Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Jurnal Mantik

LVQ Algorithm for The Classification of Hypertension Based on ESH Guideline Elvandric Lase; Wonderson Wonderson; Christensen Christensen; Dinda Afrianti; Andika Dian Permana; Abdi Abdi Dharma
Jurnal Mantik Vol. 4 No. 3 (2020): November: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.Vol4.2020.1006.pp1772-1778

Abstract

Hypertension was a global health problem, including Indonesia, that increases mortality, morbidity, and cost. In Indonesia, hypertension kept on increasing due to change in lifestyle, consumptions of food with a high level of fat, cholesterol, less physical activity, and a high level of stress, etc. One of the classifications of hypertension used in some country were European Society of Hypertension (ESH) guideline. Learning Vector Quantization (LVQ) was a method in machine learning for classifying data. LVQ were often used in pattern recognition processes such as images, sounds, etc. The purpose of this study was to see an increase in accuracy of hypertension classification based on ESH guideline as weight data. In this study, hypertension classification based on ESH guideline was used as weight data with LVQ method and the parameters used were 2 features, 100 epochs, 0.05 learning rate, 0.01 reducing factor, train data 70%, validation data 30%, and test data 30% from total data used. The result obtained in this study were 94.6667% in the hypertension classification process based on ESH guideline using LVQ method. The conclusion of this study, there was an increase in the accuracy of hypertension classification based on ESH guideline using the LVQ method.
Classification Of Indonesian Slang Using Naïve Bayes And Decision Tree Methods On Social Media Abdi Dharma; Aditya Calderon Naibaho; Lolo Mulatua Bancin; Alhoi Andrew Jefferson
Jurnal Mantik Vol. 6 No. 2 (2022): August: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.v6i2.2647

Abstract

At this time the application of language that appears on social media is the application of slang as a character of current language development. This phenomenon deserves to be discussed because it can find out how much slang is used on social media. The source of the dataset for this research is the verbal form found on the author's personal social media such as Instagram and Tiktok obtained by the web scraping method as many as 2,000 samples and the data will be divided into two categories, namely the category of slang and non-slang. This study aims to compare two classification algorithms, namely Naïve Bayes and Decision Tree to see which algorithm is more effective in classifying how many social media users use slang in commenting based on the dataset we have collected, so that results are obtained to see how high the percentage of usage is. Indonesian people's slang in commenting on social media.
Smart Prediction Model For Unplanned Icu Transfer Based On Deep Learning Optimization : An Article Review Sumita Wardani; Muhammad Uwais Akbar; A. Henpra Yogi Sitanggang; Joshua Baen Tupa; Johanes Pardede; Abdi Dharma
Jurnal Mantik Vol. 6 No. 2 (2022): August: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

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

Abstract

Problem on units ICU already is problem which critical and already happened since long ago, for the ICU is one of the highest costs unit in hospitals, which made a system to predict activity on ICU is very demanding. COVID-19 shows the need for excellent time management in dealing with the abnormal flow of patients. Prediction of ICU transfer can be useful for patients and medical personnel to reduce medical cost and giving the time required by the nurses to prepare themselves for a huge patients flow. Reviews of related articles are carried out through the Google Scholar database. Screening then conducted based on identified article based on criteria eligibility. There are 7 final articles that assessed on a large scale data samples, method algorithm, and performance from the model which used on the article. Results obtained from this study which follow PRISM flow show a number of variable indicators that are commonly applied, namely: age, gender, liver function, blood pressure, pulse rate, temperature, respiratory rate, kgd and ECG data features. The best test results was achieved by research by Jonathan Rubin, et al due to the large number of varied data sets used, much more than other studies. This research also used adaptive boosting and gradient tree boosting approaches and evaluated with 4 main parameter that is accuracy, sensitivity, specificity, and AUC ROC. This study succeed in reaching performance evaluation model of 72.8% sensitivity, 76.3% specificity, 76.2% accuracy and 79.9% AUC ROC