Article Per Year (5 Year)
p-Index From 2020 - 2025
1.99
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer UNEJ e-Proceeding Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JTAM (Jurnal Teori dan Aplikasi Matematika) Contemporary Mathematics and Applications (ConMathA) Tensor: Pure and Applied Mathematics Journal InEJ: Indonesian Engagement Journal Moneter : Jurnal Keuangan dan Perbankan
Herry Suprajitno
Departemen Matematika Fakultas Sains Dan Teknologi, Universitas Airlangga
Religion Humanities Computer Science & IT Economics, Econometrics & Finance Education Engineering Environmental Science Materials Science & Nanotechnology Mathematics Social Sciences

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
The Formula Study in Determining the Best Number of Neurons in Neural Network Backpropagation Architecture with Three Hidden Layers Syaharuddin Syaharuddin; Fatmawati Fatmawati; Herry Suprajitno
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 6 No 3 (2022): Juni 2022
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (288.715 KB) | DOI: 10.29207/resti.v6i3.4049

Abstract

The researchers conducted data simulation experiments, but they did so unstructured in determining the number of neurons in the hidden layer in the Artificial Neural Network Back-Propagation architecture. The researchers also used a general architecture consisting of one hidden layer. Researchers are still producing minimal research that discusses how to determine the number of neurons when using hidden layers. This article examines the results of experiments by conducting training and testing data using seven recommended formulas including the Hecht-Nelson, Marchandani-Cao, Lawrence & Fredrickson, Berry-Linoff, Boger-Guterman, JingTao-Chew, and Lawrence & Fredrickson modifications. We use rainfall data and temperature data with a 10-day type for the last 10 years (2012-2021) sourced from Lombok International Airport Station, Indonesia. The training and testing data used showed the results that in determining the number of neurons on the hidden-1 screen, it was more appropriate to use the Hecht-Nelson formula and the Lawrence & Fredricson formula which is more suitable for use in the 2nd & 3rd hidden layer. The resulting research was able to provide an accuracy rate of up to 97.79% (temperature data) and 99.94% (rainfall data) with an architecture of 36-73-37-19-1.
Best Architecture Recommendations of ANN Backpropagation Based on Combination of Learning Rate, Momentum, and Number of Hidden Layers Syaharuddin Syaharuddin; Fatmawati Fatmawati; Herry Suprajitno
JTAM (Jurnal Teori dan Aplikasi Matematika) Vol 6, No 3 (2022): July
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jtam.v6i3.8524

Abstract

This article discusses the results of research on the combination of learning rate values, momentum, and the number of neurons in the hidden layer of the ANN Backpropagation (ANN-BP) architecture using meta-analysis. This study aims to find out the most recommended values at each learning rate and momentum interval, namely [0.1], as well as the number of neurons in the hidden layer used during the data training process. We conducted a meta-analysis of the use of learning rate, momentum, and number of neurons in the hidden layer of ANN-BP. The eligibility data criteria of 63 data include a learning rate of 44 complete data, the momentum of 30 complete data, and the number of neurons in the hidden layer of 45 complete data. The results of the data analysis showed that the learning rate value was recommended at intervals of 0.1-0.2 with a RE model value of 0.938 (very high), the momentum at intervals of 0.7-0.9 with RE model values of 0.925 (very high), and the number of neurons in the input layer that was smaller than the number of neurons in the hidden layer with a RE model value of 0.932 (very high). This recommendation is obtained from the results of data analysis using JASP by looking at the effect size of the accuracy level of research sample data.
Grasshopper Optimizaton Algorithm (GOA) untuk Menyelesaikan Vehicle Routing Problem with Simultaneous Pickup and Delivery (VRPSPD) Anatasia Naomi; Asri Bekti Pratiwi; Herry Suprajitno
Tensor: Pure and Applied Mathematics Journal Vol 3 No 2 (2022): Tensor: Pure and Applied Mathematics Journal
Publisher : Department of Mathematics, Faculty of Mathematics and Natural Sciences, Pattimura University, Ambon, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/tensorvol3iss2pp73-84

