Kurniasari, Dian and Usman, Mustofa and Warsono, Warsono and Lumbanraja, Favorisen R (2021) A DEEP NEURAL NETWORK – BASED APPROACH FOR RECOGNIZING STATISTICAL PROBABILITY DISTRIBUTIONS. In: Seminar Nasional Bersama FMIPA Unila Tahun 2021, 8-9 September 2021, Bandar Lampung. (Unpublished)

Preview

Text Abstract.pdf Download (57kB) | Preview

Abstract

The probability distribution is extremely important in data analysis. Selection of the right distribution requires critical thinking that based on adequate mastery of the characteristics of the distribution. Classically, the probability distribution is identified by several methods, such as: Chi-square goodness of fit test, graph, normal plot and non-parametric goodness of fit test. To identify probability distributions, this article proposes Deep Neural Network (DNN) approaches. Particularly, this article discusses three DNN approaches including DNN using backpropagation with two hidden layers, Artificial Neural Network (ANN) using backpropagation with one hidden layer and Fuzzy Learning Vector Quantization (FLVQ). The implementation through a simulation to identify the probability distributions results show that the DNN approach outperforms the ANN and FLVQ approaches. Key Word: Artificial Neural Network, Deep Neural Network, Fuzzy Learning Vector Quantification, and Probability Distribution.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Q Science > Q Science (General)
Depositing User:	DIAN KURNIASARI
Date Deposited:	14 Nov 2021 12:18
Last Modified:	14 Nov 2021 12:18
URI:	http://repository.lppm.unila.ac.id/id/eprint/36794

Actions (login required)

View Item