Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal MAT-EDUKASIA Jurnal Indonesia : Manajemen Informatika dan Komunikasi The Indonesian Journal of Computer Science
Jasmarizal
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Computer Science & IT Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Library & Information Science Mathematics

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
UPAYA PENINGKATAN HASIL BELAJAR IPA MELALUI METODE JIGSAW DI KELAS IV SD NEGERI NO. 91/VI RANTAU PANJANG VI KECAMATAN TABIR KABUPATEN MERANGIN Jasmarizal
Mat-Edukasia Vol 6 No 1 (2021): April 2021
Publisher : Pendidikan Matematika | STKIP YM Bangko

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

Abstract

This study aims to determine the increase in science learning outcomes by applying the Jigsaw method to fourth grade students of SD Negeri No. 91/VI Rantau Panjang VI, Merangin District, Semester 2 of the 2017/2018 Academic Year. This type of classroom action research (CAR) consists of 3 cycles. The research subjects were all fourth grade students, totaling 16 students. The instruments used were observation sheets and formative tests at the end of the cycle. The criteria for success in this study are 80% of all fourth grade students have reached or exceeded the Minimum Completeness Criteria (KKM) which is 70 with the formula for average scores and percentages. The results showed that the application of the Jigsaw method could improve learning in cycle I, cycle II, and cycle III, student learning outcomes increased, namely the results of pre-cycle formative tests, the average grade 50 of 16 students, with details of students who completed only 2 students 13%) and 14 students (87%). Cycle I average grade 70 out of 16 students, 12 students (75%) completed and 2 (25%). Cycle II the average grades increased to 80 out of 16 students, while those who completed 14 students (88%), who had not completed 2 students (12%). Cycle III the average value of the class increased to 84 out of 16 students, as for those who completed 16 students (100%), those who had not completed 0 students (0%)
ANALISA PERFORMA ALGORITMA MACHINE LEARNING DALAM PREDIKSI PENYAKIT LIVER Nurkholifah, Mahdiawan; Jasmarizal; Umar, Yusran; Rahmaddeni
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 4 No. 1 (2023): Januari
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jimik.v4i1.149

Abstract

Currently in the world of medicine, determining liver inflammation is something that is not easy to do. But there are medical records that have kept the patient's symptoms and diagnosis of liver inflammation. The weaknesses of the manual method encourage researchers to develop a method that does not depend 100% on humans. The developed method utilizes a computer as a tool to analyze data. This kind of thing is certainly very useful for health experts. They can use existing medical records as an aid in making decisions about the diagnosis of a patient's disease. In this study, we analyzed the performance of machine learning algorithms by comparing the support vector machine, naïve Bayes and k-nearest neighbor algorithms. This study aims to determine the performance of which algorithm has the highest accuracy in liver disease data. From the research results using splinting data 80:20 it can be concluded that the Naïve Bayes algorithm model has better performance than other algorithm models when using the SMOTE technique with an accuracy value of 65.51%, whereas when not using the SMOTE technique the Support Vector Machine algorithm has the highest performance. better than other algorithm models with an accuracy value on the data not 72.41%.
Penerapan Metode Support Vector Machine Untuk Analisis Sentimen Terhadap Produk Skincare Jasmarizal; Junadhi; Rahmaddeni; M. Khairul Anam
The Indonesian Journal of Computer Science Vol. 13 No. 1 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i1.3654

Abstract

Perawatan kulit telah menjadi aspek yang signifikan dalam pola hidup modern. Kesadaran masyarakat terhadap penampilan dan kesehatan kulit semakin meningkat, mendorong permintaan terus berkembang untuk produk skincare. Konsumen sering menghadapi kesulitan dalam memilih produk yang sesuai dengan jenis kulit mereka, di mana ulasan dari pengguna lain bisa menjadi panduan berharga, namun juga berpotensi menyebabkan kebingungan jika tidak dikelola dengan baik. Mengetahui sentimen konsumen terhadap produk skincare tidak hanya membantu produsen dan pengecer memahami penerimaan produk, tetapi juga memberikan arahan bagi konsumen lain dalam pengambilan keputusan. Kemajuan dalam teknologi analisis sentimen memungkinkan penelitian yang lebih efisien dan akurat terhadap pandangan konsumen mengenai produk skincare. Analisis sentimen dapat dijalankan secara otomatis menggunakan algoritma dan model kecerdasan buatan, di mana Support Vector Machine (SVM) menjadi salah satu metode yang efektif dalam permasalahan klasifikasi. SVM memberikan wawasan mendalam mengenai sentimen yang terkandung dalam ulasan konsumen. Dataset yang digunakan mengandung komentar dan ulasan dari pengguna terkait produk skincare MS Glow, dengan total 3.006 data. Proses selanjutnya melibatkan tahap pre-processing data, yang mencakup langkah-langkah seperti Case Folding, Normalisasi Data, Tokenisasi, Filtrasi Stop Words, dan Stemming. Pada tahap pemodelan, SVM digunakan untuk mengklasifikasi sentimen atau opini pengguna terhadap produk skincare tersebut. Hasil akhir menunjukkan bahwa model dengan ketidakseimbangan kelas mengalami overfitting, di mana performa model optimal hanya pada data pelatihan dan kurang efektif pada data uji. Namun, dengan melatih model menggunakan kelas yang seimbang dan menerapkan teknik SMOTE, ditemukan hasil optimal, mencapai akurasi sebesar 99.60% dan nilai f1-score sebesar 98.55%.
Co-Authors Anam, M Khairul Junadhi Junadhi Nurkholifah, Mahdiawan Rahmaddeni Rahmaddeni Umar, Yusran