Article Per Year (5 Year)
p-Index From 2021 - 2026
6.34
P-Index
This Author published in this journals
All Journal TEKNIK INFORMATIKA PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Jurnal sistem informasi, Teknologi informasi dan komputer E-Dimas: Jurnal Pengabdian kepada Masyarakat Format : Jurnal Imiah Teknik Informatika Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Jurnal Ilmiah FIFO Jurnal Sisfokom (Sistem Informasi dan Komputer) Kilat JURIKOM (Jurnal Riset Komputer) IJISCS (International Journal Of Information System and Computer Science) JSAI (Journal Scientific and Applied Informatics) JTIK (Jurnal Teknik Informatika Kaputama) Jurnal Pasopati : Pengabdian Masyarakat dan Inovasi Pengembangan Teknologi RESOLUSI : REKAYASA TEKNIK INFORMATIKA DAN INFORMASI Dedikasi Nusantara: Jurnal Pengabdian Masyarakat Pendidikan Dasar Madani : Jurnal Pengabdian Kepada Masyarakat Jurnal Pengabdian Masyarakat Nasional JPMTT (Jurnal Pengabdian Masyarakat Teknologi Terbarukan) Journal Collabits IJISCS (International Journal of Information System and Computer Science) Indonesian Journal on Computing (Indo-JC)
Umniy Salamah
Universitas Mercu Buana
Aerospace Engineering Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Mathematics Social Sciences Other

Published : 51 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 51 Documents
Search

 2   3   4   5   6 
Hyperparameter Optimization Analysis of MultinomialNB and Logistic Regression in Multi‑Feature Text‑Based Film Genre Classification Shabrio Cahyo Wardoyo; Umniy Salamah
Indonesian Journal on Computing (Indo-JC) Vol. 10 No. 2 (2025): August, 2025
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/indojc.v10i1.9100

Abstract

This study aims to analyze and compare the performance of two text classification algorithms Multinomial Naive Bayes (MNB) and Logistic Regression (LR)—for film genre classification using multi-feature text data, both with and without hyperparameter optimization. Film genres play a crucial role in digital content recommendation systems; however, manual classification is subjective and time-consuming. The dataset, obtained from Letterboxd via Kaggle, includes film titles, descriptions, and themes. After preprocessing and text normalization (tokenization, lemmatization, and stemming), the text data were transformed into numerical features using the TF-IDF method. Two modeling scenarios were applied: the first using default parameters, and the second employing GridSearchCV to find the optimal hyperparameter settings. Model performance was evaluated using accuracy, precision, recall, and F1-score. The results indicate that the optimized LR model achieved the highest accuracy of 0.847, followed by the optimized MNB model with an accuracy of 0.837. This study concludes that hyperparameter optimization significantly improves model performance and that LR outperforms MNB in the context of multi-feature text-based genre classification.
SOSIALISASI APLIKASI PENDETEKSI DIABETES DILENGKAPI DENGAN LIE DETECTION UNTUK MASYARAKAT KELURAHAN DURI KEPA Umniy Salamah; Yuwan Jumaryadi; Diky Firdaus; Bagus Priambodo; Afifah Fitri Anggraini; Vivie Herlina; Ayaitulla Salsabilla Achmad; Putra Ardiansyah; Romeo Mulia Pratama; Zehandra Gibran Nugroho
Jurnal Pengabdian Masyarakat Nasional Vol 6, No 1 (2026)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/pemanas.v6i1.36927

Abstract

Diabetes Melitus Tipe 2 (DMT2) merupakan salah satu permasalahan kesehatan utama di wilayah perkotaan dan banyak dialami oleh kelompok usia produktif, termasuk masyarakat di Kelurahan Duri Kepa. Rendahnya pemahaman masyarakat, khususnya ibu-ibu PKK, mengenai deteksi dini diabetes menjadi latar belakang pelaksanaan kegiatan Pengabdian kepada Masyarakat (PkM) yang berfokus pada sosialisasi aplikasi pendeteksi risiko diabetes berbasis teknologi lie detection. Kegiatan yang dilaksanakan pada 10–31 Oktober 2025 ini meliputi tahap persiapan, pelaksanaan, evaluasi, dan tindak lanjut, dengan melibatkan partisipasi aktif masyarakat. Aplikasi yang diperkenalkan memanfaatkan analisis respons pengguna untuk mengidentifikasi potensi risiko diabetes dan memberikan kategori hasil berupa Tipe 1, Tipe 2, atau Tidak Terdeteksi. Hasil yang diberikan bukan merupakan diagnosis medis, tetapi indikator awal yang berfungsi sebagai pengingat agar masyarakat lebih memperhatikan pola makan, aktivitas fisik, dan gaya hidup sehat. Evaluasi kegiatan menunjukkan adanya peningkatan pengetahuan dan kesadaran masyarakat terhadap deteksi dini diabetes serta pemanfaatan teknologi informasi dalam bidang kesehatan. Program ini memberikan dampak positif dalam meningkatkan literasi kesehatan digital dan menunjukkan penerapan inovasi teknologi informasi untuk mendukung upaya pencegahan penyakit tidak menular di lingkungan masyarakat.
Komparasi Algoritma LightGBM, SVM, dan Logistic Regression dalam Memprediksi Penyakit Stroke Bryant Steven Aritonang; Umniy Salamah
JSAI (Journal Scientific and Applied Informatics) Vol 8 No 1 (2025): Januari
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v8i1.7551

