Article Per Year (5 Year)
p-Index From 2021 - 2026
0.888
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) INFORMAL: Informatics Journal Jurnal Triton Jurnal Teknoinfo
Christian Dwi Suhendra
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Environmental Science Library & Information Science Social Sciences Veterinary

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Penentuan Arsitektur Jaringan Syaraf Tiruan Backpropagation (Bobot Awal dan Bias Awal) Menggunakan Algoritma Genetika Christian Dwi Suhendra; Retantyo Wardoyo
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 9, No 1 (2015): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.6642

Abstract

AbstrakKelemahan dari jaringan syaraf tiruan backpropagation adalah sangat lama untuk konvergen dan permasalahan lokal mininum yang membuat jaringan syaraf tiruan (JST) sering terjebak pada lokal minimum. Kombinasi parameter arsiktektur, bobot awal dan bias awal yang baik sangat menentukan kemampuan belajar dari JST untuk mengatasi kelemahan dari JST backpropagation.            Pada penelitian Ini dikembangkan sebuah metode untuk menentukan kombinasi parameter arsitektur, bobot awal dan bias awal. Selama ini kombinasi ini dilakukan dengan mencoba kemungkinan satu per satu, baik kombinasi hidden layer pada architecture maupun bobot awal, dan bias awal. Bobot awal dan bias awal digunakan sebagai parameter dalam perhitungan nilai fitness. Ukuran setiap individu terbaik dilihat dari besarnya jumlah kuadrat galat (sum of squared error = SSE) masing – masing individu, individu dengan SSE terkecil merupakan individu terbaik. Kombinasi parameter arsiktektur, bobot awal dan bias awal yang terbaik akan digunakan sebagai parameter dalam pelatihan JST backpropagation.Hasil dari penelitian ini adalah sebuah solusi alternatif untuk menyelesaikan permasalahan pada pembelajaran backpropagation yang sering mengalami masalah dalam penentuan parameter pembelajaran. Hasil penelitian ini menunjukan bahwa metode algoritma genetika dapat memberikan solusi bagi pembelajaran backpropagation dan memberikan tingkat akurasi yang lebih baik, serta menurunkan lama pembelajaran jika dibandingkan dengan penentuan parameter yang dilakukan secara manual. Kata kunci  Jaringan syaraf tiruan, algoritma genetika, backpropagation, SSE, lokal minimum AbstractThe weakness of back propagation neural network is very slow to converge and local minima issues that makes artificial neural networks (ANN) are often being trapped in a local minima. A good combination between architecture, intial weight and bias are so important to overcome the weakness of backpropagation neural network.This study developed a method to determine the combination parameter of architectur, initial weight and bias. So far, trial and error is commonly used to select the combination of hidden layer, intial weight and bias. Initial weight and bias is used as a parameter in order to evaluate fitness value. Sum of squared error(SSE) is used to determine best individual. individual with the smallest SSE is the best individual. Best combination parameter of architecture, initial weight and bias will be used as a paramater in the backpropagation neural network learning.            The results of this study is an alternative solution to solve the problems on the backpropagation learning that often have problems in determining the parameters of the learning. The result shows genetic algorithm method can provide a solution for backpropagation learning and can improve the accuracy, also reduce long learning when it compared with the parameters were determined manually. Keywords: Artificial neural network, genetic algorithm, backpropagation, SSE, local minima.
Rancang Bangun Sistem Informasi Penilaian Pencapaian Materi dan Absensi Murid di Taman Pendidikan Al-Quran (TPA) DPD Lembaga Dakwah Islam Indonesia Kabupaten Manokwari menggunakan Metode Prototype Afifah Ummi Sholihah; Christian Dwi Suhendra; Pawit Rianto
INFORMAL: Informatics Journal Vol 6 No 3 (2021): Informatics Journal (INFORMAL)
Publisher : Faculty of Computer Science, University of Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19184/isj.v6i3.21963

Abstract

The Regional Representative Council of Indonesia Institute of Islamic Dakwah of Manokwari Regency has four departments from Al-Quran Education School which are required to report the attendance and achievements of students each month in their respective departments. This report will be presented to the parents and to the Head of the school for evaluation. Both of these assessments are still carried out manually so it is inefficient because the data will be easily lost or scattered. With these problems, the author did some researches to carry out the Design and Development of Information System for Assessment of Material Achievement and Student Attendance at Al-Quran Education School - Regional Representative Council of Indonesia Institute of Islamic Dakwah in Manokwari Regency. This research was conducted by creating an assessment input information system and responsive web-based data recap, using the Laravel framework, MySQL database and the research method used was the Prototype Method. At the final stage of this research is testing the system with the Black Box Method. The final result of this research is the formation of the Information System for Assessment of Material Achievement and Student Attendance for the Al-Quran Education School - Regional Representative Council of Indonesia Institute of Islamic Dakwah in Manokwari Regency. The test results show that the Prototype Method can be used in building the information system in question.
Penerapan Metode K-Means dalam Pengelompokan Data Penduduk Tidak Mampu di Distrik Oransbari Messi Triyana; Ratna Juita; Christian Dwi Suhendra
INFORMAL: Informatics Journal Vol 7 No 3 (2022): Informatics Journal (INFORMAL)
Publisher : Faculty of Computer Science, University of Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19184/isj.v7i3.34722

