Article Per Year (5 Year)
p-Index From 2021 - 2026
3.439
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Sains dan Teknologi Jurnal Teknologi Proceedings Konferensi Nasional Sistem dan Informatika (KNS&I) ELINVO (Electronics, Informatics, and Vocational Education) JOIV : International Journal on Informatics Visualization Sinkron : Jurnal dan Penelitian Teknik Informatika Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Creative Information Technology Journal Jurnal Eksplora Informatika Jurnal Pengabdian Masyarakat AbdiMas JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Jurnal FATEKSA : Jurnal Teknologi dan Rekayasa JTIULM (Jurnal Teknologi Informasi Universitas Lambung Mangkurat) Journal of Electrical Engineering and Computer (JEECOM) KLIK: Kajian Ilmiah Informatika dan Komputer Bridge: Jurnal Publikasi Sistem Informasi dan Telekomunikasi Jurnal ilmiah teknologi informasi Asia Jurnal Sistem Informasi Komputer dan Teknologi Informasi
TONNY HIDAYAT
Universitas AMIKOM Yogyakarta
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Mechanical Engineering

Published : 28 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 28 Documents
Search

 1   2   3 
OPTIMIZATION OF SOFTWARE DEFECT PREDICTION USING CNN AND ADABOOST: ANALYSIS AND EVALUATION Basit, Muhammad Abdul; Setyanto, Arief; Hidayat, Tonny
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 3 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i3.6405

Abstract

This study focuses on enhancing software defect prediction (SDP) by integrating Convolutional Neural Networks (CNN) with the AdaBoost algorithm. The PROMISE dataset was employed in this research, and data balancing was achieved using the SMOTE Tomek technique. With the help of AdaBoost, we were able to increase the prediction accuracy after building a complex CNN model to extract features from the da-taset. The AdaBoost model's hyperparameters were fine-tuned using GridSearch to find the best values for enhanced model performance. For the studies, we used StandardScaler to normalize the data after splitting it into training and testing groups with an 80:20 ratio. The ex-perimental results show that compared to the baseline method, SDP's accuracy is significantly improved when CNN, AdaBoost, and GridSearch hyperparameter tweaking are used together. Accuracy, pre-cision, recall, F1 score, MCC, and AUC were some of the measures used to assess the model's performance.
IMPROVING RESNET-50 PERFORMANCE FOR CHICKEN DISEASE CLASSIFICATION BASED ON DUNG IMAGES Andalantama, Yudikha; Hidayat, Tonny; Purwanto, Agus
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 3 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i3.6490

Abstract

This study examines the application of the ResNet-50 model for categorizing chicken illnesses. The dataset utilized comprises 8,876 samples, which are classified into four main categories: healthy feces, Salmonella, Coccidiosis, and Newcastle disease. The dataset consists of 2,057 samples classified as healthy feces, 2,276 samples classified as Salmonella, 2,103 samples classified as Coc-cidiosis, and 2,440 samples classified as Newcastle disease. The implementation of the ResNet-50 model for analysis showcases outstanding performance, with a classification accuracy of 99.25%. This result affirms the model's exceptional ability to precisely identify poultry illnesses. The results of this study highlight the effectiveness of ResNet-50 in performing complex classification tasks and also provide a basis for future improvements. Considering the exceptional results, there are other aspects that can be improved upon to attain optimal performance. By integrating modern hyperparameter tuning approaches and incorporating diverse supplementary data, the model's generalization is expected to be improved, leading to higher accuracy in many real-world settings. Moreover, this will expand the practical applications of the approach in the veterinary and poultry sectors. This study greatly contributes to the diagnosis of diseases in poultry, relying on the findings obtained. It enables the potential for further progress that can improve the effectiveness of disease detection and prevention.
Human Facial Pattern Shape Classification Using a Retraining Strategy and Convolutional Neural Network Architecture Hidayat, Tonny; Istiqomah, Dewi Anisa; Arifianto, Teguh
JOIV : International Journal on Informatics Visualization Vol 9, No 5 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.5.3471

