cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ulfi Saidata Aesyi
Contact Email
ijds.unjaya@gmail.com
Phone
+6285643086972
Journal Mail Official
ijds.unjaya@gmail.com
Editorial Address
Jl. Siliwangi, Ringroad Barat, Banyuraden, Gamping, Sleman Daerah Istimewa Yogyakarta 55293
Location
Kab. sleman,
Daerah istimewa yogyakarta
INDONESIA
Indonesian Journal on Data Science
Published by Universitas Jenderal Achmad Yani Yogyakarta
ISSN : 29877423     EISSN : 29877423     DOI : 10.30989
Core Subject : Science,
Computer Science & IT
Indonesian Journal of Data Science (IJDS) adalah Jurnal ilmiah yang memuat hasil penelitian pada ranah data science (Ilmu Data). Cangkupan jurnal meliputi: 1. Big Data 2. Machine Learning 3. Data Mining 4. Deep Learning 5. Artificial Intelligence
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 40 Documents
 1   2   3   4 
ANALLISIS PERBANDINGAN METODE FUZZY MAMDANI DAN FUZZY TSUKAMOTO DALAM MENGUKUR KEPUASAN PENDUDUK TERHADAP KINERJA PEGAWAI DI NEGERI ALLANG Upuy, Doms; Saidu , Rusnian Isfahami; Salamena , Gieska Nataly; Juma , Arman; Lopumeten, Jesica; Palembang, Citra Fathia
INDONESIAN JOURNAL ON DATA SCIENCE Vol. 2 No. 2 (2024): Indonesian Journal On Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v2i2.1384

Abstract

The aim of this research is to evaluate the level of population satisfaction with employee performance in Allaug State. The Fuzzy Mamdani and Fuzzy Tsukamoto methods are used to process qualitative and quantitative data. This study involved a survey of 100 Allaug State residents, using a questionnaire covering various aspects of public service. The research results show that the Fuzzy Tsukamoto method produces a higher level of population satisfaction compared to the Fuzzy Mamdani method. Further analysis reveals that factors such as service speed, employee friendliness, and procedural efficiency have a significant influence on satisfaction levels. This research also identifies areas that need improvement in public services in Allaug State. The implications of these findings are discussed in the context of improving government service quality and community welfare.
PREDICTING STUDENT GRADUATION USING THE FUZZY TSUKAMOTO METHOD IN COMPUTER SCIENCE STUDY PROGRAM STUDENTS CLASS OF 2022 Upuy, Doms; Suhardin, Askin; Sapri, Ismu Iqbal
INDONESIAN JOURNAL ON DATA SCIENCE Vol. 2 No. 2 (2024): Indonesian Journal On Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v2i2.1395

Abstract

This research aims to help optimize resources by designing a system that can be used to help predict student graduation at Pattimura University. The system method used is the Tsukamoto fuzzy method. Tsukamoto's method is an extension of monotonic reasoning. In the Tsukamoto method, each consequence of a rule in the form of IF-THEN must be represented by a fuzzy set with a monotonic membership function. As a result, the inference output from each rule is given firmly (crisp) based on the ?-predicate (fire strength). The final result is obtained using a weighted average. The result of this research is a student graduation prediction system to optimize good results and avoid errors that occur when predicting student graduation.
Penerapan Algoritma Support Vector Machine (SVM) untuk Deteksi Penyakit Mata Katarak: Algoritma Support Vector Machine (SVM) untuk Deteksi Penyakit Mata Katarak Supit, Yonal
INDONESIAN JOURNAL ON DATA SCIENCE Vol. 2 No. 2 (2024): Indonesian Journal On Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v2i2.1449

Abstract

Eye diseases are one of the health disorders that can have serious consequences if not diagnosed early. In an effort to improve the accuracy and efficiency of eye disease detection, the Support Vector Machine (SVM) method is used for classifying eye diseases based on image datasets or related numerical data. This research aims to implement SVM as a classification algorithm, utilizing features extracted from eye images or relevant medical data. The research process includes data collection, preprocessing, feature extraction, SVM model training, and model performance evaluation using accuracy, precision, recall, and F1-score metrics. By applying k-fold cross-validation techniques, the model is tested to avoid overfitting and ensure good generalization. The results of the study show that the SVM method can provide accurate classification results and can be used as an effective tool for diagnosing eye diseases.
ANALISIS PERSEPSI PUBLIK DI MEDIA SOSIAL TERHADAP PRODUK HALAL DI INDONESIA MENGGUNAKAN TEXT MINING Maarif, Muhammad Rifqi; Salim, D Jayus Nor
INDONESIAN JOURNAL ON DATA SCIENCE Vol. 2 No. 2 (2024): Indonesian Journal On Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v2i2.1487

