Article Per Year (5 Year)
p-Index From 2021 - 2026
3.939
P-Index
This Author published in this journals
All Journal Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Jurnal Sistem Komputer Jurnal Ilmiah Kursor Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Edukasi dan Penelitian Informatika (JEPIN) JUITA : Jurnal Informatika Journal of Information Systems Engineering and Business Intelligence ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika JOIN (Jurnal Online Informatika) JOIV : International Journal on Informatics Visualization Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Jurnal Informatika Jurnal ULTIMATICS Journal of Computer Science and Informatics Engineering (J-Cosine) MIND (Multimedia Artificial Intelligent Networking Database) Journal KOMPUTA : Jurnal Ilmiah Komputer dan Informatika Jurnal Abdimas Berdaya : Jurnal Pembelajaran, Pemberdayaan dan Pengabdian Masyarakat Journal of Applied Data Sciences Jurnal Publikasi Teknik Informatika (JUPTI) Jurnal Tera Scientific Journal of Informatics IPSSJ JuTISI (Jurnal Teknik Informatika dan Sistem Informasi)
Jasman Pardede
Program Studi Informatika, Institut Teknologi Nasional Bandung
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Astronomy Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Public Health Social Sciences Transportation Veterinary Other

Published : 41 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 41 Documents
Search

 1   2   3   4   5 
Identifikasi Ujaran Kebencian Pada Sosial Media Bahasa Inggris Menggunakan Recursive Neural Network Pardede, Jasman; Alfyansyah, Rangga
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 13 No 1 (2024): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputa.v13i1.10783

Abstract

Penyebaran ujaran kebencian pada sosial media telah menjadi masalah serius karena menciptakan serangkaian konflik ras, etnis, orientasi seksual, kebangsaan, dan agama. Penelitian ini menggali dari unggahan ujaran kebencian di media sosial. Ujaran kebencian semakin meningkat di media sosial yang merendahkan individu atau kelompok banyak ditemukan. Mengidentifikasi ujaran kebencian secara tepat menjadi penting untuk menganalisis sentimen publik dari kelompok pengguna terhadap kelompok lain serta mencegah kegiatan yang tidak diinginkan. Dengan mengidentifikasi akar penyebabnya, pihak-pihak yang berwenang dan platform-platform digital dapat mengambil tindakan yang lebih efektif dalam memitigasi dampak negatifnya dan melindungi masyarakat dari ancaman yang mungkin timbul. Algoritma seperti Support Vector Machine dan Deep Neural Networks, terutama Recursive Neural Network, dapat mengidentifikasi ujaran kebencian. Dalam penelitian ini menerapkan Recursive Neural Network untuk mengidentifikasi ujaran kebencian. Performa sistem ini diukur berdasarkan nilai precision, recall, accuracy, dan F-Measure. Hasil eksperimen yang dilakukan terhadap data ujaran kebencian diperoleh nilai rata-rata precision, recall, accuracy, dan F-Measure masing-masing sebesar 0.78, 0.74, 0.76, dan 0.76. Hasil tersebut menunjukkan bahwa Recursive Neural Networks yang diusulkan memiliki performa yang cukup baik.
IMAGE CAPTIONING USING TRANSFORMER WITH IMAGE FEATURE EXTRACTION BY XCEPTION AND INCEPTION-V3 Pardede, Jasman; Fandi
Jurnal Ilmiah Kursor Vol. 12 No. 3 (2024)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v12i3.376

