Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer (BALOK)

Penerapan Convolutional Neural Network (CNN) Untuk Klasifikasi Penggunaan Masker Rifdah Rofifah Faruk Abdullah; Maryam Hasan
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 (644.365 KB) | DOI: 10.37195/balok.v1i2.164

Abstract

ABSTRACT RIFDAH ROFIFAH FARUK ABDULLAH. T3117114. APPLICATION OF CONVOLUTIONAL NEURAL NETWORK FOR MASK USE CLASSIFICATION The use of masks is a part of the comprehensive series of prevention and control measures that can limit the spread of certain respiratory viral diseases. Masks can be used both to protect healthy people (worn to protect themselves when in contact with an infected person) and to control the sources of prevention (to be worn by an infected person to prevent further transmission). The problem that often occurs is that many people use masks, but improperly or inappropriately. For instance, the right thing, someone uses a mask to cover the mouth and nostrils. Therefore, an application for the use of computer-assisted mask detection is made. It can detect the use of a person's mask so that the right and wrong use categories are obtained that represent it by capturing it in an image. It is done by using the Convolutional Neural Network method. In the classification stage, the accuracy results are 60- 70%. Keywords: classification, masks use, Convolutional Neural Network
Prediksi Jumlah Pengunjung Pantai Bolihutuo Mengunakan Metode Fuzzy Time Series Hasan, Maryam
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.v2i2.709

Abstract

Abstract - This research is to find out the results of applying the Fuzzy time series method in predicting the number of visitors to Bolihutuo tourism each month which experiences ups and downs, this condition results in unpreparedness from the officers and administration of Bolihutuo tourism. Bolihutuo visitor data was taken from daily data from January 3 2021 to February 23 and then processed by making predictions using the fuzzy time series method. From the results of the processing carried out, we obtained a fairly good level of prediction accuracy with an accuracy value of 98.96242716% and a Mean Absolute Percentage Error (MAPE) value of 1.037572843%. From the accuracy results obtained and also the mean Absolute Percentage Error (MAPE) value obtained, it can be concluded that the prediction system obtained good results. Keywords: visitors, Bolihutuo beach, tourism, prediction, Fuzzy Time
Rancang Bangun Aplikasi Pencarian Toko Oleh-Oleh Terdekat Berbasis Android Menggunakan Algoritma Floyd Warshall Mahmud, Mohamad An Nafli; Maryam Hasan; Warid Yunus; Syarifah Fitrah Ramadani
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.v3i1.842

Abstract

Abstract- Information technology develops rapidly. The effect can be seen through the increasing use of mobile devices in supporting daily activities in carrying out various activities. With the development of mobile technology, mobile devices offer a variety of advanced computing capabilities known as smartphones. The role of smartphones is to have a good impact if the embedded applications are equipped with good service quality to support users to do or to search for a place or location. Through supporting applications, users can use it more easily, more economically, and more efficiently.  In addition, users can also find out the current developing technology model. The development of souvenir centers depends on tourism industry products regarding the tourism concept and convenience in tourism visits. The tourism sector is also very influential in the socio-cultural field, and of course, in the economic field because it can open up new business opportunities. The design of the nearest souvenir shop search application helps in finding the closest route to the souvenir shop by applying the Floyd Warshall algorithm.  The research results produce a system that can find the nearest souvenir shop and is expected to help the community in finding the nearest souvenir shop in Gorontalo City.   Keywords: nearest location point search application, souvenir shop, Floyd Warshall algorithm
Implementasi Metode XGBoost Dalam Seleksi Atribut Pada Algoritma K-Means Untuk Clustering Masyarakat Penerima Bantuan Langsung Tunai Amiruddin; Maryam Hasan; Muhammad Erdiansyah
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 3 No 2 (2024): November 2024
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37195/balok.v3i2.1193

Abstract

Penelitian ini mengkaji implementasi metode XGBoost dalam seleksi atribut pada algoritma K-Means untuk clustering masyarakat penerima Bantuan Langsung Tunai (BLT). Dalam konteks ini, 14 atribut awal digunakan untuk menggambarkan karakteristik rumah tangga penerima BLT: Luas Lantai, Lantai Rumah, Dinding Rumah, MCK, Sumber Listrik, Sumber Air, Bahan Bakar, Konsumsi, Pakaian, Tidak Sanggup Berobat, Sumber Penghasilan KK, Penghasilan KK, Pendidikan KK, dan Tabungan. Metode XGBoost diaplikasikan untuk menyeleksi atribut yang paling relevan dalam menentukan kelompok penerima BLT. Dari hasil seleksi, ditemukan tiga atribut penting yaitu Luas Lantai, Lantai Rumah, dan Penghasilan KK. Implementasi K-Means clustering dilakukan dua kali, pertama menggunakan seluruh atribut dan kedua menggunakan tiga atribut penting yang telah diseleksi oleh XGBoost. Analisis hasil clustering menunjukkan bahwa sebelum seleksi atribut, nilai Davies-Bouldin Index (DBI) sebesar 1.325. Setelah seleksi atribut penting, nilai DBI menurun menjadi 0.800. Penurunan nilai DBI sebesar 0.525 ini mengindikasikan bahwa hasil clustering menjadi lebih optimal setelah penerapan XGBoost. Dengan demikian, penelitian ini menyimpulkan bahwa penggunaan XGBoost untuk seleksi atribut dapat meningkatkan kinerja K-Means dalam clustering masyarakat penerima BLT, menghasilkan grup yang lebih jelas dan homogen. Temuan ini memiliki implikasi penting untuk meningkatkan efisiensi dan efektivitas program penyaluran BLT dengan mendasarkan keputusan pada atribut yang paling berpengaruh. Kata Kunci: XGBoost, K-Menas, Clustering, Seleksi Atribut, Bantuan Langsung Tunai