Claim Missing Document
Check
Articles

Found 11 Documents
Search

ANALISIS SENTIMEN KINERJA TENAGA MEDIS INDONESIA MENGGUNAKAN MODELING ROBERTA DAN METODE MACHINE LEARNING Husaini, Rahayun Amrullah; Priyanto, Dadang; Hendro Martono, Galih
Edu Elektrika Journal Vol. 13 No. 1 (2025)
Publisher : LPPM Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/eduel.v13i1.22163

Abstract

The development of information technology has led to the emergence of various social media applications, such as X, which allow users to share information and opinions. However, social media can also function as a platform for the spread of hoaxes and hate speech. One of the challenges faced is determining whether user comments are negative, neutral, or positive through sentiment analysis. This study aims to compare the performance of various classification algorithms in sentiment analysis of medical personnel services in X, using the Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) algorithms with RoBERTa model-based labeling. Data was collected through the tweet-harvest library and processed using the Python programming language. The results showed a significant increase in accuracy, with the model able to classify public opinion into positive, negative, or neutral categories. The SVM model achieved the highest accuracy of 91.8%, outperforming other models such as Random Forest and Naïve Bayes, and provided insight into sentiment towards government health services. These findings provide valuable insights for policymakers in improving the provision of health services and managing public perceptions of medical personnel.
Klasifikasi Gizi Lansia Menggunakan Metode Naïve Bayes Classifier Kartarina Kartarina; Adelia Azzahrah Hatina; Ria Rismayati; Baiq Fitria Rahmiati; Fatimatuzzahra Fatimatuzzahra; Rahayun Amrullah Husaini
Jurnal Teknologi Informasi dan Multimedia Vol. 6 No. 2 (2024): August
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v6i2.502

Abstract

Elderly people are a group that is vulnerable to experiencing various problems in terms of nutrition and health caused by changes in eating patterns. Nutritional status affects the independence of an elderly person, where good nutritional status means less dependence on other people and vice versa. It is necessary to treat malnutrition or malnutrition as early as possible, one of which is by having an elderly posyandu. Posyandu for the elderly as a community service provides services and assistance in special health for the elderly, by regularly recording, controlling and reviewing the medical records of the elderly in a document. The data processing method in this research uses the Naïve Bayes method, where the data used comes from the medical records of the elderly and then used as a reference as to whether the elderly have good nutrition or are malnourished and require further action. Medical record documents play an important role in posyandu services for the elderly, so that medical record documents should be digitally based and systematic in recommending the nutritional status of the elderly. The Naïve Bayes algorithm is an algorithm that can help in classifying data in diagnosis using criteria for the condition of elderly patients. Naïve Bayes also has precise accuracy when implemented in applications that have databases with large data and makes it easier for users to interpret the results. This is proven by this research which produces an accuracy value of 91% with the data used as a sample of 110 elderly patients. The system design aims to help users as posyandu cadres in knowing whether the condition of the elderly is good, whether the elderly are at risk of malnutrition and provide treatment that is appropriate to the condition of elderly patients as well as assisting the Posbindu PTM in transforming documents into computerized ones.
Rice Leaf Disease Classification Based on ResNet50 and MobileNetV3 Feature Extraction Using Random Forest Pratama, Gede Yogi; Husaini, Rahayun Amrullah; Nasri, Muhammad Haris; Hammad, Rifqi
Media Jurnal Informatika Vol 17, No 2 (2025): Media Jurnal Informatika
Publisher : Teknik Informatika Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5939

