Article Per Year (5 Year)
p-Index From 2021 - 2026
3.816
P-Index
This Author published in this journals
All Journal Jurnal Teknologi dan Manajemen Informatika Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) SMATIKA Briliant: Jurnal Riset dan Konseptual Jurnal Ilmiah Universitas Batanghari Jambi JUSIM (Jurnal Sistem Informasi Musirawas) BERNAS: Jurnal Pengabdian Kepada Masyarakat Rambideun : Jurnal Pengabdian Kepada Masyarakat Computer Science (CO-SCIENCE) Seminar Nasional Hasil Riset dan Pengabdian (SNHRP) PROSISKO : Jurnal Pengembangan Riset dan observasi Rekayasa Sistem Komputer Digital Transformation Technology (Digitech) Prosiding Seminar Nasional Pengabdian Masyarakat Journal of Information Systems Management and Digital Business Jurnal Informatika Polinema (JIP) Smatika Jurnal : STIKI Informatika Jurnal
Fandi Yulian Pamuji
Fakultas Teknologi Informasi, Universitas Merdeka Malang
Religion Agriculture, Biological Sciences & Forestry Arts Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Public Health Social Sciences Veterinary Other

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

Found 26 Documents
Search

 1   2   3 
Evaluasi Metode Single Exponential Smoothing dan Long Short-Term Memory pada Prediksi Saham Bank BRI Muhaimin, M. Rizal; Pamuji, Fandi Yulian
Digital Transformation Technology Vol. 4 No. 2 (2024): Periode September 2024
Publisher : Information Technology and Science(ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/digitech.v4i2.4948

Abstract

Penelitian ini membahas perbandingan kinerja metode peramalan harga saham Bank BRI (BBRI) menggunakan dua pendekatan kuantitatif, yaitu metode Single Exponential Smoothing (SES) dan Long Short-Term Memory (LSTM) yang dioptimasi dengan GridSearchCV. Data historis harga saham BBRI dari periode 2019 hingga 2024 yang diperoleh dari Yahoo Finance digunakan sebagai data utama. Metode SES dipilih karena sederhana dan efektif dalam menangani data deret waktu, sedangkan metode LSTM dipilih karena kemampuannya dalam menangkap pola kompleks dan ketergantungan temporal pada data saham. GridSearchCV digunakan untuk mengoptimalkan parameter LSTM agar menghasilkan akurasi peramalan yang lebih baik. Hasil penelitian menunjukkan bahwa metode LSTM yang dioptimasi dengan GridSearchCV secara konsisten memberikan performa prediksi yang lebih akurat dibandingkan dengan metode SES, yang ditunjukkan melalui nilai error yang lebih rendah, seperti Mean Absolute Error (MAE) dan Root Mean Square Error (RMSE). Dengan demikian, metode LSTM yang dioptimasi dengan GridSearchCV lebih efektif dalam memodelkan data saham dengan karakteristik jangka panjang seperti harga saham BBRI. Hasil penelitian ini diharapkan dapat memberikan kontribusi signifikan dalam pengembangan strategi peramalan dan investasi berbasis data historis.
Manajemen Akun Pengguna Berbasis Roaming Profile untuk Memperkuat Perlindungan Data di Laboratorium Komputer Aditya Wahyu Firmansyah; Ronald David Marcus; Asri Samsiar Ilmananda; Fandi Yulian Pamuji
SMATIKA JURNAL : STIKI Informatika Jurnal Vol 12 No 02 (2022): SMATIKA Jurnal : STIKI Informatika Jurnal
Publisher : LPPM UBHINUS MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/smatika.v12i02.688

