Article Per Year (5 Year)
p-Index From 2021 - 2026
2.844
P-Index
This Author published in this journals
All Journal Jurnal Prima Edukasia Sinkron : Jurnal dan Penelitian Teknik Informatika Jurnal Pilar Nusa Mandiri IKRA-ITH Informatika : Jurnal Komputer dan Informatika Jurnal Teknologi Informasi MURA Jurnal Riset Informatika JUSIM (Jurnal Sistem Informasi Musirawas) Jurnal Teknologi Informasi dan Komunikasi Jurnal Teknologi Informasi Mura
Jupriyanto .
Universitas Mandiri
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Other

Published : 20 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 20 Documents
Search

 1   2 
KOMPARASI ALGORITMA KLASIFIKASI DALAM MEMPREDIKSI KINERJA AKADEMIK MAHASISWA MENGGUNAKAN WEKA Pattiasina, Tiska; Jupriyanto, Jupriyanto
Jurnal Teknologi Informasi Mura Vol 17 No 1 (2025): Jurnal Teknologi Informasi Mura JUNI
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jti.v17i1.2608

Abstract

Data mining merupakan serangkaian proses sistematis yang digunakan untuk menggali nilai tambah berupa informasi yang tersembunyi dan belum diketahui secara eksplisit dari suatu basis data. Dalam konteks pendidikan, data mining berperan penting dalam menghasilkan informasi yang dapat digunakan untuk menganalisis dan mengevaluasi kinerja akademik mahasiswa. Pada penelitian ini, penulis mengambil sampel dari mahasiswa semester I kelas C jurusan Administrasi Niaga di Politeknik Negeri Ambon. Penelitian difokuskan pada proses klasifikasi kinerja akademik mahasiswa berdasarkan 22 atribut yang telah ditentukan. Proses penggalian pengetahuan dilakukan dengan mengacu pada tahapan Knowledge Discovery in Database (KDD), yang mencakup proses seleksi data, praproses, transformasi, data mining, hingga interpretasi hasil. Tiga algoritma klasifikasi yang digunakan dalam penelitian ini adalah Decision Tree, Naive Bayes, dan K-Nearest Neighbor (KNN). Untuk mengukur kinerja masing-masing algoritma secara objektif, dilakukan evaluasi model menggunakan teknik validasi silang k-fold cross validation, sehingga hasil klasifikasi dapat dibandingkan secara menyeluruh berdasarkan sejumlah indikator evaluasi, seperti akurasi, presisi, dan recall.
PENDEKATAN ANALISIS PREDIKTIF REGRESI MENGGUNAKAN METODE PEMBELAJARAN MESIN UNTUK MEMPERKIRAKAN EFFORT PENGEMBANGAN PERANGKAT LUNAK PADA APPLIKASI MENARA MASJID BAZNAS RI Jupriyanto, Jupriyanto; Kusuma, Muhammad Romadhona
JUSIM (Jurnal Sistem Informasi Musirawas) Vol 10 No 1 (2025): JUSIM : Jurnal Sistem Informasi Musi Rawas JUNI
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jusim.v10i1.2595

Abstract

Suatu proyek pastinya membutuhkan suatu estimasi, pada proyek pengembangan perangkat lunak estimasinya berfokus untuk memperkirakan effort apa saja yang diperlukan pada saat mengembangkan perangkat lunak dengan mencakup sumber daya, kebutuhan tenaga kerja yang diperlukan, waktu serta pengolahan jadwal kegiatannya serta berusaha menekan anggaran menjadi seminimal mungkin. Biasanya seorang Manajer proyek yang akan bertanggung jawab serta memberi keputusan untuk menangani perhitungan proyek estimasi tersebut. Seringkali membuat keputusan di bawah ketidakpastian yang tinggi adalah masalah kritis dalam pengembangan perangkat lunak. Sedangkan dalam hal Memprediksi tentunya membutuhkan suatu pengalaman tingkat lanjut dan juga alat bantu yang dapat digunakan untuk meningkatkan keakuratan prediksi tersebut. Sebuah prediksi berbasis algortima machine learning dapat memprediksi effort pengembangan perangkat lunak secara efisien dan berguna yang keakuratannya membantu memprediksi kinerja berdasarkan data historis metrik pengembangan perangkat lunak, tentu hal ini bagi manajer proyek dapat bermanfaat sebagai salah satu opsi sistem pendukung keputusan untuk meningkatkan ketepatan dalam hal memperkirakan effort pengembangan perangkat lunak. Berdasarkan latar belakang tersebut maka pada penelitian ini adalah bagaimana melakukan pengukuran untuk meningkatkan efisiensi dalam memperkirakan effort pembangunan perangkat lunak. kami mencoba membangun model estimasi regresi prediktif untuk memprediksi effort pada proses proyek pengembangan perangkat lunak, menggunakan beberapa algortima machine learning seperti Linier Regresion (LR), K-Nearest Neighbors (KNN), maupun Support Vector Machine (SVM) dan Random Forest (RF) serta Decision Tree (DT)
Perbandingan Kinerja Algoritma Naïve Bayes dan C4.5 pada Sistem Web Klasifikasi Kelayakan PKH Jupriyanto, Jupriyanto; Apandi, Jamaludin; Wijaya, Anderias Eko; Hermawan, Rian; Siallagan, Timbo Faritcan Parlaungan; Udoyono, Kodar; Ahmad, Hermansyah Nur
Jurnal Teknologi Informasi dan Komunikasi Vol 18 No 1 (2025): April
Publisher : STMIK Subang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47561/jtik.v18i1.287

