Article Per Year (5 Year)
p-Index From 2021 - 2026
1.203
P-Index
This Author published in this journals
All Journal ILKOM Jurnal Ilmiah Jurnal Nasional Komputasi dan Teknologi Informasi J-Dinamika: Jurnal Pengabdian Kepada Masyarakat International Journal Software Engineering and Computer Science (IJSECS) Nusantara of Engineering (NOE)
Drajana, Ivo Colanus Rally
Unknown Affiliation
Aerospace Engineering Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Mechanical Engineering Neuroscience Transportation

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
K-Nearest Neighbor for Gorontalo City Chili Price Prediction Using Feature Selection, Backward Elimination, and Forward Selection Labolo, Abdul Yunus; Utiarahman, Siti Andini; Lasulika, Mohamad Efendi; Drajana, Ivo Colanus Rally; Bode, Andi
International Journal Software Engineering and Computer Science (IJSECS) Vol. 3 No. 3 (2023): DECEMBER 2023
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v3i3.1709

Abstract

This study addresses chili price volatility, an important concern that impacts the national economy and societal welfare. Fluctuations in chili prices in the retail market greatly influence market demand, thereby influencing farming decisions, especially chili cultivation. To help make better decisions, Researchers use forecasting, which is defined as the projection of future trends based on the analysis of historical data, using statistical methods. The K-Nearest Neighbor (K-NN) algorithm is used because of its resistance to high noise on large training datasets. However, challenges arise in determining the optimal value of 'k' and selecting related attributes. To overcome this, Feature Selection is applied to refine the model by removing irrelevant features, resulting in a significant reduction in the model error rate. This improvement indicates an increase in the efficiency of the K-NN algorithm with the incorporation of Feature Selection. Our findings show that the model, with backward elimination in Feature Selection, achieves a Root Mean Square Error (RMSE) of 0.202, outperforming the model using forward selection. The prediction accuracy of this model reaches an average of 78.86%, which is much higher than the baseline data of 50%. This shows the success of the proposed method in predicting chili prices.
Prediksi Harga Jagung Menggunakan Support Vector Machine dengan Fitur Seleksi Forward Selection di Kabupaten Pohuwato Drajana, Ivo Colanus Rally; Betrisandi, Betrisandi
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 7, No 5 (2024): Oktober 2024
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v7i5.8059

Abstract

Abstrak - Kabupaten Pohuwato yang terletak di bagian paling barat Provinsi Gorontalo merupakan salah satu daerah penghasil jagung terbesar. Menurut Kementerian Pertanian, luas lahan perkebunan di Kabupaten Pohuwato seluas 87.104 hektare dimanfaatkan warga untuk menanam jagung. Jagung merupakan salah satu komoditas tanaman pangan utama sebagai sumber karbohidrat sehingga harga jagung menjadi perhatian penting bagi pemerintah, namun harga jagung berfluktuasi. Solusi yang diberikan pada penelitian ini adalah prediksi harga jagung di masa depan dengan menggunakan Algoritma Support Vector Machine dengan Fitur Forward Selection yang dapat memberikan solusi tepat bagi petani perkebunan, pedagang dan pemerintah. Dari hasil percobaan yang telah dilakukan, prediksi harga jagung menggunakan algoritma support vector machine dengan fitur forward seleksi telah berhasil dilakukan. Hasil RMSE sebesar 0.682 terdapat pada algoritma support vector machine yang menggunakan fitur forward seleksi, hasil ini dinyatakan lebih baik dibandingkan tanpa menggunakan fitur seleksi.Kata kunci: Prediction, Corn Price, Support Vector Machine, Forward Selection Abstract - Pohuwato Regency, which is located in the westernmost part of Gorontalo Province, is one of the largest corn producing areas. According to the Department of Agriculture, the area of plantation land in Pohuwato Regency, which is 87,104 hectares, is used by residents to grow corn. Corn is one of the main food crop commodities as a source of carbohydrates so that the price of corn is an important concern for the government, but the price of corn fluctuates. The solution provided in this study predicts future corn prices using the Support Vector Machine Algorithm with the Forward Selection Feature which can provide the right solution for plantation farmers, traders and the government. From the results of the experiments that have been carried out, the prediction of corn prices using the support vector machine algorithm with the forward selection feature has been successfully carried out. The RMSE result of 0.682 is found in the support vector machine algorithm that uses the forward selection feature, this result is stated to be better than without using the selection feature.Kata kunci: Prediction, Corn Price, Support Vector Machine, Forward Selection
Support Vector Machine Untuk Prediksi Produksi Tanman Pangan di Provinsi Gorontalo Drajana, Ivo Colanus Rally; Bode, Andi
Nusantara of Engineering (NOE) Vol 4 No 2 (2021): Volume 4 No 2 Tahun 2021
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (513.243 KB) | DOI: 10.29407/noe.v4i2.16757