Abstract

Image captioning is a task in image processing that involves creating text descriptions that can describe the image content. The formation of the image captioning system model is influenced by image interpretation related to the given image caption. Image interpretation is influenced by the feature extraction used. This research proposes feature extraction with Xception and Inception-V3 by generating an image captioning model using Transformer. Model performance is measured based on BLUE and METEOR values. Based on the results of research conducted on the Flickr8k Dataset, it shows that the best model performance is using Xception feature extraction and batch_size = 256. The image captioning performance of Xception feature extraction for BLUE-1, BLUE-2, BLUE-3, BLUE-4, and METEOR when compared with Inception-V3 achieves increasing of 13.15%, 18.03%, 18.71%, 27.27%, and 15.43% respectively. The performance for Xception feature extraction with batch_size = 256 compared with batch_size = 128, increasing BLUE-1, BLUE-2, BLUE-3, BLUE-4, and METEOR namely 19.81%, 41.84%, 52.23%, 53.14%, and 31.56% respectively.
Prediksi Jumlah Target dan Realisasi Wajib Pajak Atas PBB "“ P2 Menggunakan Multi Regression, Regression Lasso, dan PCR Pardede, Jasman; Ekklesia, Maleakhi
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 10, No 1 (2024): Volume 10 No 1
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v10i1.68890

Abstract

Perubahan besaran Pajak Bumi dan Bangunan memberikan dampak bagi beberapa sektor maupun masyarakat di Kota Bandung, karena perubahan yang cukup signifikan dalam besaran Pajak Bumi dan Bangunan ini memberikan pengaruh pada kesadaran dan juga kepedulian masyarakat dalam membayar pajak. Terdapat beberapa penggunaan machine learning dalam penentuan pajak ini dimana salah satunya adalah dengan memprediksikan sebuah besaran Target dan Realisasi pada Pajak Bumi Bangunan, sehingga dilakukan sebuah penelitian dengan membandingkan metode Multi Regression, Regression Lasso, dan PCR (Principle Component Regression) untuk menentukan jumlah prediksi terbaik pada Target dan Realisasi penerimaan Pajak Bumi dan Bangunan di Kota Bandung. Hasil pengujian yang telah dilakukan, didapatkan bahwa Regression Lasso memiliki nilai keakuratan prediksi terbaik sebesar 79.08%. Hasil tersebut diakibatkan karena Regression Lasso dapat mengestimasi parameter, mengatasi permasalah multicolinearity yang terjadi pada data yang digunakan dan menyeleksi variabel yang ada untuk mendapatkan nilai keakuratan prediksi terbaik. Sehingga dapat disimpulkan bahwa terdapat pengaruh positif pada variabel Ketetapan, Target, dan Realisasi yang saling berkaitan. Hal tersebut saling mempengaruhi besarannya, dimana ketetapan mempengaruhi jumlah target, dan jumlah target mempengaruhi jumlah realisasi pada model yang terbentuk, dan proses pre "“ processing membuat model Regression Lasso ini menjadi lebih baik.
Face Race Classification using ResNet-152 and DenseNet- 121 PARDEDE, JASMAN; KLEB, SYAFIQ SALIM
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 3: Published July 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i3.798

Abstract

ABSTRAKPenelitian ini bertujuan untuk membandingkan hasil kinerja arsitektur ResNet-152 dan DenseNet-121 dalam mengklasifikasikan wajah berdasarkan ras. Ras yang diklasifikasikan terdiri dari 4 kelas: Putih, Hitam, India, dan Asia. Penelitian ini menggunakan parameter batch_size 32, optimizer, dan learning rate untuk meningkatkan kinerja model. Dua optimizer yang dibandingkan, yaitu Adam Optimizer dan Nadam Optimizer. Nilai learning rate yang dipertimbangkan adalah 0,0001 dan 0,001. Berdasarkan hasil percobaan klasifikasi wajah berdasarkan ras, baik arsitektur ResNet-152 maupun DenseNet-121 mencapai kinerja akurasi dan recall yang sama yaitu 0,788. Kinerja terbaik untuk presisi dan f1-score adalah ResNet-152. ResNet-152 memiliki presisi dan f1-score yang lebih baik masingmasing sebesar 0,376% dan 0,252%, jika dibandingkan dengan DenseNet-121. Oleh karena itu, ResNet-152 memiliki kinerja terbaik jika dibandingkan DenseNet-121 dalam klasifikasi wajah berbasis ras.Kata kunci: kinerja, ResNet-152, DenseNet-121, wajah, klasifikasi ABSTRACTThis study aims to compare the performance results of the ResNet-152 and DenseNet-121 architectures for classifying faces based on race. The classified race consists of 4 classes i.e.: White, Black, Indian, and Asian. The study used a batch size of 32, an optimizer, and a learning rate to improve model formation performance. Two optimizers are being compared, namely Adam Optimizer and Nadam Optimizer. The learning rate values considered are 0.0001 and 0.001. Based on the results of facial classification experiments based on race, both the ResNet-152 and DenseNet-121 architectures achieve the same accuracy and recall performance, namely 0.788. The best performance for precision and f1-score is ResNet-152. The ResNet-152 has better Precision and F1-Score of 0.376% and 0.252% respectively, in case it’s compared to DenseNet-121. Hence, it can be inferred that ResNet-152 surpasses DenseNet-121 in delivering superior performance outcomes for racial-based facial classification.Keywords: performance, ResNet-152, DenseNet-121, face, classification
Perbandingan Algoritma Stemming Porter, Sastrawi, Idris, Dan Arifin & Setiono Pada Dokumen Teks Bahasa Indonesia Pardede, Jasman; Darmawan, Dicky
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 12 No 1: Februari 2025
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2025128860

