cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Sarida Sirait
Contact Email
saridasrt@gmail.com
Phone
+6281319494217
Journal Mail Official
saridasrt@gmail.com
Editorial Address
Jl. Sriwijya No. 9 C-E Pematangsiantar, Sumatera Utara
Location
Kota pematangsiantar,
Sumatera utara
INDONESIA
Jurnal Tekinkom (Teknik Informasi dan Komputer)
Published by Politeknik Bisnis Indonesia
ISSN : 26211556     EISSN : 26213079     DOI : https://doi.org/10.37600/tekinkom
Core Subject : Science,
Computer Science & IT
Jurnal TEKINKOM merupakan jurnal yang dimaksudkan sebagai media terbitan kajian ilmiah hasil penelitian, pemikiran dan kajian analisis-kritis mengenai isu Ilmu - ilmu komputer dan sistem informasi, seperti : Pemrograman Jaringan, Jaringan Komputer, Teknik Komputer, Ilmu Komputer/Informatika, Sistem Informasi, dan Multi Disiplin Penunjang Domain Penelitian Komputasi, Sistem dan Teknologi Informasi dan Komunikasi, dan lain-lain yang terkait. Artikel ilmiah dimaksud berupa kajian teori (theoritical review) dan kajian empiris dari ilmu terkait, yang dapat dipertanggungjawabkan serta disebarluaskan secara nasional maupun internasional.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 407 Documents
 19   20   21   22   23 
ANALISIS KOMPARASI ALGORITMA C5.0 DAN NAIVE BAYES PENENTUAN PENERIMA BEASISWA UNIVERSITAS PRIMA INDONESIA Fantasy, Carolus Laberto; Simanjuntak, Felix Luther Mateus; Purba, Raja Levi Aldi; Sihombing, Oloan
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 6 No 2 (2023)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v6i2.926

Abstract

In developing quality human resources, Prima Indonesia University offers a scholarship program to help with educational costs for outstanding students. This research aims to help solve the problem of scholarship recipient selection which requires in-depth analysis using data mining technology. In this research, the use of the C5.0 algorithm and Naive Bayes algorithms was compared in determining scholarship recipients at Prima Indonesia University. The research method involves research locations at Prima Indonesia University using scholarship student data for 2019-2022 as research objects. The research instrument includes the use of the Python programming language with Google Colab as an editor, the Windows 10 operating system, and hardware with certain specifications. Data collection involves observation, literature study, data cleaning, data mining, and exploratory data analysis. The results of research using and comparing the C5.0 and Naive Bayes algorithms show an accuracy of 98.62% and 91.37% respectively. Evaluation involves precision, recall, F1, and confusion matrix values. In conclusion, the C5.0 algorithm is more accurate in determining scholarship eligibility than Naive Bayes, with accuracy increasing by around 8%. This research contributes to the development of data mining and predictive analysis in the context of determining scholarship recipients in higher education institutions.
IMPLEMENTASI MIKROKONTROLER NODEMCU ESP8266 SEBAGAI PENGENDALI PERANGKAT ELEKTRONIK BERBASIS VOICE ASSISTANT Muhammad Qosdy Jauharul Arzaq; Irwan Alnarus Kautsar; Azmuri Wahyu Azinar
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 1 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i1.1262

Abstract

One prominent development is the concept of the Internet of Things (IoT), which connects various physical devices via an internet network. By leveraging platforms like the NodeMCU ESP8266, IoT enables integration between the digital and physical worlds, opening up new opportunities in device monitoring and control. This research aims to implement the NodeMCU ESP8266 microcontroller as a voice assistant-based electronic device controller, by designing and implementing electronic device control using the basis of the Internet of Things (IoT) on a smartphone platform by utilizing the sistem development life cycle (SDLC) model. The research results show that the NodeMCU ESP8266 microcontroller is capable of controlling electronic devices based on voice assistants well. The sistem is able to detect and process voice commands with high accuracy, as well as control connected electronic devices efficiently, with an average success percentage of voice commands of 96.5%.
ANALISIS METODE PREFERENCE SELECTION INDEX DALAM MANAJERIAL EVALUASI KINERJA SUMBER DAYA MANUSIA Laia, Angelus Aprianus; Aisyah, Siti; Togatorop, Aprianto; Marpaung, Dolly Martin
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 6 No 2 (2023)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v6i2.923

