Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JURNAL REKAYASA TEKNOLOGI INFORMASI PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat Jurnal Teknik Informatika (JUTIF) Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen
Maura Widyaningsih, Maura
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Engineering Law, Crime, Criminology & Criminal Justice Public Health Social Sciences

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Identifikasi Kematangan Buah Apel Dengan Gray Level Co-Occurrence Matrix (GLCM) Widyaningsih, Maura
Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen Vol 6 No 1 (2016): Maret 2016
Publisher : STMIK Palangkaraya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1584.457 KB) | DOI: 10.33020/saintekom.v6i1.7

Abstract

Digital image processing is part of the technological developments in the concepts and reasoning, the human wants the machine (computer) can recognize images like human vision. Recognizing the image is one way to distinguish the traits that exist in the image. Texture is one of the characteristics that distinguish the image, is the basic characteristic of the image identification. Gray Level Co-Occurrence Matrix (GLCM) is one method of obtaining characteristic texture image by calculating the probability of adjacency relationship between two pixels at a certain distance and direction. The characteristics of texture obtained from GLCM methods include contrast, correlation, homogeneity, and energy. The extracted features are then used for identification with the nearest distance calculations (Eucledian Distance). The final results analysis program to identify the category of apples raw, half-ripe or overripe. Training data used are 12 images apple, consisting of 4 is crude, 4 is half-cooked, and 4 is ripe, 7 data used for testing. Testing GLCM with 00 angle feature extraction results of the test images can be recognized by a factor Eucledian Distance to the query image. Identification of test data is information all the data can be recognized. Eucledian Distance is a method that helps the introduction of a test object data.
Dempster Shafer Untuk Sistem Diagnosa Gejala Penyakit Kulit Pada Kucing Widyaningsih, Maura; Gunadi, Rio
Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen Vol 7 No 1 (2017): March 2017
Publisher : STMIK Palangkaraya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1237.787 KB) | DOI: 10.33020/saintekom.v7i1.24

Abstract

Expert System which is a branch of Artifical Intelligence, who learned about the estimation or decision-making ability of an expert. Methods and concepts are still needed in solving the problem of diagnosis, with engineering calculations involve computing systems., given the level of need for information and resolving cases. The application development is aimed at implementing the knowledge of an expert into a program that can help in diagnosing the symptoms of skin health problems in cats. Dempster Shafer (DS) is a method that is non monotonous in solving the problem of uncertainty due to the addition or subtraction of new facts.The system is made to diagnose the type of skin disease in cats after applying the method of DS. The system can also perform data management if there is a data change disease, symptoms, treatment solutions, as well as the rules of the disease. The diagnosis system with DS according to analysis from experts.
Optimalisasi Kinerja Pembelajaran Guru SMKN dengan Pendekatan Partisipatif melalui Integrasi ChatGPT dari OpenAI: Optimizing SMKN Teacher Learning Performance with a Participatory Approach through ChatGPT Integration from OpenAI Widyaningsih, Maura; Pratama, Bayu; Herkules, Herkules; Hendartie, Susi
PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat Vol. 10 No. 3 (2025): PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat
Publisher : Institute for Research and Community Services Universitas Muhammadiyah Palangkaraya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33084/pengabdianmu.v10i3.7796

Abstract

The mastery of constantly evolving technology is a difficult challenge for teachers at SMK Negeri 2 Palangka Raya. To overcome this, self-development through training is necessary, such as using ChatGPT to make learning more effective. ChatGPT helps find educational resources with clear commands and supports the preparation of study plans, performance objectives, and task completion. This training was held at the Digital Marketing Laboratory of SMK Negeri 2 Palangka Raya and included preparation, implementation, and evaluation. Initial evaluation showed that 65% of participants did not know about ChatGPT, 15% were somewhat knowledgeable, and 20% were knowledgeable. After the training, understanding significantly increased, with the average correct answers rising from 52% to 85%. Recommendations for sustainability include focusing on difficult material, evaluating and revising training materials, and using interactive teaching methods. Implementation of interactive teaching through approaches such as group discussions, simulations, and case studies as well as direct practice.
Predicting Anxiety of STMIK Palangkaraya Students Using K-Means Clustering and Gaussian Naïve Bayes Widyaningsih, Maura; Rosmiati, Rosmiati; Prakoso, Paholo Iman
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 1 (2026): JUTIF Volume 7, Number 1, February 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.1.5259