Abstract

Information Retrieval (IR) memiliki fungsi untuk memisahkan dokumen-dokumen yang relevan dari sekumpulan dokumen yang ada. Terdapat sebuah proses penting pada IR, yaitu stemming. Stemming adalah proses untuk mengurangi kata-kata berimbuhan menjadi bentuk kata dasar. Pada beberapa penelitian sering menggunakan stemming yang berbeda-beda, bahkan ada penelitian yang telah mencoba membandingkan dua algoritma stemming. Sedangkan pada penelitian ini membandingkan empat algoritma stemming. Tujuan penelitian ini adalah untuk mengungkapkan pengaruh stemming pada IR menggunakan dokumen bahasa Indonesia. Algoritma stemming yang digunakan pada penelitian ini adalah Porter, Sastrawi, Idris, dan Arifin Setiono. Kinerja masing-masing algoritma stemming diukur berdasarkan nilai presisi dan kebutuhan waktu. Terdapat 120 dokumen berbahasa Indonesia yang digunakan untuk mengukur kinerja masing-masing algoritma. Berdasarkan hasil eksperimen diperoleh bahwa kinerja terbaik untuk presisi adalah stemming Sastrawi. Sedangkan kinerja terbaik dari segi kebutuhan waktu adalah stemming Arifin Setiono. Kinerja presisi masing-masing stemming Sastrawi, Arifin Setiono, Porter, dan Idris adalah 70.3%, 55.8%, 49.9%, dan 32.2%. Sedangkan kinerja kebutuhan waktu rata-rata masing-masing stemming Arifin Setiono, Sastrawi, Idris, dan Porter adalah sebesar 0,123 detik, 160.1 detik, 168.8 detik, dan 188.4 detik.   Abstract Information Retrieval (IR) has the function of separating relevant documents from a set of existing documents. An important process in IR is stemming. Stemming is the process of reducing affixed words into basic word forms. In several studies, different stemming is often used, and even studies have tried to compare two stemming algorithms. In this study, four stemming algorithms were compared. The purpose of this study was to reveal the effect of stemming on IR using Indonesian language documents. The stemming algorithms used in this study were Porter, Sastrawi, Idris, and Arifin Setiono. The performance of each stemming algorithm was measured based on the accuracy value and time requirements. There were 120 Indonesian language documents used to measure the performance of each algorithm. Based on the experimental results, it was obtained that the best performance for precision was the Sastrawi stemming. While the best performance in terms of time requirements was the Arifin Setiono stemming. The precision performance of each stemming of Sastrawi, Arifin Setiono, Porter, and Idris is 70.3%, 55.8%, 49.9%, and 32.2%. Meanwhile, the average time requirement performance of each stemming of Arifin Setiono, Sastrawi, Idris, and Porter is 0.123 sec, 160.1 sec, 168.8 sec, and 188.4 sec.
Sistem Informasi Gereja Efata Batujajar Untuk Pengelolaan Persembahan Donasi, Dan Konseling Pardede, Jasman; Putra Riyanto, Aquila; Alpriatna Malik, Yuzzar; Luthfi Athallah, Rifqi; Satria Darmawan, Kevin; Fadhillah Prasetyo, Rachma
Jurnal Abdimas Berdaya : Jurnal Pembelajaran, Pemberdayaan dan Pengabdian Masyarakat Vol 8, No 1 (2025): Jurnal Abdimas Berdaya
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30736/jab.v8i1.1048

