Article Per Year (5 Year)
p-Index From 2021 - 2026
4.666
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) JUITA : Jurnal Informatika International Journal of Advances in Intelligent Informatics Indonesian Journal on Computing (Indo-JC) Jurnal Kimia Riset JOIN (Jurnal Online Informatika) Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Jiko (Jurnal Informatika dan komputer) Jurnal Teknik Informatika (JUTIF) Charity : Jurnal Pengabdian Masyarakat eProceedings of Engineering Jurnal INFOTEL Scientific Journal of Informatics LOGIC: Jurnal Penelitian Informatika Proceeding of Community Service and Engagement
Isman Kurniawan
Universitas Telkom
Arts Humanities Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Social Sciences

Published : 40 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 40 Documents
Search

 1   2   3   4 
Classification Model of Consumer Question about Motorbike Problems by Using Naïve Bayes and Support Vector Machine Wicaksana, Ekky; Murdiansyah, Danang Triantoro; Kurniawan, Isman
Indonesian Journal on Computing (Indo-JC) Vol. 6 No. 2 (2021): September, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.2.561

Abstract

The motorbike plays an important role in supporting daily activity. The motorbike is known as one of the transportation modes that is frequently used in Indonesia. The number of motorbikes used in Indonesia is continuously increasing time by time. Hence, the occurrence of motorbike problems can affect community activity and disturb the economic condition in society. Since the problem of the motorbike can occur at any time, a prevention action is required by providing an online consultation platform. However, a classification model is required to handle a wide range of questions about the motorbike problem. By classifying those questions into a specific class of problems, the solution can be delivered to the consumer faster. In this study, we developed prediction models to classify consumer questions. The data set was collected from consumer questions regarding motorbike problems that are commonly occurring. The model was developed using two machine learning algorithms, i.e., Naïve Bayes and Support Vector Machine (SVM). Text vectorization was performed by using the n-gram and term frequency-inverse document frequency (TF-IDF) method. The results show that the SVM model with the uni-trigram model performs better with the value of accuracy and F-measure, which are 0.910 and 0.910, respectively.
Gastroesophageal Reflux Disease Early Detection using XGBoost Method Classifier Wisesty , Untari Novia; Delfina, Haura Adzkia; Kurniawan, Isman
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 2 (2025): JUTIF Volume 6, Number 2, April 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.2.4143

Abstract

Gastroesophageal reflux disease (GERD) is a clinical condition that occurs when the gastric content within the stomach rises into the esophagus. If left untreated, GERD can result in complications such as esophageal inflammation, ulcers, and even cancer. In this study, the early detection of GERD is performed using the GERD dataset obtained from the Harvard Dataverse online repository and processed with the XGBoost machine learning model. The SMOTE technique was implemented as a solution to address the data imbalance present in the dataset. In addition, this study applied Principal Component Analysis (PCA) and Pearson Correlation to select the most relevant attributes, with the aim of improving computational efficiency. The results demonstrated that feature selection through Pearson correlation and feature extraction using principal component analysis (PCA) yielded the optimal model performance when utilizing 16 attributes and 16 principal components, respectively. The XGBoost model with PCA achieves a macro average F1-score of 0.9615, while the XGBoost model with Pearson Correlation attains a value of 0.9809. Subsequently, the XGBoost model based on the original dataset yielded a macro F1-score value of 0.9568. The findings of this research indicate that the XGBoost model with the Pearson Correlation-based feature selection method has a better f1-score value than the feature extraction method with PCA or based on the original dataset with a difference in value of 0.0194 and 0.0241 respectively in enhancing the performance of the XGBoost model for early detection of GERD in this study.
Model Klasifikasi berbasis Ekspresi Gen Non-Small Cell Lung Carcinoma (NSCLC) pada Wanita Bukan Perokok Menggunakan Metode Ensemble Azizah, Kholishoh Nur; Kurniawan, Isman; Nhita, Fhira
LOGIC: Jurnal Penelitian Informatika Vol. 1 No. 1 (2023): September 2023
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/logic.v1i1.6389

