Akbar, M. Birky Auliya (2018) Optimasi Peramalan Metode Backpropagation Menggunakan Algoritme Genetika Pada Jumlah Penumpang Kereta Api Di Indonesia. Sarjana thesis, Universitas Brawijaya.
Abstract
Kereta api merupakan salah satu moda transportasi umum yang memiliki segmentasi peminat yang sangat tinggi, hal ini terjadi karena tingkat layanan perkeretaapian Indonesia memiliki nilai yang baik, yakni mencapai indeks 4.09 dari 5, pada tahun 2014, selain itu juga dukung denga fakta yang diungkap harian tempo (www.bisnis.tempo.co) yang menyatakan bahwa pengguna kereta api dari tahun ke tahun terus mengalami peningkatan. Namun dengan peningkatan jumlah penumpang kereta api tanpa adanya prediksi akan berakibat buruk bagi perkeretaapian di Indonesia. Untuk itu dibutuhkan suatu metode peramalan dengan hasil yang dapat dipertanggungjawabkan, dengan menggunakan metode yang populer seperti jaringan saraf tiruan backpropagation dan dilakukan optimasi dalam penentuan inisialisasi bobot (w) dengan menggunakan variabel jumlah populasi sebesar 800, jumlah generasi sebesar 20, kombinasi nilai Cr = 0.7 dan Mr = 0.3, dengan variabel utama dari jaringan saraf tiruan backpropagation yang terdiri dari jumlah iterasi sebesar 100 dan nilai alpha sebesar 0.9, juga dengan mengguanakan dataset berupa data bulanan dari bulan januari 2006 sampai dengan bulan juni 2017 berupa data timeseries, dengan data latih 100 pola data awal dan data uji 10 pola data akhir. Sehingga menghasilkan tingkat akurasi berdasarkan nilai error (MSE) sebesar 0.065869861 dari hasil hibridisasi metode jaringan sarat tiruan backpropagation dengan menggunakan algoritme genetika, sedangkan jika tanpa menggunakan hibridisasi nilai error yang didapat sebesar 0.072517977.
English Abstract
Train is one way of public transport that have very much interest in this segmentation, this happens due to the level of services railways Indonesia has good value, ie the index reached 4.09 of 5, in 2014, in addition it also supports the fact that the revealed tempo daily (www.bisnis.tempo.co) states that the train user from year to year continues to increase. However, with an increase in the number of passengers on board the train without the prediction would be bad for the railroad in Indonesia. After that, it needs a method of predicting the results that can be answered, using methods that are popular as backpropagation artificial neural networks and optimization when setting the initial balance (w) with using a variable population is 800, the amount of generation is 20, the combination of the value Cr = 0.7 and Mr = 0.3, with the main variable backpropagation artificial neural network, which consists of nuber iterations is 100 and the number of alpha is 0.9, also with use of data sets in the form of monthly data from January 2006 until June 2017 in time series data with data form, with 100 training pattern of the initial data and 10 pattern of test data of last data. So the result is the level of precision based on error value (MSE) results 0.065869861 from the results of the hybridization method backpropagation artificially neural networks using a genetic algorithm, while without using the hybridization error value is 0.072517977.
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/FTIK/2018/980/051900771 |
| Uncontrolled Keywords: | Kereta Api Indonesia, Peramalan. Jaringan Syaraf Tiruan (JST), Backpropagation, Algoritme Genetika.-Indonesian’s Railway, Forecasting, Artificial Neural Networks (ANN), Backpropagation, Genetic Algorithm |
| Subjects: | 000 Computer science, information and general works > 005 Computer programming, programs, data > 005.1 Programming |
| Divisions: | Fakultas Ilmu Komputer > Teknik Informatika |
| Depositing User: | soegeng sugeng |
| Date Deposited: | 23 Apr 2020 16:26 |
| Last Modified: | 19 Oct 2021 08:19 |
| URI: | http://repository.ub.ac.id/id/eprint/167138 |
![[thumbnail of Thumbnails conversion from text to thumbnail_lightbox]](http://repository.ub.ac.id/167138/2/lightbox.jpg) |
Other (Thumbnails conversion from text to thumbnail_lightbox)
lightbox.jpg Download (25kB) |
![[thumbnail of Thumbnails conversion from text to thumbnail_preview]](http://repository.ub.ac.id/167138/3/preview.jpg) |
Other (Thumbnails conversion from text to thumbnail_preview)
preview.jpg Download (11kB) |
![[thumbnail of Thumbnails conversion from text to thumbnail_medium]](http://repository.ub.ac.id/167138/4/medium.jpg) |
Other (Thumbnails conversion from text to thumbnail_medium)
medium.jpg Download (4kB) |
![[thumbnail of Thumbnails conversion from text to thumbnail_small]](http://repository.ub.ac.id/167138/5/small.jpg) |
Other (Thumbnails conversion from text to thumbnail_small)
small.jpg Download (1kB) |
![[thumbnail of M. Birky Auliya Akbar.pdf]](http://repository.ub.ac.id/style/images/fileicons/text.png) |
Text
M. Birky Auliya Akbar.pdf Download (2MB) |
![[thumbnail of Thumbnails conversion from text to thumbnail_lightbox]](http://repository.ub.ac.id/167138/8/lightbox.jpg) |
Other (Thumbnails conversion from text to thumbnail_lightbox)
lightbox.jpg Download (18kB) |
![[thumbnail of Thumbnails conversion from text to thumbnail_preview]](http://repository.ub.ac.id/167138/9/preview.jpg) |
Other (Thumbnails conversion from text to thumbnail_preview)
preview.jpg Download (8kB) |
![[thumbnail of Thumbnails conversion from text to thumbnail_medium]](http://repository.ub.ac.id/167138/10/medium.jpg) |
Other (Thumbnails conversion from text to thumbnail_medium)
medium.jpg Download (2kB) |
![[thumbnail of Thumbnails conversion from text to thumbnail_small]](http://repository.ub.ac.id/167138/11/small.jpg) |
Other (Thumbnails conversion from text to thumbnail_small)
small.jpg Download (1kB) |
Actions (login required)
 |
View Item |