Abstract

IMPLEMENTASI “PRINCIPAL COMPONENT ANALYSIS - SCALE INVARIANT FEATURE TRANSFORM” PADA CONTENT BASED IMAGE RETRIEVAL Jasman Pardede; Dina Budhi Utami; adlan chosyiyar rochman
Jurnal Teknik Informatika dan Sistem Informasi Vol 3 No 3 (2017): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v3i3.696

Abstract

Content based image retrieval (CBIR) adalah teknik pencarian gambar dari database gambar besar dengan menganalisis fitur-fiturnya. Fiturnya bisa berupa warna, tekstur, bentuk, dll. Metode yang digunakan dalam penelitian ini adalah kombinasi antara Principal Component Analysist dan Scale Invariant Feature Transform (metode PCA-SIFT). Metode SIFT digunakan untuk mendeteksi dan menggambarkan fitur lokal sedangkan PCA digunakan untuk mengurangi dimensi gambar. Nilai dimensi menjadi masalah tersendiri dalam perhitungan. Metode PCA diterapkan untuk proyeksi dimensi tinggi dengan dimensi gambar rendah. Sebelumnya PCA dan PCA saja sudah sering diaplikasikan untuk pengambilan citra digital. Hasil pencarian diperoleh dengan membandingkan deskriptor titik kunci dari query ke dataset. Hasil pencarian citra menggunakan dataset Wang, menunjukkan bahwa CBIR yang menggunakan metode PCA-SIFT dapat mencapai Precission  90,00% dan recall 18,00%.
Implementasi DenseNet Untuk Mengidentifikasi Kanker Kulit Melanoma Jasman Pardede; Dwi Adi Lenggana Putra
Jurnal Teknik Informatika dan Sistem Informasi Vol 6 No 3 (2020): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v6i3.2814

Abstract

Skin is a part of a human body that covers the entire body and protect the lower layer from direct sunlight and another microorganism. Because of that, skin cells are always changing and could be changed because of genetic mutation that causes skin cancer. In general, skin cancer is divided into three groups, namely : skin cancer Basal cell carcinoma, skin cancer Squamous cell carcinoma, and skin cancer Melanoma. Melanoma skin cancer is caused by abnormal growth in melanocyte cells. Several methods are proposed to predict Melanoma skin cancer using ResNet, LeNet, and Support Vector Machine. System performance is measured based on the value of accuracy, precision, recall, and f-measure. This experiment is conducted using a Melanoma skin cancer dataset that obtained the average value in terms of accuracy, precision, recall, and f-measure are 0.94, 0.95, 0.92, and 0.94 respectively. Based on that result, the proposed DenseNet121 performs better with 0.94 accuracy, compared with ResNet, LeNet, and Support Vector Machine method. Keywords— Convolutional Neural Network; Image Classification; Melanoma Classification; DenseNet121.
The Effect of Hyperparameters on Faster R-CNN in Face Recognition Systems Pardede, Jasman; Rijal, Khairul
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 3 (2025): June 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i3.6405

