Article Per Year (5 Year)
p-Index From 2021 - 2026
2.913
P-Index
This Author published in this journals
All Journal Sistemasi: Jurnal Sistem Informasi Jurnal Komtika (Komputasi dan Informatika) AJAD : Jurnal Pengabdian kepada Masyarakat Jurnal Ilmiah Sistem Informasi dan Ilmu Komputer DEVICE : JOURNAL OF INFORMATION SYSTEM, COMPUTER SCIENCE AND INFORMATION TECHNOLOGY Technology and Informatics Insight Journal Jurnal Informatika dan Rekayasa Komputer Jurnal Manajemen Sistem Informasi Akademika Jurnal Komtika (Komputasi dan Informatika) JITCoS : Journal of Information Technology and Computer System Journal of Engineering and Technology Innovation Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer Journal of Social Science Utilizing Technology
Niko Akbar
Unknown Affiliation
Humanities Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Mechanical Engineering Transportation

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

Found 17 Documents
Search

 1   2 
Image Classification Based On Color Using Thresholding Method Teguh Agara Selian; Niko Akbar; M. Irfan Hidayat
Journal of Information Technology and Computer System Vol. 1 No. 1 (2025): June
Publisher : CV. Multimedia Teknologi Kreatif

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65230/jitcos.v1i1.5

Abstract

This research aims to categorize images based on color using the method of thresholding. Image classification based on color plays a crucial role in various applications such as object detection, traffic monitoring, and medical image processing. The thresholding method is a popular approach used in image segmentation due to its effectiveness and computational efficiency. In this method, grayscale images are converted into binary images by determining a specific threshold value. This research utilizes the thresholding method to separate pixels based on their color intensity. The research methodology consists of several steps, including dataset collection, image pre-processing, color feature extraction, application of the thresholding method, and class labeling. The study's benefits include object recognition, cost and time reduction in image classification, and improved product quality and income for farmers.
Evaluasi Sistem Informasi Perpustakaan SMA/SMK Kota Jambi Menggunakan Metode Cognitive Walkthrough dan Heuristic Evaluation Adfa Aditiya; Edi Saputra; Muhammad Razi A; Niko Akbar; Putri Hazmawati; Muhammad Ari Prayitno
Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer Vol. 5 No. 3 (2025): November: Jurnal Ilmiah Teknik Mesin, Elektro dan Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/juritek.v5i3.5769

Abstract

Penelitian ini mengevaluasi aspek usability pada Sistem Informasi Perpustakaan SMA/SMK Kota Jambi menggunakan metode Cognitive Walkthrough (CW) dan Heuristic Evaluation (HE). Hasil analisis menunjukkan bahwa sistem telah memiliki struktur fungsional yang baik, namun masih terdapat kendala pada aspek kemudahan penggunaan dan kejelasan informasi antarmuka. Melalui pengujian CW ditemukan 27 permasalahan usability, terutama pada kategori User dan Text and Icon, dengan tingkat keparahan sedang hingga ringan yang berpotensi menurunkan kenyamanan serta efisiensi penggunaan sistem. Sementara itu, hasil evaluasi HE mengidentifikasi perlunya peningkatan pada aspek Visibility of System Status, Match between System and the Real World, User Control and Freedom, Error Prevention, Recognition Rather Than Recall, serta Flexibility and Efficiency of Use. Sebagian besar temuan termasuk kategori Minor dan Major Errors yang memengaruhi kenyamanan dan fungsi utama sistem, sedangkan Cosmetic Errors bersifat ringan namun tetap perlu diperhatikan untuk penyempurnaan antarmuka. Penelitian ini diharapkan dapat berkontribusi dalam meningkatkan kualitas dan efektivitas sistem informasi perpustakaan di lingkungan SMA/SMK Kota Jambi.
Emotional Intelligence and Its Impacts on Educational Psychology: Developing a New Model for Student Assessment Riyanti Riyanti; Niko Akbar; Fitri Hilmiyati
Journal of Social Science Utilizing Technology Vol. 2 No. 2 (2024)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jssut.v2i2.972

