Article Per Year (5 Year)
p-Index From 2020 - 2025
2.203
P-Index
This Author published in this journals
All Journal Jurnal Teknik Kimia USU Nusantara Medical Science Journal KOMPUTA : Jurnal Ilmiah Komputer dan Informatika Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Jurnal Computer Science and Information Technology (CoSciTech) These proceedings represent the work of researchers participating in The International Conference on Elementary Education (ICEE) which is being hosted by the Elementary Education Study Programme School of Postgraduate Studies, Universitas Pendidikan Jurnal Teknik Kimia USU J-COSCIS : Journal of Computer Science Community Service Technologica Tarumanagara Medical Journal The Indonesian Journal of Computer Science
Taslim
Unknown Affiliation
Humanities Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Materials Science & Nanotechnology Mathematics Medicine & Pharmacology Neuroscience Public Health Social Sciences

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Optimasi Parameter Support Vector Machine Dengan Particle Swarm Optimization Untuk Prediksi Tunggakan Iuran Sekolah Syahril; Medikawati Taufiq, Reny; Taslim; Toresa, Dafwen; Fajrizal; Handayani, Susi
Technologica Vol. 3 No. 2 (2024): Technologica
Publisher : Green Engineering Society

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55043/technologica.v3i2.162

Abstract

Penelitian ini berfokus pada pengembangan model prediktif untuk mengidentifikasi tunggakan iuran siswa di Sekolah Madrasah Ibtidaiyah Muhammadiyah Pekanbaru. Model ini memanfaatkan metode Support Vector Machine (SVM) dengan optimasi parameter menggunakan algoritma Particle Swarm Optimization (PSO) untuk mencapai akurasi prediksi yang tinggi. Data iuran siswa tahun 2022 digunakan sebagai sumber data, dan proses pra-pemrosesan data dilakukan untuk membersihkan noise dan outlier serta mengatasi ketidakseimbangan kelas dengan teknik SMOTE. Model yang diusulkan menggabungkan SVM dengan PSO untuk mencari nilai C dan gamma yang optimal pada model SVM. Hasil penelitian menunjukkan bahwa SVM dengan kernel radial dan 80% data latih mencapai akurasi sebesar 86,39%. Pengujian SVM+PSO dilakukan dengan dua ukuran populasi (10 dan 15) dan 1000 generasi evolusi. Penggunaan 10 populasi menghasilkan akurasi sebesar 89,20%, sedangkan 15 populasi mencapai akurasi 90,64% dengan nilai optimal C=1,4 dan gamma=2,6. Penelitian ini menekankan pentingnya penyesuaian parameter dan strategi evolusi seperti PSO dalam meningkatkan kinerja model SVM untuk tugas mengklasifikasikan tunggakan iuran siswa. Hasil ini menunjukkan bahwa model yang diusulkan mampu memberikan prediksi yang lebih akurat dibandingkan SVM standar, sehingga memberikan kontribusi penting dalam identifikasi dan pengambilan keputusan terkait tunggakan iuran siswa di sekolah
Teaching Materials Based On Local Wisdom Ogan Komering Ilir Regency Sub-Theme Of The Uniqueness Of The Region Where I Live In Class IV Elementary School Taslim; Siti Dewi Maharani
International Conference on Elementary Education Vol. 5 No. 1 (2023): Proceeding The 5th International Conference in Elementary Education
Publisher : Elementary Education Study Program School of Postgraduate Studies Universitas Pendidikan Indonesia in collaboration with UPI PRESS