Abstract

This research aims to solve the problem of performance assessment in a private company in the city of Medan. The quality of human resources (HR) is a key factor in achieving company goals, and performance appraisals often give rise to the effects of social jealousy among workers. To assist managerial parties in evaluating the performance of Human Resources, the Preference Selection Index (PSI) method is used to assist decision making. This research uses quantitative methods with employee data from the company's administration department as a sample by applying 4 assessment criteria such as performance, persistence, loyalty, discipline. Data collection involves interviews and direct visits to research locations. Data analysis was carried out by formulating a decision matrix, normalizing the data, calculating the normalized average value, preference variation value, determining the value in preferences, calculating the criteria weights, and calculating the overall preference value. The results showed that Individual 8 had the highest performance. This conclusion provides an overview of the extent to which employee performance meets the standards set by the company. This PSI method can be an effective tool in assisting management in making decisions regarding HR performance evaluation, by providing valuable information for understanding and increasing employee productivity.
KLASIFIKASI DATA MINING UNTUK PREDIKSI PENYAKIT KARDIOVASKULAR Nia Nuraeni
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 1 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i1.1276

Abstract

According to the World Health Organization (WHO), cardiovascular diseases are one of the leading causes of death worldwide. Cardiovascular diseases involve heart and blood vessel conditions that commonly occur in communities. These conditions encompass various diseases such as coronary heart disease, heart failure, stroke, and peripheral vascular disease. Major risk factors include high blood pressure, high cholesterol, and smoking. Premature deaths due to heart diseases can be prevented by controlling the risk factors and identifying individuals at high risk of developing such diseases. One of the most effective ways to identify and predict heart diseases is through the use of data mining algorithms. Data mining algorithms can address issues in diagnosing cardiovascular or heart diseases by utilizing predictive models, such as Decision Tree, Naive Bayes, Logistic Regression, K-Nearest Neighbor, and others. In this study, identification was performed using classification algorithms including Naïve Bayes, Logistic Regression, Decision Tree Classifier, k-NN, SVM, XGBoost, and Random Forest. The highest accuracy, reaching 98%, was obtained from the Random Forest algorithm
IMPLEMENTASI SCAN MARKER AUGMENTED REALITY UNTUK MEDIA PENGENALAN ORGAN TUBUH MANUSIA Rifai, Anes Sayful Bahtiyar; Aji, Adam Sekti
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 6 No 2 (2023)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v6i2.1039

Abstract

Learning involves the exchange of information and knowledge between educators, disciples, and educational resources. Currently, the transmission of educational content from educators to disciples generally has not used technology as a learning tool, thus making disciples exhibit a lack of enthusiasm and experience disinterest when it comes to grasping educational content. Researchers designed and created an application as an interactive learning tool to learn human organs for elementary school students. The research findings are translated into an application for the introduction of human organs using Augmented reality technology, all button functions on the hull learning application function properly. The accuracy of marker detection is influenced by several parameters including light intensity, marker scanning distance, and marker movement. This learning application's aim is to facilitate the learning application of human organs for elementary school students fun and easy to learn by elementary school students, successfully achieved.
ANALISIS PERBEDAAN ATENSI VISUAL CUSTOMER SHOPEE TERHADAP PRODUK FLASH SALE DENGAN PRODUK NORMAL BERBASIS EYE TRACKING Zabbrina Ayu Marcellina Tanjung; Dita Sari Vita L.S; Monalisa Br Sembiring Depari; Evta Indra; Deni Adha Akbari; Rizki Edmi Edison
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 1 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i1.1368

Abstract

Shopee is known as the e-commerce platform that is most widely used by people in Indonesia. One of the advantages offered by this platform is flash sales on various products at certain times. This study aims to determine the visual attention patterns of shopee users when viewing websites with flash sale captions using eye tracker technology. A total of 63 participants who were divided into two groups based on their experience using shopee were shown four types of products, each of which had a flash sale display and a normal display. There were five regions of interest in each display and two types of functions, first time fixation and Dwell time, were analyzed. This study shows that even though the longest duration was used by participants to view the flash sale description region, the first region viewed by both groups of participants was the product region. We hope that this data can be a reference for e-commerce platform website design to increase attention to the main message.
OPTIMASI PENERAPAN ALGORITMA CONVOLUTION NEURAL NETWORK DALAM KLASIFIKASI TINGKAT KESEGARAN DAGING SAPI Sahera, Charisa Nur; Rahmawati, Yunianita; Dijaya, Rohman
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 1 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i1.1122

