Jurnal Teknologi Informasi dan Terapan

K-Nearest Neighbors Optimization using Particle Swarm Optimization in Selection Digital Payments

Ridwansyah Ridwansyah — 2025-06-30

Fintech developments have increased the use of digital payment systems such as OVO and GoPay. However, selecting a payment method that suits user preferences is still a challenge. This research proposes a combination of K-Nearest Neighbors (KNN) and Particle Swarm Optimization (PSO) to improve the classification accuracy of digital payment systems. The dataset used comes from a survey of Fintech users with factors such as ease of application, data security, cashback and customer service. KNN is used as a classification method, while PSO is applied for feature selection to improve model efficiency. Evaluation is carried out using accuracy, precision, recall, and AUC. The research results show that accuracy increased from 94.00% to 95.47% after optimization with PSO. The most influential factors are customer service, user employment and cashback. However, the AUC value remains 0.500, which shows that the model still has limitations in optimally differentiating categories. Further research is recommended to explore other algorithms such as Random Forest and SVM, as well as developing a machine learning-based digital payment recommendation system

Clustering-based Machine Learning Approach For Predicting Tourism Trends From Social Media Behavior

Candra Agustina — 2025-06-30

Digital technology has significantly transformed tourist behavior, particularly in searching for, selecting, and sharing travel experiences. Social media has become a primary source of information, influencing travel decisions through real-time recommendations and user-generated content. However, the large volume of data generated by social media presents challenges in understanding and predicting tourist behavior. This study aims to analyze tourist behavior patterns using a clustering-based machine learning approach, specifically K-Means Clustering. The research examines engagement levels on platforms such as Instagram, TikTok, and TripAdvisor to categorize tourists into three key segments: Digital-Savvy Travelers, Passive Travelers, and Conservative Travelers. The results indicate that machine learning effectively analyzes large-scale tourism data, providing valuable insights for destination marketing, personalized recommendations, and service optimization. The findings highlight the potential of machine learning to identify emerging trends, improve customer segmentation, and enhance targeted promotional strategies. Understanding these patterns enables tourism businesses to create data-driven strategies aligned with modern travel behaviors. In a broader perspective, artificial intelligence can revolutionize tourism marketing, increase customer engagement, and improve the overall travel experience

Color Feature Selection Optimized with Bio- Inspired Algorithms in Classify Purity of Luwak Coffee

Shinta Widyaningtyas — 2025-06-30

Assessing the purity of Luwak Coffee is a complex challenge due to its unique production and limited availability, as visual inspection is unreliable. This study explores the use of image processing and feature selection to classify Luwak Coffee purity by analyzing 11 color features including RGB, HSV, HSL, and Lab color spaces. Two classification methods k-Nearest Neighbors (k-NN) and Random Forest (RF) were optimized using six Bio-Inspired Algorithms (Differential Evolution, Firefly Algorithm, Flower Pollination Algorithm, Harris Hawk Algorithm, Jaya Algorithm, and Particle Swarm Optimization) to identify the most important features for classifying the purity of Luwak Coffee. The results revealed that feature selection significantly improved accuracy, with the Jaya Algorithm paired with k-NN achieving the highest accuracy (0.918) using only three features (R_Mean, B_Mean, and H_Mean). For RF, the Flower Pollination Algorithm yielded the best performance (0.899) with three features. The study demonstrates a classification method coupled with Bio-Inspired Algorithms for classifying Luwak Coffee purity providing high accuracy as a non-destructive method. These findings contribute to the development of reliable tools for classifying purity of Luwak Coffee

Machine Learning-Based Book and Library Recommendation Application Using Content-Based Filtering Method

