Article Per Year (5 Year)
p-Index From 2021 - 2026
2.735
P-Index
This Author published in this journals
All Journal JOIV : International Journal on Informatics Visualization Digital Zone: Jurnal Teknologi Informasi dan Komunikasi Diklat Review : Jurnal manajemen pendidikan dan pelatihan Innovation in Research of Informatics (INNOVATICS) Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Mejuajua J-COSCIS : Journal of Computer Science Community Service Technologica The Indonesian Journal of Computer Science
Toresa, Dafwen
Unknown Affiliation
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Languange, Linguistic, Communication & Media Library & Information Science Public Health Social Sciences Other

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
PENINGKATAN KOMPETENSI SISWA KELAS XI OTKP SMK MIGAS INOVASI RIAU MELALUI PELATIHAN MENGETIK CEPAT DAN AKRAT Toresa, Dafwen; Fanawiza; Muzdalifah, Indah
J-COSCIS : Journal of Computer Science Community Service Vol. 5 No. 2 (2025): J-COSCIS : Journal of Computer Science Community Service
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/wspbv316

Abstract

Peningkatan kemampuan bagi siswa haruslah selalu dilakukan agar kompetensi dapat dicapai dan memperbesar peluang kesempatan kerja. Hal ini juga dilakukan pada siswa kelas XI jurusan Otomatisasi dan Tata Kelola Perkantoran (OTKP) SMK Migas Inovasi Riau yang beralamat di jalan Garuda Sakti kecamatan binawidya panam. Sebagai calon administrasor perkantoran baik pemerintahan maupun perkantoran swasta, siswa jurusan OTKP harus mampu bekerja cekatan dan cepat dalam menyelesaikan administrasi dalam bentuk surat menyurat. Cekatan dalam melakukan penyelesaian surat menyurat tidak lepas dari kemampuan mengetik yang cepat dan akurat. Oleh kareana itu sebagai pelajar yang sudah menjalani Pendidikan 1 tahun lebih dan sudah melaksanakan Praktek Kerja Lapangan (PKL) sangat perlu untuk meningkatkan kompetensi mengetik cepat. Salah satu cara untuk bisa mencapai tujuan tersebut salah satunya dengan menggunakan apliaksi mengetik cepat yang banyak tersedia dan gratis di internet. Salah satu aplikasi mengetik cepat adalah Rapid Typing 5.4 yang dikemas dengan tampilan menarik dan fitur lengkap, mulai mengetik huruf sampai mengetik kalimat. Dari 15 orang peserta pelatihan diukur hasil tes berupa jumlah yang diketik permenit (CPM), persentase akurasi karakter yang diketik (AC) dan kesalahan pengetikan karakter (EC) terjadi peningkatan sebelum diberikan pelatihan (Pre-test) dengan setelah diberikan pelatihan mengetik cepat (Pos-test). Rata rata peserta, CPM terjadi peningkatan yaitu pre-test 100 karakter dan post-tes 146 karakter, AC meningkat yaitu pre-tes 70% dan post-tes 84% dan EC menurun yaitu saat pre-tes 38% dan pada post-tes 18%
Evaluating Contextual Embedding Models for Multi-Label PICO Classification in Heart Disease: Addressing the Intervention - Comparison Bottleneck Taslim, Taslim; Handayani, Susi; Walhidayat, Walhidayat; Toresa, Dafwen
Digital Zone: Jurnal Teknologi Informasi dan Komunikasi Vol. 16 No. 2 (2025): Digital Zone: Jurnal Teknologi Informasi dan Komunikasi
Publisher : Publisher: Fakultas Ilmu Komputer, Institution: Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/digitalzone.v16i2.28375