Abstract

Diseases in rice plants are one of the main factors contributing to decreased agricultural productivity. Early and accurate disease identification is crucial to support effective decision-making in plant disease management. This study aims to compare the performance of deep learning models based on Convolutional Neural Networks (CNN), namely ResNet50 and MobileNetV3, as well as their integration with the Random Forest (RF) algorithm for rice leaf disease classification. The dataset used consists of rice leaf images categorized into several disease classes. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics with a macro-average approach. The results show that the standalone ResNet50 and MobileNetV3 models achieved accuracies of 62.5% and 65.7%, respectively, with macro F1-scores below 0.65, indicating moderate classification performance. However, combining CNN models with Random Forest significantly improved classification performance. The ResNet50 + RF model achieved an accuracy of 99.6%, while the MobileNetV3 + RF model attained the highest accuracy of 99.8%, along with equally high macro-averaged precision, recall, and F1-score values. These findings demonstrate that integrating CNN-extracted features with the Random Forest algorithm enhances the model’s ability to distinguish disease classes more accurately and consistently. Therefore, the hybrid CNN–Random Forest approach shows strong potential as an effective solution for image-based rice plant disease detection systems.
Autism Classification Using MobileNetV3 Feature Extraction and K-Nearest Neighbor Algorithm Husaini, Rahayun Amrullah; Pratama, Gede Yogi; Latif, Kurniadin Abd.; Zulfikri, Muhammad; Augustin, Kartarina
Media Jurnal Informatika Vol 17, No 2 (2025): Media Jurnal Informatika
Publisher : Teknik Informatika Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5934

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by difficulties in social interaction, communication, and repetitive behaviors. Early detection of ASD is crucial; however, conventional diagnostic methods rely heavily on clinical observation and expert assessment, which can be time-consuming and resource-intensive. Along with the rapid development of artificial intelligence, especially in computer vision and machine learning, automated image-based approaches have gained attention as alternative tools for ASD screening. This study proposes a hybrid classification approach that integrates MobileNetV3 as a feature extraction model with the K-Nearest Neighbor (KNN) algorithm for autism classification using facial image data. Unlike previous CNN–KNN approaches, this study specifically explores the use of MobileNetV3’s lightweight architecture to generate compact and discriminative facial features, which are then classified using KNN to evaluate its effectiveness in low-complexity and resource-efficient settings. This design highlights the novelty of combining an optimized lightweight CNN with a distance-based classifier for autism detection from facial images. The dataset used in this research was obtained from Kaggle and consists of 2,940 labeled facial images of children categorized into Autism and non-Autism classes. This study proposes a hybrid classification approach that combines MobileNetV3 as a lightweight feature extraction model with the K-Nearest Neighbor (KNN) algorithm for autism classification. Experimental evaluations were conducted over multiple independent runs to improve statistical reliability, and model performance was assessed using accuracy, precision, recall, and F1-score. The results indicate that the proposed hybrid model achieves satisfactory and consistent performance while maintaining computational efficiency. These findings suggest that integrating lightweight deep learning models with classical machine learning algorithms can provide an effective and resource-efficient approach for autism classification, with potential applicability as a supportive tool for early ASD screening rather than a definitive clinical diagnosis.
Klasifikasi Ulasan Pengguna Tiket Pesawat Online dengan Penanganan Ketidakseimbangan Data Menggunakan SMOTE dengan Machine Learning Rahayun Amrullah Husaini; Gede Yogi Pratama; Azral Satrani
Jurnal Tata Kelola dan Kerangka Kerja Teknologi Informasi Vol. 12 No. 1 (2026): April 2026
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/jtk3ti.v11i3.18906

Abstract

The COVID-19 pandemic affected public habits in air travel and increased the use of online ticket booking platforms. This study aimed to analyze sentiment in online flight ticket purchase reviews using the Support Vector Machine and K-Nearest Neighbor methods. The research was conducted by collecting user review data from the Tiket.com website, followed by preprocessing, term weighting using TF-IDF, and classification using both methods. The results show that the Support Vector Machine method achieves an accuracy of 51 percent, while the K-Nearest Neighbor method reaches 55 percent after applying data balancing techniques. This study concludes that both methods are effective in classifying user sentiment and can assist service providers in improving service quality and understanding customer needs
Local Wisdom-Based Treatment Recommendation System for Tropical Diseases Using Bayesian Network and Association Rule Mining Muhammad Haris Nasri; Rifqi Hammad; Pahrul Irfan; I Nyoman Switrayana; Rahayun Amrullah Husaini
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6290

