Garuda - Garba Rujukan Digital

Improving Adaptive Learning Rate With Backpropogation on Retail Rice Price Prediction in Traditional Markets Erwin Binsar Hamonangan Ompusunggu; Solikhun Solikhun; Iin Parlina; Sumarno Sumarno; Indra Gunawan
IJISTECH (International Journal of Information System and Technology) Vol 3, No 1 (2019): November
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v3i1.26

Rice is the most important staple food and carbohydrate food in the world especially people in Indonesia. This study aims to predict the retail price of rice in traditional markets using backpropogation by improvising Adaptive Learning Rate to increase the value of accuracy. Data sources were obtained from the Central Statistics Agency (BPS) in 33 provinces in Indonesia for the retail price of rice in the traditional market (Rupiah / kg) for the past 6 years (2011-2016). The results of the study state that the improvised learning rate uses 2 models: 2-10-1 and 2-15-1 (LR= 0,1; 0,5; 0,9) that the best architectural models are 4-15-1 (LR= 0.9) with an accuracy of 82%, Training MSE 0,000999936, Testing MSE 0.016051433 and Epoch 20515. The results of this study are expected to provide input to the government in providing input on predictions of retail rice prices that have an impact on the stability of rice prices in Indonesia.

Pelatihan Pemanfaatan Mendeley Desktop Sebagai Program Istimewa Untuk Akademisi Dalam Membuat Citasi Karya Ilmiah Agus Perdana Windarto; Dedy Hartama; Anjar Wanto; Iin Parlina
Aksiologiya: Jurnal Pengabdian Kepada Masyarakat Vol 2, No 2 (2018): Agustus
Publisher : Universitas Muhammadiyah Surabaya

Desktop mendeley application is actually an application intended to facilitate the creation of citations and a list of libraries commonly used by the authors, so the authors will be pressed error in making the bibliography and facilitate in obtaining the writings to be cited. In addition to creating scientific papers, this application can also be used to manage the files of online journal articles that are the output of a scientific work. Furthermore, participants can utilize this application for the purpose of making a bibliography or collection of abstracts of certain fields of journal articles subscribed. Training activities undertaken in Community Service activities show that participants have a material understanding and the potential to make refernsi managers better and maximum by utilizing mendeley desktop applications.

Artificial Neural Network Pada Industri Non Migas Sebagai Langkah Menuju Revolusi Industri 4.0 Iin Parlina; Anjar Wanto; Agus Perdana Windarto
InfoTekJar : Jurnal Nasional Informatika dan Teknologi Jaringan Vol 4, No 1 (2019): InfoTekJar September
Publisher : Universitas Islam Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30743/infotekjar.v4i1.1682

The research conducted aims to make predictions with artificial neural metwork (backpopagation) and sensitivity analysis in the non-oil processing industry for the value of industrial exports. Data was obtained from the Badan Pusat Statistik (BPS) in collaboration with the Ministry of Industry of the Republic of Indonesia in the last 7 years (2011-2017). The process is carried out by dividing the data into 2 parts (training and testing) to obtain the best architectural model. The data processing uses the help of Matlab 6.0 software. Model selection is done by try and try to get the best architectural model. In this study using 7 architectural models (15-2-1; 15-5-1; 15-10-1; 15-15-1; 15-2-5-1; 15-5-10-1 and 15- 10-5-1) who have been trained and tested. By using the help of Matlab 6.0 software, the best architectural model is obtained 15-2-1 with an accuracy rate of 93%, epoch training = 189,881, MSE testing = 0.001167108 and MSE training = 0,000999622. The best architecture will be continued to predict the non-oil industry based on the most dominant export value using sensitivity analysis. From the architectural model a prediction of 5 out of 15 non-oil and gas industries contributes: Food Beverage Industry, Textile Apparel Industry, Basic Metal Industry, Rubber Industry, Rubber and Plastic Goods and Metal Goods Industry, Not Machines and Equipment , Computers, Electronics and Optics.