Abstract

Stroke is a serious condition that can lead to disability or death due to disrupted blood flow to the brain. This study aims to compare three machine learning algorithms: LightGBM, Support Vector Machine (SVM), and Logistic Regression, in predicting the risk of stroke. The dataset used contains 5110 rows with 12 attributes, including demographic information and health history. The research process began with data preprocessing, followed by splitting the data into training and testing sets. Models were then trained using the three algorithms and evaluated using accuracy, precision, recall, and F1-score metrics. The analysis results indicate that Logistic Regression performed the best overall, providing a balance between detecting stroke cases and identifying healthy individuals. SVM showed stable results with a balance between recall and precision, while LightGBM, despite high accuracy, was less effective in detecting stroke cases. The study concludes that Logistic Regression is the most suitable model for predicting stroke risk, though SVM can be a good alternative.
Perbandingan Performa Algoritma XGBoost, CatBoost Dan GBM Dalam Prediksi Penyakit Kardiovaskular Panwasto Samosir P; Umniy Salamah
JSAI (Journal Scientific and Applied Informatics) Vol 8 No 1 (2025): Januari
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v8i1.7552

Abstract

Cardiovascular disease remains the primary cause of mortality globally, encompassing conditions affecting the heart and blood vessels, such as hypertension and coronary artery disease. Risk factors include unhealthy lifestyle habits and immutable factors like age and family history. To tackle the challenges in early detection and prediction of cardiovascular disease, machine learning techniques, especially boosting algorithms, have emerged as promising tools. This study evaluates the performance of three prominent boosting algorithms: XGBoost, CatBoost, and Gradient Boosting—using publicly available datasets to predict cardiovascular disease risk. The findings reveal that CatBoost surpasses the other models with an accuracy of 75%, a Precision of 0.83, and a ROC AUC of 0.81, highlighting its exceptional predictive capabilities. Gradient Boosting achieves 70% accuracy with a well-balanced Recall and Precision, whereas XGBoost records the lowest performance with 63.3% accuracy across all metrics. These results position CatBoost as the most effective model for cardiovascular disease risk prediction.
Application of Random Contrast and Brightness Range Methods on Phytomedicine Leaf Image Dataset Mariana Purba; Vina Ayumi; Sarwati Rahayu; Umniy Salamah; Inge Handriani; Ida Farida
JSAI (Journal Scientific and Applied Informatics) Vol 8 No 2 (2025): Juni
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v8i2.8766

Abstract

This study aimed to enhance the performance of deep learning models in detecting and classifying medicinal plant leaf images by applying two data augmentation techniques, namely Random Contrast Augmentation (RCA) and Brightness Range Augmentation (BRA). The RCA technique randomly adjusted the contrast of images by calculating the pixel average and modifying each pixel value based on a contrast factor, thereby increasing the variation in image lighting. Meanwhile, BRA randomly altered the brightness of the images to simulate varying lighting conditions. The research process began with the collection of medicinal plant leaf image datasets, which were then divided into three parts: training data, validation data, and testing data. The dataset was then pre-processed to prepare the images before applying the augmentation. Augmentation techniques were employed to enrich the dataset by generating modified copies of images using RCA and BRA techniques. The application of both augmentation techniques resulted in a training dataset of 2,400 images, 300 validation images, and 300 testing images.
Penerapan Metode Gamma Correction dan MobileNet Untuk Klasifikasi Citra Daun Mariana Purba; Vina Ayumi; Sarwati Rahayu; Umniy Salamah; Inge Handriani; Nur Ani
JSAI (Journal Scientific and Applied Informatics) Vol 8 No 3 (2025): November
Publisher : Fakultas Teknik Universitas Muhammadiyah Bengkulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36085/jsai.v8i3.9459

