Human Activity Recognition through Accelerometer Sensor Using Data Mining

Abstract

Balance is the key phenomenon to maintain human body in good health which requires correct human calorie intake and calorie burning. Humans performs various activity during the day, each activity performed burns different amount of calories depending on the weight of the person. Accelerometers are widely being used to detect human activity data measurement capability. Many android applications using accelerometer are available on smart phones which have wide visibility and potential market place for creation of new health care applications. An attempt is made in this paper to classify different human activities using data mining through six tri-axial accelerometer mounted over human body. The classification parameters used in this study are mean and standard deviation of each activity. Five different classification algorithms like J48, Naïve bayes, Random forest, random tree, multilayer perceptron were tested, and the best algorithm was determined.

Authors and Affiliations

Lakshmikantha K. S, M. V. Achutha, N. V. Raghavendra, Madhushekar

Keywords

Related Articles

An Efficient Design of Low Pass Fir Filter Using Kaiser, Parzen and Bartlett Hanning Window Technique

In everyday enhancing field of signal processing has digital filter to play a vital role. Digital filters are widely used in the field of communication and computation purpose. On the other hand a digital finite impulse...

Utilization of Copper Slag in Bituminous Concrete with a Stone Dust and Flyash as a Filler Material

In this paper an attempt has been made to utilize the copper slag, stone dust and fly ash in bituminous concrete. The copper slag is produced as waste from roasting of copper, in which sulphur is eliminated. Copper slag...

Gas Level Alert and Automatic Cut-Off in a Stove

this paper proposes a technique which lets us to completely eliminate any mishappenings that generally occur with the leakage of gas in a daily base Gas stove system. The system can be operated in a way as to check whet...

Performance Evaluation of Automobile Crankshaft

The crankshaft is the main component of IC engine. So the design & analysis is carried out for important aspects to get high power transmission & efficiency. Selection of suitable material plays a important role while d...

Improved Scalability and Security on Data Retrieval for Decentralized DTN’S Using CP-ABE Algorithm

Mobile Nodes in some challenging network scenarios suffer from intermittent connectivity and frequent divisions, for example in battleground if the network failure occurs then there is a chance to lose the data. Many of...

Download PDF file
  • EP ID EP21174
  • DOI -
  • Views 197
  • Downloads 7

How To Cite

Lakshmikantha K. S, M. V. Achutha, N. V. Raghavendra, Madhushekar (2018). Human Activity Recognition through Accelerometer Sensor Using Data Mining. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 3(8), -. https://europub.co.uk/articles/-A-21174