Abstract

Accurate extraction of Population, Intervention, Comparison, and Outcome (PICO) elements from clinical texts is essential for supporting evidence-based medicine, particularly in cardiology where clinical data complexity presents significant challenges. This study investigates the comparative effectiveness of three contextual embedding models—BioBERT, PubMedBERT, and SciBERT—integrated with a Bidirectional Long Short-Term Memory (BiLSTM) architecture for multi-label PICO element classification on heart disease datasets. The experimental framework involved pre-processing clinical sentences, transforming them into contextual embeddings, and classifying PICO elements using BiLSTM-based sequence modeling. Evaluation was conducted using five key metrics: accuracy, precision, recall, F1-score, and hamming loss, supplemented by confusion matrix analysis for each PICO element. Results demonstrate that the BioBERT-BiLSTM model achieved superior performance, with an accuracy of 73.89%, F1-score of 78.54%, precision of 81.60%, and recall of 76.64%. PubMedBERT-BiLSTM exhibited the highest precision (84.12%) but lower recall, while SciBERT-BiLSTM produced slightly inferior results overall. These findings confirm the importance of using domain-specific embeddings, particularly models pre-trained on biomedical corpora, to improve classification accuracy in specialized clinical text tasks. This study concludes that the BioBERT-BiLSTM combination offers a reliable approach for automated PICO element extraction in the cardiology domain, contributing to the development of more accurate and efficient clinical decision-support systems
PELATIHAN MENGETIK CEPAT DAN AKURAT MENGGUNAKAN APLIKASI RAPID TYPING UNTUK SISWA KELAS X SMK MIGAS INOVASI RIAU Toresa, Dafwen; Fanawiza; Muzdalifah, Indah
J-COSCIS : Journal of Computer Science Community Service Vol. 4 No. 2 (2024): J-COSCIS : Journal of Computer Science Community Service
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/jcoscis.v4i2.19127

Abstract

Pada kegiatan ini peserta didik yang merupakan siswa kelas X jurusan Teknik Komputer dan Jaringan (TKJ) SMK Migas Inovasi Riau yang beralamat di jalan Garuda Sakti kecamatan binawidya panam. Sebagai calon administrasor jaringan, siswa TKJ harus mampu bekerja cekatan dan cepat dalam melakukan konfigurasi dan instalasi jaringan. Cekatan dalam melakukan konfigurasi tidak lepas dari kemampuan mengetik yang cepat dan akurat. Oleh kareana itu sebagai pelajar yang baru masuk di jurusan TKJ sangat perlu memiliki kompetensi mengetik cepat. Salah satu cara untuk bisa mencapai tujuan tersebut salah satunya dengan menggunakan apliaksi mengetik cepat yang banyak tersedia dan gratis di internet. Salah satu aplikasi mengetik cepat adalah Rapid Typing 5.4 yang dikemas dengan tampilan menarik dan fitur lengkap, mulai mengetik huruf sampai mengetik kalimat. Dari 22 orang peserta pelatihan diukur hasil tes berupa jumlah yang diketik permenit (CPM), persentase akurasi karakter yang diketik (AC) dan kesalahan pengetikan karakter (EC) terjadi peningkatan sebelum diberikan pelatihan (Pre-test) dengan setelah diberikan pelatihan mengetik cepat (Pos-test). Rata rata peserta, CPM terjadi peningkatan yaitu pre-test 49,9 dan post-tes 164, AC meningkat yaitu pre-tes 49% dan post-tes 84% dan EC menurun yaitu saat pre-tes 49% dan pada post-tes 15%. Semoga dengan mampunya siswa dalam mengetik dengan cepat dan akurat akan membantu siswa dalam menyelesaikan dengan cepat semua pelajaran sekolah yang berhubungan dengan penggunaan komputer melalui pengetikan.
Automated Detection and Counting of Hard Exudates for Diabetic Retinopathy by using Watershed and Double Top-Bottom Hat Filtering Algorithm Toresa, Dafwen; Shahril, Mohamad Azrul Edzwan; Harun, Nor Hazlyna; Bakar, Juhaida Abu; Amnur, Hidra
JOIV : International Journal on Informatics Visualization Vol 5, No 3 (2021)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.5.3.664

