Claim Missing Document
Check
Articles

Found 33 Documents
Search
Journal : Computer

OTOMATISASI JEMURAN PAKAIAN MENGGUNAKAN SENSOR HUJAN BERBASIS ARDUINO VIA BOT WHATSAPP Andy; Handoko, Koko
Computer Science and Industrial Engineering Vol 13 No 1 (2025): Comasie Vol 13 No 1
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i1.10143

Abstract

Indonesia has two seasons, namely the dry season and the rainy season. During the dry season, the need for sunlight is very much needed, one example is drying wet clothes. However, when the weather is uncertain, the job of drying clothes becomes quite troublesome and will take time and energy to lift and dry the clothes again. In this study, researchers will design a prototype that can protect clotheslines when it rains and provide notifications to the user's WhatsApp that this prototype detects rain and immediately protects the clotheslines from the rain. This prototype is designed using Arduino Uno as the main controller on this prototype and can be connected to the internet network, a rain sensor as a rain detector, and a micro servo as a roof driver above the clothesline. The results of conducting trials on the prototype are that this prototype can protect clotheslines from rain and also successfully send notifications in the form of WhatsApp messages that rain has been detected.
PREDIKSI IMPLAN GIGI MENGGUNAKAN ALGORITMA MACHINE LEARNING Zebua, Alisa; Handoko, Koko
Computer Science and Industrial Engineering Vol 13 No 2 (2025): Comasie Vol 13 No 2
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i2.10431

Abstract

Advances in digital technologies, particularly artificial intelligence (AI), are transforming healthcare practices, including dental implant decision-making. This study introduces a machine learning model utilizing the Classification and Regression Tree (CART) algorithm to estimate dental implant candidacy, drawing on anonymized patient records from Ellisa Dental Clinic, Batam. The dataset comprises various demographic and clinical attributes such as age, sex, smoking patterns, bone condition, and the presence of chronic illnesses including diabetes, hypertension, and autoimmune disorders. The exploratory analysis reveals that factors like heavy smoking, systemic diseases, and jawbone integrity substantially affect implant suitability. The quality and consistency of the dataset support robust modeling. The proposed system is intended to function as a clinical decision aid, offering dentists evidence-based recommendations regarding patient eligibility. This work demonstrates the potential of predictive analytics to enhance decision accuracy and streamline dental care, contributing to the integration of AI into routine clinical workflows.
IMPLEMENTASI DAN ANALISIS SENTIMEN PADA ULASAN APLIKASI GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA RoBERTa Nainggolan, Brian Natanael; Handoko, Koko
Computer Science and Industrial Engineering Vol 13 No 3 (2025): Comasie Vol 13 No 3
Publisher : LPPM Universitas Putera Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33884/comasiejournal.v13i3.10501

Abstract

The rapid growth of Instagram user reviews on the Google Play Store poses challenges in understanding sentiment quickly and accurately. This research aims to develop an automatic sentiment analysis dashboard based on the Indonesian-RoBERTa model. Review data was collected using the google_play_scraper library and analyzed using a fine-tuned model. Fine-tuning was performed on the w11wo/indonesian-roberta-base-sentiment-classifier model using Indonesian tweet datasets during the PPKM period with 23,645 labeled data points (positive, neutral, negative). The preprocessing process included text cleaning, tokenization, and class weighting. Model evaluation used precision, recall, F1-score, and confusion matrix metrics. Test results showed good performance on positive and neutral classes, but performance on the negative class still needs improvement. The dashboard successfully performed scraping, sentiment prediction, and data visualization automatically. This research demonstrates the potential application of transformer-based models in Indonesian language and supports data-driven decision making.