Abstract

Sektor pertanian sudah menjadi peranan penting bagi masyarakat pada daerah yang memiliki lahan luas dan tanah yang subur. Pertanian sangat penting dalam peningkatan suatu daerah serta perekonomian daerah itu sendiri. Dinas Pertanian Provinsi Gorontalo adalah sebuah instansi yang bergerak diberbagai bidang pertanian, dalam kegiatan tahunan melakukan pencatatan hasil produksi tanaman pangan. Hasil yang didapatkan setiap tahunnya sering mengalami perubahan, maka diperlukan suatu sistem untuk melakukan prediksi, tujuannya yaitu untuk mengetahui hasil produksi tanaman pangan. Dengan penerapan algoritma support vector machine (SVM) telah berhasil dilakukan. Maka hasil dari prediski tersebut dapat digunakan untuk bahan pertimbangan atau kebijakan didalam pengambilan keputusan. Tingkat error paling terkecil yaitu 207. Model yang diusulkan mendekati nilai kesempurnaan, karena perbandingan hasil eksperimen prediksi produksi tanaman pangan dengan data set yang ada menghasilkan nilai keakuratan kisaran 70% - 100%. Dengan demikian metode yang diusulkan dinyatakan berhasil.
SPK Penilaian Kinerja Dosen Menggunakan Metode Multy Attribute Utility Theory Drajana, Ivo Colanus Rally; Polimengo, Novriyanti; Riadi, Annahl
Nusantara of Engineering (NOE) Vol 4 No 2 (2021): Volume 4 No 2 Tahun 2021
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (3390.305 KB) | DOI: 10.29407/noe.v4i2.16758

Abstract

Dosen merupakan pendidik profesional dan ilmuwan yang mempunyai tugas utama untuk mengembangkan, mentransformasikan, dan menyebarluaskan berbagai ilmu pengetahuan melalui pendidikan, penelitian, dan pengabdian kepada masyarakat. Universitas Pohuwato adalah Perguruan Tinggi Swasta baru yang terdapat di Pohuwato yang selalu berupaya dalam meningkatkan Mutu Internal secara berkelanjutan agar dapat bersaing dengan perguruan tinggi lain. Salah satu upaya yang dapat dilakukan adalah melakukan evaluasi terhadap Kinerja Dosen. Maka solusi yang dapat membantu dalam menyelesaikan penilaian kinerja dosen yaitu dibuatlah sebuah sistem pendukung keputusan menggunakan Metode Multy Attribute Utility Theory (MAUT), Metode ini memberikan penilaian hasil akhir dengan melakukan perengkingan dari Nilai Alternatif tertinggi ke terendah. Sistem ini sudah melalui pengujian sistem untuk menghindari kesalahan sistem pengujian White Box dan pengujian Black Box. Berdasarkan hasil pengujian white box disimpulkan bahwa sistem pndukung keputusan ini bebas dari kesalahan program dengan total Cyclomatic Complexity = 7, Region =6, dan independent Path = 7.
The K-Nearest Neighbor Algorithm using Forward Selection and Backward Elimination in Predicting the Student’s Satisfaction Level of University Ichsan Gorontalo toward Online Lectures during the COVID-19 Pandemic Bode, Andi; Lamasigi, Zulfrianto Y; Drajana, Ivo Colanus Rally
ILKOM Jurnal Ilmiah Vol 15, No 1 (2023)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v15i1.1381.118-123