Abstract

Roaming profile is a feature of managing user’s profile centrally through the active directory on Windows Server, which is useful to redirects all application settings and data storage to the server, so that users can access their profiles on any computer on the network. Compared to the local profile that relies on a local hard drive, a roaming profile is more suitable for user account management in a computer laboratory, because students use PCs interchangeably and move from one PC to another. This study aims to shift the local profile setting which was previously still used in the computer laboratory of the Faculty of Information Technology, Universitas Merdeka Malang, to a roaming profile-based setting. This research is expected to present a solution to make it easier for students to access their own profiles, while providing protection for the files they store. The method of this research is based on a qualitative and experimental approach. The results showed that the implementation of an active directory with a roaming profile was able to improve the quality of service in the computer laboratory, as well as increase security and convenience for students.
PENERAPAN DIGITALISASI DALAM PENGEMBANGAN POTENSI DAN FASILITAS UMUM DI DESA PANDANLANDUNG Fandi Yulian Pamuji; Istisfaqo Izzafiu Rohmah; Irma Yuniarti
Seminar Nasional Hasil Riset dan Pengabdian Vol. 7 (2025): Seminar Nasional Hasil Riset dan Pengabdian (SNHRP) Ke 7 Tahun 2025
Publisher : LPPM Universitas PGRI Adi Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Desa Pandanlandung di Kabupaten Malang memiliki beragam potensi sumber daya alam, sosial, dan budaya yang belum terdokumentasi dan terpromosikan secara optimal. Kegiatan Pengabdian kepada Masyarakat Universitas Merdeka Malang ini bertujuan untuk memanfaatkan teknologi digital dalam mengembangkan potensi serta menyediakan informasi fasilitas umum desa. Metode pelaksanaan meliputi survei lapangan, wawancara dengan perangkat desa dan tokoh masyarakat, serta pengambilan data visual berupa foto, video, dan audio. Hasil kegiatan berupa video profil desa yang menampilkan keunikan potensi lokal serta peta digital fasilitas umum yang berfungsi sebagai panduan bagi masyarakat dan pengunjung. Implementasi digitalisasi terbukti meningkatkan visibilitas desa, memperluas akses informasi, dan mempermudah promosi kepada pihak luar. Selain itu, kegiatan ini berpotensi menarik minat wisatawan dan investor, sehingga mendukung peningkatan ekonomi lokal. Rekomendasi yang dihasilkan mencakup pengembangan platform digital desa secara berkelanjutan dan pelatihan bagi masyarakat agar mampu mengelola konten digital secara mandiri. Program ini menunjukkan bahwa digitalisasi dapat menjadi strategi efektif dalam memperkuat identitas dan daya saing desa.
Komparasi Metode SMOTE-Tomek dan SMOTE-ENN untuk Mengatasi Data Imbalanced Fandi Yulian Pamuji; Mohammad Dwi Irfan Affandi; Andriyan Rizki Jatmiko
Jurnal Informatika Polinema Vol. 12 No. 3 (2026): Vol. 12 No. 3 (2026)
Publisher : UPT P2M State Polytechnic of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jip.v12i3.9550

Abstract

Perkembangan teknologi informasi dan data analisis saat ini mendorong meningkatnya pemanfaatan machine learning dalam berbagai bidang. Namun, salah satu permasalahan umum yang sering muncul dalam penerapan machine learning adalah kondisi data tidak seimbang (imbalanced data) yaitu ketidakseimbangan jumlah data antar kelas, di mana kelas mayoritas jauh lebih dominan dibandingkan kelas minoritas. Untuk mengatasi permasalahan dataset tidak seimbang adalah dengan menyeimbangkan distribusi kelas tidak seragam di antara kelas-kelas dengan komparasi menggunakan metode SMOTE-Tomek dan SMOTE-ENN supaya jumlahnya seimbang dari kelas mayoritas (negatif) maupun kelas minoritas (positif). Berdasarkan hasil eksperimen yang telah dilakukan dari penelitian ini yaitu bahwa pengujian metode SMOTE-Tomek dengan metode klasifikasi mampu menangani jumlah kelas mayoritas (negatif) dan kelas minoritas (positif) pada data tidak seimbang dengan menghasilkan nilai MCC dan G-mean mencapai kinerja prediksi yang lebih besar dibandingkan dengan menggunakan metode klasifikasi saja maupun menggunakan Metode SMOTE-ENN. Kemudian untuk dataset Binary nilai MCC dan G-mean yang paling tinggi menggunakan SMOTE-ENN + Random Forest dengan nilai tertinggi MCC = 0.99 dan nilai G-mean = 0.99 dari nilai MCC dan G-mean diatas akurasinya sudah bagus karena nilai MCC dan G-mean yang mendekati 1 menunjukkan bahwa model memiliki performa klasifikasi yang sangat baik dalam menangani data tidak seimbang dengan menggunakan Metode SMOTE-Tomek + Random Forest dapat mencapai kinerja prediksi yang lebih besar untuk menangani dataset tidak seimbang Binary. Hal tersebut menunjukkan bahwa proses penanganan terhadap distribusi kelas yang tidak seimbang pada tahap preprocessing data memberikan pengaruh terhadap nilai akurasi MCC maupun G-mean metode SMOTE-Tomek + Random Forest.
Performance of Distance Metrics in SMOTE for Binary Imbalanced Classification Fandi Yulian Pamuji; Luthfi Indana; Mohammad Dwi Irfan Affandi
Computer Science (CO-SCIENCE) Vol. 6 No. 2 (2026): July 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i2.12543