Abstract

Kanker paru-paru adalah penyebab utama kematian terkait kanker di seluruh dunia dan membawa dampak sosial ekonomi yang signifikan bagi pasien, keluarga, dan masyarakat secara keseluruhan. Dalam diagnosis kanker, klasifikasi berbagai jenis tumor sangat penting. Prediksi akurat dari berbagai jenis tumor memungkinkan untuk pengobatan yang lebih baik dan meminimalkan toksisitas pada pasien. Untuk menganalisis masalah klasifikasi kanker menggunakan data ekspresi gen, untuk pemilihan fitur dan model prediksi. Penelitian ini bertujuan untuk memprediksi NSCLC dengan menerapkan metode ensemble pada data microarray. Penulis menggunakan tiga metode ensemble untuk memprediksi NSCLC, yaitu Random Forest, Adaptive Boosting (AB), dan Extreme Gradient Boosting (XG). Seleksi fitur dilakukan menggunakan variance threshold dan parameter chi-square kemudian dilanjutkan dengan membangun model prediksi menggunakan ensemble. Hasil validasi model terbaik berdasarkan yang terdiagnosis kanker yaitu model AB dengan 10 fitur, XG dengan 10 fitur, dan XG dengan 20 fitur yang menghasilkan nilai accuracy, recall, dan f1-score yang sama berturut-turut yaitu 0.93, 1.00, dan 0.93.
Implementasi Metode Support Vector Machine (SVM) pada Model Prediksi Rating Obat Berdasarkan Ulasan Pasien Jayanata, Wisnu; Kurniawan, Isman
LOGIC: Jurnal Penelitian Informatika Vol. 1 No. 1 (2023): September 2023
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/logic.v1i1.6410

Abstract

Pesatnya perkembangan internet dan media sosial mengakibatkan membaca ulasan sebelum membeli suatu produk, terutama produk obat menjadi hal yang lumrah. Namun, jumlah ulasan yang banyak dan tersebar mengakibatkan kesulitan dalam melakukan penilaian kualitas produk obat. Oleh karena itu, sistem yang dapat membantu pelanggan dalam menghadapi kendala ini sangat dibutuhkan. Pada pemodelan sistem, digunakan TF-IDF untuk mereduksi fitur dan Support Vector Machine sebagai metode klasifikasi. Dilakukan puka Hyperparameter Tuning untuk meningkatkan performa sistem. Pada penelitian ini didapat bahwa polynomial merupakan kernel SVM yang paling optimal untuk memprediksi rating obat berdasarkan ulasan pasien dengan akurasi mencapai 75.00% dan f-1 score sebesar 74.23%.
In Silico and In Vivo Approaches to Exploring the Antidiabetic of Vegetable Fern (Diplazium esculentum S.) Iljannah, Nissa; Sapitri, Nazwa Martina; Rizki, Alfath Muhammad; Yuningsih, Lela Mukmilah; Khumaisah, Lela Lailatul; Kurniawan, Isman
Jurnal Kimia Riset Vol. 10 No. 2 (2025): December
Publisher : Universitas Airlangga, Campus C Mulyorejo, Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jkimris.v10i2.73695

Abstract

Diabetes mellitus (DM) is a chronic metabolic disease characterized by increased blood glucose levels (hyperglycemia). Efforts to treat and prevent DM are made by using antidiabetics, usually synthetic drugs. However, continuous use may cause side effects. Other alternatives are needed to handle DM by utilizing plants as antidiabetics, such as the vegetable fern (Diplazium esculentum S.). Therefore, this research aims to analyze the components of a vegetable fern leaf extract and determine its effectiveness as an antidiabetic through in silico and in vivo assays. The sample was macerated using 98% ethanol for 3x24 hours. Phytochemical screening and LC-MS/MS analysis were performed on the extract. In vivo studies were conducted on mice with extract doses of 200, 400, and 600 mg/BW along with positive (Glibenclamide) and negative controls. An in silico study was conducted by molecular docking against the ɑ-glucosidase receptor with PDB ID 5KZW, which was docked to 18 compounds from the extract. The analysis revealed that the D. esculentum S. leaf extract contained 22 compounds, including flavonoids, terpenoids, steroids, and phenolics. The best dosage for the in vivo antidiabetic efficacy assays was 400 mg/BW of extract, which significantly reduced glucose levels for 21 days, reaching 30%, which was better than Glibenclamide's 27%. Based on in silico tests, the molecules kaempferol 3-rhamno-glucoside and 4,4-Bis[2,2-bis(4-methoxyphenyl)vinyl]biphenyl had the highest affinity, with a value of -6.3 kcal/mol. Dantaxusin A and Phorone A came in second and third, respectively, with -6.0 and -5.9 kcal/mol. These results suggest the potential antidiabetic effects of D. esculentum S. leaf extract.
Gene Expression-Based Lung Cancer Prediction in Smokers Using SVM and Moth-Flame Optimization Algorithm Ramandha, Salma Safira; Afinda, Angel Metanosa; Kurniawan, Isman
Scientific Journal of Informatics Vol. 13 No. 1: February 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i1.38268

