Article Per Year (5 Year)
p-Index From 2020 - 2025
2.149
P-Index
This Author published in this journals
All Journal Prosiding SNATIF Infotech Journal Sistemasi: Jurnal Sistem Informasi Sinkron : Jurnal dan Penelitian Teknik Informatika JURNAL ILMIAH MATEMATIKA DAN TERAPAN Jiko (Jurnal Informatika dan komputer) JURIKOM (Jurnal Riset Komputer) Jurnal Informatika dan Rekayasa Elektronik JATI (Jurnal Mahasiswa Teknik Informatika) Jurnal Informatika dan Teknologi Komputer ( J-ICOM) Journal La Multiapp Jurnal Locus Penelitian dan Pengabdian Jurnal Informatika Polinema (JIP)
Gunawan Abdillah, Gunawan
Unknown Affiliation
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Library & Information Science Mathematics

Published : 17 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 17 Documents
Search

 1   2 
Enhanching Prophet Time Series Forecasting on Sparse Data via Hyperparameter Optimizattion: A Case Study in Retail Atamimi, Fadel Muhamad Hafid; Wintanti, Wina; Abdillah, Gunawan
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 2 (2025): Research Articles April 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i2.14804

Abstract

In today’s competitive business landscape, accurate sales forecasting is crucial for retailers to optimize inventory, prevent overstock, and support strategic decision-making. However, many small to medium enterprises operate with sparse and irregular sales data, making conventional forecasting methods less effective. This study aims to evaluate the performance of the Prophet time series model in such non-ideal conditions and to investigate how hyperparameter tuning affects its forecasting accuracy. The research adopts the Prophet algorithm, an additive time series forecasting model developed by Facebook, which incorporates trend, seasonality, and holiday components. The model was implemented in two configurations: one using default parameters, and another with manually tuned hyperparameters, including changepoint prior scale (CP), seasonality prior scale (SP), and seasonality mode. A total of 32 experiments were conducted using historical transaction data from PT Eko Hejo. Results show that the default Prophet model achieved a MAPE of 9.50%, while the best-performing configuration (CP = 0.5, SP = 0.01, additive mode) reduced the MAPE to 6.80%. This indicates that hyperparameter tuning significantly improves forecast accuracy, even in sparse data environments. The study contributes both practically and scientifically by demonstrating that Prophet, when properly configured, is a robust and adaptable tool for business forecasting with limited data. It also highlights the value of manual tuning in enhancing model responsiveness and generalization, offering insights for further research in model comparison, automated optimization, and hybrid forecasting approaches.
Implementasi Metode Recurrent Neural Network Untuk Prediksi Kejang Pada Penderita Epilepsi Berdasarkan Data Electroenephalogram Febiyane, Raisya; Chrisnanto, Yulison Harry; Abdillah, Gunawan
JURIKOM (Jurnal Riset Komputer) Vol 12, No 3 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i3.8656

Abstract

Epilepsy is a chronic neurological disorder that causes patients to experience recurrent seizures. Seizures are one of the main symptoms of epilepsy, requiring medical treatment and close monitoring. A major challenge in epilepsy management is the difficulty in predicting when seizures will occur. Electroencephalogram (EEG) can detect seizures as it contains physiological information about brain neural activity. This study aims to predict seizures using a Recurrent Neural Network (RNN) method based on EEG data. Deep Learning is a branch of Machine Learning that uses artificial neural networks to solve problems involving large datasets. The data used in this research is the Epileptic Seizure Recognition dataset obtained from Kaggle. It consists of patient ID attributes, 178 numerical attributes representing EEG signals, and a label y indicating conditions during the recording, including eyes open, eyes closed, healthy brain, tumor location, and seizure activity. The deep learning model tested is a Recurrent Neural Network (RNN) designed to learn patterns in the data. Performance evaluation was conducted using metrics including accuracy, precision, recall, and F1-Score. Based on the application of the RNN method and testing using EEG data, the best condition was achieved with a three-layer Long Short-Term Memory architecture and optimal training parameters, resulting in a seizure prediction accuracy of 98.6%. This result demonstrates that the model is capable of effectively and efficiently predicting the likelihood of seizure occurrences.
Analisis Sentimen Komunitas Counter-Strike 2 (CS2) Menggunakan Support Vector Machine (SVM) Riyadi, Saiful Faris; Chrisnanto, Yulison Herry; Abdillah, Gunawan
JURIKOM (Jurnal Riset Komputer) Vol 12, No 3 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i3.8620