Abstract

Many shapes and patterns on the human body might be considered a person's uniqueness or feature since they differ significantly from one another, one of which is the shape of the face. In computer vision, the shape of a face is divided into five fundamental shapes. The experiment in this paper provides a model based on the final layer of the results of retraining InceptionV3, a Convolutional Neural Network (CNN) architecture for classifying human face photos. Inspired by human neural networks, this method generally works well for face recognition and computer vision research. This research begins with the stages of data acquisition, data exploration, classification, and evaluation. Retraining is performed to improve accuracy using the distance and angle of facial landmarks. The results are compared to other classification methods, including linear discriminant analysis (LDA), support vector machine with a linear kernel (SVM-LIN), support vector machine with a radial basis function kernel (SVM-RBF), artificial neural networks or multilayer perceptrons (MLP), and k-nearest neighbors. The facial dataset used consists of 747 photos, divided into five categories: oval, round, square, heart, and oblong. The Canny edge detector approach is utilized to enhance CNN accuracy, which has been effectively improved through training and testing. The maximum accuracy achieved was 91.7% based on training and testing at 85%-98%. This demonstrates that the outcomes of inceptionV3 retraining may appropriately adapt training data and outperform alternative classification techniques without the need to specify the function of certain features during the model training process.
Klasifikasi Tingkat Kematangan Tandan Buah Segar Kelapa Sawit Menggunakan Pendekatan Deep Learning Zulkarnain, Jefri; Kusrini; Hidayat, Tonny
JST (Jurnal Sains dan Teknologi) Vol. 12 No. 3 (2023): Oktober
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/jstundiksha.v12i3.59140

Abstract

Menilai kematangan Tandan Buah Segar (TBS) kelapa sawit sangat kompleks, kematangan TBS dilihat berdasarkan jumlah atau persentase dari buah yang terlepas dari TBS serta berdasarkan perubahan warna kulit luar TBS, dalam melakukan klasifikasi tingkat kematangan rentan terjadi kesalahan penilaian oleh manusia, kesalahan klasifikasi dapat terjadi oleh berbagai faktor. Untuk membantu kesalahan dalam klasifikasi, Deep learning diusulkan dalam melakukan mengklasifikasi tingkat kematangan. Tujuan dalam penelitian ini adalah menganalisis klasifikasi menggunakan Deep learning untuk memprediksi tingkat kematangan TBS kelapa sawit. Dalam penelitian ini diusulkan Deep learning dengan model ResNet50 untuk melakukan klasifikasi pada empat tingkat kematangan TBS: mentah, kurang matang, matang, dan terlalu matang. Penelitian ini akan melakukan eksperimen berdasarkan empat alokasi data, dua optimizer, dan enam learning rate serta melakukan augmentasi data. Penelitian menunjukan experimen model yang diusulkan menghasilkan kondisi terbaik alokasi data 90/10, optimizer adam, dan learning rate 0.0001 dengan precision 96%, recall 98%, F1 score 97%, dan accuracy 97%. Kesimpulan dari hasil penelitian model yang diusulkan berhasil mencapai akurasi 97%, namun demikian dalam melakukan klasifikasi tingkat kematangan membutuh data latih dengan ukuran besar untuk mendapatkan hasil kalsifikasi yang baik serta memperhatikan dataset dan metode yang digunakan.
Analisis Clustering Pegawai Berdasarkan Tingkat Kedisiplinan Menggunakan Algoritma K-Means dan Davies-Bouldin Index Alfian, Wahyu; -, Kusrini; Hidayat, Tonny
Journal of Electrical Engineering and Computer (JEECOM) Vol 6, No 2 (2024)
Publisher : Universitas Nurul Jadid

