Responsive Banner

Level kesulitan adaptif pada game edukasi bencana gunung meletus menggunakan metode Artifical Neural Network Backpropagation

Khafidoh, Nurul (2022) Level kesulitan adaptif pada game edukasi bencana gunung meletus menggunakan metode Artifical Neural Network Backpropagation. Undergraduate thesis, Universitas Islam Negeri Maulana Malik Ibrahim.

[img]
Preview
Text (Fulltext)
17650041.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB) | Preview

Abstract

ABSTRACT:

Perkembangan dunia game saat ini sangatlah pesat dari masa ke masa, mulai dari game yang paling sederhana sampai yang paling rumit dalam genre apapun. Selain itu game telah digunakan dalam banyak bidang, salah satu yang paling sering digunakan adalah dalam bidang pendidikan atau biasa disebut dengan game edukasi. Metode artificial neural network backpropagation pada game edukasi bencana alam gunung meletus akan digunakan sebagai pengaturan level kesulitan adaptif guna memberikan hasil yang baik. Pada metode artificial neural network terdapat masukan (input), layar tersembunyi (hidden layer), dan keluaran (output). Berdasarkan pengujian yang telah dilakukan oleh penulis menggunakan metodee Artifical Neural Network Backpropagation diperoleh hasil arsitektur jaringan paling optimal adalah arsitektur jaringan 7-4-3-4 nilai akurasi 1, dan nilai loss 0,2341120 dengan 5 pengujian skenario yaitu 90 : 10, 80 : 20, 70 : 30, 60 : 40, 50 : 50, dan skenario uji yang optimal adalah 70 : 30.

ABSTRACT:

The development of the game world is currently very rapid from time to time, ranging from the simplest to the most complex games in any genre. In addition, games have been used in various fields, one of the most frequently used is in the field of education or commonly known as educational games. The backpropagation method of artificial neural networks in volcanic eruption natural disaster education games will be used as an adaptive difficulty level setting to give good results. In the artificial neural network method there are inputs, hidden screens, and outputs. Based on the tests that have been carried out by the author using the Artificial Neural Network Backpropagation method, the most optimal network architecture results are 7-4-3-4 network architecture with an accuracy value of 1, and a loss value of 0.2341120 with 5 test scenarios namely 90:10, 80 :20, 70:30, 60:40, 50:50, and the optimal test scenario is 70:30.

مستخلص البحث:

٢ ٍ أ ً أمثشها حؼق ُذًا ف ِ أبسظ الأىؼاب إى ٍ ِخش ، بذءًا ِ وقج ٍ ٌ اىيؼبت حاى ًُا سش َغ جذًا ُ حطىس ػاى إ
ٌ أو ُ ٍجاه اىخؼي ٍ ِ أمثشها اسخخذا ًٍا ف ٍ ٍخخيفت ، و ٍجالاث ٍ ً الأىؼاب ف ٌ اسخخذا ً رىل ، ح بالإضافت إى
اىَؼشوف باس ٌ الأىؼاب اىخؼيَُُت٢ سُخ ٌ اسخخذا ً طشَقت الاّخٍشاس اىؼنس ٍ ىيشبناث اىؼصبُت الاصطْاػُت ف
ٍ
أىؼاب حؼي ُ ٌ اىنىاسد اىطبُؼُت ىيثىسا ُ اىبشما ّ ٍ مئػذاد ىَسخىي اىصؼىبت اىخنُف ٍ لإػطاء ّخائج جُذة٢ ف
ٍ
ً الاخخباساث اىخ ٍخف ُت و ٍخشجاث٢ ب ْاء ً ػي ٍذخلاث وشاشاث طش َقت اىشبنت اىؼصب ُت الاصط ْاػ ُت ه ْاك
أجشاها اىَؤىف باسخخذا ً طشَقتالاصطْاػُتىيشبنت اىؼصبُت الاصطْاػُت ، فئ ُ أفضو ّخائج هْذست اىشبنت
ٍ
ه٧-٤-٣-٤بُْت شبنت بقَُت دقت١، وقَُت خساسة٠٢٢٣٤١١٢٠ٍغ5ٍسُْاسَىهاث اخخباس وه
٠٠:١٠، و٠٠:٢٠، و٧٠:٣٠، و٦٠:٤٠، و٥٠:٥٠، وسُْاسَى الاخخباس الأٍثو هى٧٠:٣٠

Item Type: Thesis (Undergraduate)
Supervisor: Nugroho, Fresy and Nurhayati, Hani
Contributors:
ContributionNameEmail
UNSPECIFIEDNugroho, FresyUNSPECIFIED
UNSPECIFIEDNurhayati, HaniUNSPECIFIED
Keywords: Game; Artifical Neural Network Backpropagation; Level Kesulitan Adaptif Game; Artificial Neural Network Backpropagation; Adaptive Difficulty Level. اىنيَاث اىذاىت:أىؼاب;ػىدة اّخشاس اىشبنت اىؼصبُت الاصطْاػُت;سخىي صؼىبت اىخنُف
Subjects: 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080108 Neural, Evolutionary and Fuzzy Computation
Departement: Fakultas Sains dan Teknologi > Jurusan Teknik Informatika
Depositing User: Nurul Khafidoh
Date Deposited: 09 Feb 2023 13:28
Last Modified: 09 Feb 2023 14:53
URI: http://etheses.uin-malang.ac.id/id/eprint/43126

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item