Abstract

Academic anxiety is a common psychological problem experienced by students, especially before final exams, which impacts learning performance and mental well-being. This study aims to identify and predict students' anxiety levels using a Machine Learning approach, specifically the web framework Gradio, through a combination of the K-Means Clustering and Gaussian Naïve Bayes (GNB) methods. The research instrument used a Google Form-based questionnaire modified from the Zung Self-Rating Anxiety Scale (ZSAS) with 20 items (K1–K20) on a Likert scale (0–3). Data were obtained from 110 students of the Information Systems and Informatics Engineering Study Program at STMIK Palangkaraya. The research process consisted of five main stages: pre-processing, clustering using the K-Means algorithm, training the GNB classification model, evaluation, and prediction of new data. The clustering results categorized the data into three levels of anxiety: Low, Median, and High. The GNB model showed 95% accuracy with a balanced distribution of evaluation metrics (precision, recall, and F1 score). Comparison with other algorithms shows that while SVM achieved the highest accuracy (100%), GNB was more balanced in handling uneven class distributions and more practical for implementation in web-based systems. This prediction system has the potential to be used as an early detection tool for student anxiety, while also supporting educational institutions in designing more targeted psychological interventions. Further improvements can be made by expanding the scope of respondents, balancing the data distribution, and testing other machine learning methods to improve model generalization. The program and data are available at: https://github.com/maurawidya75/StudentAnxiety2025.
Multi-Class Semantic Segmentation of Oil Palm Areas Using a VGG-19 U-Net Improvement Widyaningsih, Maura; Priyambodo, Tri Kuntoro; Wibowo, Moh Edi; Kamal, Muhammad
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 1 (2026): February 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i1.7062

Abstract

UAV imagery-based semantic segmentation is crucial for mapping tropical agricultural areas such as oil palm plantations. The main challenges are overlapping vegetation objects, unclear boundaries, and spectral similarities between classes, which reduce the accuracy of conventional models. This study proposes a modified U-Net architecture with a VGG-19 backbone, achieved through hyperparameter tuning (M7) and the integration of residual blocks (M8), to enhance multi-class segmentation performance. Experiments were conducted on aerial imagery with two resolutions (512×512 and 256×256) using four-class and three-class scenarios. The results show that M7 and M8 consistently outperform the baseline model (M2) in terms of accuracy, precision, recall, and average Intersection over Union (IoU). In the 512x512 four-class scenario, M8 achieved the highest accuracy (87.40%), precision (88.32%), recall (86.32%), and MIoU (0.132). M7 reached similar accuracy (>86%) but trained significantly faster than the baseline. In the 256x256 scenario, M8 maintained strong performance with 86.44% accuracy and 0.302 MIoU. For the three-class experiment, M8 reached a top MIoU of 0.178. Accuracy, precision, and recall were all above 87%, showing improved recognition of minority classes such as waterways. Confusion matrix analysis confirmed that M8 provided more balanced class predictions. It also reduced false negatives for oil palm vegetation. M7 showed slight fluctuations, suggesting possible overfitting. These findings support M8 as a robust solution for UAV-based oil palm mapping and large-scale monitoring.
Penerapan Arsitektur CNN EfficientNet-B1 Untuk Klasifikasi Tanaman Hias Tropis Yadi, Muhammad Fathul; Widyaningsih, Maura; Rusdiana, Lili
Jurnal Rekayasa Teknologi Informasi (JURTI) Vol 10, No 1 (2026): Jurnal Rekayasa Teknologi Informasi (JURTI)
Publisher : Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/jurti.v10i1.22884

Abstract

Penelitian ini bertujuan mengembangkan metode klasifikasi tanaman hias tropis Indonesia menggunakan Jaringan Saraf Tiruan Konvolusional (CNN) dengan arsitektur EfficientNet-B1 berbasis pembelajaran transfer. Indonesia memiliki keanekaragaman tanaman hias yang tinggi, namun identifikasi spesies masih menjadi tantangan karena kemiripan morfologi antar jenis. Untuk mengatasi hal ini, penelitian menerapkan tahapan prapemrosesan data, pelatihan model, dan pengujian menggunakan dataset dari Kaggle, yang dibagi dalam tujuh skenario evaluasi. Parameter kinerja yang digunakan meliputi akurasi, presisi, recall, dan skor F1. Hasil pengujian menunjukkan bahwa model EfficientNet-B1 yang telah dilatih sebelumnya masih mengalami kesulitan dalam membedakan beberapa kelas tanaman hias tropis dari objek non-tanaman. Namun, skenario 1 menghasilkan performa terbaik dengan akurasi 98% dan skor F1 sebesar 97,92%, serta keseimbangan antara presisi dan recall yang optimal.Analisis menunjukkan bahwa keberhasilan model sangat dipengaruhi oleh kualitas dan keseimbangan dataset, serta proses penyetelan hiperparameter yang tepat. Oleh karena itu, penelitian ini merekomendasikan optimasi lanjutan melalui teknik augmentasi data untuk menambah variasi citra, penyeimbangan kelas, dan penyesuaian parameter pelatihan agar model mampu mengenali lebih baik berbagai spesies tanaman hias tropis. Dengan peningkatan tersebut, metode ini berpotensi diterapkan dalam sistem identifikasi otomatis tanaman hias yang dapat membantu bidang hortikultura, konservasi, dan perdagangan tanaman tropis di Indonesia.
Co-Authors Bayu Pratama, Bayu Gunadi, Rio Gunadi, Rio Herkules Herkules, Herkules Lili Rusdiana, Lili Muhammad Kamal Prakoso, Paholo Iman Rosmiati Rosmiati Susi Hendartie Tri Kuntoro Priyambodo Wibowo, Moh Edi Yadi, Muhammad Fathul