Abstract

Purpose: Lung cancer remains one of the leading causes of death worldwide, especially among active smokers, yet early detection is still difficult because traditional imaging methods have limited sensitivity for identifying early-stage abnormalities. This study was conducted to address the need for a more accurate computational approach capable of detecting lung cancer at a molecular level using gene expression data. The goal is to build a model that can reliably distinguish cancerous from non-cancerous samples based on genomic features. Methods: This study uses the GSE4115 gene-expression dataset consisting of 187 bronchial epithelial samples and 22,215 gene features. The Moth-Flame Optimization (MFO) algorithm was implemented to select the most informative subset of genes from this high-dimensional dataset. A Support Vector Machine (SVM) classifier was then trained using multiple kernels, with hyperparameter tuning performed to identify the optimal configuration for each kernel. Results: Experimental results show that the Polynomial kernel achieved the highest performance using 286 MFO-selected features, reaching an accuracy of 0.84 and an F1-score of 0.85. These results confirm that combining MFO with SVM improves classification performance compared to using raw gene data without feature selection. Novelty: This study provides the first application of MFO-based feature selection for lung cancer prediction in smokers using the GSE4115 dataset. The findings demonstrate the value of nature-inspired optimization for handling high-dimensional genomic data and offer a promising direction for developing early computational detection methods.
Optimized LSTM Model Using Simulated Annealing for Autoignition Temperature (AIT) Prediction as a Hazard Indicator Zahra, Nurul Izzah Abdussalam; Afinda, Angel Metanosa; Kurniawan, Isman
Scientific Journal of Informatics Vol. 12 No. 4: November 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v12i4.38278

Abstract

Purpose: Autoignition Temperature (AIT) is the lowest temperature at which a substance will spontaneously ignite in normal air without any external ignition source. AIT is an important safety parameter in industries that handles flammable materials. Measuring AIT with conventional method is unfortunately slow, costly, and dangerous. As an alternative, an AIT prediction model can be developed using in silico approaches, specifically based on machine learning. Methods: One of the methods that can be used is Long Short-Term Memory (LSTM) since it is good at modeling the complex relationships that is involved, but unfortunately it is difficult to tune manually due to their numerous hyperparameters. Therefore, an automated strategy can be used to find the best hyperparameters for the architecture. This study aims to develop an AIT prediction model as a hazard indicator using an LSTM model optimized with Simulated Annealing (SA). Result: The experiment showed that the SA-LSTM model which uses a cooling schedule of Delta T = 0.7 outperformed the unoptimized baseline model. Novelty: The optimization raised the R2 on test data from 0.5682 to 0.5939 while also lowering the RMSE from 74.35 K to 72.10 K and the MAPE from 9.29% to 8.87%. These results confirmed that optimizing LSTM with SA gave a more robust tool for hazard indicator.
PERBAIKAN APLIKASI BINAR ILMU GRADING SYSTEM UNTUK PENINGKATAN EFEKTIVITAS DAN EFISIENSI PROSES BISNIS DAN BASIS DATA MASYARAKAT SASAR: SMP DAN SMA BINAR ILMU Isman Kurniawan; Erwin Budi Setiawan; Danang Triantoro Murdiansyah
The Proceeding of Community Service and Engagement (COSECANT) Seminar Vol. 3 No. 1 (2023): Prosiding COSECANT : Community Service and Engagement Seminar
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/cosecant.v3i1.7094

Abstract

Proyek pengabdian masyarakat ini bertujuan untuk mengatasi permasalahan dalam manajemen akademik dan pengelolaan data di SMP dan SMA Binar Ilmu. Dengan fokus pada perbaikan aplikasi dari sisi proses bisnis dan basis data, proyek ini memberikan solusi yang dapat meningkatkan efisiensi dalam proses input nilai, pelaporan, dan akses informasi akademik. Melalui kolaborasi dengan mitra sekolah, solusi ini dirancang untuk memenuhi kebutuhan nyata dan membawa dampak yang signifikan dalam membantu siswa mendapatkan pemahaman yang lebih baik tentang perkembangan akademik mereka dan memberdayakan staf sekolah untuk fokus pada kegiatan pengajaran yang lebih kreatif dan produktif. Potensi keberlanjutan proyek ini terletak pada peningkatan kapasitas internal sekolah, peran sumber daya internal dalam pemeliharaan teknologi, komitmen sekolah terhadap inovasi, dukungan pemangku kepentingan, dan pemantauan yang berkelanjutan. Dengan kombinasi dari faktor-faktor ini, proyek ini diharapkan akan memberikan perubahan positif yang berkelanjutan dalam manajemen akademik sekolah dan pemberdayaan siswa serta staf.
Implementasi Rapor Digital Berbahasa Inggris untuk Mendukung Standar Pendidikan Global di SMP dan SMA Binar Ilmu Danang Triantoro Murdiansyah; Isman Kurniawan
The Proceeding of Community Service and Engagement (COSECANT) Seminar Vol. 4 No. 2 (2024): The Proceeding of Community Service and Engagement (COSECANT) Seminar
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/cosecant.v4i2.8578

