Article Per Year (5 Year)
p-Index From 2020 - 2025
2.42
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) ILKOM Jurnal Ilmiah Jambura Journal of Electrical and Electronics Engineering Jurnal Tecnoscienza Jurnal Indonesia : Manajemen Informatika dan Komunikasi Jurnal Nasional Cosphi Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer (BALOK) Jurnal Indonesia : Manajemen Informatika dan Komunikasi
Serwin
Universitas Ichsan Gorontalo
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering Languange, Linguistic, Communication & Media Library & Information Science Mathematics Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Identifikasi Tingkat Kesegaran Ikan Tuna Menggunakan Metode GLCM dan KNN Zulfrianto Yusrin Lamasigi; Serwin -; Husdi -; Yulianti Lasena
Jambura Journal of Electrical and Electronics Engineering Vol 4, No 1 (2022): Januari - Juni 2022
Publisher : Teknik Elektro - Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (574.7 KB) | DOI: 10.37905/jjeee.v4i1.12045

Abstract

Abstrak-Dari potensi perikanan dan kelautan secara Nasional, Provinsi Gorontalo memiliki  potensi perikanan dan kelautan cukup besar yang dapat dikelola  untuk  menunjang pembangunan Gorontalo. Potensi perikanan tangkap Provinsi Gorontalo tidak bisa dipisahkan dari potensi perikanan tangkap yang  berbasis  pada  WPP  (Wilayah Pengelolaan  dan Pemanfaatan)  dan diakui  secara Nasional maupun Internasional. Provinsi Gorontalo merupakan salah satu provinsi penghasil ikan tuna di Indonesia, hasil tangkapan ikan tuna di gorontalo telah diekspor keberbagai negara. Tuna merupakan salah satu komoditi andalan perikanan di Gorontalo yang juga banyak melibatkan nelayan kecil. Penelitianini bertujuan untuk melakukan identifikasi tingkat kesegaran ikan tuna dengan menggukanan metode Gray LevelCo-Occurrence Matrix(GLCM)sebagai metode ektraksi fitur dan K-Nearest Neighbour (K-NN) digunakan sebagai metode klasifikasi. Padapenelitian ini, akan dilakukan 5 kali percobaan berdasarkan sudut 0°, 45°, 90°, 135° dan 180° pada nilai k=1, 3, 5, dan 7. Sementara itu, untuk menghitung tingkat akurasi dari klasifikasi K-NN akan menggunakan confusion matrix. Dari uji coba yang di lakukan dengan menggunakan jumlah data training sebanyak 130 citra dan data testing 45 citra pada semua kelas dan sudut mendapatkan hasil akurasi tertinggi pada sudut 0° dengan nilai k=1 yaitu sebesar 82,28% dan yang paling rendah ada pada sudut 135° dan 180° dengan nilai k=1 yaitu sebesar 53,71%. Berdasarkan hasil akurasi yang didapatkan menunjukkan bahwah GLCM bekerja dengan baik untuk meningkatkan hasil akurasi klasifikasi K-NN yang dibuktikan dengan hasil rata-rata akurasi yang diperoleh mencapai 50%.Abstract-From the national fisheries and marine potential, Gorontalo Province has a large enough fishery and marine potential that can be managed to support the development of Gorontalo. The capture fisheries potential of Gorontalo Province cannot be separated from the potential of capture fisheries based on the WPP (Management and Utilization Area) and is recognized both nationally and internationally. Gorontalo province is one of the tuna-producing provinces in Indonesia, tuna catches in Gorontalo have been exported to various countries. Tuna is one of the mainstay fisheries commodities in Gorontalo which also involves many small fishermen. This study aims to identify the freshness level of tuna by using the Gray Level Co-Occurrence Matrix (GLCM) method as a feature extraction method and K-Nearest Neighbor (K-NN) is a classification method. In this experiment, 5 experiments were conducted based on the angles of 0°, 45°, 90°, 135° and 180° at the values of k=1, 3, 5, and 7. Meanwhile, to calculate the accuracy level of the K-NN classification, we will use a confusion matrix. From the trials carried out using the amount of training data as many as 130 images and testing data 45 images against all classes based on angles 0°, 45°, 90°, 135°, and 180° at the values of k=1, 3, 5, and 7, the highest accuracy obtained is at an angle of 0° with a value of k=1 which is 82.28% and the lowest is at an angle of 135° and 180° with a value of k=1 which is 53.71%. The results of the trials conducted show that GLCM works well to improve the accuracy of the K-NN classification as evidenced by the average accuracy of 50%.
LL-KNN ACW-NB: Local Learning K-Nearest Neighbor in Absolute Correlation Weighted Naïve Bayes untuk Klasifikasi Data Numerik Azminuddin I. S. Azis; Budy Santoso; Serwin
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 1 (2020): Februari 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (602.934 KB) | DOI: 10.29207/resti.v4i1.1348