Novit Saputri — 2025-06-30

This research focuses on the development of a Book Recommendation System application, which aims to simplify book searches based on reader preferences. Faced with the challenge of selecting books that match their interests, readers often find it difficult to navigate the vast array of information available. The availability of different genres and authors can make the selection process complicated and time-consuming. Therefore, the development of a Book Recommendation System application is a relevant and necessary solution. The author's research question is how to optimize the book search experience through accurate recommendation algorithms. This project will use a collaborative algorithm-based recommendation model to analyze reader behavior patterns and provide accurate book recommendations based on the similarity of reader preferences. The application that the author designed allows readers to easily find suitable books. The author is committed to overcoming readers' difficulties in dealing with the abundance of information, increasing the accessibility of books, and improving reader satisfaction. The success of the project is measured by the application's ability to provide satisfactory recommendations, find relevant works, and simplify the literature exploration process. With the development of the era of vast information, the development of a Book Recommendation System is a relevant solution to guarantee a more enjoyable and efficient reading experience for readers

Utilizing Data Mining Approach For Hypertension Diagnosis Classification

Pudji Widodo — 2025-06-30

Hypertension is one of the factors contributing to the highest death rates from non-communicable diseases in various countries. Every year, the number of hypertension sufferers increases significantly. It is estimated that in 2025, the number of hypertension sufferers will reach 1.5 billion individuals. Data mining aims to identify patterns that can help in decision making, classification, and prediction. One of the well-known algorithms or methods for classification is the Support Vector Machine (SVM). The SVM method aims to find the best hyperplane or decision boundary function that can separate two or more classes of data in the input space. This research purpose is to determine the classification results and accuracy of the diagnosis of hypertension using the SVM method. Eleven attributes used include age, smoking habits, physical activity, sugar consumption, salt consumption, fat consumption, alcohol consumption, lack of fruit and vegetable consumption, systolic and diastolic blood pressure. This research will utilize Jupyter Notebook tools and Python programming language as research tools. The SVM method was trained with various kernel attributes and hyperparameters to produce the best model. From the results it is known that the RBF kernel used with parameters ???? = 100 and ???? = 0.1 produces an accuracy of 97.5% which is the best model in classifying hypertension. From these results it can be concluded that the SVM method is able to produce a very good classification of hypertension diagnosis and can provide a diagnosis to detect hypertension early

Efficient Intrusion Detection System Utilizing Ensemble Learning and Statistical Feature Selection in Agricultural IoT Networks

Bekti Maryuni Susanto — 2025-06-30

To enhance agricultural processes, smart agriculture combines a variety of devices,
protocols, computing paradigms, and technologies. The cloud, edge computing, big data, and
artificial intelligence all offer tools and solutions for managing, storing, and analyzing the vast
amounts of data produced by various parts. Smart agriculture is still in its infancy and lacks several
security measures, brought in the creation of numerous networks that are vulnerable to cyberattacks.
The most well-known cyberattack is called a denial of service (DoS) attack, in which the attackers
overwhelm the network with massive amounts of data or requests, preventing the nodes from
accessing the various services that are provided in that network. Intrusion Detection Systems (IDS)
have shown to be effective defense mechanisms in the event of a cyberattack. The implementation
of conventional intrusion detection systems (IDS) approaches in Internet of Things (IoT) devices
was hindered by resource constraints, such as reduced computing capacity and low power
consumption. In this paper, we used an ensemble learning and statistical based feature selection
strategy to create a lightweight intrusion detection solution. The results show that the stacking
ensemble method is able to improve the performance of single machine learning in the classification
of anomalous events even though the computation time required is quite large compared to the
computation time of single machine learning

Implementation of the Template Matching Algorithm for Smart Light Control through Speech Recognition for People with Disabilities

Sholihah Ayu Wulandari — 2025-10-20

Voice control systems in smart homes provide significant convenience for people with disabilities, especially in operating household devices such as lights without physical interaction. This study develops a voice-based light control system that runs locally on IoT devices using the template matching method. This system utilizes Mel-Frequency Cepstral Coefficients (MFCC) for voice feature extraction and Dynamic Time Warping (DTW) to match test voices with pre-recorded templates. Out of 66 voice samples tested, the system successfully recognized 13 out of 22 voices belonging to the primary user and rejected 43 out of 44 voices from other users, with an accuracy rate of 84.85%. Thus, this system shows potential as an inclusive, efficient, and disability-friendly voice control solution for smart home environments