Feb-15
Document File: 2 page(s) / 68K

Publishing Venue

The Prior Art Database


Disclosed is a method for intelligent data normalizing. It legitimately averages Internet of Things (IoT) data that is not normally distributed in order to leverage Cognitive Computing to gather information.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 59% of the total text.


Cognitive Computing in Internet of Things (IoT)

Internet of Things (IoT) technology generates a large amount of multivariate time series data over time for different measurements (e.g., temperature, humidity, air quality, light, noise, pressure, etc.). Given one multivariate set of time series data from one sensor in one location, businesses can leverage Cognitive Computing to gather information such as which sensor in one location is the most similar to a sensor in another location, the different measurement forecasts for each location, or group sensors by measurements, rather than by location.

No current system or method aggregates different measurements in different scales or different distributions before modeling. This relationship between normal equivalent scores and percentile ranks does not hold at values other than 1, 50, and 99. It also fails to hold in general if scores are not normally distributed. Normal Curve Equivalents (NCEs) are on an equal-interval scale.

In IoT, many sensors exist. Each sensor may output a wide variety of measurements at different time points and at different places. Without consolidating different measurements of the many sensors, performing cognitive computing in IoT may become difficult. (Figure 1)

Figure: Summary graphic

NCEs can be legitimately averaged. The novel solution is a method for intelligent data normalizing . It legitimately averages IoT data that is not normally distributed, as well as data integrating and various machine...