Abstract

This study discusses the development of a web-based classification system for determining the eligibility of recipients of the Family Hope Program (PKH), by comparing two data mining algorithms: C4.5 and Naïve Bayes. The dataset used includes various attributes relevant to eligibility assessment for social assistance. The C4.5 algorithm is employed to generate an interpretable decision tree, while the Naïve Bayes algorithm is used for probabilistic classification. The results show that Naïve Bayes achieved the highest accuracy at 98%, excelling in processing large datasets more efficiently. Meanwhile, C4.5 achieved an accuracy of 93.33% and offered better interpretability through its decision tree visualization. Both algorithms proved effective in classifying PKH eligibility and can be implemented in social assistance information systems to improve the accuracy and efficiency of the beneficiary selection process. This research concludes that the choice of algorithm should be based on system priorities—whether the focus is on processing speed or result interpretability.
Evaluasi Performa Naive Bayes dan CART pada Klasifikasi Kualitas Tahu Nugraha, Luthfy Akmal; Jupriyanto, Jupriyanto; Haq, Haris Nizhomul; Wijaya, Anderias Eko; Ahmad, Hermansyah Nur
Jurnal Teknologi Informasi dan Komunikasi Vol 18 No 2 (2025): October
Publisher : STMIK Subang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47561/jtik.v18i2.328

Abstract

Untuk tetap bersaing di pasar global, produsen tahu harus memastikan kualitas produk yang konsisten. Pabrik Tahu Sumber Barokah, sebagai pemasok tahu bernutrisi tinggi yang telah lama beroperasi, menghadapi tantangan dalam menjaga kualitas sepanjang proses produksi. Penelitian ini membandingkan kinerja algoritma Naïve Bayes dan Classification and Regression Trees (CART) dalam mengklasifikasikan kualitas tahu menggunakan dataset yang dikumpulkan dari pabrik, yang berisi sampel tahu berkualitas tinggi dan rendah. Metodologi penelitian mencakup identifikasi masalah, pengumpulan data, preprocessing, klasifikasi, validasi, evaluasi, dan penarikan kesimpulan. Cross-validation digunakan untuk validasi model, dan confusion matrix digunakan untuk menilai precision, recall, dan F1-score. Hasil eksperimen menunjukkan bahwa Naïve Bayes mencapai akurasi 91%, precision 100%, recall 85%, dan F1-score 92%, sedangkan CART mencapai akurasi 86%, precision 70%, recall 100%, dan F1-score 82%. Hasil ini menunjukkan bahwa Naïve Bayes lebih cocok untuk mengklasifikasikan kualitas tahu dalam konteks ini.
PERBANDINGAN KINERJA ALGORITMA SVM DAN NAIVE BAYES PADA KLASIFIKASI PRESTASI AKADEMIK SISWA: STUDI KASUS SMAS BPD TOBELO SELATAN Pattiasina, Tiska; Fredriksz, Grace; Luturmas, Join Rachel; Salhuteru, Andrie CH; Matuankotta, Febiola; Nunumete, Laura S; Jupriyanto, Jupriyanto
Jurnal Teknologi Informasi Mura Vol 18 No 1 (2026): Jurnal Teknologi Informasi Mura
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jti.v18i1.2915