Abstract

This study proposed an enhanced leaf image classification model by integrating gamma correction as a preprocessing technique with the MobileNet (MNET) architecture to improve visual feature extraction. The dataset consisted of 750 images representing five classes of medicinal plants, namely Psidium guajava, Syzygium polyanthum, Piper betle, Annona muricata, and Andrographis paniculata, obtained from personal documentation, online sources, and public datasets. Gamma correction was applied to adjust illumination and enhance leaf texture clarity, followed by resizing and normalization processes. Data augmentation was performed using rotation, contrast adjustment, horizontal and vertical flipping, brightness adjustment, and channel shifting to increase training data variation. The MobileNet architecture was expanded with additional layers, including global average pooling, flatten, Dense–ReLU, and Dense–softmax, enabling it to function as an efficient feature extractor and classifier. Experiments were conducted using a batch size of 32, 50 epochs, the Adam optimizer, and a learning rate of 0.0001. The combined MNET and gamma correction model achieved a training accuracy of 99.00%, a validation accuracy of 87.50%, and a testing accuracy of 84.16%.
Machine Learning Approaches to Sentiment Analysis of Mental Health Discussions on Platform X Yuwan Jumaryadi; Riri Fajriah; Umniy Salamah; Bagus Priambodo; Arie Lystha
PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Vol. 13 No. 2 (2025): September 2025
Publisher : LPPM Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/piksel.v13i2.11350

Abstract

Sentiment analysis on mental health issues is crucial for understanding public perceptions of healthcare services. This study analyzed tweets related to mental health on platform X in 2025 using SVM, Random Forest, and Naive Bayes algorithms. Data was collected through web scraping with Python, then evaluated using a confusion matrix with accuracy, precision, f1-score, and recall metrics. The classification results showed a distribution of sentiment: positive (3,667 tweets), neutral (838 tweets), and negative (704 tweets). A comparative analysis of the three algorithms revealed that SVM achieved the highest accuracy (78.69%), followed by Random Forest (75.04%) and Naive Bayes (70.44%), proving the superiority of SVM in classifying mental health sentiment. These findings provide valuable insights for stakeholders in improving mental healthcare services based on public feedback, while also offering a reference for effective sentiment analysis methods for social media data.
Multimodal Transfer Learning for Anti-Inflammatory Medicinal Plant Leaf Classification using ResNet50 Umniy Salamah; Nur Ani; Yuwan Jumaryadi; Agustiawan
PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Vol. 14 No. 1 (2026): March 2026
Publisher : LPPM Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/piksel.v14i1.12279

Abstract

This study aimed to develop an AI-based image classification model using transfer learning methods to identify seven types of anti-inflammatory plant leaves commonly used in traditional medicine. The novelty of this research lies in approach to integrating Canny Edge detection and Gamma Correction with the ResNet50 architecture for multimodal fusion. The class plants, including Aloe Vera, Annona Muricata, Centella Asiatica, Muntingia Calabura, and Ocimum Basilicum, are known for their therapeutic properties and bioactive compounds. A dataset consisting of 350 images per species was collected, with images divided into training (70%), validation (20%), and testing (10%) sets. Data augmentation techniques such as rotation, flipping, and zooming were applied to improve model generalization. To enhance classification performance, pre-trained convolutional neural network (CNN) models, including ResNet50 and VGG16, were employed for transfer learning. The study also integrated image processing techniques, such as the Laplacian Filter, Canny Edge, and Gamma Correction, to extract additional features and improve the model’s accuracy. Among the different configurations tested, the combination of Canny Edge and Gamma Correction with ResNet50 yielded the best results, achieving a training accuracy of 89.3%, validation accuracy of 88.1%, and test accuracy of 87.0%. In contrast, the use of Laplacian Filter and Canny Edge with ResNet50 led to lower performance, suggesting that multimodal fusion of certain feature extraction methods could enhance classification accuracy. This research highlighted the potential of AI-driven approaches in the classification of medicinal plant leaves and offered a more efficient, accurate method for identifying anti-inflammatory plants used in traditional medicine.
SOSIALISASI APLIKASI PENDETEKSI DIABETES DILENGKAPI DENGAN LIE DETECTION UNTUK MASYARAKAT KELURAHAN DURI KEPA Umniy Salamah; Yuwan Jumaryadi; Diky Firdaus; Bagus Priambodo; Afifah Fitri Anggraini; Vivie Herlina; Ayaitulla Salsabilla Achmad; Putra Ardiansyah; Romeo Mulia Pratama; Zehandra Gibran Nugroho
Jurnal Pengabdian Masyarakat Nasional Vol. 6 No. 1 (2026)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/pemanas.v6i1.36927

