Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal Dinamik Sinkron : Jurnal dan Penelitian Teknik Informatika
Simarmata, Allwin M.
Unknown Affiliation
Computer Science & IT

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
ANALISIS SENTIMEN TIK TOK PADA MEDIA SOSIAL DENGAN ALGORITMA NAIVE BAYES CLASSIFIER Rahmadani, Putri Suci; Tampubolon, Fenny Chintya; Jannah, Adelia Nurfattul; Hutabarat, Novia Lucky Halen; Simarmata, Allwin M.
Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 3 (2022): Article Research Volume 6 Number 3, July 2022
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v7i3.11579

Abstract

Social media is a computer application designed to make it simpler to communicate with others without having to do it face-to-face, as well as a tool for having fun and reducing feelings of isolation. Existing social media applications include games, music, and media for communicating with distant individuals, among others. These social media are utilized by parents, adolescents, and even young children. The application Tik-Tok is frequently used by children as a social networking platform. Tik-Tok has succeeded in grabbing the interest of youngsters, such that children are curious about creating short movies on the platform. Due to the fact that this application is used by children, the researcher seeks to use the Naïve Bayes Classifier Algorithm to recognize and differentiate unfavorable remarks on TikTok's social media. The rising number of negative remarks in the TikTok comments column can hinder the mental development of youngsters, and it is hoped that this algorithm would encourage users to post positive comments on this application. Based on the data gathering until the results of classification are obtained. There are 600 comments data randomly collected from TikTok users, gathered through the export comments website. After evaluating, the accuracy of the application of the Naïve Bayes Classifier algorithm in conducting sentiment analysis is 80% while the result of the AUC is 46%
Data Mining using clustering method to predict the spread of Covid 19 based on screening and tracing results Simarmata, Allwin M.; Manik, Riwanto; Simanjorang, Ourent Chrisin Renatta; Purba, Dymas Frepian
Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 4 (2022): Article Research: Volume 6 Number 4, October 2022
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v7i4.11740

Abstract

Coronavirus is a virus that causes disease in humans and animals. The virus was discovered in Wuhan, China in December 2019. Initially, it was suspected to be pneumonia, with general symptoms similar to the flu. However, unlike influenza, coronaviruses can progress rapidly, leading to more severe infections and organ failure. The number of COVID-19 sufferers in Indonesia is increasing every month. Anticipation and reducing the number of people infected with the coronavirus in Indonesia have been carried out in all regions. Including providing policies that limit activities outside the home. Indonesia has a very wide area, so it is necessary to classify the spread of Covid-19 based on regions or regions in Indonesia. This grouping provides a central point for the spread of Covid-19 pandemic cases in Indonesia. In testing data using data mining, data mining allows users to find knowledge in databases that were previously unknown to the user. By using the Clustering technique and the K-Means algorithm to predict the spread of COVID-19 based on the results of screening and tracing. The Clustering method produces 3 clusters, Cluster 0 with a medium category with a total of 6 regions, Cluster 1 with a low category with a total of 3 regions, and Cluster 2 with a high cluster with a total of 7 regions, with a DBI value of -0.784.
Densenet Architecture Implementation for Organic and Non-Organic Waste Simarmata, Allwin M.; Salim, Philander; Waruwu, Netral Jaya; Jessica
Sinkron : jurnal dan penelitian teknik informatika Vol. 7 No. 4 (2023): Article Research Volume 7 Issue 4, October 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i4.12765

Abstract

Garbage is the result left over from the process of daily human activities and activities which are considered no longer suitable for use, ranging from household waste to large-scale industrial waste. Therefore, the classification of waste is important because the problem of waste disposal is increasing and the way of processing is wrong. This research focuses on the classification of organic and non-organic waste using the DenseNet architecture. The dataset is processed first and each image in the dataset is resized to 128x128 pixels before being used in the model. We then trained all DenseNet types namely DenseNet121, DenseNet169, DenseNet 201, and compared their performance. Based on the test results, all DenseNet models that were trained were able to produce good accuracy, precision, recall, and F1 scores in garbage classification. In particular, our designed DenseNet121 model achieves 93.1 accuracy, 94.08% precision, 94.00% recall, 94.03% F1 score and 1min 34s training time as the best among other models. These results prove that the DenseNet architecture can be used to classify organic and non-organic waste correctly.
Identifikasi Aritmia pada Lansia menggunakan Algoritma K-Nearest Neighbor berdasarkan Data ElektroKardiogram Siahaan, Maherni; Panjaitan, Sabina; Purba, Agnes Alvionita; Cahya, Mutiara; Simarmata, Allwin M.
Dinamik Vol 31 No 1 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i1.10336

Abstract

Aritmia merupakan gangguan irama jantung yang umum terjadi pada lansia dan dapat menimbulkan risiko kesehatan serius jika tidak terdeteksi secara dini. Penelitian yang dilakukan bertujuan untuk mengidentifikasi aritmia pada lansia menggunakan algortima K- Nearest Neighbor (KNN) berdasarkan data elektrokardiogram (EKG). Data yang digunakan berjumlah 105 data EKG lansia yang diperoleh dalam format CSV. Proses awal melibatkan pembersihan dan normalisasi data menggunakan metode StandardScaler, serta pelabelan awal menggunakan algoritma K-Means Clustering untuk mengelompokkan data ke dalam dua kelas: Normal dan Sangat Berpotensi Aritmia. Data kemudian dibagi menjadi 70% data latih dan 30% data uji dengan metode stratified split untuk menjaga proporsi label. Model KNN dilatih dengan parameter k = 3, dan dievaluasi menggunakan confusion matrix serta classification report. Hasil pengujian menunjukkan akurasi model sebesar 97% dengan nilai precision dan recall yang tinggi pada kedua kelas. Hasil ini menunjukkan bahwa algoritma KNN efektif dalam mengklasifikasikan kondisi aritmia pada lansia dan memiliki potensi untuk diterapkan dalam sistem pendukung diagnosis berbasis data EKG.
Co-Authors Hutabarat, Novia Lucky Halen Jannah, Adelia Nurfattul Jessica Manik, Riwanto Mutiara Cahya Panjaitan, Sabina Purba, Agnes Alvionita Purba, Dymas Frepian Rahmadani, Putri Suci Salim, Philander Siahaan, Maherni Simanjorang, Ourent Chrisin Renatta Tampubolon, Fenny Chintya Waruwu, Netral Jaya