Abstract

Kegiatan pengabdian masyarakat ini bertujuan untuk mengembangkan dan mengimplementasikan sistem rapor digital berbahasa Inggris di SMP dan SMA Binar Ilmu guna mendukung lulusan dalam mengakses peluang pendidikan internasional. Setelah diskusi awal dengan masyarakat sasaran, sistem dirancang sesuai kebutuhan sekolah, termasuk fitur untuk input nilai dan translasi raport ke dalam bahasa Inggris. Pemaparan sistem dilakukan melalui sesi demo dan tutorial, yang berhasil meningkatkan pemahaman staf akademik mengenai penggunaan aplikasi. Hasilnya, sistem ini diakui sangat membantu dalam proses bisnis akademik sekolah dengan menghasilkan rapor otomatis dalam dua bahasa, sehingga meningkatkan efisiensi dan kesiapan administrasi sekolah untuk menghadapi tuntutan globalisasi.
LSTM Algorithm in Predicting Chronic Kidney Disease Optimized Using Genetic Algorithm Brillyando Magathan Achmad; Siti Sa'adah; Isman Kurniawan
JUITA: Jurnal Informatika JUITA Vol. 12 No. 2, November 2024
Publisher : Department of Informatics Engineering, Universitas Muhammadiyah Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30595/juita.v12i2.22965

Abstract

Chronic Kidney Disease is a health condition in which the kidneys experience a progressive decline in function. Kidneys are vital organs that filter waste and excess blood fluids. CKD can lead to excess products in the body and cause various health issues, so early detection of CKD is necessary. While traditional machine learning techniques have performed well in predicting CKD in existing studies, this study investigates the potential of long short-term memory (LSTM) optimized with Genetic Algorithm to enhance predictive accuracy and efficiency by optimizing its hyperparameters, including number of units, hidden layers, activation function, recurrent activation, and dropout rate. The result demonstrates that the optimized LSTM slightly performs better than without optimization, achieving higher precision, recall, accuracy, and f1 score by 100% respectively. This outstanding result can be attributed to several key factors, such as ensuring rigorous data preprocessing and utilizing k-fold cross-validation to make the model more reliable. This indicates the hybrid approach can be a powerful method for the early detection of CKD, leading to better patient outcomes. Despite the promising performance, further research is suggested, specifically using a larger dataset to ensure applicability to more general population and exploring other optimization methods to reduce computational cost.
Co-Authors Afinda, Angel Metanosa Ali Assegaf Annisa Aditsania Ardannur Deswanto, Farrel Ardhyka Dewantara Arionmaro Asi Simaremare Arsytania, Ihsani Hawa Azizah, Kholishoh Nur Bambang Hadi Prakoso Brillyando Magathan Achmad Crisanadenta Wintang Kencana Danang Triantoro Murdiansyah Danang Triantoro Murdiansyah Delfina, Haura Adzkia Deni Saepudin Devi Munandar Didit Adytia Diya Namira Purba Ekky Wicaksana Erwin Budi Setiawan Erwin Budi Setiawan Fadhli Rahman Farid, Husnul Khotimah Farid, Mochammad Rafi Fhira Nhita Furqon Hidayat Husnul Khotimah Farid Hutama, Nanda Yonda I Kadek Andrean Pramana Putra Pramana Iljannah, Nissa Indra A Aditya Jayanata, Wisnu Kamil, Nabilla Kemas Muslim Lhaksmana Khoerunnisa, Ghina Komang Triolascarya Lela Lailatul Khumaisah Lela Mukmilah Yuningsih Lusi Sofiana Silaban Maya Rosalinda Mela Mai Anggraini Mohammad Adietya Perdana Nabilla Kamil Nanda Yonda Hutama Nurul Ikhsan Ramandha, Salma Safira Reina Wardhani Reza Fauzi Iskandar Reza Rendian Septiawan Rian Febrian Umbara Rizki Amanullah Hakim Rizki, Alfath Muhammad Salsabil, Adinda Arwa Sapitri, Nazwa Martina Saut Sihol Ritonga Siti Sa'adah Wicaksana, Ekky Wisesty , Untari Novia Yusuf, Muhammad Rizky Yusfian Zahra, Nurul Izzah Abdussalam