Claim Missing Document
Check
Articles

Found 3 Documents
Search

Implementation of the K-Means Method for Beverage Clustering Based on Calorie and Protein Rewina, Anggita Eka; Hapsari, Rinci Kembang; Putri, Chatarina Natassya; Lande, Gamaliel Virani Fofid; Aditya, Andre Fransisco; Alamsyah, Mochamad Tegar Bagas
Zeta - Math Journal Vol 10 No 1 (2025): May
Publisher : Universitas Islam Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31102/zeta.2025.10.1.19-29

Abstract

Recently, the number of coffee shops in big cities in Indonesia has increased. This makes it easier for coffee lovers to enjoy it. With the increasing public awareness of the importance of healthy drinking patterns in preventing diabetes and other diseases, consuming low-calorie drinks has become a prominent trend. This study aims to group the coffee drink menu at Starbucks based on the calorie and protein content of Starbucks drinks. It is grouped into 2 clusters, namely, high and low clusters. In this study, the clustering process of Starbucks drink menu data was carried out by applying the K-Means algorithm. The clustering results can identify members of Cluster 1 and members of Cluster 2. From the tests that have been carried out, it can group the drink menu into 2 clusters based on the amount of protein and calories from Starbucks drinks and help the public choose which drinks are better to consume.
Implementasi Algoritma Pengklasifikasi Long Short–Term Memory (LSTM) untuk Data Time Series Sari, Arum Indah; Hapsari, Dian Puspita; Wibowo, Handi F. Resi; Putri, Chatarina Natassya; Lande, Gamaliel V. Fofid; Aldero, Exacta Bunayya
Prosiding Seminar Nasional Teknik Elektro, Sistem Informasi, dan Teknik Informatika (SNESTIK) 2025: SNESTIK V
Publisher : Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/p.snestik.2025.7034

Abstract

Meramalkan harga emas sangat penting untuk membuat keputusan keuangan yang tepat, menawarkan informasi berharga bagi investor dan pemangku kepentingan di pasar emas. Metode pembelajaran mendalam telah membuat kemajuan signifikan di berbagai bidang, seperti pengenalan gambar dan analisis sentimen. Makalah ini mengimplementasikan jaringan Memori Jangka Panjang dan Pendek (LSTM) untuk klasifikasi data kemudian kinerjanya dibandingkan dengan model regresi linier untuk memprediksi fluktuasi harga emas. Analisis prediksi harga emas harian menunjukkan bahwa model LSTM mencapai tingkat akurasi 88%, sedangkan model regresi linier berkinerja sedikit lebih baik dengan tingkat akurasi 98%. Dengan memanfaatkan kekuatan kedua model, penelitian ini memberikan wawasan penting bagi investor di pasar emas.
Klasifikasi Jenis Jerawat pada Data Citra Jerawat Wajah Menggunakan Convolutional Neural Network Putri, Chatarina Natassya; Qornain, Wafi Dzul; Bamahri, Fakhirah; Yuliastuti, Gusti Eka; Kurniawan, Muchamad
TIN: Terapan Informatika Nusantara Vol 5 No 2 (2024): July 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v5i2.5231

Abstract

Acne is a condition caused by pilosebaceous inflammation which affects 85% of skin conditions in adolescents and adults. Acne has an impact on the psychological and social health of sufferers. To treat acne, it is necessary to know the right type of acne so that sufferers can treat the type of acne according to how they are treated. This research was carried out to classify the types of acne in facial acne images using the Convolutional Neural Network (CNN) method. Based on previous research, it shows that the use of CNN is considered effective and appropriate in increasing classification accuracy. This research uses a dataset of acne types from Kaggle with a total of 351 data, divided into 5 classes, namely acne fulminans, acne nodules, fungal acne, papules and pustules which will be tested using 2 different optimizers, namely Adam and RMS- prop. From the results of this test, the highest accuracy was 100% using the Adam optimizer and the RMS-prop optimizer test obtained the highest accuracy value of 80%.