Abstract

The assurance of the halal status of a product is crucial for Muslim consumers, especially in Indonesia, the country with the largest Muslim population in the world. The government, through the Ministry of Religious Affairs, has implemented halal certification to ensure the validity of products. However, the implementation of the halal assurance system remains controversial, with some viewing it as an effort for government profit, particularly by the Ministry of Religious Affairs through the Indonesian Council of Ulama (MUI). Negative sentiments from opposing groups have the potential to escalate and influence other individuals or communities if not properly addressed. One preventive measure is to promote education and awareness of halal products through digital media, especially social media. Given the widespread use of social media, particularly among millennials, it can serve as an effective and cost-efficient platform for education and promotion. Educational efforts via social media require specific strategies to ensure the optimal dissemination of information as intended. Understanding the patterns and characteristics of content as well as the socio-cultural context of social media users is essential. This understanding can be achieved through a comprehensive analysis of the diverse and abundant user-generated content on social media platforms. Therefore, this study proposes a text mining-based method to develop a framework for understanding the characteristics and dynamics of public discourse on halal products on social media.
Sistem Chabot Layanan Informasi Mahasiswa Menggunakan Algoritma Long Short-Term Memory Arumsari, Dewi; kharisma; Aesyi, Ulfi Saidata
INDONESIAN JOURNAL ON DATA SCIENCE Vol. 2 No. 2 (2024): Indonesian Journal On Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v2i2.1489

Abstract

In the era of globalization and rapid information flow, the demand for efficient and accurate information, especially within academic institutions, is rising. Students often face challenges in accessing educational resources and real-time information, particularly outside official working hours. Existing online information services have limitations in providing continuous access. This research focuses on developing and evaluating a student information service chatbot system at Universitas Jenderal Achmad Yani Yogyakarta (UNJAYA) using the Long Short-Term Memory (LSTM) algorithm. The primary objective is to create a system that delivers real-time, accurate, and efficient information services to students. The Machine Learning Development Cycle (MLDC) is employed in the model development process, including stages such as data collection, processing, model training, evaluation, and implementation. The system's performance is tested using a questionnaire distributed to students, with responses measured on a Likert scale. The results demonstrate a chatbot with a 97.76% accuracy rate, 98.34% precision, and 97.76% recall. The overall system evaluation yielded an average score of 3.87, categorized as good. This research concludes that the LSTM-based chatbot successfully enhances information services at the Faculty of Engineering and Information Technology, providing an innovative solution to meet student needs in real-time
Penerapan ResNet50-CNN untuk Optimalisasi Klasifikasi pada Data Fashion Arimbi Puspitasari; Diana Sava Salsabila; Dwi Roliawati
INDONESIAN JOURNAL ON DATA SCIENCE Vol. 3 No. 1 (2025): Indonesian Journal On Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v3i1.1533

Abstract

Penelitian ini bertujuan untuk menerapkan arsitektur Convolutional Neural Network (CNN) berbasis ResNet-50 dalam klasifikasi gambar produk fashion. Model ini dikembangkan untuk mengenali berbagai kategori produk, seperti kaos, celana, dan sepatu, dengan memanfaatkan konsep residual learning yang memungkinkan jaringan mempelajari fitur visual kompleks secara lebih efektif. Metode penelitian meliputi pengumpulan dan pemrosesan data gambar, pelatihan model CNN menggunakan ResNet-50, serta evaluasi performa menggunakan metrik accuracy, precision, recall, dan F1-score. Hasil eksperimen menunjukkan bahwa model mencapai accuracy sebesar 99,44% pada data training dan 97,83% pada data testing, menunjukkan kemampuan generalisasi yang baik terhadap data yang belum pernah dilihat sebelumnya. Evaluasi lebih lanjut menggunakan confusion matrix menunjukkan bahwa sebagian besar sampel diklasifikasikan dengan benar, meskipun masih terdapat beberapa kesalahan prediksi pada kategori tertentu. Dengan rata-rata precision, recall, dan F1-score mencapai 98%, model ini terbukti memiliki performa tinggi dalam klasifikasi gambar fashion. Hasil penelitian ini menunjukkan bahwa ResNet-50 dapat menjadi solusi yang andal untuk sistem rekomendasi produk, katalog digital, dan pengelolaan inventaris berbasis gambar, meskipun masih terdapat ruang untuk peningkatan terutama pada kelas yang sulit diklasifikasikan
ON THE COMPREHENSIVE ANALYSES OF CTU-13 BOTNET DATASET FOR CYBER SECURITY RESEARCHES Gbenga, Jimoh Rasheed; OYELAKIN, Akinyemi
INDONESIAN JOURNAL ON DATA SCIENCE Vol. 3 No. 1 (2025): Indonesian Journal On Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v3i1.1554