Abstract

Students’ academic achievement is an important indicator of the success of the educational process; however, its assessment is often subjective and not yet fully data-driven. Therefore, a systematic analytical approach is required to classify students’ academic achievement objectively and accurately. This study aims to compare the performance of Support Vector Machine (SVM) and Naive Bayes algorithms in classifying the academic achievement of grade III students at SMAS BPD Tobelo Selatan. A data mining approach using classification techniques was applied, involving 17 attributes as predictor variables and two target classes of academic achievement, namely Very Good and Good. Data processing and model evaluation were conducted using the WEKA software, with performance measured through accuracy, precision, recall, and the Area Under the Receiver Operating Characteristic Curve (AUC-ROC). The results indicate that the SVM algorithm achieves the best performance in terms of accuracy, precision, and recall, each reaching 97.78%, while the Naive Bayes algorithm obtains the highest AUC-ROC value of 98.08%. These findings demonstrate that SVM is superior in prediction accuracy, whereas Naive Bayes shows excellent capability in class discrimination. This study is expected to support data-driven academic decision-making in school environments.
SISTEM INFORMASI GEOGRAFIS PARIWISATA BERBASIS WEB MENGGUNAKAN REACT JS DI KABUPATEN SUBANG Ahmad, Hermansyah Nur; Jupriyanto, Jupriyanto
Jurnal Teknologi Informasi Mura Vol 18 No 1 (2026): Jurnal Teknologi Informasi Mura
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jti.v18i1.2917

Abstract

Subang Regency, West Java has significant natural and cultural tourism potential; however, tourism location information is not yet optimally integrated. Scattered information makes it difficult for tourists to obtain accurate location data, descriptions, and access to tourist destinations. This study aims to develop a web-based Geographic Information System (GIS) for tourism using React JS with a full-stack architecture. The system development applies the Agile method, enabling iterative and adaptive development based on user requirements. The system utilizes interactive digital maps based on Leaflet, search and category filtering features, multiple map display modes, and a review and rating feature without user login. The results show that the system provides accurate tourism location information, is easy to access, and offers real-time visit statistics. This system is expected to support regional tourism promotion and assist tourism management in data-driven decision-making.
PERBANDINGAN KINERJA ALGORITMA SVM DAN NAIVE BAYES PADA KLASIFIKASI PRESTASI AKADEMIK SISWA: STUDI KASUS SMAS BPD TOBELO SELATAN Pattiasina, Tiska; Fredriksz, Grace; Luturmas, Join Rachel; Salhuteru, Andrie CH; Matuankotta, Febiola; Nunumete, Laura S; Jupriyanto, Jupriyanto
Jurnal Teknologi Informasi Mura Vol 18 No 1 (2026): Jurnal Teknologi Informasi Mura
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jti.v18i1.2915

Abstract

Students’ academic achievement is an important indicator of the success of the educational process; however, its assessment is often subjective and not yet fully data-driven. Therefore, a systematic analytical approach is required to classify students’ academic achievement objectively and accurately. This study aims to compare the performance of Support Vector Machine (SVM) and Naive Bayes algorithms in classifying the academic achievement of grade III students at SMAS BPD Tobelo Selatan. A data mining approach using classification techniques was applied, involving 17 attributes as predictor variables and two target classes of academic achievement, namely Very Good and Good. Data processing and model evaluation were conducted using the WEKA software, with performance measured through accuracy, precision, recall, and the Area Under the Receiver Operating Characteristic Curve (AUC-ROC). The results indicate that the SVM algorithm achieves the best performance in terms of accuracy, precision, and recall, each reaching 97.78%, while the Naive Bayes algorithm obtains the highest AUC-ROC value of 98.08%. These findings demonstrate that SVM is superior in prediction accuracy, whereas Naive Bayes shows excellent capability in class discrimination. This study is expected to support data-driven academic decision-making in school environments.
SISTEM INFORMASI GEOGRAFIS PARIWISATA BERBASIS WEB MENGGUNAKAN REACT JS DI KABUPATEN SUBANG Ahmad, Hermansyah Nur; Jupriyanto, Jupriyanto
Jurnal Teknologi Informasi Mura Vol 18 No 1 (2026): Jurnal Teknologi Informasi Mura
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jti.v18i1.2917

