IMPLEMENTASI DEEP LEARNING DENGAN METODE CONVOLUTIONAL NEURAL NETWORK UNTUK IDENTIFIKASI OBJEK SECARA REAL TIME BERBASIS ANDROID

Indra Fransiskus Alam, Muhammad Ihsan Sarita, Adha Mashur Sajiah

Abstract


The development of artificial intelligence has now undergone significant changes. This underlies the birth of a method to deal with object detection in real time with high accuracy. Basically Deep Learning is the implementation of the basic concept of Machine Learning which applies the smart algorithm with more layers between the input layer and the output layer. Convolutional Neural Network (CNN) is one method of Deep learning (DL) that can be used to detect and recognize an object in a digital image. The ability of CNN is claimed to be the best model to solve the problem of object detection and object recognition because it is a development of the backpropagation method and does not require large computation in the process. The results obtained in this study that android applications can run well with an accuracy of 92.33% can be seen from the test results using the 10-fold cross validation method, all available menus can be run and the mention of object labels is appropriate for image recognition and classification. Calculation of precision and recall has good values, each at 97.51% and 94.33%. In the classification process, objects that do not exist in datasets that have been modeled by the system will be null or unrecognized, especially in the image of an object captured by an Android camera that has many objects and is close together


Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Copyright (c) 2019 semanTIK

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.


Editor's Address :

Informatics Engineering Department of Halu Oleo University, Engineering Faculty Building 3rd Floor
H.E.A. Mokodompit Street, Bumi Tridharma Green Campus, Halu Oleo University

Telp. (0401) 3196237
Fax. (0401) 3195287
Website:http://ojs.uho.ac.id/index.php/semantik/index
E-mail: semantik.informatika@uho.ac.id