Abstract

The purpose of this paper is to solve the Vehicle Routing Problem with Simultaneous Pickup and Delivery (VRPSPD) using the Grasshopper Optimization Algorithm (GOA). Vehicle Routing Problem with Simultaneous Pickup and Delivery (VRPSPD) is a problem of forming routes that serve each customer, by delivering and retrieving simultaneously. The purpose of VRPSPD is to minimize the total mileage to serve all customers with the limit that each customer is served exactly once, and the vehicle load does not exceed its maximum capacity. Grasshopper Optimization Algorithm (GOA) is an algorithm inspired by nature by mimicking the living behavior of grasshopper swarms in search of food sources. GOA has several main stages, namely initialization of parameters, determination of target grasshoppers, calculating the coefficient of decline, calculating the distance between grasshoppers, and calculating the new position of the grasshoppers. Implementation of the GOA program to complete VRPSPD using the C++ programming language using 3 types of data, data with 13 customers, 22 customers, and 100 customers. Based on the results of the running program, it can be concluded that the more iterations and the number of populations, the solution obtained tends to be better.
Cuckoo Search Algorithm untuk Menyelesaikan Bi-Objective Permutation Flowshop Scheduling Problem Asri Bekti Pratiwi; Herry Suprajitno; Siti Sarah
Tensor: Pure and Applied Mathematics Journal Vol 2 No 1 (2021): Tensor : Pure And Applied Mathematics Journal
Publisher : Department of Mathematics, Faculty of Mathematics and Natural Sciences, Pattimura University, Ambon, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/tensorvol2iss1pp5-12

Abstract

Tujuan dari penelitian ini adalah menyelesaikan permasalahan Bi-objective Permutation Flowshop Scheduling Problem (BPFSP) menggunakan Cuckoo Search Algorithm (CSA). BPFSP memiliki lebih dari satu fungsi tujuan yaitu meminimalkan makespan dan total tardiness. Program penerapan CSA untuk menyelesaikan BPFSP diimplementasikan dalam kasus dengan tiga jenis data yaitu data kecil dengan 5-pekerjaan 4-mesin, data sedang dengan 20-pekerjaan 10-mesin, dan data besar 50-pekerjaan 20-mesin dengan penggunaan beberapa nilai parameter yang bervariasi diantaranya maksimum iterasi, banyaknya sarang serta probabilitas pergantian sarang. Berdasarkan hasil running pada ketiga jenis data diperoleh bahwa semakin banyak jumlah sarang serta iterasi maka akan memberikan nilai fungsi tujuan BPFSP yang cenderung lebih baik. Sebaliknya, nilai fungsi tujuan BPFSP akan cenderung lebih baik jika nilai probabilitas pergantian sarang semakin kecil.
Enhancing Spare Parts Management through Support Vector Regression: A Case Study in the Service and Maintenance Industry Riwayadi, Eko; Suprajitno, Herry; Miswanto, Miswanto
Moneter: Jurnal Keuangan dan Perbankan Vol. 12 No. 2 (2024): JULI
Publisher : Universitas Ibn Khladun Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32832/moneter.v12i2.866

Abstract

This study investigates the effectiveness of Support Vector Regression (SVR) in accurately predicting spare part usage within the service and maintenance industry, with a specific focus on coolers and freezers. Leveraging historical data from Hutama spanning January 2019 to December 2023, the SVR model successfully forecasts future spare parts demand with remarkable precision. Through rigorous parameter tuning using the grid search with optimization method, the SVR model achieves optimal performance, yielding reliable predictions with MAPE 8.55% and RMSE 9.43. Despite its effectiveness, limitations include the study's narrow focus on coolers and freezers within the service and maintenance sector, potential influences of external factors on prediction accuracy, and assumptions regarding the linear or nonlinear patterns in spare parts usage data.
Co-Authors Anatasia Naomi Asri Bekti Pratiwi, Asri Bekti Atika Dwi Hanun Amalia Auli Damayanti Bain Khusnul Khotimah Bella Pristianisa Subari Derby Prayogo Samdean Edi Winarko Fatmawati Fatmawati Fatmawati Fatmawati Fatmawati, Fatmawati Ihda Septiyafi Kiswara A. Santoso Laula Ika Setya Rahman Miswanto Miswanto Miswanto Muhammad Syarief Piping Prabawati Quinn Nathania PJY Riwayadi, Eko Siti Sarah Syaharuddin Syaharuddin Syaharuddin Syaharuddin Yayuk Wahyuni Zeni Murtafiani