Abstract

Background. Quantum computing is a technology that has great potential to revolutionize various scientific disciplines with its extraordinary computing capabilities. Multiple fields, such as cryptography, optimization, and complex simulation, have begun to explore quantum computing applications. However, a deep understanding of how these technologies can be used effectively in cross-disciplinary informatics still needs to be improved. Purpose. This research aims to develop a theoretical framework that explains the role of quantum computing in advancing interdisciplinary informatics. The main focus is to identify potential applications and challenges faced in applying this technology in various fields and evaluate its impact on the development of science and technology. Method. This research uses a qualitative approach, a literature review, and theoretical analysis methods. Data were collected from various academic sources, including journals, books, and conferences relevant to quantum computing and interdisciplinary informatics. Analysis was conducted to identify patterns, themes, and relationships between quantum computing and cross-disciplinary applications. Results. The research results show that quantum computing has the potential to solve complex computational problems in various fields, including cryptography, optimization, and physical simulation. Quantum computing can provide more efficient and faster solutions than classical computing. However, the research also identified several significant challenges, such as the need for quantum-specific algorithms and sophisticated technological infrastructure. Conclusion. Quantum computing is essential in advancing interdisciplinary informatics by providing superior computing capabilities. The theoretical framework developed in this research can be used to further study and develop quantum computing applications in various fields. The identified challenges require special attention to ensure effective and efficient implementation of this technology.
Klasifikasi Risiko Gempa Bumi menggunakan metode Decision Tree Akbar, Niko; Alghifari, Hamzah; Abdillah, Nurul; Dahwanu, Oki
DEVICE : JOURNAL OF INFORMATION SYSTEM, COMPUTER SCIENCE AND INFORMATION TECHNOLOGY Vol. 6 No. 2: DESEMBER 2025
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/device.v6i2.7843

Abstract

Gempa bumi merupakan salah satu bencana alam yang sulit diprediksi namun memiliki dampak besar terhadap kehidupan manusia. Oleh karena itu, diperlukan suatu pendekatan analitis yang mampu mengidentifikasi pola dan hubungan antarparameter gempa untuk mendukung sistem peringatan dini. Penelitian ini bertujuan untuk melakukan Klasifikasi Dampak akan kejadian gempa bumi menggunakan metode Data Mining berbasis Decision Tree. Data yang digunakan berasal dari katalog gempa yang memuat atribut seperti Tanggal Kejadian (timestamp), magnitudo, kedalaman, serta koordinat lokasi (latitude dan longitude). Proses analisis meliputi tahap pembersihan data (data cleaning), transformasi, dan pembuatan model klasifikasi Decision Tree untuk menentukan tingkat potensi dan dampak gempa serta mengetahui keakuratan gempa bumi berdasarkan data dari tahun ketahun. Hasil penelitian menunjukkan bahwa atribut magnitudo memiliki pengaruh signifikan terhadap tingkat risiko gempa. Model Decision Tree yang dibangun mampu menghasilkan aturan klasifikasi seperti “Jika magnitudo <5 maka berpotensi Risiko gempa bumi rendah, sedangkan magnitudo antara 5-7 berisiko gempa bumi sedang, dan magnitudo ≥ 7 maka berpotensi Risiko Gempa Bumi Tinggi”, yang dapat digunakan untuk mendukung pengambilan keputusan dalam mitigasi bencana. Dengan demikian, metode Decision Tree terbukti efektif dalam mengungkap pola tersembunyi dari data gempa bumi dan dapat menjadi dasar bagi sistem prediksi serta peringatan dini gempa di masa mendatang. Disimpulkan bahwa akurasi masing – masing sebesar 100 %, sedangkan recall sebesar 100 % tapi hasil precision menunjukkan statistik yang berbeda yakni Prediksi Tidak Berpotensi Gempa Bumi  Besar sebesar 100%, sedangkan Prediksi Tidak berpotensi Gempa Bumi sedang sebesar 99,67%, dan terakhir prediksi Tidak berpotensi Gempa Bumi Kecil sebesar 96 %. Hasil pengujian ternyata menghasilkan magnitude rendah dengan ukuran >5,350 tergolong rendah, sedangkan magnitude rendah dengan ukuran <5,350 mempunyai frekuensi yang banyak. Dan Beberapa data berdasarkan statistik Magnitudo >5.350 ukuran sedang dari data sebanyak 16 data. Sedangkan magnitudo ≤ 5.350 Ukuran Rendah sebanyak 6716 Data yang ditemukan dan sudah dianalisis.
KLASIFIKASI DAN PREDIKSI KELUARGA BERISIKO STUNTING DI PROVINSI JAMBI MENGGUNAKAN METODE KNN DAN NAIVE BAYES Akbar, Niko; Alghifari, Hamzah; Abdillah, Nurul; Dahwanu, Oki
DEVICE : JOURNAL OF INFORMATION SYSTEM, COMPUTER SCIENCE AND INFORMATION TECHNOLOGY Vol. 7 No. 1: JUNI 2026
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/device.v7i1.8522