Improving Adaptive Learning Rate With Backpropogation on Retail Rice Price Prediction in Traditional Markets Erwin Binsar Hamonangan Ompusunggu; Solikhun Solikhun; Iin Parlina; Sumarno Sumarno; Indra Gunawan
IJISTECH (International Journal of Information System and Technology) Vol 3, No 1 (2019): November
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Rice is the most important staple food and carbohydrate food in the world especially people in Indonesia. This study aims to predict the retail price of rice in traditional markets using backpropogation by improvising Adaptive Learning Rate to increase the value of accuracy. Data sources were obtained from the Central Statistics Agency (BPS) in 33 provinces in Indonesia for the retail price of rice in the traditional market (Rupiah / kg) for the past 6 years (2011-2016). The results of the study state that the improvised learning rate uses 2 models: 2-10-1 and 2-15-1 (LR= 0,1; 0,5; 0,9) that the best architectural models are 4-15-1 (LR= 0.9) with an accuracy of 82%, Training MSE 0,000999936, Testing MSE 0.016051433 and Epoch 20515. The results of this study are expected to provide input to the government in providing input on predictions of retail rice prices that have an impact on the stability of rice prices in Indonesia.

Prototype Alat Pengamanan Pintu dengan Menggunakan Sensor Sidik Jari Berbasis Arduino Mega2560 Rudi Handika; Dedy Hartama; Ika Okta Kirana; M. Safii; Iin Parlina
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 1 No. 6 (2021): Juni 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar

The door is the most important and important part of a room to pay attention to its safety compared to other parts because it is from the door that everyone will enter or leave. This study aims to build a door security device using a Fingerprint sensor based on Arduino Mega 256. The door that will be given a security device is the door in classes at STIKOM Tunas Bangsa Pematangsiantar. This tool can be used as a security control system at the classroom door, users do not need to use manual security such as keys, and this tool is also equipped with an alarm as a marker when the Fingerprint sensor is accessed by someone who is not the owner, this alarm will sound. This system consists of hardware and Software. The hardware consists of an Arduino Uno, Fingerprint sensor, buzzer, Selenoid door, LCD and then the Software on this system uses the Arduino IDE program. This system runs if the Fingerprint sensor detects a finger from the user, the solenoid as a door lock will open. Otherwise, if the sensor does not see a finger from the user, the solenoid as a door lock will not open, and an alarm will sound. This door safety device can effectively be used as security on classroom doors and other rooms such as leadership rooms, education rooms and staff rooms

SISTEM PENDUKUNG KEPUTUSAN DALAM SELEKSI PENYIAR RADIO BOSS FM 102.8 PEMATANG SIANTAR MENGGUNAKAN METODE ELECTRE Habibah Jayanti Damanik; Iin Parlina; Heru Satria Tambunan; Eka Irawan
KOMIK (Konferensi Nasional Teknologi Informasi dan Komputer) Vol 1, No 1 (2017): Intelligence of Cognitive Think and Ability in Virtual Reality
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/komik.v1i1.470

Radio merupakan salah satu media dengar yang masih populer dimasyarakat sampai saat ini. Ketika persaingan semakin tinggi dalam perkembangan industri penyiaran radio dimasa sekarang ini, umumnya stasiun radio siaran akan memprioritaskan calon penyiarnya yang memiliki dedikasi dan komitmen yang tinggi terhadap dunia penyiaran radio. Penyiar radio adalah orang yang bertugas membawakan atau memandu acara di radio sekaligus menjadi ujung tombak sebuah stasiun radio dalam berkomunikasi dengan pendengar. Maka dari itu pemilihan calon penyiar sangat berpengaruh terhadap kualitas radio tersebut. Seleksi penyiar radio yang dilakukan pada Radio Boss Fm 102.8 Pematangsiantar masih bersifat konvensional dan subjektif yang berdampak pada penyiar yang terpilih nantinya bukan berdasarkan dari kemampuan yang dimiliki sehingga penilaiannya menjadi kurang efektif . Untuk mengatasi masalah tersebut maka digunakan Sistem Pendukung Keputusan (SPK) dengan menggunakan metode ELECTRE. Sistem ini dibuat sebagai rekomendasi dan diharapkan dapat memudahkan Pihak radio dalam menentukan pemenang sesuai dengan kriteria yang telah mereka tentukan.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search