Abstract

Attackers use malware to launch attacks in the internet and corporate networks. Over the years, machine learning techniques have been found promising for the classification of these attacks because they have the ability to identify unknown threats.  Botnets are networks of compromised devices and have been found to be powerful threat vectors that are used against modern systems because they use command and control (C2) characteristics which make their detection very difficult.  Generally, to build attack detection models, intrusion datasets are employed. Comprehensive study of the benchmarking datasets used in intrusion detection researches can provide different actionable insights to other researchers. There have been studies that investigated the analyses of datasets for building intrusion detection systems. However, there has been less focus on the analysis of intrusion detection datasets that are used specifically for botnets detection. This study reported an overview of a popular botnet dataset named CTU-13. Thereafter, the work carried out detailed exploratory analysis of the dataset. The study equally sought to identify if the dataset is representative enough for Machine Learning based botnet detection studies. All the thirteen scenarios in the dataset were used for the experimentations. The exploratory analyses were carried out on each of the thirteen scenarios of the dataset with a view to gaining better understanding of the patterns and characteristics of data in each of them. The information obtained from the overview and exploratory analyses provided actionable insights on how to better use the datasets for improved botnet classification. The challenges of using the captures of the dataset were also identified. In particular, the exploratory investigation of the thirteen captures of the CTU-13 dataset revealed that it has very complex patterns, contain mixed data types and suffers from high class imbalance problem. The results of the exploratory analyses can guide the decision of future cyber security researches. Thus, improved machine learning-based botnet detection models can be built by attending to the issues in the dataset.
Prediksi Rekomendasi Buku Berdasarkan Riwayat Peminjaman Menggunakan Collaborative Filtering Pada Perpustakaan Unjaya: Penggunaan Item-Based Collaborative Filtering untuk Meningkatkan Layanan Perpustakaan Digital Mita Aprilia Damayanti; Dini Siskasari; Syarief Hidayatullah; Rois Ali Fernandi; Irmma Dwijayanti
INDONESIAN JOURNAL ON DATA SCIENCE Vol. 3 No. 1 (2025): Indonesian Journal On Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v3i1.1570

Abstract

Perpustakaan Universitas Jenderal Achmad Yani Yogyakarta (Unjaya) berperan penting dalam mendukung ekosistem pendidikan tinggi melalui penyediaan layanan informasi. Untuk meningkatkan relevansi dan kenyamanan layanan, penelitian ini bertujuan memprediksi rekomendasi buku berdasarkan riwayat peminjaman menggunakan metode Item-based Collaborative Filtering. Metode yang digunakan melibatkan pemrosesan data peminjaman dan koleksi buku untuk membentuk matriks kesamaan antar item menggunakan adjusted cosine similarity. Rekomendasi diberikan berdasarkan kemiripan buku dengan yang pernah dipinjam oleh pengguna. Model dievaluasi menggunakan Mean Absolute Error (MAE), dengan hasil menunjukkan nilai MAE sebesar 0.0024 dan 0.0047. Nilai MAE yang mendekati 0 ini menunjukkan bahwa model memiliki tingkat kesalahan prediksi yang sangat rendah, sehingga performa sistem dapat dikategorikan baik. Hasil penelitian membuktikan bahwa sistem mampu menghasilkan rekomendasi yang relevan, mempercepat pencarian informasi, dan mendukung peningkatan kualitas layanan perpustakaan di lingkungan perguruan tinggi. Penelitian ini diharapkan dapat berkontribusi terhadap pengembangan layanan informasi berbasis teknologi di perpustakaan pendidikan tinggi.
Pengembangan Aplikasi Mobile Saffco Skin untuk Edukasi Perawatan Wajah dengan Sistem Rekomendasi Menggunakan Algoritma KNN : Pengembangan Aplikasi Mobile Saffco Skin untuk Edukasi Perawatan Wajah dengan Sistem Rekomendasi Menggunakan Algoritma KNN Mita Aprilia Damayanti; Dini Siskasari; Syarief Hidayatullah; Rois Ali Fernandi; Herdiesel Santoso
INDONESIAN JOURNAL ON DATA SCIENCE Vol. 3 No. 1 (2025): Indonesian Journal On Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v3i1.1585