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

Abstract

Learning based on local wisdom, especially in Ogan Komering Ilir Regency, has not yet established a curriculum. It is necessary to carry out education based on local wisdom as an increase in knowledge, integrating a sense of love for the local wisdom of the area, and equipping students with manners and attitudes compared to the values and regulations that apply around or in the size of the students. Therefore, the development of teaching materials based on local wisdom was carried out. The purpose of this study was to produce a product, determine the validity, and determine the practicality of developing teaching materials based on local wisdom in Ogan Komering Ilir Regency, with the sub-theme of the uniqueness of where I live at SDN 1 Lebung Batang. Model development uses a 4D model with 3D modifications (Define, Design, Develop). The result of the research is a product of thematic teaching materials. Then, the validation results show very valid criteria. Furthermore, the results of development testing on 16 students showed very practical achievements. These results show that the teaching materials developed focusing on Ogan Komering Ilir Regency's local wisdom are feasible and can be used in elementary school learning.
Penentuan Kadar Flavonoid dan Kandungan Fitokimia Ekstrak Kulit Bawang Merah (Allium cepa L) dengan Berbantukan Microwave sebagai Potensi Bahan Aktif Tabir Surya Dalimunthe, Nisaul Fadilah; M. Thoriq Al Fath; Taslim; S. Ginting, M. Hendra; Farah Nurul Alifia; Berta, Grace Adela
Jurnal Teknik Kimia USU Vol. 13 No. 2 (2024): Jurnal Teknik Kimia USU
Publisher : Talenta Publisher (Universitas Sumatera Utara)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jtk.v13i2.16318

Abstract

The skin serves as a protective barrier against dust and ultraviolet (UV) radiation. Excessive UV exposure is associated with accelerated skin aging, erythema, hyperpigmentation, and carcinogenesis. This study aimed to quantify flavonoid concentrations and characterize phytochemical constituents in shallot skin extracts for their potential as active ingredients in sunscreen formulations. Shallot skin was subjected to microwave assisted extraction using 70% ethanol as the solvent. Phytochemical screening revealed the presence of flavonoids, tannins, saponins, and alkaloids in the extract. Flavonoid content was determined via UV-Vis spectrophotometry, yielding 36.33 mgQE/g. The high flavonoid concentration observed in shallot skin extract suggests its potential efficacy as an active ingredient in sunscreen formulations.
Peningkatan Performa Model Gradient Boosting dalam Klasifikasi Stroke Melalui Optimasi Grid Search Handayani, Susi; Fajrizal; Taslim; Toresa, Dafwen; Syahril
JURNAL FASILKOM Vol. 14 No. 3 (2024): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Publisher : Unversitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/jf.v14i3.7893

Abstract

Studi ini menyelidiki pengaruh optimasi hyperparameter dengan grid search pada model XGBoost dan LightGBM dalam klasifikasi stroke. Hasil penelitian menunjukkan bahwa optimasi parameter secara signifikan meningkatkan performa kedua model, terutama dalam akurasi, precision, F1 Score, dan ROC-AUC Score. Pada model XGBoost, peningkatan terutama terlihat akurasi dan precision, sementara LightGBM menunjukkan peningkatan merata di semua metrik evaluasi. Temuan ini menggarisbawahi pentingnya optimasi hyperparameter dalam membangun model klasifikasi yang efektif untuk memprediksi risiko stroke dengan lebih akurat dan dapat diandalkan. Penemuan ini dapat berkontribusi dalam pemahaman lebih lanjut tentang faktor-faktor yang mempengaruhi stroke serta mendukung penanganan yang lebih tepat dan efektif dalam praktik klinis
PELATIHAN PEMROGRAMAN JAVASCRIPT BAGI SISWA SMK INOVASI RIAU Fajrizal; Susi Handayani; Taslim; Walhidayat; Syahril
J-COSCIS : Journal of Computer Science Community Service Vol. 5 No. 1 (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/jcoscis.v5i1.22458

Abstract

Pelatihan pemrograman JavaScript ini bertujuan untuk membekali siswa SMK dengan keterampilan yang dibutuhkan untuk menjadi pengembang web yang kompeten. Melalui pendekatan pembelajaran yang berbasis proyek dan didukung oleh tools berbasis android, siswa akan belajar membangun aplikasi web interaktif yang dinamis dan responsif. Materi pelatihan mencakup sintaks JavaScript, manipulasi DOM, event handling, asynchronous programming, dan best practices dalam pengembangan web. Diharapkan melalui pelatihan ini, siswa dapat mengembangkan minat yang berkelanjutan dalam bidang pemrograman dan siap untuk berkontribusi dalam pengembangan industri teknologi informasi di Indonesia.
Case report: Unexpected presentation of Wellens’ syndrome in Public Health Centers Afandy, Jonathan Edbert; Taslim; Putra, Swastya Dwi
Tarumanagara Medical Journal Vol. 6 No. 2 (2024): TARUMANAGARA MEDICAL JOURNAL
Publisher : Fakultas Kedokteran Universitas Tarumanagara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24912/tmj.v6i2.30337

