Article Per Year (5 Year)
p-Index From 2021 - 2026
1.554
P-Index
This Author published in this journals
All Journal JURNAL TEKNOLOGI DAN ILMU KOMPUTER PRIMA (JUTIKOMP) JURNAL MAHAJANA INFORMASI Jurnal Sains dan Teknologi Jurnal Tekinkom (Teknik Informasi dan Komputer) INFOKUM Journal of Computer Networks, Architecture and High Performance Computing Jurnal Sistem Informasi, Teknik Informatika dan Teknologi Pendidikan (JUSTIKPEN)
Windania Purba
Program Studi Sistem Informasi Universitas Prima Indonesia Medan
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Library & Information Science Mathematics Mechanical Engineering Physics Social Sciences Other

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : INFOKUM

 1 
APPLICATION OF DATA MINING TO IDENTIFY DIABETES MELLITUS USING THE SUPPORT VECTOR MACHINE (SVM) ALGORITHM AND KNN Windania Purba; Yessy Yessy; Riski Nofarianus Gulo
INFOKUM Vol. 10 No. 02 (2022): Juni, Data Mining, Image Processing, and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (253.474 KB)

Abstract

Damage to the performance of human organs is very detrimental Received Revised Accepted And is the source of the most problems at this time. One of the diseases that is the number one killer in the world is diabetes mellitus. Diabetes mellitus is a metabolic disease characterized by hyperglycemia caused by and obstacle in insulin secretion from insulin action or both. Diabetes mellitus is divided into several types, type 1 diabetes mellitus generally gives rise to indications before the patient is 30 years old. Although in fact the indications of the disease can arise at any time. This study aims to apply the Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) method to identify diabetes mellitus and calculate the comparison value of the accuracy of the two algorithms. From the results of this study. It can be concluded that the Support Vector Machine (SVM) algorithm produces an accuracy value of 76% while the accuracy value of the K-Nearest Neighbor (KNN) algorithm is 75%
USING THE NAIVE BAYES CLASSIFIER METHOD ON SOCIAL MEDIA SENTIMENT ANALYSIS Windania Purba; Ade Syahpitri; Grace Fitri Anggi Munthe
INFOKUM Vol. 10 No. 02 (2022): Juni, Data Mining, Image Processing, and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (396.042 KB)

Abstract

Social media is one of the many technological developments that greatly affect human communication and socialization systems. Most people voice their opinions through social media, with the aim that they can be heard and seen by the general public. However, the use of social media often backfires for the owners themselves due to their excessive use. In particular, this study discusses the grouping of sentiment data from Prima Indonesia University students where to seek negative and positive opinions from students as a benchmark for online learning methods carried out in the campus environment. The data grouping process uses the nave Bayes algorithm, because this algorithm has been widely used in data processing. The tests carried out in this study resulted in an accuracy of 68% of the dataset selected as the data training process. This results in a classification of new data to find out a sentiment on students belonging to the negative or positive class.
Co-Authors Ade Syahpitri Aguan Aritonang Angelin Angelin Ayu Elpriyani Sidabutar Derry Rosanta Br.sitanggang Desty Rukmana Elbert Ghozali Evta Indra Fransisco Andreas Sirait Grace Fitri Anggi Munthe Henry Triadi Manurung Irsan Jaya Sihombing Lina Sari Harefa Mario Gota Manalu Maxwell Paulus Siregar Nur Ainun Siahaan Okta Jaya Harmaja Palma Juanta Riski Nofarianus Gulo Saut Parsaoran Tamba Siti Aisyah Steven Steven Tonny Tendean Yessy Yessy Yoel Ferdinand Zai