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33650/jeecom.v6i2.9556

Abstract

Fenomena kedisiplinan pegawai dalam organisasi menjadi salah satu aspek penting yang mempengaruhi efisiensi dan efektivitas operasional. Dalam konteks rumah sakit kedisiplinan pegawai tidak hanya berdampak pada kelancaran operasional tetapi juga berhubungan langsung dengan kualitas pelayanan. Namun, pengukuran dan penentuan tingkat kedisiplinan pegawai seringkali menjadi tantangan tersendiri. Metode tradisional seperti penilaian manual cenderung subjektif dan tidak konsisten. Oleh karena itu, diperlukan metode yang lebih objektif dan terstruktur untuk mengelompokkan pegawai berdasarkan tingkat kedisiplinan mereka. Data yang digunakan mencakup berbagai aspek seperti kepribadian, keterampilan teknis, kemampuan menyelesaikan tugas, dan hubungan kerja, yang dikumpulkan melalui aplikasi SIPEKA. Algoritma K-Means diterapkan untuk mengelompokkan pegawai ke dalam empat cluster, yaitu: dari 4788 data pegawai dari januari 2024 sampai juli didapatkan 1995 di dalam Cluster 1 yang berstatus sangat baik, 1936 di dalam Cluster 2 yang berstatus baik, 842 dalam Cluster 3 yang berstatus Cukup baik dan 15 dalam Cluster 4 yang berstatus kurang baik. Evaluasi Cluster dilakukan dengan menggunakan Davies-Bouldin Index (DBI) untuk mengukur validitas dan kepaduan cluster yang terbentuk. Hasil penelitian menunjukkan bahwa penentuan jumlah cluster (k=4) dan titik pusat (centroid) awal sangat berpengaruh terhadap hasil akhir Clusterisasi. Nilai DBI yang diperoleh sebesar 1.89 mengindikasikan bahwa nilai tersebut menandakan bahwa ada beberapa tingkat overlap atau ketidaksempurnaan dalam pemisahan cluster, meskipun nilai ini tidak terlalu buruk. Namun, tidak bisa disebut hasil clustering yang optimal, karena nilai yang ideal seharusnya mendekati 0.Fenomena kedisiplinan pegawai dalam organisasi menjadi salah satu aspek penting yang mempengaruhi efisiensi dan efektivitas operasional. Dalam konteks rumah sakit kedisiplinan pegawai tidak hanya berdampak pada kelancaran operasional tetapi juga berhubungan langsung dengan kualitas pelayanan. Namun, pengukuran dan penentuan tingkat kedisiplinan pegawai seringkali menjadi tantangan tersendiri. Metode tradisional seperti penilaian manual cenderung subjektif dan tidak konsisten. Oleh karena itu, diperlukan metode yang lebih objektif dan terstruktur untuk mengelompokkan pegawai berdasarkan tingkat kedisiplinan mereka. Data yang digunakan mencakup berbagai aspek seperti kepribadian, keterampilan teknis, kemampuan menyelesaikan tugas, dan hubungan kerja, yang dikumpulkan melalui aplikasi SIPEKA. Algoritma K-Means diterapkan untuk mengelompokkan pegawai ke dalam empat cluster, yaitu: dari 4788 data pegawai dari januari 2024 sampai juli didapatkan 1995 di dalam Cluster 1 yang berstatus sangat baik, 1936 di dalam Cluster 2 yang berstatus baik, 842 dalam Cluster 3 yang berstatus Cukup baik dan 15 dalam Cluster 4 yang berstatus kurang baik. Evaluasi Cluster dilakukan dengan menggunakan Davies-Bouldin Index (DBI) untuk mengukur validitas dan kepaduan cluster yang terbentuk. Hasil penelitian menunjukkan bahwa penentuan jumlah cluster (k=4) dan titik pusat (centroid) awal sangat berpengaruh terhadap hasil akhir Clusterisasi. Nilai DBI yang diperoleh sebesar 1.89 mengindikasikan bahwa nilai tersebut menandakan bahwa ada beberapa tingkat overlap atau ketidaksempurnaan dalam pemisahan cluster, meskipun nilai ini tidak terlalu buruk. Namun, tidak bisa disebut hasil clustering yang optimal, karena nilai yang ideal seharusnya mendekati 0.
User Interface Yang Adaptif Pada Kernwerk Mobile App Berbasis Ekstensi Modular UEQ+ Alif Syaiful Huda; Alva Hendi Muhammad; Tonny Hidayat
Bridge : Jurnal Publikasi Sistem Informasi dan Telekomunikasi Vol. 2 No. 2 (2024): Bridge: Jurnal Publikasi Sistem Informasi dan Telekomunikasi
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/bridge.v2i2.44

Abstract

The diversity in societal exercise preferences has increased significantly, with fitness emerging as a favored modern activity, particularly in urban areas of Indonesia. Fitness is valued for its effectiveness in restoring body fitness and achieving ideal body shapes swiftly. However, in the era of Industry 4.0, technological advancements have revolutionized the approach to fitness. Smartphone fitness applications have replaced the role of personal trainers by providing tailored exercise and dietary programs. User Interface (UI) plays a pivotal role in fitness applications, influencing User Experience (UX). The challenge lies in designing UI to accommodate user heterogeneity, both internally and externally. Adaptive UI emerges as a solution, capable of altering layout and content according to user characteristics. Kernwerk® Functional Fitness exemplifies a fitness application utilizing AI to optimize fitness routines. To enhance Kernwerk's UI adaptability, UX evaluation is conducted using UEQ+ modular extension, a comprehensive instrument for effectively and efficiently measuring user experience. Through this evaluation, components of UI and UX requiring further development to enhance Kernwerk's adaptability can be identified.
Grouping of Image Patterns Using Inceptionv3 For Face Shape Classification Hidayat, Tonny; Astuti, Ika Asti; Yaqin, Ainul; Tjilen, Alexander Phuk; Arifianto, Teguh
JOIV : International Journal on Informatics Visualization Vol 7, No 4 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.7.4.1743

