Text

SMART ATTENDANCE SYSTEM MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORKS (CNN)

---

Penilaian

---

Face clasification using the convolutional neural networks method has become an interesting research topic in recent years. development method using convolutional neural networks and facenet architecture. Research by collecting primary data from direct observation, in completing this research is of course the FaceNet model. The FaceNet model that has been built is based on the configuration that has been trained using training data of 7,600 facial image data. The results of the FaceNet model training process for training data are 100,000 for accuracy and 100,000 for test. this proves the level of accuracy of this architecture is very good in classifying faces. to classify images for presence presence using the Convolutional Neural Network model using the FaceNet architecture and gives very good classification results. The results of the FaceNet architectural model training obtained an accuracy value of 100% in the model training process. The results of the testing process on the test data set with the threshold configuration obtained an F1 score of 100% for each test data. The results of the FaceNet model training process on training data are 100,000 for accuracy and 100,000 for test. this proves the level of accuracy of this architecture is very good in classifying faces. The results of the FaceNet architectural model training obtained an accuracy value of 100% in the model training process. The results of the testing process on the test data set with the threshold configuration obtained an F1 score of 100% for each test data. The results of the FaceNet architectural model training obtained an accuracy value of 100% in the model training process. The results of the testing process on the test data set with the threshold configuration obtained an F1 score of 100% for each test data.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307001006	T87595	T875952023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T875952023

Publisher

Inderalaya : Prodi Sistem Informasi, Fakultas Ilmu Komputer, Universitas Sriwijaya., 2023

Collation

xvi, 100 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem Pakar
Prodi Sistem Informasi

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment