Demonstration of Machine Learning Capabilities on Internet of Things Devices
Since the problem definition mentioned in the title of this paper is very broad it was narrowed down to temperature sensing using the IoT device and demonstrating the machine learning capabilities using the TensorFlow with the Python libraries. The data was started collecting starting 1:45 PM and collected till 6:00 PM. As the temperature in India starts cooling down from 2:00 till the evening, we should be getting down-ward slope i.e temperature starts tapering down. It is clearly linear regression problem where the slope is down-ward as we proceed further in time line. If we start collecting the data in the morning and collect till after-noon we should again get the linear regression model however this time the temperature increases as we proceed in the time line till 2:00 PM.
(1) CircuitsToday.2019. CircuitsToday. Retrieved from CircuitsToday: http://www.circuitstoday.com/lm35-and-arduino-interfacing
(2) Daimen, A. 2019. Americ. From Americ: https://github.com/aymericdamien/TensorFlow-Examples
(3) Edu, K. 2019. Kean Edu. From Kean Edu: https://www.kean.edu/~fosborne/bstat/09rc.html
(4) Weka. 2019. University of Waikato. From University of Waikato: https://www.cs.waikato.ac.nz/ml/weka/