Abstract

Naïve Bayes (NB) algorithm is still in the top ten of the Data Mining algorithms because of it is simplicity, efficiency, and performance. To handle classification on numerical data, the Gaussian distribution and kernel approach can be applied to NB (GNB and KNB). However, in the process of NB classifying, attributes are considered independent, even though the assumption is not always right in many cases. Absolute Correlation Coefficient can determine correlations between attributes and work on numerical attributes, so that it can be applied for attribute weighting to GNB (ACW-NB). Furthermore, because performance of NB does not increase in large datasets, so ACW-NB can be a classifier in the local learning model, where other classification methods, such as K-Nearest Neighbor (K-NN) which are very well known in local learning can be used to obtain sub-dataset in the ACW-NB training. To reduction of noise/bias, then missing value replacement and data normalization can also be applied. This proposed method is termed "LL-KNN ACW-NB (Local Learning K-Nearest Neighbor in Absolute Correlation Weighted Naïve Bayes)," with the objective to improve the performance of NB (GNB and KNB) in handling classification on numerical data. The results of this study indicate that the LL-KNN ACW-NB is able to improve the performance of NB, with an average accuracy of 91,48%, 1,92% better than GNB and 2,86% better than KNB.
Aplikasi Diagnosa Penyakit Tanaman Cabai Merah menggunakan Algoritma K-Nearest Neighbor Sunarto Taliki; Serwin Serwin; Jabal Nur; Ivo Colanus Rally Drajana
JURNAL TECNOSCIENZA Vol. 6 No. 2 (2022): TECNOSCIENZA
Publisher : JURNAL TECNOSCIENZA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51158/tecnoscienza.v6i2.712

Abstract

Tanaman cabai merah merupakan komoditas holtikultura yang begitu sangat penting bagi kebutuhan dan keperluan manusia, seperti, ramuan obat-obatan tradisional, sebagai bumbu untuk makanan, dimakan bersama makanan ringan dan lain-lain. Dilihat dari tingkat serangan dan kondisi pertanian cabai merah di lapangan saat ini masi terkendala dengan belum adanya rekomendasi metode pengendalian yang efektif sehingga petani cenderung menggunakan pastisida kimia yang berdampak negatif terhadap lingkugan. Untuk mendiagnosa berbagai jenis penyakit yang menyerang tanaman cabai merah diperlukan seorang pakar/ahli. Pada peniltian ini akan membangun sebuah aplikasi yang dapat mendiagnosa dan memberikan solusi kepada petani mengenai masalah penyakit tanaman cabai merah. Aplikasi sistem pakar diagnosa penyakit tanaman cabai dapat diimplementasikan dengan melihat hasil pengujian berdasarkan konsultasi diagnosis serta solusi yang diberikan. Hal ini dapat dilihat pada jenis penyakit Busuk Akar dengan gejala kasus G01, G02 nilai Bobot 3.1, Gejala Dipilih (Benar) dan Nilai Kedekatan K-NN (3/4) = 0.75.
Game Edukasi Sebagai Media Pembelajaran Fisika Untuk Siswa Kelas X SMK Negeri 1 Boalemo Berbasis Android Firmansyah Kadir; Zulfrianto Y Lamasigi; Serwin Serwin
Jurnal Cosphi Vol 4, No 2 (2020): Agustus-Desember 2020
Publisher : Teknik Elektro - Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (411.749 KB)

Abstract

Dalam bidang pendidikan, pemanfaatan teknologi informasi dan komunikasi mendorong penciptaan inovasi-inovasi dalam pembelajaran, memberikan solusi dan kemudahan untuk memfasilitasi peserta didik agar dapat belajar dimana saja dan kapan saja tanpa dibatasi ruang dan waktu dengan mudah dan terjangkau. Penggunaan game  edukatif sebagai media pembelajaran sudah banyak dilakukan dan dapat membantu meningkatkan minat belajar peserta didik. Penelitian game edukatif ini dapat diimplementasikan dilihat dari hasil pengujian dengan menggunakan metode user acceptance testing yang di lakukan pada 10 orang siswa sebagai sampel dan mendapatkan nilai skor rata-rata 9 dapat disimpulkan bahwa Game Edukasi media pembelajaran Fisika ini Menarik, mudah dipahami, mudah dioperasikan,  mendukung kebijakan, membantu/memudahkan, aplikasi ini baik, dokumentasi baik, teknologi aplikasi canggih, bebas dari error dan perlu diimplementasikan. Serta Kelayakan dan keefektifan game edukatif ini dinilai layak berdasarkan hasil pengujian black box yang telah dilakukan, terlihat bahwa semua pengujian black box yang diperoleh sudah dites satu kali. Maka berdasarkan ketentuan tersebut dari segi kelayakan aplikasi, maka aplikasi ini sudah memenuhi syarat
PENERAPAN METODE LEAST SQUARE UNTUK PREDIKSI PENJUALAN BRIGHT GAS 5,5 KG Serwin; Yulianti Lasena
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 4 No. 1 (2023): Jurnal Indonesia : Manajemen Informatika dan Komunikasi (JIMIK)
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) AMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jimik.v4i1.133