Abstract

Aplikasi Saffco Skin dirancang untuk membantu pengguna memahami kebutuhan kulit mereka dan memperoleh rekomendasi produk perawatan wajah yang sesuai. Sistem rekomendasi pada aplikasi ini menggunakan algoritma K-Nearest Neighbors (KNN) yang menganalisis data profil pengguna, termasuk tipe kulit (berminyak, kering, sensitif, normal, dan kombinasi), untuk memberikan saran produk yang relevan. EvaluasI model dilakukan dengan dua metrik utama, yaitu jarak rata-rata ke lima tetangga terdekat dan konsistensi tipe kulit produk rekomendasi. Hasil pengujian menunjukkan bahwa rata-rata jarak dari sepuluh sampel produk ke lima rekomendasi terdekat adalah 0.1075, yang menandakan bahwa produk yang direkomendasikan memiliki kemiripan fitur yang tinggi. Selain itu, pada pengujian produk "Perfect Lip Gloss", seluruh rekomendasi (5 dari 5) memiliki tipe kulit yang sama, menghasilkan 100% konsistensi tipe kulit. Model KNN diintegrasikan ke dalam backend berbasis Flask dan terhubung ke antarmuka pengguna Flutter melalui API. Selain sistem rekomendasi, aplikasi ini juga menyediakan katalog produk, artikel edukatif seputar perawatan kulit, serta fitur daftar favorit. Dengan demikian, Saffco Skin menjadi solusi praktis dan cerdas bagi pengguna dalam memilih produk perawatan wajah yang sesuai dengan karakteristik kulit mereka.
Implementasi Metode Weighted Product Pada Sistem Rekomendasi Tempat Makan di Sekitar Bandara Yogyakarta International Airport (YIA) Berbasis Web Ayuningtyas, Astika; Fakhri Yahya, Muhammad; Kusumaningrum, Anggraini; Sajati, Haruno; Dewi Retnowati, Nurcahyani
INDONESIAN JOURNAL ON DATA SCIENCE Vol. 3 No. 1 (2025): Indonesian Journal On Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v3i1.1648

Abstract

Pertumbuhan sektor kuliner di kawasan Bandara Yogyakarta International Airport (YIA) menimbulkan kebutuhan akan sistem informasi yang mampu memfasilitasi pengambilan keputusan pemilihan tempat makan secara efektif. Kompleksitas pemilihan ini dipengaruhi oleh beragam kriteria, antara lain rating (rasa dan layanan), harga, jarak, jam operasional, dan fasilitas yang tersedia. Penelitian ini bertujuan mengembangkan sistem rekomendasi berbasis website dengan menerapkan metode Weighted Product (WP) sebagai pendekatan Sistem Pendukung Keputusan (SPK). Pengumpulan data dilakukan melalui integrasi data sekunder dari Google Maps serta survei primer terhadap 15 rumah makan di sekitar Bandara YIA. Validasi sistem dilakukan menggunakan metode black box, serta evaluasi akurasi dilakukan melalui perbandingan hasil sistem dengan perhitungan manual, yang menghasilkan tingkat akurasi sebesar 83%. Hasil penelitian menunjukkan bahwa penerapan metode WP pada sistem rekomendasi ini mampu memberikan rekomendasi yang relevan dengan preferensi pengguna. Temuan ini diharapkan dapat berkontribusi pada pengembangan aplikasi SPK di bidang pariwisata kuliner serta menjadi acuan pengembangan sistem rekomendasi berbasis multikriteria di lingkungan serupa.

Page 4 of 4 | Total Record : 40

 1   2   3   4 

Filter by Year

2023 2025


Reset
Filter By Issues
All Issue Vol. 3 No. 1 (2025): Indonesian Journal On Data Science Vol. 2 No. 2 (2024): Indonesian Journal On Data Science Vol. 2 No. 1 (2024): Indonesian Journal on Data Science Vol 2 No 1 (2024): Indonesian Journal on Data Science Vol. 1 No. 2 (2023): Indonesian Journal on Data Science Vol 1 No 2 (2023): Indonesian Journal on Data Science Vol. 1 No. 1 (2023): Indonesian Journal on Data Science Vol 1 No 1 (2023): Indonesian Journal on Data Science