Loading…
Title

B3186078219.pdf - international journal of soft computing ...

Description
Sensor data along with name of the human face recognized or ... 10 and the type proportions are maintained in every fold to. 9 pages
/9
Full Text
International Journal of Recent Technology and Engineering (IJRTE)ISSN: 2277-3878, Volume-8 Issue-2, July 20193582Published By:Blue Eyes Intelligence Engineering& Sciences PublicationRetrieval Number: B3186078219/19©BEIESPDOI: 10.35940/ijrte.B3186.078219Abstract: This paper describes the construction of Internet ofThings (IoT) enabled system which not only captures the sensorsdata in textual and numeric form but also performs live humanface recognition to monitor physical location effectively. Thedataset used in order to apply supervised machine learningalgorithms is the combination of automatically captured livesensor data along with name of the human face recognized orunknown and additional manually introduced class label.Performance measurement of face recognition is done with thehelp of Decision Tree (DT), K-Nearest Neighbors (KNN), NaïveBayes (NB) and Logistic Regression (LR). The results show thatDT gives the best performance with respect to classifier’saccuracy; True Positive R...