Abstract

This company sells 5.5 kg of Bright gas which will be distributed to the base every month, experiencing ups and downs. In addition, it also resulted in the inappropriate procurement of 5.5 kg Bright gas. Every month it is not adjusted to monthly sales estimates because it has not used a prediction system. Therefore, there is a sales prediction system of 5.5 kg of bright gas every month, the amount of bright gas is 5.5 kg which will be distributed to the base. The purpose of this research is to find out good accuracy in the Least Square method for the selling process of 5.5 kg bright gas at PT. Togo Jaya Gorontalo. Results achieved With the bright gas prediction system, predictions can be made for the next period and measurement results using MAPE of 0.20%.
Identification of the Freshness Level of Tuna based on Discrete Cosine Transform on Feature Extraction of Gray Level Co-Occurrence Matrix using K-Nearest Neighbor Zulfrianto Yusrin Lamasigi; Serwin Serwin; Yusrianto Malago
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.v15i1.1426.153-164

Abstract

Gorontalo Province is one of the provinces that have fishery potential and has a large sea area that can be managed to support the economy and development of the province. Gorontalo is also one of the tuna-producing provinces in Indonesia, where tuna is also one of the mainstay fisheries commodities.  This study aimed to combine transformation and texture feature extraction methods to improve the identification of the freshness level of tuna. This research used Discrete Cosine Transform as transformation detection and Gray Level Co-Occurrence Matrix as texture feature extraction. To find out the value of the proximity of the training data and image testing of tuna fish, the K-Nearest Neighbor classification method was employed. Then, the Confusion Matrix was used to calculate the accuracy level of the K-Nearest Neighbor classification.   This research was carried out with 4 stages of testing, namely at angles of 0°, 45°, 90°, and 135°, and using the values of k=1, 3, 5, and 7. The test results of using training data of 428 images and testing data of 161 images in four classes used with angles of 0°, 45°, 90°, 135°, and the value of k=1, 3, 5, 7. The highest accuracy results was obtained at an angle of 0° with a value of k = 1 of 94.40%, while the lowest accuracy value was at an angle of 90° and 135° with a value of k=7 of 59%. This showed that the Discrete Cosine Transform transformation method was very effective to improve the performance of texture feature extraction of Gray Level Co-Occurrence Matrix in extracting tuna image features. It was proven from the results of the accuracy of the K-Nearest Neighbor classification obtained.
Klasifikasi Malware Menggunakan Teknik Machine Learning Evan Valdis Tjahjadi; Budi Santoso; Serwin
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 2 No 1 (2023): Edisi Mei 2023
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37195/balok.v2i1.525

Abstract

Abstract Computer networks connected to the Internet can access information from all over the world very easily. However, the connection between the network and the Internet increases the potential for system failure. One of the methods that can be used in machine learning is the random forest algorithm method. Random forest is one of the methods in machine learning that is used to solve clarification problems. Based on the problems, it is necessary to classify malware where data is taken from malware datasets to make it easier to learn and distinguish the types of malware. The process consists of collecting datasets, pre-processing, training machine learning, and testing model performance. This study aims to find out the performance of Machine Learning using a random forest algorithm for malware- random forest classification. In this process, pre-processing of data is done by installing several Python libraries. Pandas is an open-source Python library that is usually used for data analysis needs. The model is trained on a dataset with various features and the results show a high accuracy of 99%. The random forest model provides excellent results without preprocessing the data. The results are good even if the data is not balanced. There is no need to use any technique to balance it. Scaling is not necessary. The random forest model is a recursive partitioning model that depends on data partitioning as it works on splitting the feature values and does not perform any calculations in it. The results indicate that the model has a precision of 0.99.
Prediksi Jumlah Produksi Ikan Asin Menggunakan Metode Regresi Linear Sederhana M Rajab Mudatsir; Serwin Serwin
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 1 No 2 (2022): Edisi November (2022)
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (460.402 KB) | DOI: 10.37195/balok.v1i2.143