Abstract

Tropical diseases remain a major public health problem in Indonesia, particularly in regions with limited access to healthcare facilities, leading communities to rely on traditional medicine based on local wisdom. However, the integration of traditional and modern treatment knowledge in intelligent recommendation systems remains limited. This study aimed to develop a tropical disease treatment recommendation system by integrating Bayesian Network (BN) and Association Rule Mining (ARM). Traditional and modern treatment knowledge were collected from scientific literature and expert interviews, validated by medical practitioners and traditional medicine experts, and incorporated into the system. A quantitative and experimental approach was conducted using a dataset of 150 tropical disease cases comprising dengue fever (42 cases), malaria (35), leptospirosis (28), tuberculosis (30), and leprosy (15). The dataset included 47 symptom attributes, 34 traditional treatment attributes, and 12 modern treatment attributes. Bayesian Network was used to model probabilistic relationships among symptoms, diagnoses, and treatments, while the Apriori algorithm in ARM was applied with minimum support and confidence thresholds of 0.3 and 0.7, respectively. Experimental evaluation on 30 testing cases showed that the integrated BN-ARM model achieved 86.7% accuracy and an F1-score of 86.0%, outperforming standalone BN (82.0% accuracy; F1-score 82.5%) and ARM (79.0% accuracy; F1-score 78.8%). The system generated accurate and contextually relevant treatment recommendations by combining local wisdom and modern medical knowledge.
Autism Classification Using MobileNetV3 Feature Extraction and K-Nearest Neighbor Algorithm Rahayun Amrullah Husaini; Gede Yogi Pratama; Kurniadin Abd. Latif; Muhammad Zulfikri; Kartarina Augustin
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5934

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by difficulties in social interaction, communication, and repetitive behaviors. Early detection of ASD is crucial; however, conventional diagnostic methods rely heavily on clinical observation and expert assessment, which can be time-consuming and resource-intensive. Along with the rapid development of artificial intelligence, especially in computer vision and machine learning, automated image-based approaches have gained attention as alternative tools for ASD screening. This study proposes a hybrid classification approach that integrates MobileNetV3 as a feature extraction model with the K-Nearest Neighbor (KNN) algorithm for autism classification using facial image data. Unlike previous CNN–KNN approaches, this study specifically explores the use of MobileNetV3’s lightweight architecture to generate compact and discriminative facial features, which are then classified using KNN to evaluate its effectiveness in low-complexity and resource-efficient settings. This design highlights the novelty of combining an optimized lightweight CNN with a distance-based classifier for autism detection from facial images. The dataset used in this research was obtained from Kaggle and consists of 2,940 labeled facial images of children categorized into Autism and non-Autism classes. This study proposes a hybrid classification approach that combines MobileNetV3 as a lightweight feature extraction model with the K-Nearest Neighbor (KNN) algorithm for autism classification. Experimental evaluations were conducted over multiple independent runs to improve statistical reliability, and model performance was assessed using accuracy, precision, recall, and F1-score. The results indicate that the proposed hybrid model achieves satisfactory and consistent performance while maintaining computational efficiency. These findings suggest that integrating lightweight deep learning models with classical machine learning algorithms can provide an effective and resource-efficient approach for autism classification, with potential applicability as a supportive tool for early ASD screening rather than a definitive clinical diagnosis.
Rice Leaf Disease Classification Based on ResNet50 and MobileNetV3 Feature Extraction Using Random Forest Gede Yogi Pratama; Rahayun Amrullah Husaini; Muhammad Haris Nasri; Rifqi Hammad
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5939