Abstract

Counter-Strike 2 (CS2) is a game that has received a lot of enthusiasm from the gaming community since its release. User reviews on the Steam platform are the main source for understanding community sentiment towards this game. This study aims to analyze sentiment towards CS2 reviews using the Support Vector Machine (SVM) method. Data was collected through the Apify platform, then cleaned through processes such as tokenization, stopword removal, and lemmatization. Text features were converted into numerical values using Term Frequency-Inverse Document Frequency (TF-IDF) to be used in the SVM model. The SVM model was used to classify review sentiment into three categories: positive, neutral, and negative. Evaluation was conducted by measuring accuracy, confusion matrix, and classification reports. In the evaluation results, the SVM model using the One-vs-Rest (OVR) approach showed that the model without SMOTE produced an accuracy of 81.95%. After applying the Synthetic Minority Over-sampling (SMOTE) technique to the training data to balance the distribution between classes, the model accuracy increased slightly to 82.18%. This study provides valuable insights for game developers in understanding players' opinions about CS2. Additionally, this study demonstrates the potential of SVM in text-based sentiment analysis on user review platforms.
Klasterisasi Data Penjualan Toko Perak J-Maskus Mengguanakan Algoritma HDBSCAN Rusmana, Hendri Diana; Witanti, Wina; Abdillah, Gunawan
Jurnal Locus Penelitian dan Pengabdian Vol. 4 No. 8 (2025): JURNAL LOCUS: Penelitian dan Pengabdian
Publisher : Riviera Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58344/locus.v4i7.4162

Abstract

Di era digital, analisis data penjualan menjadi kunci pengambilan keputusan bisnis. Toko Perak J-Maskus menghadapi tantangan dalam mengelola stok akibat ketidakseimbangan persediaan dan permintaan. Penelitian ini mengelompokkan produk berdasarkan pola penjualan menggunakan algoritma HDBSCAN, yang dipilih karena kemampuannya mengidentifikasi cluster dengan kepadatan bervariasi dan mendeteksi outlier. Dataset terdiri dari 5.765 transaksi (2022–2024) dengan atribut produk dan jumlah terjual. Hasil eksperimen menunjukkan parameter optimal min_samples=5 dan min_cluster_size=5 dengan silhouette score 0.6507 (struktur menengah), menghasilkan 206 cluster. Visualisasi t-SNE mengonfirmasi distribusi cluster yang terpisah jelas. Temuan ini dapat digunakan untuk strategi manajemen stok, seperti identifikasi produk laris dan pengurangan overstock.
Klasterisasi Akademik Prestasi Siswa Di Mts Nurul Hidayah Menggunakan Algoritma K-Means Firdaus, Muhammad Fauzi; Abdillah, Gunawan; Ramadhan, Edvin
Jurnal Locus Penelitian dan Pengabdian Vol. 4 No. 8 (2025): JURNAL LOCUS: Penelitian dan Pengabdian
Publisher : Riviera Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58344/locus.v4i8.4233

Abstract

Di dunia pendidikan seringkali terjadi permasalahan bagaimana cara menentukan tingkat prestasi murid dengan kategori rendah, cukup, dan tinggi serta menemukan top rank murid unggulan dalam kelas. Dalam hal ini data miningdengan pendekatan K-Means Clustering dapat digunakan untuk mengelompokkan data menjadi kumpulan data. Dalam sistem analisis, pendekatan data miningberdasarkan algoritma K-Means dapat digunakan untuk pengelompokan prestasi murid. Dalam penelitian ini data nilai siswa kelas VII-IX MTs Nurul Hidayah tahun 2021-2024, dari semester ganjil sampai genap dikelompokkan berdasar nilai rapor. Clustering digunakan dalam pembangunan program analitik ini untuk menilai dampak data murid terhadap kecenderungan keberhasilan murid di setiap kelompok yang dapat dibuktikan dengan kelulusan murid yang menduduki top rank serta dari hasil wawancara guru pengajar maupun wali kelas serta data nilai yang diperoleh dari Dapodik. Hasil dari penelitian ini membuktikan bahwa teknik clustering K-Means dapat dimanfaatkan oleh pengajar untuk mengkategorikan murid berdasarkan nilai mata pelajaran dan absensi, serta menggunakannya untuk menganalisis prestasi murid dengan mengelompokkan dari kategori prestasi rendah, rata-rata, dan tinggi. Dengan adanya sistem clastering ini, pihak sekolah dapat dengan lebih mudah mengidentifikasi siswa yang memerlukan bimbingan tambahan serta mengembangkan strategi pembelajaran yang lebih tepat sasaran.
Comparison of AlexNet and ResNet50 Model Performance in Classifying Images of Indonesian Traditional Food Kurniawan, Muhammad Randy; Christanto, Yulison Herry; Abdillah, Gunawan
Journal La Multiapp Vol. 6 No. 4 (2025): Journal La Multiapp
Publisher : Newinera Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37899/journallamultiapp.v6i4.2269