Abstract

Diabetic Retinopathy (DR) is one of diabetes complications that affects our eyes. Hard Exudate (HE) are known to be the early signs of DR that potentially lead to blindness. Detection of DR automatically is a complicated job since the size of HE is very small. Besides, our community nowadays lack awareness on diabetic where they do not know that diabetes can affect eyes and lead to blindness if regular check-up is not performed. Hence, automated detection of HE known as Eye Retinal Imaging System (EyRis) was created to focus on detecting the HE based on fundus image. The purpose of this system development is for early detection of the symptoms based on retina images captured using fundus camera. Through the captured retina image, we can clearly detect the symptoms that lead to DR. In this study, proposed Watershed segmentation method for detecting HE in fundus images. Top-Hat and Bottom-Hat were use as enhancement technique to improve the quality of the image. This method was tested on 15 retinal images from the Universiti Sains Malaysia Hospital (HUSM) at three different stages: Normal, NPDR, and PDR. Ten of these images have abnormalities, while the rest are normal retinal images. The evaluation of the segmentation images would be compared by Sensitivity, F-score and accuracy based on medical expert's hand drawn ground truth. The results achieve accuracy 0.96 percent with 0.99 percent sensitivity for retinal images.
ASSISTANCE IN THE APPLICATION OF THE ARTIFICIAL INTELLIGENCE PARAPHRASING TOOL "QUILLBOT" IN ARTICLE WRITING Muzdalifah, Indah; Toresa, Dafwen; Wiza, Fana; Farwitawati, Reni
Diklat Review : Jurnal manajemen pendidikan dan pelatihan Vol. 9 No. 3 (2025): JURNAL DIKLAT REVIEW
Publisher : Komunitas Manajemen Kompetitif

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35446/diklatreview.v9i3.2482

Abstract

Writing is a fundamental skill for writers, researchers, lecturers, and students, especially in academic contexts where clarity, structure, and proper referencing are essential. Beyond composing coherent sentences, academic writing demands the ability to integrate references ethically and effectively. One key technique is paraphrasing—rephrasing others’ ideas in one’s own words while preserving the original meaning. This requires linguistic precision and conceptual understanding, yet many educators still struggle with it. Recognizing this challenge, the Community Service (PKM) team initiated a program titled Assistance in the Application of Artificial Intelligence Paraphrasing Tool Technology “Quillbot. The initiative aimed to introduce and train educators in using Quillbot, an AI-powered tool designed to support ethical and plagiarism-free paraphrasing in scientific writing. Delivered through a participatory approach, the training combined theoretical insights with hands-on practice. The results were impactful: 70% of participants had never used Quillbot before, highlighting the program’s success in expanding technological literacy. All participants found the tool helpful in improving writing efficiency and language quality. Many felt newly motivated to write, citing increased confidence and productivity. Beyond technical skills, the program fostered ethical awareness in writing practices. Overall, this initiative significantly contributed to promoting responsible and effective use of AI in education.
Co-Authors Ayoe Jumala, Tjik Bakar, Juhaida Abu Bunda, Yola Permata Deny Jollyta Des Suryani Fajrizal Fajrizal Fajrizal, Fajrizal Fana Wiza, Fana Fanawiza Harun, Nor Hazlyna Hidra Amnur Lisnawita Lisnawita Muzdalifah, Indah Pane, Eddissyah Putra Qadafi, Muhammad Reni Farwitawati, Reni Rico Francsisco Sitorus, Shimphony Rometdo Muzawi, Rometdo Rosda Syelly RR. Ella Evrita Hestiandari Sabna, Eka Shahril, Mohamad Azrul Edzwan Susi Handayani Syahril Syahril Syahril Taslim Taslim Taslim Taslim, Taslim Malano Taufiq, Reny Medikawati Unang Rio Walhidayat Walhidayat, Walhidayat Yoyon Efendi Yuhelmi Yuhelmi