Abstract

Face recognition is one of the main challenges in the development of computer vision technology. This study aims to develop a face recognition system using a Faster R-CNN architecture, optimized through hyperparameter tuning. This research utilizes the "Face Recognition Dataset" from Kaggle, which comprises 2,564 face images across 31 classes. The development process involves creating bounding boxes using the LabelImg application and implementing the Grid Search method. The Grid Search is applied with predefined hyperparameter combinations (3 epochs [10, 25, and 50] × 3 learning rates [0.001, 0.0001, and 0.00001] × 3 optimizers [SGD, Adam, and RMS], resulting in 27 models). The evaluation metrics used were accuracy, precision, recall, and F1-score. The experimental results show that the selection of hyperparameters significantly affects the model performance. Based on the experimental results, the combination of the learning rate 0.00001, 50 epochs, and Adam optimizer yielded the highest accuracy and improvement of 8.33% compared to the baseline model. The results indicate that hyperparameter optimization enhances the ability of the model to recognize faces. Compared to conventional models, a Faster R-CNN performs better in detecting faces more accurately. Future research could further enhance the face recognition efficiency and accuracy by exploring other deep learning architectures and more advanced hyperparameter optimization techniques.
Comparison of Cosine Similarity, Rabin-Karp, and Levenshtein Distance Algorithms for Plagiarism Detection in Document Pardede, Jasman; Yudistira, Agil
ULTIMATICS Vol 17 No 1 (2025): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v17i1.3867

Abstract

Prevention and detection of plagiarism are crucial. There are several algorithms that can be used to detect plagiarism in documents, including the Cosine Similarity, Rabin-Karp, Levenshtein Distance, Hamming Distance, Euclidean Distance, Edit Distance, Ratcliff/Obershelp, etc. Based on the literature review from previous research, three best algorithms were identified: Cosine Similarity, Rabin-Karp, and Levenshtein Distance. However, there has been no study analyzing the comparison of these three algorithms. Therefore, this study will compare the performance of each algorithm and determine the best algorithm for plagiarism detection in documents based on similarity scores and execution time. The research objects use a sample of documents consisting of titles and abstracts from Indonesian-language informatics journals. Cosine Similarity algorithm is superior to others for plagiarism detection in documents, as it produces the highest average similarity score with a relatively fast execution time. The similarity values of Cosine Similarity, Rabin-Karp with 4 k-grams, and Levenshtein Distance are 48.80%, 47.13%, 20.61%, respectively. The average execution time of Cosine Similarity, Rabin-Karp with 4 k-grams, and Levenshtein Distance are 0.22 s, 0.45 s, and 39.15 s, respectively
Co-Authors Abdullah, Syadda adlan chosyiyar rochman Adli, Muhammad Arkan Afis Siswantini Ahmada, Marsa Akbar, Saiful Alfyansyah, Rangga Alpriatna Malik, Yuzzar Amal M, Ichlasul Amal, Irfan Asep Nana Hermana B, Mira Musrini Benhard Sitohang Bernovaldy, Muhammad Akbar Chazar, Chalifa Daffa A R, Muhammad Darmawan, Dicky Dewi, Renita Dika Prasetia Pamungkas Dina Budhi Utami Dina Budhi Utami, Dina Budhi Dwi Adi Lenggana Putra Dwianto, Rio Ekklesia, Maleakhi Fadhillah Prasetyo, Rachma Fandi Galih Swarghani HENDRI HARDIANSAH Hermana, Asep Nana Hilwa Athifah Ilyas Al-Fadhlih, Muhammad KLEB, SYAFIQ SALIM Luqman Yudhianto Luthfi Athallah, Rifqi Marisa Premitasari, Marisa Miftahuddin, Yusup Milenio, Rizka Milandga Mira Musrini B Muhammad Akbar Bernovaldy MUHAMMAD FAUZAN RASPATI Muhammad Ichwan MUHAMMAD RIFALDI BADU Nurhasanah, Youllia Indrawaty Nurrohmah, Desita Pakpahan, Ivan Prameswari, Anindya Pratama, Muhamad Rifki Putra Riyanto, Aquila Putra, Dwi Adi Lenggana Putri Setyaningrum, Anisa Raka Gemi Ibrahim Raka Satria, Marius Rawosi, Muhammad Fadlansyah Zikri Akhiruddin RAYYAN RAYYAN Renita Dewi Ridhwana M, Fadhlan Rijal, Khairul rochman, adlan chosyiyar Satria Darmawan, Kevin Setyaningrum, Anisa Putri Siswantini, Afis Swarghani, Galih Ungkawa, U. Uung Ungkawa Yudhianto, Luqman Yudistira, Agil Yunastrian, Kurniandha Yusuf S, Muhammad