Abstract

The human face is an extraordinary part where nearly everybody is not quite the same as each other. One perspective that should be visible plainly is the shape. Face shape grouping can be used for amusement, security, or excellence. One technique that can be utilized in picture grouping is the InceptionV3 model. InceptionV3 is the structure of the Convolutional Neural Network (CNN) created by Google, which can tackle picture examination and item discovery issues. This engineering is utilized to order face shapes into five classes: Round, Heart, Square, Oblong, and Oval. At that point, the Google Pictures dataset goes through the pre-handling stage, and the Shrewd Edge Identifier is applied to each picture. Hair turns into a commotion. Consider recognizing the side of the face because it does not make any difference what the hairdo resembles. What is important is the side of the face. When there is a dataset of elongated class and heart class with a comparable hairdo, InceptionV3 will identify the component and expect the two pieces of information to come from a similar class. The exchange learning strategy is done in preparation for the last Layer of ImageNet's InceptionV3 model. This strategy puts the high precision level with an exactness of 93% preparation and testing between 88% - 98%. InceptionV3 could arrange upwards of 692 from 747 datasets or around 92.65%. The most reduced information class is the heart class, where out of 150 information, InceptionV3 can characterize upwards of 130 information.
Classification of Mental Disorders Using Modified Balanced Random Forest And Feature Selection Arsad; Alva Hendi Muhammad; Tonny Hidayat
Jurnal Teknologi Informasi Universitas Lambung Mangkurat (JTIULM) Vol. 9 No. 2 (2024)
Publisher : Fakultas Teknik Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/jtiulm.v9i2.320

Abstract

This study employs the Modified Balanced Random Forest (MBRF) algorithm and Correlation-based Feature Selector (CfsSubsetEval) for mental disorder classification. The "Mental Disorder Classification" dataset from Kaggle was used with the aim of improving accuracy, evaluating feature selection, and assessing MBRF's performance in handling data imbalance. The study compares the performance of Random Forest (RF) and MBRF, and examines the impact of feature selection using CFS on mental disorder classification. The results indicate that MBRF outperforms RF with an 8.33% improvement in accuracy, 8.61% in precision, 8.33% in recall, and 9.08% in F1-Score. Additionally, the comparison between MBRF and MBRF with CFS reveals that while accuracy and recall remain the same, MBRF achieves 0.23% higher precision and 0.81% higher F1-Score than MBRF with CFS. In conclusion, the use of MBRF proves to be superior to the standard RF in addressing data imbalance for mental disorder classification, significantly improving accuracy, precision, recall, and F1-Score. However, feature selection with CFS does not significantly enhance performance. While accuracy and recall remain unchanged, MBRF without CFS demonstrates higher precision and F1-Score, indicating that the model performs better without feature selection in maintaining the balance between precision and recall.
Co-Authors AGUS PURWANTO Agustina, Nova Ainul Yaqin Alexander Phuk Tjilen Alfian, Wahyu Ali Mustopa, Ali Alif Syaiful Huda Alva Hendi Muhammad Alva Hendi Muhammad Andalantama, Yudikha Andi Sunyoto Arief Setyanto Aris Harwanto Arsad Basit, Muhammad Abdul Bentar Candra P Dewi Anisa Istiqomah Ema Utami Ema Utami Firza Septian Ika Asti Astuti Ika Asti Astuti Ilmawati, Fahma Inti Jeki Kuswanto JOKO DWI SANTOSO Kurniawan , Hendra KUSRINI Kusrini , Kusrini Kusrini Kusrini Kusrini Kusrini Kusrini Kusrini Kusrini, Kusrini Liana Trihardianingsih M. Ilham Arief Madhika, Yudha Randa Maie Istighosah Mawene, Brenstein Mohammad Rezza Pahlevi Muhammad Anwar Fauzi Mulyatun, Sri Mustopa , Ali Risna Sari Safril, Martinus Seniwati, Erni Setiawanto, Irwan TEGUH ARIFIANTO, TEGUH Theofanis Orphanoudakis Tutut Dwi Prihatin Zulkarnain, Jefri