Article Per Year (5 Year)
p-Index From 2021 - 2026
3.618
P-Index
This Author published in this journals
All Journal JURNAL MEDIA INFORMATIKA BUDIDARMA Jurnal Sains dan Informatika PROCESSOR Jurnal Ilmiah Sistem Informasi, Teknologi Informasi dan Sistem Komputer Jurnal Ilmiah Media Sisfo Building of Informatics, Technology and Science Jurnal Teknik Informatika (JUTIF) JIKI (Jurnal Ilmu Komputer dan Informatika) Jurnal Informatika Dan Tekonologi Komputer (JITEK) Journal of Applied Business and Technology Jurnal Informatika dan Rekayasa Komputer Jurnal Manajemen Teknologi dan Sistem Informasi Jurnal Manajemen Sistem Informasi The Indonesian Journal of Computer Science Jurnal Pengabdian Masyarakat Unama Jurnal Komtika (Komputasi dan Informatika) Jurnal Informatika Dan Tekonologi Komputer
Chindra Saputra
Universitas Dinamika Bangsa
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Mathematics Other

Published : 26 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 26 Documents
Search

 1   2   3 
Enhancing Fake News Detection on Imbalanced Data Using Resampling Techniques and Classical Machine Learning Models Abidin, Dodo Zaenal; Siswanto, Agus; Saputra, Chindra; Betantiyo , Betantiyo; Nehemia Toscany, Afrizal
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 5 (2025): JUTIF Volume 6, Number 5, Oktober 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.5.5177

Abstract

Class imbalance remains a critical challenge in fake news detection, particularly in domains such as entertainment media where class distributions are highly skewed. This study evaluates seven resampling techniques—Random Oversampling, SMOTE, ADASYN, Random Undersampling, Tomek Links, NearMiss, and No Resampling—applied to three classical machine learning models: Logistic Regression, Support Vector Machine (SVM), and Random Forest. Using the imbalanced GossipCop dataset comprising 24,102 news headlines, the proposed pipeline integrates TF-IDF vectorization, stratified 3-fold cross-validation, and five evaluation metrics: F1-score, precision, recall, ROC AUC, and PR AUC. Experimental results show that oversampling methods, particularly SMOTE and Random Oversampling, substantially improve minority class (fake news) detection. Among all model–resampling combinations, SVM with SMOTE achieved the highest performance (F1-score = 0.67, PR AUC = 0.74), demonstrating its robustness in handling imbalanced short-text classification. Conversely, undersampling methods frequently reduced recall, especially with ensemble models like Random Forest. This approach enhances model robustness in fake news detection on skewed datasets and contributes a reproducible, domain-specific framework for developing more reliable misinformation classifiers.
Implementasi Algoritma SIFT (Scale-Invariant Feature Transform) Dan Algoritma Kalman Filter Dalam Mendeteksi Objek Bola saputra, chindra
Jurnal PROCESSOR Vol 18 No 1 (2023): Jurnal Processor
Publisher : LPPM Universitas Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/processor.2023.18.1.791

Abstract

The Indonesian Football Robot Contest (KRSBI) is a division of the Indonesian Robot Contest (KRI) which is held annually by RISTEKDIKTI and KEMENDIKBUD. In a soccer robot contest, the robot is required to detect the ball and then lead it to the opponent's goal so that a goal can be created. a good object detection system must be fast, light, and of course it must have good accuracy. Currently, the object detection system that has been applied to robots is in the form of color filtering which is considered quite good in detecting an object. However, if you only rely on this method, it is still lacking when viewed from the point of view of object tracking. The Kalman Filter algorithm serves as an estimator that can be used to predict the direction of movement of an object based on the object's status from the previous frame. This allows the robot to move 1 (one) frame faster than the object to be tracked. The SIFT algorithm can compare two images through the features of the image and produce whether the images are similar or not. This algorithm is useful for ascertaining whether the object detected by the robot is a ball or not. This research combines the SIFT and Kalmal Fiter algorithms to produce a better detection system than before. It is hoped that the results of this research can be used by robots in participating in the Indonesian soccer robot contest.
Design of Dodol Mixer on Based on Microcontroller Arduino Nano Saputra, Chindra; Sutoyo, Mochammad Arief Hermawan; Bustami, M. Irwan; Kibianty, Desi; Kustiansyah, Anggy
Journal of Applied Business and Technology Vol. 5 No. 1 (2024): Journal of Applied Business and Technology
Publisher : Institut Bisnis dan Teknologi Pelita Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35145/jabt.v5i1.160

Abstract

In the process of cooking dodol dough requires the power of several people to continuously stir until the dough releases air bubbles. the process of making dodol generally takes time depending on how much dough you want to cook. If you want to cook 10 kg of dodol dough, then the time needed to cook it is approximately 8-10 hours with normal or medium heat. Currently, the household-scale dodol industry still uses the manual method for the dodol mixing process, which will require energy. more than one person to stir for a long time so that it will take time for one repetitive job and the production costs will be higher. With this tool, it is hoped that the household-scale dodol industry will become more efficient, because there is no need to manually stir and can do another work while the dodol dough is being stirred.
Pengembangan E-Learning Universitas X Menggunakan Gamifikasi dan Analisa Sentimen Sutoyo, Mochammad Arief Hermawan; Yulvianda, Renaldi; Saputra, Chindra
Jurnal Komtika (Komputasi dan Informatika) Vol 8 No 2 (2024)
Publisher : Universitas Muhammadiyah Magelang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31603/komtika.v8i2.12190

