Application of Facebook's Prophet Algorithm for Successful Sales Forecasting Based on Real-world Data
E. Žunić, K. Korjenić, und K. Hodžić. International Journal of Computer Science & Information Technology (IJCSIT), 12 (2):
25 - 36(April 2020)
Zusammenfassung
In this paper, feature tracking based and histogram based traffic congestion detection systems are developed. Developed all system are designed to run as real time application. In this work, ORB (Oriented FAST and Rotated BRIEF) feature extraction method have been used to develop feature tracking based traffic congestion solution. ORB is a rotation invariant, fast and resistant to noise method and contains the power of FAST and BRIEF feature extraction methods. Also, two different approaches, which are standard deviation and weighed average, have been applied to find out the congestion information by using histogram of the image to develop histogram based traffic congestion solution. Both systems have been tested on different weather conditions such as cloudy, sunny and rainy to provide various illumination at both daytime and night. For all developed systems performance results are examined to show the advantages and drawbacks of these systems.
%0 Journal Article
%1 uni2020application
%A Žunić, Emir
%A Korjenić, Kemal
%A Hodžić, Kerim
%D 2020
%J International Journal of Computer Science & Information Technology (IJCSIT)
%K Backtesting Classification Prophet Real-world Sales dataset forecasting
%N 2
%P 25 - 36
%T Application of Facebook's Prophet Algorithm for Successful Sales Forecasting Based on Real-world Data
%U http://airccse.org/journal/ijcsit2020_curr.html
%V 12
%X In this paper, feature tracking based and histogram based traffic congestion detection systems are developed. Developed all system are designed to run as real time application. In this work, ORB (Oriented FAST and Rotated BRIEF) feature extraction method have been used to develop feature tracking based traffic congestion solution. ORB is a rotation invariant, fast and resistant to noise method and contains the power of FAST and BRIEF feature extraction methods. Also, two different approaches, which are standard deviation and weighed average, have been applied to find out the congestion information by using histogram of the image to develop histogram based traffic congestion solution. Both systems have been tested on different weather conditions such as cloudy, sunny and rainy to provide various illumination at both daytime and night. For all developed systems performance results are examined to show the advantages and drawbacks of these systems.
@article{uni2020application,
abstract = {In this paper, feature tracking based and histogram based traffic congestion detection systems are developed. Developed all system are designed to run as real time application. In this work, ORB (Oriented FAST and Rotated BRIEF) feature extraction method have been used to develop feature tracking based traffic congestion solution. ORB is a rotation invariant, fast and resistant to noise method and contains the power of FAST and BRIEF feature extraction methods. Also, two different approaches, which are standard deviation and weighed average, have been applied to find out the congestion information by using histogram of the image to develop histogram based traffic congestion solution. Both systems have been tested on different weather conditions such as cloudy, sunny and rainy to provide various illumination at both daytime and night. For all developed systems performance results are examined to show the advantages and drawbacks of these systems.},
added-at = {2020-05-13T12:33:51.000+0200},
author = {Žunić, Emir and Korjenić, Kemal and Hodžić, Kerim},
biburl = {https://www.bibsonomy.org/bibtex/240a2e994a15c31ae753eb6eaea1960c9/shamerjose},
interhash = {022d0ee3b9cccbe363b7d3ab0251c2f4},
intrahash = {40a2e994a15c31ae753eb6eaea1960c9},
journal = {International Journal of Computer Science & Information Technology (IJCSIT) },
keywords = {Backtesting Classification Prophet Real-world Sales dataset forecasting},
month = {April},
number = 2,
pages = {25 - 36},
timestamp = {2020-05-13T12:36:19.000+0200},
title = {Application of Facebook's Prophet Algorithm for Successful Sales Forecasting Based on Real-world Data},
url = {http://airccse.org/journal/ijcsit2020_curr.html},
volume = 12,
year = 2020
}