Abstract

Di Indonesia Prevalensi stunting sebesar 37,2%, naik dari 35,6% pada tahun 2019 dan 36,8%, dengan mayoritas dipengaruhi oleh penduduk setempat. Kementerian Kesehatan Indonesia memperkirakan bahwa prevalensi stunting akan mencapai 38,9% pada tahun 2020. Permasalahannya Beberapa Data yang diambil dan dipakai berupa data sekunder yang di ada diwebsite opendata provinsi jambi yang berjudul Faktor Penapisan Keluarga Berisiko Stunting di Provinsi Jambi. Dengan menggunakan algoritma KNN dan Naïve Bayes, maka didapatkan hasilnya berupa kedua algoritma cocok untuk pengklasteran dan Scoring dari algoritma menunjukkan hasil yang berbeda. Karena keakurasiannya sesuai dengan perhitungan manual yang telah dijabarkan pada bagian pengolahan data. Beberapa hasil dari cross-validasi menyatakan bahwa nilai accuracy 85,29%, nilai precision berupa 83,33%, nilai recall 85,29%.
Analisis Kepuasan Pengguna Aplikasi Canva Menggunakan Metode EUCS (End User Computing Satisfaction) Di Kota Jambi Anggun Rahmadha Cevi; Davina Naja Sabila; Bagas Alif Armando Nasution; Alfi Alifio Liputo; Ulfa Khaira; Rahmad Ashar; Niko Akbar
Technology and Informatics Insight Journal Vol. 5 No. 2 (2026): TIIJ
Publisher : LP3M Universitas Putra Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32639/hxymfd71

Abstract

Canva is a widely used graphic design platform that supports academic activities, work and creativity. The high level of Canva usage needs to be balanced by an assessment of user satisfaction to determine the extent to which the application meets users’ needs. This study aims to analyse the level of user satisfaction with the Canva application in Jambi City using the End User Computing Satisfaction (EUCS) method. The study employs a quantitative approach with purposive sampling and involves 150 Canva users in Jambi City. Data were collected via an online questionnaire and analysed using SmartPLS 4. The results indicate that the model explains 71.3% of user satisfaction. The variables ‘Content’, ‘Ease of Use’ and ‘Timeliness’ have a positive and significant influence on user satisfaction, whilst ‘Accuracy’ and ‘Format’ do not have a significant influence. ‘Content’ is the most dominant factor influencing user satisfaction with the Canva application in Jambi City.
Improving Digital Fraud Detection Performance Using SMOTE and Comparative Analysis of Classification Algorithms Niko Akbar; Yandi Anzhari; Oki Dahwanu; Nurul Abdillah
SISTEMASI Vol 15, No 10 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i10.6813

Abstract

The digital transformation of social media platforms, particularly X (formerly Twitter), has been accompanied by an increase in digital fraud cases. Machine learning approaches are widely used for fraud detection; however, they face the challenge of class imbalance, in which fraudulent posts are substantially outnumbered by legitimate posts. This study aims to evaluate the effect of the Synthetic Minority Over-sampling Technique (SMOTE) on fraud detection performance and compare three classification algorithms: Naive Bayes, Support Vector Machine (SVM), and Logistic Regression. The data were obtained from the Kaggle dataset “ScamTags: Indonesian NER for Fraud Identification,” with features extracted using Term Frequency–Inverse Document Frequency (TF-IDF). To prevent data leakage, training and test data were strictly separated within the cross-validation procedure, ensuring that SMOTE was applied exclusively to the training folds and never to the test data. The experimental results show that, for this small and imbalanced dataset, SMOTE did not consistently improve model performance. Naive Bayes was the only model that effectively detected fraudulent posts, achieving the highest recall of 90.00% and an F-measure of 60.76% in the scenario without SMOTE. In contrast, SVM failed to detect the fraud class, yielding a recall of 0%, despite its seemingly high accuracy. These findings underscore the importance of leakage-free evaluation and highlight how accuracy can be misleading when dealing with imbalanced data. Consequently, minority-class recall and F-measure provide more informative measures for evaluating fraud detection systems. In practical terms, this study suggests that a simple model such as Naive Bayes can serve as a reliable initial option for screening Indonesian-language fraudulent posts, particularly when training data are limited. Nevertheless, these findings should be interpreted in light of the dataset's small size and single-source origin. Further validation using larger and more diverse datasets is required to establish the generalizability of the results.
Co-Authors Adfa Aditiya Ahmad Jurnaidi Wahidin Alfi Alifio Liputo Alghifari, Hamzah Anggun Rahmadha Cevi Ari Prayitno Bagas Alif Armando Nasution Bayu Putra Sanjaya Davina Naja Sabila Edi Saputra Hilmiyati, Fitri Ismaun Rusman Joni Devitra, Joni Khaira, Ulfa M. Ari Prayitno M. Irfan Hidayat Muh Imam Quraisy Muhammad Adfa Aditiya Muhammad Ari Prayitno Muhammad Razi A Nurul Abdillah Oki Dahwanu Putra Sanjaya, Bayu Putri Hazmawati Rahmad Ashar Rini Yunita Riyanti Riyanti Riyanti Sutoyo, Mochammad Arief Hermawan Teguh Agara Selian Yandi Anzhari