Abstract

CV. Tirta Tenggiri produces salted fish caught from the sea or local fishermen. The production is to meet the local and outside demands of the Pohuwato District. Even though market demand for salted fish is always available, CV. Tirta Tenggiri is sometimes not able to adjust the production of salted fish with consumer demand. To obtain the information about the total production of salted fish for better development of the company in the future, predictions are made by using the simple linear regression method. The variables used include raw materials and the total demand (X) and land area as a prediction result (Y). The dataset in this study for the prediction of salted fish production takes data from 2019 to 2021. The results show that the number of salted fish to produce in May 2022 obtains a value of y = 168.53 + 24.175. The accuracy with MAPE is 0.8%. Testing the system by using a white box that has the same value of V(G) and CC, namely =2.Keywords: prediction, salted fish production, simple linear regression, White Box and Black Box Testing
Implementasi Metode Regresi Linear Sederhana Untuk Prediksi Harga Cabai Rawit Moha Lalapa, Nazarullah; Warid; Serwin
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 2 No 2 (2023): November 2023
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37195/balok.v2i2.121

Abstract

Abstract ; The potential for developing cayenne pepper farming is widely open, especially in Gorontalo Province. After being designated as the second leading commodity in Gorontalo province after corn, the total cayenne pepper production in 2020 reached 147,292 tons (Central Bureau of Statistics of Gorontalo Province in 2020). Gorontalo District is one of the centers for cayenne pepper production in Gorontalo Province. The production contribution until 2020 reaches 35.65% of the whole cayenne pepper production in Gorontalo Province. This contribution places Gorontalo District as the second-largest producer of cayenne pepper after Bone Bolango. The high price of cayenne pepper production in Gorontalo District often causes a market price to drop by up to IDR 20,000/kg, while in fact, it is before religious holidays.  The cayenne pepper price soars drastically. To cope with the problem, it is necessary to use a prediction technique using the Simple Linear Regression and MAPE method. This research aims to design a system to predict the price of cayenne pepper. The variables used are Production as the value of X and Price as the value of Y. Based on the prediction results, it gains an error rate of 24.00% or an accuracy rate of 76.00%.  It means that the system designed is feasible to be used or applied to predict the price of cayenne pepper. Keywords: simple linear regression, mape, cayenne pepper
Aplikasi Pencarian Rute Terdekat Tempat Dokter Praktek Fasilitas Bpjs Mengunakan Metode Djikstra Luviani, Luviani; Apriyanto Alhamad; Serwin; Mohamad Efendi Lasulika
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 3 No 1 (2024): Mei 2024
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37195/balok.v3i1.752

Abstract

Abstract- Searching for the fastest route while traveling is necessary besides finding the destination. The reason for finding the fastest route is to streamline the trip and save travel costs. Another problem in making an effective trip is a city search carried out by someone who knows, someone who spreads hospitals, health centers, clinics, and pharmacies that serve the Social Insurance Administration Organization in Gorontalo City/Regency, and knows several nearby places. In the implementation of the Social Insurance Administration Organization in Gorontalo City/Regency branch, there are still obstacles faced by the community. The lack of information regarding the distribution of health facilities and information makes people confused when choosing and locating which health facility they will visit for treatment using a card from the Social Insurance Administration Organization. By designing this information system, people can map the health facilities that serve the Social Insurance Administration Organization. The designation of this system uses the DJikstra algorithm to find the fastest route to the health facilities of Social Insurance Administration Organization to obtain a research result of a system that can find the fastest route to the health facilities of the Social Insurance Administration Organization. It is hoped that it can help the public in getting the fastest way to health facilities of the Social Insurance Administration Organization in Gorontalo City/Regency. Keywords: fastest route search system, health facilities, Social Insurance Administration Organization, Djikstra algorithm
Co-Authors Abd Rahmat karim Haba Andi Bode Apriyanto Alhamad Asmaul Husnah Nasrullah Azminuddin I. S. Azis Balok, Admin Budy Santoso Evan Valdis Tjahjadi Firmansyah Kadir Furqan Abdillah Ibram Sukata Husdi Irvan Abraham Salihi Ivo Colanus Rally Drajana Luviani, Luviani M Rajab Mudatsir Moha Lalapa, Nazarullah Mohamad Efendi Lasulika Nur, Muh Jabal Sunarto Taliki Warid Yunus Yulianti Lasena Yusrianto Malago Zulfrianto Yusrin Lamasigi