Abstract

Diseases in rice plants are one of the main factors contributing to decreased agricultural productivity. Early and accurate disease identification is crucial to support effective decision-making in plant disease management. This study aims to compare the performance of deep learning models based on Convolutional Neural Networks (CNN), namely ResNet50 and MobileNetV3, as well as their integration with the Random Forest (RF) algorithm for rice leaf disease classification. The dataset used consists of rice leaf images categorized into several disease classes. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics with a macro-average approach. The results show that the standalone ResNet50 and MobileNetV3 models achieved accuracies of 62.5% and 65.7%, respectively, with macro F1-scores below 0.65, indicating moderate classification performance. However, combining CNN models with Random Forest significantly improved classification performance. The ResNet50 + RF model achieved an accuracy of 99.6%, while the MobileNetV3 + RF model attained the highest accuracy of 99.8%, along with equally high macro-averaged precision, recall, and F1-score values. These findings demonstrate that integrating CNN-extracted features with the Random Forest algorithm enhances the model’s ability to distinguish disease classes more accurately and consistently. Therefore, the hybrid CNN–Random Forest approach shows strong potential as an effective solution for image-based rice plant disease detection systems.
Peningkatan Kompetensi Digital Siswa melalui Pelatihan Pengembangan Aplikasi Web dalam Mendukung Kualitas Sumber Daya Manusia Mohammad Najib Roodhi; Rahayun Amrullah Husaini; Gede Yogi Pratama; Rifqi Hammad; I Nyoman Switrayana; Muhammad Haris Nasri; Gilang Primajati
Rengganis Jurnal Pengabdian Masyarakat Vol. 6 No. 1 (2026): Mei 2026
Publisher : Pendidikan Matematika, FKIP Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/rengganis.v6i1.1102

Abstract

The rapid development of digital technology demands an increase in the quality of human resources (HR) that are adaptive to change, especially in the field of information technology. One of the competencies needed is the ability to develop web-based applications, which are increasingly relevant to industry needs. This community service activity aims to improve students' digital competencies and reduce the dynamic skills gap through web application development training. The partners in this activity were grade X students of SMKN 2 Mataram with a total of more than 20 participants. The training method used was a learning-by-doing approach, which included material delivery, demonstrations, direct practice, and evaluation. The results of the activity showed an increase in the average score of participants from 65 in the pre-test to 85 in the post-test, indicating a significant increase in participant understanding. In addition, participants were also able to develop simple web applications and demonstrated improved problem-solving skills and self-confidence. This activity contributes to improving digital competencies and strengthening the quality of human resources who are better prepared to face technological developments in the digital era.
Enhancing Software Defect Prediction Performance using NR-Clustering SMOTE to Address Class Imbalance Hairani Hairani; Muhamad Masjun Efendi; Gede Yogi Pratama; Rahayun Amrullah Husaini; M.Khaerul Ihsan
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 4 (2026): August 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i7558

Abstract

Software defect detection is important to prevent system failures and increased maintenance costs. However, the complexity of modern software makes manual testing inefficient, so machine learning approaches are used. The main challenge of this approach is data imbalance, where defective cases are far fewer, causing the model to overlook the minority class and reducing detection capability, even though accuracy appears high. This study aims to address class imbalance in software defect detection by applying the NR-Clustering SMOTE method to improve machine learning performance—the classification methods using Random Forest. NR-Clustering SMOTE not only oversamples the minority class but also incorporates a noise-reduction mechanism to remove minority data that may degrade classification performance. The results show that NR-Clustering SMOTE improves the performance of Random Forest compared with the original data, SMOTE, and NR-Modified SMOTE across all evaluation metrics, namely accuracy, recall, and F1-score. These findings indicate that integrating noise reduction and SMOTE-based data balancing using Manhattan distance within each cluster produces a more representative data distribution, thereby improving the model’s ability to classify software defect cases more accurately. Therefore, this study confirms that NR-Clustering SMOTE effectively improves Random Forest performance for software defect detection compared with existing approaches.