Claim Missing Document
Check
Articles

Found 4 Documents
Search

Implementation of You Only Look Once Version 8 Algorithm to Detect Multi-Face Drivers and Vehicle Plates Saputra S, Kana; Taufik, Insan; Ramadhani, Irham; Siregar, Angginy Akhirunnisa; Pinem, Josua; Lubis, Afiq Alghazali; Pane, Yeremia Yosefan; Putri, Rezkya Nadilla
Jurnal Informatika Vol 11, No 2 (2024): October
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/inf.v11i2.22026

Abstract

Checking the identity of motorcycle owners when leaving the college area is a mandatory activity for security officers to ensure that vehicles entering and exiting the college are the same driver. The conventional checking process often causes the impact of vehicle queues when the volume of vehicles increases. Therefore, an intelligent system is needed to detect multi-plate vehicles automatically. One approach in the world of image detection of an object is the use of the YOLO (You Only Look Once) algorithm. This algorithm predicts bounding boxes and possible classes in a single frame. This research divides objects into 3 classes, namely vehicles, driver's faces, and vehicle plates. The dataset used was 74 varied images consisting of 50 training data, 12 validation data and 12 testing data. The image was trained using 300 epochs and a batch size of 8 and resulted in an F1 score calculation for detecting objects reaching 92%.
Classification of Pear Varieties Using the K-Nearest Neighbor Algorithm and Extraction of Shape, Color, Texture, and Size Features Putri, Rezkya Nadilla; Kiswanto, Dedy; Sitepu, Keysa Shifa Adwitia
Golden Ratio of Data in Summary Vol. 5 No. 1 (2025): November - January
Publisher : Manunggal Halim Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52970/grdis.v5i1.910

Abstract

This study develops a pear variety classification system based on digital images using the K-Nearest Neighbor (KNN) algorithm. The data used included 195 images from three pear varieties, namely Century, Forel Afrika, and Singo, which were analyzed by utilizing various features such as color (RGB), texture (Local Binary Pattern), shape (area, circumference, length-width ratio), and size (bounding box dimensions). The preprocessing process removes the image's background to increase focus on the main object, thus allowing for more optimal feature extraction. The dataset is divided into 80% for training and 20% for model testing. The evaluation results show that the KNN model can achieve an accuracy of 85%, with an average precision value of 0.85, recall of 0.89, and F1-score of 0.85. These results prove that the KNN algorithm is effective in accurately classifying pear varieties, which can significantly contribute to applying digital image-based technology for automatic classification needs in the agricultural sector.
Peramalan Permintaan Roti Harian dengan Simulasi Monte Carlo di Reza Bakery Sitepu, Keysa Shifa Adwitia; Putri, Rezkya Nadilla; Harliana, Putri
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 6 No. 2 (2025): Mei
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v6i2.1419

Abstract

The fluctuating daily demand at Reza Bakery leads to an imbalance between production capacity and consumer needs. This study aims to forecast the daily demand of the three best-selling bread products using the Monte Carlo simulation method: Small White Bread, Mocha Bread, and French Chocolate Bread. Sales data from April 2025 covering 30 days were used as the simulation basis. The simulation involves calculating the probability distribution of demand, generating random numbers, and mapping them to demand predictions. Results show that daily demand predictions range from 33–40 units for Small White Bread, 16–22 units for Mocha Bread, and 7–12 units for French Chocolate Bread. This method helps in formulating more efficient production strategies, with good accuracy estimates based on the match between simulation results and historical trends. The simulation offers potential to reduce overstock risks and improve operational efficiency.
Classification of Pear Varieties Using the K-Nearest Neighbor Algorithm and Extraction of Shape, Color, Texture, and Size Features Putri, Rezkya Nadilla; Kiswanto, Dedy; Sitepu, Keysa Shifa Adwitia
Golden Ratio of Data in Summary Vol. 5 No. 1 (2025): November - January
Publisher : Manunggal Halim Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52970/grdis.v5i1.910

Abstract

This study develops a pear variety classification system based on digital images using the K-Nearest Neighbor (KNN) algorithm. The data used included 195 images from three pear varieties, namely Century, Forel Afrika, and Singo, which were analyzed by utilizing various features such as color (RGB), texture (Local Binary Pattern), shape (area, circumference, length-width ratio), and size (bounding box dimensions). The preprocessing process removes the image's background to increase focus on the main object, thus allowing for more optimal feature extraction. The dataset is divided into 80% for training and 20% for model testing. The evaluation results show that the KNN model can achieve an accuracy of 85%, with an average precision value of 0.85, recall of 0.89, and F1-score of 0.85. These results prove that the KNN algorithm is effective in accurately classifying pear varieties, which can significantly contribute to applying digital image-based technology for automatic classification needs in the agricultural sector.