Abstract

Subang Regency, West Java has significant natural and cultural tourism potential; however, tourism location information is not yet optimally integrated. Scattered information makes it difficult for tourists to obtain accurate location data, descriptions, and access to tourist destinations. This study aims to develop a web-based Geographic Information System (GIS) for tourism using React JS with a full-stack architecture. The system development applies the Agile method, enabling iterative and adaptive development based on user requirements. The system utilizes interactive digital maps based on Leaflet, search and category filtering features, multiple map display modes, and a review and rating feature without user login. The results show that the system provides accurate tourism location information, is easy to access, and offers real-time visit statistics. This system is expected to support regional tourism promotion and assist tourism management in data-driven decision-making.
COMPARATIVE ANALYSIS OF THE K-NEAREST NEIGHBOR ALGORITHM ON VARIOUS INTRUSION DETECTION DATASETS Riyadi , Andri Agung; Amsury , Fachri; Pattiasina , Tiska; Jupriyanto, Jupriyanto
Jurnal Riset Informatika Vol. 4 No. 1 (2021): December 2021
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v4i1.147

Abstract

Because we have flaws in developing security rules, inadequate computer system settings, or software defects, security in computer networks can be vulnerable. Intrusion detection is a computer network security method that detects, prevents, and blocks unauthorized access to confidential information. The IDS method is intended to defend the system and minimize the harm caused by any attack on a computer network that violates computer security policies such as availability, confidentiality, and integrity. Data mining techniques were utilized to extract relevant information from IDS databases. The following are some of the most widely utilized IDS datasets NSL-KDD, 10% KDD, Full KDD, Corrected KDD99, UNSW-NB15, ADFA Windows, Caida, dan UNM have been used to get the accuracy rate using the k-Nearest Neighbors algorithm (k-NN). The latest IDS dataset provided by the Canadian Institute of Cybersecurity contains most of the latest attack scenarios named the CICIDS2017 dataset. Preliminary experiment shows that the approach using the k-NN method on the CICIDS2017 dataset successfully produces the highest average value of intrusion detection accuracy than other IDS datasets.
Development of Indonesian historical heritage comics to enhance elementary school students’ higher-order thinking skills Yulina Ismiyanti; Yunita Sari; Jupriyanto Jupriyanto; Lolita Enfesta
Jurnal Prima Edukasia Vol. 14 No. 2 (2026): May 2026
Publisher : Asosiasi Dosen PGSD dan Dikdas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/jpe.v14i2.94090

Abstract

This study aimed to develop a digital comic based on Indonesian historical heritage and to examine its feasibility, practicality, and effectiveness in enhancing elementary school students’ higher-order thinking skills (HOTS). The research employed a Research and Development (R&D) approach using the ADDIE model, which consisted of analysis, design, development, implementation, and evaluation stages. The participants involved 35 fifth-grade elementary school students selected through purposive sampling. Data were collected through expert validation sheets, teacher and student response questionnaires, and HOTS tests administered through pretests and posttests. The data were analysed using descriptive percentage analysis and paired sample t-tests. The results showed that the developed digital comic was categorized as very feasible based on expert validation, very practical based on teacher and student responses, and effective in significantly improving students’ HOTS as indicated by the statistical difference between pretest and posttest scores. These findings suggested that digital comics integrating Indonesian historical heritage could serve as an innovative and engaging instructional medium for promoting higher-order thinking in elementary social studies learning. The study implied that culturally contextual digital learning media could support HOTS-oriented instruction and contribute to the development of more meaningful and interactive learning environments in elementary education.
Co-Authors Achmad Fauzi Ahmad, Hermansyah Nur Amsury , Fachri Anderias Eko Wijaya Andri Agung Riyadi Apandi, Jamaludin Azhari, Lukman Budilaksono, Sularso Fachri Amsury Fredriksz, Grace Haq, Haris Nizhomul Hernawati Irwansyah Saputra Kodar Udoyono, Kodar Kusuma, Muhammad Romadhona Lolita Enfesta Luturmas, Join Rachel Mahpud, Mahpud Matuankotta, Febiola Maulana, Lutfi Novita Mariana Nugraha, Luthfy Akmal Nunumete, Laura S Pattiasina , Tiska Pattiasina, Tiska Permana, Eka Putri, Cerafine Delna Rian Hermawan Riyadi , Andri Agung Salhuteru, Andrie CH Siallagan, Timbo Faritcan Parlaungan siti nurlela Suwarno, M.Anno Suwartane, I Gede Agus Yulina Ismiyanti Yunita Sari