Abstract

Pada penelitian sebelumnya didapatkan hasil perhitungan usability terhadap aplikasi e-Learning Universitas X menggunakan system usability testing sebesar 68.97 yang berarti aplikasi yang digunakan saat ini masih bisa diterima penggunaannya oleh pengguna namun bersifat marginal sehingga perlu adanya pengembangan sistem. Berdasarkan permasalahan tersebut, maka penulis mengajukan sebuah penelitian untuk mengembangkan sistem e-learning yang ada saat ini dengan menggunakan gamifikasi. Metodelogi yang digunakan pada penelitian ini adalah throw away prototyping, yang pada tahap analisisisnya menggunakan metode penyebaran kuesioner serta analisa sentimen. Berdasarkan penelitian yang telah dilakukan maka gamifikasi layak untuk diterapkan pada e-Learning Universitas X, nilai system usabilty scale gamifikasi dan e-Learning yang sama yaitu 72.5, namun mahasiswa memiliki keinginan untuk mencoba penerapan prototipe.
ANALISIS MINAT MAHASISWA UNIVERSITAS DINAMIKA BANGSA JAMBI DALAM PENGGUNAAN MENDELEY DENGAN MENGGUNAKAN METODE TAM Nabila Kamila Hasna; Kurniabudi Kurniabudi; Chindra Saputra
Jurnal Informatika Dan Tekonologi Komputer (JITEK) Vol. 2 No. 1 (2022): Maret : Jurnal Informatika dan Teknologi Komputer
Publisher : Pusat Riset dan Inovasi Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jitek.v2i1.219

Abstract

The acknowledgment of innovation is a significant element in the supportability of a data innovation. The motivation behind this study was to decide and break down understudy acknowledgment and interest in utilizing the Mendeley application. This study utilizes an estimation model, specifically Technology Acceptance Model 3, in which the estimation model was created by Venkatesh and Bala. The model has eight factors and eight theories. Models and theories were gotten from information handling through an internet based poll comprising of 100 respondents from Mendeley application clients among Jambi Bangsa Dinamika Bangsa University understudies. The information from the respondents' outcomes were handled utilizing the Structural Equation Model (SEM) helped by SmartPLS 3 Software. The outcomes got in this study were that the TAM 3 utilized had a positive and huge impact between every factor, so it was reasoned that the Mendeley application was acknowledged by University understudies. The elements of the Jambi Nation and understudies who are keen on utilizing the Mendeley application are impacted by two principle aspects of TAM, in particular the view of value that has a positive (0.728) and critical (0.000) impact and the impression of convenience has a positive (0.613) and huge (0.000) impact so the two factors are extremely demonstrated to give positive and huge impact on interest in utilizing Mendeley.
Klasifikasi Tumor Otak pada Citra MRI Menggunakan Transfer Learning EfficientNetB1 dan Visualisasi Grad-CAM Suyanti; Ophelia S, Chandy; Aryani, Lies; Saputra, Chindra; Prayitno
Jurnal Manajemen Teknologi Dan Sistem Informasi (JMS) Vol 6 No 1 (2026): JMS Vol 6 No 1 MARET 2026
Publisher : LPPM STIKOM Dinamika Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33998/jms.2026.6.1.2782

Abstract

Magnetic resonance imaging (MRI) provides rich anatomical contrast for brain tumor assessment, yet routine interpretation remains time-intensive and demands high precision. This work develops a pipeline for four-class brain MRI image classification (glioma, meningioma, pituitary tumor, and no tumor) by combining automated brain-region cropping, data augmentation, and transfer learning with EfficientNetB1. Experimental results demonstrate exceptional performance, achieving an overall accuracy of 0.99 (99%) on the test set. Specifically, the model reached an F1-score of 1.00 for the no tumor class, 0.99 for pituitary, and 0.98 for both glioma and meningioma classes. Beyond reporting numerical performance, the study utilizes Grad-CAM heatmaps to verify that predictions rely on clinically plausible regions rather than spurious background cues. These results indicate that an efficiency-oriented backbone, paired with systematic preprocessing, can achieve reliable and interpretable performance for brain tumor classification tasks.
Co-Authors Abdul Harris Abidin, Dodo Zaenal Afrizal Nehemia Toscany Agus Siswanto Arahmad Taupiq Aryani, Lies Betantiyo , Betantiyo Bustasmi, M.Irwan Cahyana Putra Pratama Dodi Sandra Effiyaldi, Effiyaldi Hansen, Hansen Hendy Saryanto Husaein, Ahmad Irawan Istoningtyas , Marrylinteri Janu Hadi Susilo Jasmir Jumersyah Pratama, Raka KARMAN, ZULFI Kibianty, Desi Kisbianty , Desi Kurniabudi Kurniabudi, Kurniabudi Kustiansyah, Anggy M Irwan Bustami M. Irwan Bustasmi M.Irwan Bustasmi Mhd Ridho Saputra Muhammad Rafly Ramadhan MUHAMMAD SURYA Nabila Kamila Hasna Nugroho, M. Restu Ophelia S, Chandy Pareza Alam Jusia Prayitno Renaldi Yulvianda ROBY SETIAWAN Setiawan Assegaf SIKA, XAVERIUS Sutoyo, Mochammad Arief Hermawan Suyanti taupiq, Arahmad Wahyu Nugraha Xaverius Sika Xaverius Sika YOSE, IMELDA Yovi Pratama Yulia Arvita ZULFI KARMAN