Abstract

Diabetes Melitus Tipe 2 (DMT2) merupakan salah satu permasalahan kesehatan utama di wilayah perkotaan dan banyak dialami oleh kelompok usia produktif, termasuk masyarakat di Kelurahan Duri Kepa. Rendahnya pemahaman masyarakat, khususnya ibu-ibu PKK, mengenai deteksi dini diabetes menjadi latar belakang pelaksanaan kegiatan Pengabdian kepada Masyarakat (PkM) yang berfokus pada sosialisasi aplikasi pendeteksi risiko diabetes berbasis teknologi lie detection. Kegiatan yang dilaksanakan pada 10–31 Oktober 2025 ini meliputi tahap persiapan, pelaksanaan, evaluasi, dan tindak lanjut, dengan melibatkan partisipasi aktif masyarakat. Aplikasi yang diperkenalkan memanfaatkan analisis respons pengguna untuk mengidentifikasi potensi risiko diabetes dan memberikan kategori hasil berupa Tipe 1, Tipe 2, atau Tidak Terdeteksi. Hasil yang diberikan bukan merupakan diagnosis medis, tetapi indikator awal yang berfungsi sebagai pengingat agar masyarakat lebih memperhatikan pola makan, aktivitas fisik, dan gaya hidup sehat. Evaluasi kegiatan menunjukkan adanya peningkatan pengetahuan dan kesadaran masyarakat terhadap deteksi dini diabetes serta pemanfaatan teknologi informasi dalam bidang kesehatan. Program ini memberikan dampak positif dalam meningkatkan literasi kesehatan digital dan menunjukkan penerapan inovasi teknologi informasi untuk mendukung upaya pencegahan penyakit tidak menular di lingkungan masyarakat.
Perancangan Aplikasi Media Sosial TeiTei Diofavian Rafif Chairulsyah; Claudio Nehemia Panggabean; Aditya Dwi Wibowo; Umniy Salamah
FORMAT Vol 14 No 2 (2025)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/format.2025.v14.i2.003

Abstract

Digital transformation has driven the need for social media platforms that can provide simple, personal, and effective interactions. However, many existing applications tend to offer complex features that are less relevant to user needs. This research aims to design and develop TeiTei, a web-based social media application that emphasizes ease of use, convenience, and interactivity. This research includes identifying user needs, designing a user-friendly interface using the CSS Bootstrap framework, developing a PHP-based system with the Laravel framework, and managing the database using MySQL. In addition, a search algorithm was implemented to improve the efficiency of finding other users on the platform. The results of this research produced a web-based social media application prototype that can meet user needs through an intuitive interface design and relevant features. The implementation of search algorithms also adds value by expanding users' social networks. This research is expected to make a significant academic contribution to the development of social media applications, as well as serve as a reference for similar studies aimed at enhancing digital social interaction experiences.
Co-Authors Aditya Dwi Wibowo Afifah Fitri Anggraini Agustiawan Ahmad Ali Mutezar Aldi Rahman Andi Nugroho Andi Purnomo Andrean, Rifky Anita Ratnasari Anjar Hero Wilarto Arey Nur Warisman Arie Lystha Arrachman, Abdul Kholiq Athillah, Naufal Ayaitulla Salsabilla Achmad Ayumi, Vina Bagus Priambodo Bagus Priambodo Bagus Priambodo Bagus Priambodo Bryant Steven Aritonang Chairulsyah, Diofavian Rafif Claudio Nehemia Panggabean Desi Ramayanti Dheo Alpian Nanda Krisna Dianing Asri, Sri Diky Firdaus Diofavian Rafif Chairulsyah Eka Maulana Fajriah, Riri Fajrin Nur Utami Fani Putri Oktavia Fauzi Nur Iman Gusty Age Rusandy Hadiguna Setiawan Ida Farida Ida Farida Inge Handriani Inge Handriani Irene Ananda Iryani, Lemi Ivan Hardi Pratama Jumaryadi, Yuwan Kurnia Kito, Ramadani Mariana Purba Mariana Purba Maritza, Kaka Irsyad Noprisson, Handrie Nur Ani Nur Ani Panggabean, Claudio Nehemia Panwasto Samosir P Prasha, Achmad Ardani Purba, Mariana Putra Ardiansyah Putra, Erwin Dwika Richi Ramadhan Romeo Mulia Pratama Sambada, Arga Sarwati Rahayu Shabrio Cahyo Wardoyo Soemantri, Syauqi Adli Sulis Sandiwarno Suratno, Igo Prayoga Syifa Fauziah Vera Yunita Vina Ayumi Vina Ayumi Vincentius Krisna Aditya Vivie Herlina Warisman, Arey Nur Wibowo, Aditya Dwi Zamzami, Muhammad Aryaka Zehandra Gibran Nugroho