Abstract

Image classification using deep learning has become an effective approach in various fields, including visual object recognition such as food identification. This study aims to compare the performance of two well-known Convolutional Neural Network (CNN) architectures, AlexNet and ResNet50, in classifying traditional Indonesian food images. The dataset used in this research is a combination of two sources: a traditional Indonesian cake dataset from Kaggle and an additional set of images of Cirebon's traditional dishes. The final dataset consists of 24 food categories with more than 4,000 images in total. Each image was preprocessed through several steps including resizing to 224x224 pixels, applying data augmentation to training samples to enhance variation, and normalization based on standard input formats of the models. The training process was carried out using the 5-Fold Cross Validation method, while performance was evaluated using accuracy, precision, recall, and F1-score metrics. Experimental results show that ResNet50 consistently outperformed AlexNet across all evaluation metrics. ResNet50 achieved an average accuracy of 92%, compared to 86% obtained by AlexNet. Additionally, ResNet50 demonstrated superior performance in terms of precision, recall, and F1-score. This difference indicates that deeper and more complex architectures like ResNet50 are more effective in learning visual patterns in diverse traditional food images. The study concludes that ResNet50 is a more optimal choice for the task of traditional Indonesian food image classification. These findings serve as a basis for future development of image-based food recognition systems and support the preservation of culinary heritage through artificial intelligence technology.
Klasifikasi Diagnosa Penyakit Tiroid Menggunakan Metode Random Forest Darmawan, Raja; Chrisnanto, Yulison Herry; Abdillah, Gunawan
Jurnal Informatika dan Teknologi Komputer (J-ICOM) Vol 6 No 2 (2025): Jurnal Informatika dan Teknologi Komputer ( J-ICOM)
Publisher : E-Jurnal Universitas Samudra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55377/j-icom.v6i2.10356

Abstract

The thyroid is a vital gland in the human neck, regulating metabolism through its hormones. Hormonal disorders in the thyroid can significantly affect health. Data mining techniques, such as the random forest algorithm, are used to analyze thyroid disease data. Previous research has used methods such as Decision Tree and Support Vector Machine with high accuracy results. This study aims to apply the random forest method in the classification of thyroid disease diagnoses. Research questions include factors that affect accuracy, the effect of parameter changes on the model, and optimal data sharing. The results show that parameters such as the number of decision trees, maximum depth, and minimum number of samples can affect the accuracy of the model. The evaluation showed that the highest accuracy was obtained in the first test with a data split of 80/20 with an accuracy result of 99%. This study concludes that the random forest method is effective in improving the accuracy of thyroid disease diagnosis and the importance of parameter adjustment for optimal results.
Co-Authors Andri Taufiq, Andri Anggoro, Sigit Ashaury, Herdi Atamimi, Fadel Muhamad Hafid Azzahra, Cynthia Nur Chrisnanto, Yulison Harry Christanto, Yulison Herry Darmawan, Raja Dewi Purnamasari Edvin Ramadhan Fadilah, Rifal Faiza Renaldi, Faiza Febiyane, Raisya Firdaus, Muhammad Fauzi Ghozali, Mohamad Aditya Muttaqin Hasbia, Muhamad Komarudin, Agus Komarudin, Agus Kurniawan, Muhammad Randy Rahayu, Ania Ramadhani, Hary Rizqi Riyadi, Saiful Faris Rusmana, Hendri Diana Wahyudiputra, Helmy Fauzan Wina Witanti Wintanti, Wina Yulison Herry Chrisnanto Zizilia, Regitha