Abstract

Academic services are actions taken by state and private universities to provide convenience for student’s academic activities. During the current covid-19 pandemic, every university remains active in academic activities. This study aimed to apply the K-Nearest Neighbor algorithm in predicting the level of student satisfaction with online lectures at University Ichsan Gorontalo. Our main aim was to obtain quantitative information to measure student satisfaction with online lectures during the pandemic, which should be taken into account when making decisions. K-Nearest Neighbor is a non-parametric Algorithm that can be used for classification and regression, but K-Nearest Neighbor are better if feature selection is applied in selecting features that are not relevant to the model. Feature Selection used in this research is Forward Selection and Backward Elimination. Seeing the results of experiments that have been carried out with the application of the K-nearest Neighbor algorithm and the selection feature, the results of the forecasting can be used for consideration or policy in decision making. The highest level of accuracy in the K-Nearest Neighbor algorithm model used Forward Selection with an accuracy rate of 98.00%. Thus, the experimental results showed that feature selection, namely forward selection, was a better model in the relevant selection variables compared to backward elimination.
METODE SUPPORT VECTOR MACHINE DAN FORWARD SELECTION PREDIKSI PEMBAYARAN PEMBELIAN BAHAN BAKU KOPRA Drajana, Ivo Colanus Rally
ILKOM Jurnal Ilmiah Vol 9, No 2 (2017)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v9i2.134.116-123

Abstract

Telah banyak peneliti-peneliti termotivasi dalam meningkatkan kinerja performa prediksi. Support Vector Machine (SVM) metode yang berlandaskan pada teori pembelajaran statistic dan memberi hasil yang menjanjikan akan lebih baik dibanding metode lain. SVM bekerja juga dengan baik terhadap data yang berdimensi tinggi dengan menggunakan teknik kernel. Penentuan variabel yang relevan sangat dibutuhkan untuk dapat memberikan kinerja performa lebih efektif lagi pada suatu model. Pada penelitian ini bermaksud untuk mengembangkan model prediksi dengan mengkombinasikan algoritma Support Vector Machine dengan Feature Selection, khususnya forward selection dalam memprediksi pembayaran pembelian bahan baku kopra. Model yang diusulkan dievaluasi menggunakan data time pembelian bahan baku kopra. Hasil eksperimen penelitian ini menunjukan dimana series pembayaran algoritma SVM dan Forward Selection memberikan kinerja performa yang terbaik dibandingkan SVM, SVM dan Backward Elimination serta BPNN dan Feature Selection.
Indonesia Pemberdayaan Masyarakat Melalui Pengembangan E-Commerce Bandeng Presto Berbasis Digital dan Pelatihan Kewirausahaan Desa Lomuli Lemito Drajana, Ivo Colanus Rally; Nasrul , Muhammad; Fitriyanti Bulotio, Nur
J-Dinamika : Jurnal Pengabdian Masyarakat Vol 11 No 1 (2026): April
Publisher : Politeknik Negeri Jember

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

Abstract

     The development of digital technology opens up opportunities for people to utilize digital-based e-commerce as a means of promotion and sales. One business that can be developed through community empowerment is presto milkfish. Milkfish processing was chosen as one of the culinary products developed by the Casamur UKM of Lomuli Village because the fish harvest in Lomuli Village is quite abundant. The PMP Team of Pohuwato University collaborated with the Casamur UKM of Lomuli Village in improving the development of the milkfish processing business by looking at the problems faced by partners, namely technology adoption, human resources and marketing aspects. The aim of implementing this PMP is to increase the knowledge, skills and income of the Casamur UKM in Lomuli Village in the presto milkfish business. The method used in this PMP activity is in technology adoption by carrying out mentoring and counseling related to digital-based E-Commerce for Casamur SME partners in Lomuli Village, in the human resource aspect by carrying out training activities on making presto milkfish so that partner skills can improve and in the marketing aspect, namely by carrying out digital marketing-based entrepreneurship training activities by creating a Google Business platform and the percentage of presto milkfish business income. The sustainability of this program is to provide assistance and guidance to improve the capabilities and skills of the Casamur SME in Lomuli Village in processing and marketing processed milkfish products. The results of the PMP activity are that the Casamur Lomuli Village UKM partners know and understand the adoption of innovative use of technology in the production of presto milkfish and have skills in conducting digital-based e-commerce marketing as well as a 50% increase in revenue and establishing partner collaborations.
Co-Authors Andi Bode Betrisandi, Betrisandi Fitriyanti Bulotio, Nur Labolo, Abdul Yunus Mohamad Efendi Lasulika Nasrul , Muhammad Polimengo, Novriyanti Riadi, Annahl Utiarahman, Siti Andini Zulfrianto Yusrin Lamasigi