Abstract

Electrocardiography (ECG) is an essential tool for diagnosing and risk-stratifying acute coronary syndrome patients. Only 20% of acute ischemia ECG changes are recognized by emergency medical service (EMS) providers. Wellens’ syndrome is an ECG characteristic, as certain ST-T segment abnormalities in the setting of impending myocardial infarction (MI) patients suggestively caused by critical stenosis in the proximal left anterior descending (LAD) artery. Myocardial infarction from a culprit lesion in the LAD artery is related to worse clinical outcomes. The first patient was a 27-year-old man smoker who presented with epigastric pain accompanied by shortness of breath in the past 1 hour. His blood pressure was 170/100 mmHg and physical examination revealed epigastric tenderness. ECG revealed biphasic T waves in leads V2-V5, suggestive of Wellens type A. The second patient was a 37-year-old man who presented after being stung by an insect 15 minutes before. Upon observation, the patient suddenly experienced left-sided chest pain accompanied by diaphoresis. ECG revealed inverted T waves in leads V2-V4, suggestive of Wellens type B. Further history-taking revealed that he had experienced this kind of symptoms three months prior and had a history of hypertension, dyslipidemia, and a current smoker. Unfortunately, both patients refused to be referred for further examination and management. Physicians and EMS providers should be aware of Wellen’s syndrome. Misinterpretation of this ECG characteristic could lead to fatal outcomes. Educating patients thoroughly about their condition is also important.
Inovasi Edible Coating Buah Mangga Berbasis Kitosan Kulit Udang dengan Aditif Ekstrak Daun Asam Jawa sebagai Antimikroba Pratama, Deska Rizki; Berutu, Aidha Sekar; Husin, Fahrizal; Panjaitan, Maychel Yohana; Taslim
Jurnal Teknik Kimia USU Vol. 14 No. 1 (2025): Jurnal Teknik Kimia USU
Publisher : Talenta Publisher (Universitas Sumatera Utara)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jtk.v14i1.19093

Abstract

Edible coating is a thin layer that can be consumed which protects the surface of the fruit from environmental influences. This study evaluates the effectiveness of shrimp shell chitosan-based edible coating with tamarind leaf extract as an antimicrobial, along with glycerol and tween 80, in preserving mango quality during 15 days of storage. The variables evaluated were the concentration of tamarind leaf extract (0.5, 1.0, and 1.5%) and mango storage duration (0, 3, 6, 9, 12, and 15 days). While the amount of chitosan used was constant. The parameters measured included total microbial count, weight loss, fruit skin color, total soluble solids, titratable acidity, and vitamin C content. The results showed that the combination of shrimp shell chitosan and tamarind leaf extract as an antimicrobial significantly reduced the degradation of mango quality, with the 0.5% concentration of tamarind leaf extract being the most effective in maintaining quality and extending shelf life of mango until 15 days.
Penerapan K-Nearest Neighbors untuk Klasifikasi Kasus Hukum di Pengadilan Federal Australia: Penerapan K-Nearest Neighbors untuk Klasifikasi Kasus Hukum di Pengadilan Federal Australia Karan; Rafi Fadilla; M Alidin; Taslim
Computer Science and Information Technology Vol 6 No 1 (2025): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

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

Abstract

With the development of information technology, especially in the legal field, legal case analysis can now be done more efficiently through the application of machine learning. This study aims to classify legal cases based on the status of Cited and Uncited using the K-Nearest Neighbor (KNN) algorithm. The classification process includes text preprocessing stages, word weighting using the TF-IDF method, and testing the KNN algorithm with various values ​​of the parameter k. The research data was taken from the Federal Court of Australia (FCA) covering legal cases from 2006–2009, with three data sharing scenarios: 90:10, 80:20, and 70:30. The evaluation model was carried out using a confusion matrix with metrics of accuracy, precision, recall, and F1-score. The best results were obtained in the 80:20 scenario with a value of k = 3, resulting in an accuracy of 96.36%, a precision of 96.80%, a recall of 99.49%, and an F1-score of 98.13%. With these results, the KNN algorithm is proven to be effective in supporting the automatic legal document classification process.
Challenges in Managing Myocardial Stunning Following Cardiac Arrest in a Very High-Risk NSTE-ACS Patient: A Case Report Afandy, Jonathan Edbert; Taslim
Nusantara Medical Science Journal Vol. 10 No. 1 (2025): Volume 10 Issue 1, January - June 2025
Publisher : Faculty of Medicine, Hasanuddin University.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/nmsj.v10i1.44050