Abstract

Proverty is a serious problem, the occurrence of proverty in the community is caused by a condition of the inability of the family economically to meet primary needs. Poor people are found in almost every country, city, and region. One of them is in the Oransbari District, which is one of the areas in Indonesia where the population does not receive assistance evenly. Based on these conditions, clustering is carried out to assist the district in grouping the poor population, so that the assistance provided can be right on target. With this problem, data mining with k-means clustering method used in clustering the poor population to make it easier for the Oransbari District to provide the population so that it is right on target. The data used is the data of the poor population in 2020 which amounted to 1872 with 17 attributes. Based on the results of tests carried out by applying the k-means algorithm, the results obtained with 3 clusters, the first cluster with a population of 471 with the category of poor population with medium priority, the second cluster has a population of 428 with a high priority category of poor population, and the third cluster has a population of 826 a low priority category of poor population. The k-means method is expected to be able to assist the Oransbari District in making decisions so that assistance is more targeted.
ANALISIS KLASTERISASI DAFTAR PEMILIH KABUPATEN MANOKWARI MENGGUNAKAN METODE K-MEANS CLUSTERING BERBASIS ELBOW METHOD Marselinda Rante Uma; Christian Dwi Suhendra; Josua Josen A. Limbong
Jurnal Teknoinfo Vol. 19 No. 2 (2025): July 2025 Period
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/teknoinfo.v19i2.163

Abstract

General Elections (Pemilu) are a crucial pillar in Indonesia's democratic system, ensuring public representation in government. As voter data becomes increasingly complex due to population growth and community mobility, electoral data management requires more efficient analytical approaches to support accurate decision-making. Therefore, methods capable of accurately grouping voters based on specific characteristics are needed. This study aims to cluster voter registration data in Manokwari Regency based on age and neighborhood unit (RT) using the K-Means algorithm. A total of 16,871 entries obtained from the General Election Commission of Manokwari Regency were used, but two outliers due to input errors were removed, leaving 16,869 valid entries analyzed using Jupyter Notebook. The Elbow Method was applied to determine the optimal number of clusters by calculating the Sum of Squared Errors (SSE) from K = 2 to K = 9. The most significant drop in SSE occurred from K = 2 to K = 3 and K = 3 to K = 4, with gradual decreases afterward, indicating the elbow point lies between K = 3 and K = 4. Considering data density and segmentation, K = 4 was chosen with an SSE value of 347,575. The K-Means algorithm then clustered the data based on age and RT through random centroid initialization, Euclidean distance calculation, reassignment, and iterative centroid updates until convergence. The results showed four clusters: Cluster_0 with 6,332 young voters aged 17–29 years (RT 0–17), Cluster_1 with 3,478 productive-age voters aged 43–56 years (RT 0–14), Cluster_2 with 1,768 elderly voters aged 57–93 years (RT 0–14), and Cluster_3 with 5,291 voters aged 30–42 years (RT 0–15). The broad RT distribution across clusters indicates diverse voter age groups across the region. These findings can help the Manokwari General Election Commission (KPU) and related institutions in planning effective voter education, outreach, and logistics distribution strategies.
Analisis Integrasi Algoritma YOLOv8 dan CNN terhadap Klasifikasi Kualitas Telur Ayam Ras Petelur di Kabupaten Manokwari Helmi Saputra; Christian Dwi Suhendra; Alex De Kweldju
JURNAL TRITON Vol 17 No 1 (2026): JURNAL TRITON (Issue in Progress)
Publisher : Politeknik Pembangunan Pertanian Manokwari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47687/jt.v17i1.1912

Abstract

Penilaian mutu telur ayam petelur umumnya masih dilakukan secara manual sehingga rentan terhadap subjektivitas dan ketidakkonsistenan hasil, sementara kebutuhan akan proses grading yang cepat dan akurat semakin meningkat. Penelitian ini dilakukan untuk mengembangkan model klasifikasi mutu telur berbasis warna dan bentuk kerabang dengan memanfaatkan algoritma YOLOv8 dan Convolutional Neural Network (CNN). Data dikumpulkan dari peternak lokal di Kabupaten Manokwari menggunakan metode Stratified Random Sampling dan menghasilkan 957 citra telur yang diberi label berdasarkan pedoman SNI 3926:2023. Proses preprocessing meliputi penyesuaian ukuran citra menjadi 640×640 piksel, normalisasi, serta augmentasi variasi pencahayaan dan sudut. YOLOv8 digunakan untuk mendeteksi posisi telur, sementara EfficientNet-B0 sebagai CNN digunakan untuk klasifikasi tiga tingkat mutu telur. Hasil penelitian menunjukkan bahwa YOLOv8 mampu mendeteksi objek dengan performa sangat baik dengan nilai mAP@0.5 sebesar 0.980, precision 0.97, dan recall 0.95, sedangkan model CNN mencapai akurasi validasi 91.9% dengan performa stabil pada seluruh kelas. Integrasi kedua model menghasilkan sistem yang mampu bekerja secara real-time dengan kecepatan 20–35 FPS dan dapat menghitung jumlah telur per grade secara otomatis. Berdasarkan hasil tersebut, dapat disimpulkan bahwa kombinasi YOLOv8 dan CNN mampu memberikan solusi yang cukup akurat untuk proses grading telur ayam petelur serta berpotensi diterapkan pada sistem sortasi pascapanen skala produksi.
Co-Authors Afifah Ummi Sholihah Alex De Kweldju Helmi Saputra Josua Josen A. Limbong Marselinda Rante Uma Messi Triyana Pawit Rianto Ratna Juita Retantyo Wardoyo