Garuda - Garba Rujukan Digital

Application of YOLOv8 Model for Early Detection of Diseases in Bean Leaves Indra Yustiana; Alun Sujjada; Tirawati
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2514

Bean plant is one of the high economic value horticultural commodities widely cultivated in Indonesia. However, its productivity declines due to pest attacks and leaf diseases. Farmers' limitations in accurately identifying disease types also pose obstacles in early mitigation efforts. Therefore, technology-based solutions capable of quickly and accurately detecting plant diseases are needed. This research aims to develop and evaluate the performance of a leaf disease detection model for bean plants using the You Only Look Once version 8 (YOLOv8) algorithm with a transfer learning approach. The dataset used consists of 1,037 images of bean leaves, classified into three categories: angular leaf spots, leaf rust, and healthy leaves. Data were obtained from two sources, namely field documentation in Sindang Village, Sukabumi Regency, and an open repository on GitHub. The dataset was divided into training data (70%), validation (20%), and testing (10%). The model was trained using the YOLOv8s architecture for 30 epochs and achieved a detection accuracy of 85%. Performance evaluation was conducted using precision, recall, and mean average precision (mAP) metrics. The results of this study are expected to be an initial contribution to the application of artificial intelligence in agriculture, particularly in helping farmers efficiently detect leaf diseases in beans to improve productivity and quality of harvest.

Application Of Random Forest Algorithm in Music Recommendation System Using Content-Based Filtering Rubby Malik Fajar; Indra Yustiana; Alun Sujjada
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2803

The rapid growth of digital technology has revolutionized how people access and listen to music, especially through online streaming platforms. However, the overwhelming number of available songs often confuses users, particularly new users who have no listening history. To address this, the study proposes a music recommendation system using a content-based filtering approach that recommends songs based on similarities in both textual and numerical features, such as genre, artist, lyrics, tempo, energy, and danceability. The system operates in two main stages. First, it classifies the popularity of songs into two categories, “High” and “Low,” using three classification algorithms: Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). Second, it generates music recommendations based on content similarity using TF-IDF and cosine similarity. Random Forest is chosen as the main algorithm due to its superior performance in high-dimensional data and its ensemble learning mechanism. The evaluation uses confusion matrix metrics including accuracy, precision, recall, and F1 score, tested across multiple data split ratios (90:10, 80:20, 70:30, 60:40). The results show that Random Forest consistently delivers better classification and recommendation performance compared to KNN and SVM. It demonstrates higher accuracy and F1 score, making it suitable for real-world applications. The system is developed using Streamlit, allowing users to interactively receive music recommendations through a user-friendly web interface. The findings support the integration of Random Forest in content-based recommendation systems to improve accuracy and solve cold-start problems effectively in digital music platforms.

Implementation of Content-Based Filtering in a Novel Recommendation System to Enhance User Experience Imam Sanjaya; Alun Sujjada; Yudistira Pratama
bit-Tech Vol. 8 No. 1 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i1.2833

This study addresses a critical challenge in digital novel platforms: the difficulty of delivering personalized and accurate recommendations due to limited user interaction data. This limitation often leads to irrelevant or generic suggestions, which can diminish user engagement and hinder content discovery. The significance of solving this issue lies in enhancing user experience by ensuring that readers are presented with novels that truly align with their interests, even in the absence of extensive behavioral data. To overcome this problem, the study proposes an innovative hybrid recommendation system that integrates Content-Based Filtering (CBF) with the Random Forest algorithm. The system generates personalized recommendations by analyzing novel attributes such as title, genre, score, and popularity. The methodology involves extracting features from textual data using Term Frequency-Inverse Document Frequency (TF-IDF), followed by the calculation of cosine similarity to assess title relevance. These similarity scores are then combined with popularity predictions derived from the Random Forest model to produce final recommendations that reflect both content similarity and statistical relevance. The proposed system demonstrates strong performance, achieving an accuracy of 94.0%, precision of 81.4%, recall of 80.3%, and an F1-score of 80.8%. These results underscore the system’s capability to deliver accurate and diverse suggestions. By enhancing personalization and addressing the limitations of conventional CBF systems, this hybrid approach offers practical value for digital novel platforms. It serves as an effective tool for improving content discovery, increasing reader satisfaction, and supporting user retention in content-rich environments.

Enhancing E-Commerce System Scalability Through Event-Driven Architecture with RabbitMQ and Docker Rifqi Ramdhani; Alun Sujjada; Nugraha Nugraha
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.2948

The rapid expansion of e-commerce in Indonesia has intensified the demand for highly scalable and responsive systems, especially during high-traffic periods. Traditional architectures that rely on synchronous Remote Procedure Call (RPC) models often experience performance bottlenecks, which can degrade user experience during peak load. To address this limitation, this study evaluates the use of an Event-Driven Design (EDD) architecture to improve system scalability and responsiveness. The objective is to compare the performance of RPC and EDD architectures using the "Add to Cart" feature an essential interaction in the e-commerce transaction flow as a benchmark. Two identical e-commerce prototypes were developed: one utilizing RPC and the other EDD, which incorporates asynchronous message processing. Performance testing was conducted using virtual users under multiple load scenarios to assess average response time and throughput. Results showed that the EDD-based system achieved up to 495 requests per second and maintained response times as low as 49–52 ms, whereas the RPC-based system peaked at only 5.1 requests per second with significant latency increases. These results represent a performance improvement of over 9,000% in throughput, confirming EDD's superiority in high-concurrency environments. This study contributes empirical evidence to the architectural decision-making process in e-commerce system design by demonstrating the substantial advantages of asynchronous, decoupled communication models. The findings support the adoption of EDD as a scalable and resilient solution for modern e-commerce platforms facing unpredictable traffic loads.

Title

Found 4 Documents
Search

Abstract

Abstract

Abstract

Abstract

Title Search

Found 4 Documents Search

Abstract

Abstract

Abstract

Abstract

Title

Found 4 Documents
Search