Abstract

Introduction: Myocardial stunning is a reversible myocardial dysfunction that can occur due to various conditions, including focal ischemia—such as acute coronary syndrome (ACS)—and global ischemia, such as cardiac arrest. The proposed mechanisms include oxygen free radical damage during early reperfusion and altered calcium inflow leading to transient myofilament desensitization. Case Presentation: A 61-year-old woman with a history of uncontrolled hypertension and obesity presented with sudden loss of consciousness lasting one hour, preceded by chest pain and dyspnea. She experienced cardiac arrest and achieved return of spontaneous circulation (ROSC) after 10 minutes of cardiopulmonary resuscitation. Initial echocardiography showed a left ventricular ejection fraction (LVEF) of 32.9% and global hypokinesia. She was diagnosed with very high-risk non-ST-elevation ACS (NSTE-ACS), with suspected left main coronary artery obstruction or three-vessel disease. Her clinical course was complicated by acute pulmonary edema, respiratory failure, and cardiogenic shock. Management included intubation, dual antiplatelet therapy, anticoagulation, statin therapy, and inotropic support with dopamine and dobutamine. Her hemodynamic status improved within 18 hours, and she was extubated. On the third day post-arrest, follow-up echocardiography revealed a restored LVEF of 69.5% with normal wall motion. The patient was discharged after 9 days and continued to do well on outpatient follow-up for at least 6 months. Conclusions: Myocardial stunning should be considered in post-cardiac arrest and ACS patients with transient ventricular dysfunction. Early supportive care and close monitoring are essential, particularly in settings lacking advanced cardiac interventions.
Optimasi Augmentasi Data Berbasis Synonym Replacement pada Klasifikasi Teks Berita Menggunakan Neural Network Huriah, Iffah Risma; Widianingrum, Amelia Ismania Sita; Azlina; Taslim
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 14 No 1 (2025): 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.v14i1.15339

Abstract

In the digital era, online news has become one of the primary sources of information, encompassing various categories such as politics, technology, entertainment, and business. The increasing volume of news poses challenges in organizing and categorizing information into relevant categories. This study aims to enhance the accuracy of news text classification through a data augmentation approach based on synonym replacement. The methods employed include text preprocessing for data cleaning, augmentation using synonym replacement to improve data diversity, feature representation using TF-IDF and Word2Vec, and modeling with Neural Networks. Evaluation metrics such as accuracy, precision, recall, and F1-score were used to assess performance. The results indicate that data augmentation can improve model accuracy by up to 95%, with balanced training and validation data distributions. The confusion matrix shows that most data can be correctly classified, although some errors occur in categories with similar features. This study demonstrates that synonym replacement-based data augmentation is effective in improving news text classification performance, particularly for datasets with limited training data.
Co-Authors Afandy, Jonathan Edbert Azlina Berta, Grace Adela Berutu, Aidha Sekar Dalimunthe, Nisaul Fadilah Fajrizal Farah Nurul Alifia Huriah, Iffah Risma Husin, Fahrizal Ida Ayu Putu Sri Widnyani Iriany Karan M Alidin M. Thoriq Al Fath Maulisa Moh. Fatkuroji Ningsih, Kursiah Warti Panjaitan, Maychel Yohana Pratama, Deska Rizki Putra, Swastya Dwi Rafi Fadilla Sabna, Eka Salsabila Siti Dewi Maharani Susi Handayani Susi Handayani Syahril Taufiq, Reny Medikawati Toresa, Dafwen Walhidayat Widianingrum, Amelia Ismania Sita Yuhelmi Yuhelmi