Abstract

Skewed class distribution continues to be one of the central obstacles in binary classification, since a learning model tends to lean toward the dominant class and consequently overlooks observations belonging to the under-represented class. The purpose of this research is to examine how the choice of distance measure inside SMOTE, specifically Euclidean, Manhattan, Chebyshev, and Hamming, affects predictive quality on imbalanced binary data. Ten publicly available binary datasets drawn from the KEEL repository, whose imbalance ratios span from 1.86 up to 15.80, were used in the experiment. Every dataset was preprocessed and partitioned into 80% for training and 20% for testing; oversampling with SMOTE was carried out on the training portion only, after which four learners, namely Naive Bayes, Decision Tree, Logistic Regression, and k-Nearest Neighbor, were assessed. Model quality was judged through the Matthews Correlation Coefficient (MCC) together with the G-Mean, as these two indicators describe imbalanced performance more faithfully than plain accuracy. The comparison revealed that pairing Euclidean-based SMOTE with Logistic Regression yielded the strongest average scores (MCC = 0.72; G-Mean = 0.79); Manhattan-based SMOTE reached its top MCC again with Logistic Regression (MCC = 0.68) and its top G-Mean with the Decision Tree (G-Mean = 0.79); Chebyshev-based SMOTE delivered the best overall combination together with the Decision Tree (MCC = 0.74; G-Mean = 0.84); and Hamming-based SMOTE performed best alongside Logistic Regression (MCC = 0.73; G-Mean = 0.81). Taken together, these outcomes suggest that the distance function chosen within SMOTE shapes the quality of the generated synthetic points and, in turn, the behavior of the trained classifier.
Gaussian Based-SMOTE Method for Handling Imbalanced Small Datasets Muhammad Misdram; Edi Noersasongko; Purwanto Purwanto; Muljono Muljono; Fandi Yulian Pamuji
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 4 (2023): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i4.26881

Abstract

The problem of dataset imbalance needs special handling, because it often creates obstacles to the classification process. A very important problem in classification is to overcome a decrease in classification performance. There have been many published researches on the topic of overcoming dataset imbalances, but the results are still unsatisfactory. This is proven by the results of the average accuracy increase which is still not significant. There are several common methods that can be used to deal with dataset imbalances. For example, oversampling, undersampling, Synthetic Minority Oversampling Technique (SMOTE), Borderline-SMOTE, Adasyn, Cluster-SMOTE methods. These methods in testing the results of the classification accuracy average are still relatively low. In this research the selected dataset is a medical dataset which is classified as a small dataset of less than 200 records. The proposed method is Gaussian Based-SMOTE which is expected to work in a normal distribution and can determine excess samples for minority classes. The Gaussian Based-SMOTE method is a contribution of this research and can produce better accuracy than the previous research. The way the Gaussian Based-SMOTE method works is to start by determining the random location of synthesis candidates, determining the Gaussian distribution. The results of these two methods are substituted to produce perfect synthetic values. Generated synthetic values are combined with SMOTE sampling of the majority data from the training data, produce balanced data. The result of the balanced data classification trial from the influence of the Gaussian Based SMOTE result in a significant increase in accuracy values of 3% on average.
Co-Authors Aditya Wahyu Firmansyah Agrippina, Annisya Parera Agus Suryanto Andriyan Rizki Jatmiko Anggelika Royinda Annisya Parera Agrippina Asri Samsiar Ilmananda Edi Noersasongko Edi Subiyantoro Endarchepy, Azallea Giska Firnanda Al-Islama Achyunda Putra Gabriella, Widea Hudan Eka Rosyadi Indana, Luthfi Irma Yuniarti Istisfaqo Izzafiu Rohmah Marcus, Ronald David Mardiana Andarwati Mohammad Dwi Irfan Affandi Muhaimin, M. Rizal Muhammad Misdram Muljono, - Muslikh, Ahmad Rofiqul Purwanto Purwanto Rahmad Anjar Saputro Ramadhan, Viry Puspaning Ronald David Marcus Ronald David Marcus Sari, Arum Ganda Sephia Dwi Arma Putri Sherly Fauziyah Syaharani Swalaganata, Galandaru Tiara, Tiara Viry Puspaning Ramadhan Wenny, Rizca Widea Gabriella Wiranata, Ardy Bima