Abstract

This research discusses optimizing the application of the Convolutional Neural Network (CNN) algorithm to overcome the problem of mixing fresh and non-fresh beef on the market. The focus of the research is classification of freshness levels in beef images using the CNN method with ADAM optimizer. Data collection involves open and private data. Image preprocessing is done with LabelEncoder and cv2. The research results show that this method is very effective in identifying and classifying the level of freshness in beef images. By determining optimal parameters, the model achieved the highest accuracy level of 98.50% at 10 epochs and a learning rate value of 0.001. Confusion matrix shows good results with a high number of True Positives. By applying CNN with the ADAM optimizer, it provides an effective solution to the problem of classifying beef freshness levels because this model is able to classify beef images well.
PENERAPAN METODE TREND MOMENT DALAM MEMPREDIKSI HARGA MINYAK MENTAH PADA PT ASIAN AGRI Mujahid, Putra Edi; Gultom, Maju Parsaoran; Lahagu, Hasrat Gideon; Sinaga, Indah
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 6 No 2 (2023)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v6i2.930

Abstract

In this research, this study aims to explore the potential and benefits of applying the Trend Moment method in predicting crude oil price trends at PT Asian Agri. The method used is the Trend Moment Method. Based on the results of the evaluation of the trend moment, it can be concluded that the method is good at predicting crude oil prices. With historical data for 2 years. The evaluation value shows that the trend moment value for Adj Close crude oil prices, the value obtained is 1615.65. UMK produces a value of 5079929.413333333. MAPE produces values ​​of 2.698007510149617 and 1.94.
KLASIFIKASI DATA PENJUALAN UNTUK MEMPREDIKSI TINGKAT PENJUALAN PRODUK MENGGUNAKAN METODE DECISION TREE Demira Intan Suranda; Adi Nugroho
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 1 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i1.1269

Abstract

A mature strategy is one of the keys so that a company can increase sales effectively and consistently. With recorded and accurate information, companies can make decisions quickly to predict what supplies consumers will need for the future. Aruna Boutique sells various types of Muslim clothing such as robes and headscarves with several brands of each type. The aim of this research is to determine the sales of the best-selling and least-selling products using the Decision Tree method with the ID3 algorithm. The tool used is a rapid miner using boutique sales transaction data from July - September. The results obtained in this research are the best-selling products Gamis 2 (Umama), veil 2 (DYN) and the less popular products Gamis 1 (Mahdani), veil 3 (Azara) with an accuracy value of 88.24%, which means that the method used it's good enough. Based on the rules obtained, information can be used to increase sales in terms of stock inventory, display and promotion strategies.
PENERAPAN NEURAL NETWORK LSTM DALAM MEMPREDIKSI SENTIMEN PENGGUNA TWITTER TERHADAP BITCOIN Pratama, Duta; Wijaya, Salim; Santosa, Sofian Ali; Tamba, Saut Parsaoran
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 6 No 2 (2023)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v6i2.921

Abstract

Abstract This research aims to apply the Long Short-Term Memory (LSTM) Neural Network to predict Twitter users' sentiment towards the price of Bitcoin. Bitcoin, as the leading cryptocurrency in the world, faces high price volatility influenced by external factors and market sentiment. Twitter has become a valuable source of information for market analysis, including sentiment towards Bitcoin. Several algorithms have been studied previously for predicting sentiment towards cryptocurrencies, but LSTM has shown excellent results in text analysis and sequence-based data prediction. This research utilizes LSTM to account for the temporal dependencies in Bitcoin tweet data. During testing, the implementation of Bitcoin sentiment prediction using the LSTM model achieved an accuracy level of 96%, indicating the model's capability to make accurate predictions regarding Bitcoin tweet sentiment. The results of this research can contribute to the development of Bitcoin trading strategies and a better understanding of the cryptocurrency market based on Twitter users' sentiment.

Page 21 of 41 | Total Record : 407

 19   20   21   22   23 

Filter by Year

2018 2025


Reset
Filter By Issues
All Issue Vol 8 No 1 (2025) Vol 7 No 2 (2024) Vol 7 No 1 (2024) Vol 6 No 2 (2023) Vol 6 No 1 (2023) Vol 5 No 2 (2022) Vol 5 No 1 (2022) Vol 4 No 2 (2021) Vol 4 No 1 (2021): Jurnal Tekinkom Vol 3 No 2 (2020) Vol 3 No 1 (2020) Vol 2 No 2 (2019) Vol 2 No 1 (2019) Vol 1 No 2 (2018) Vol 1 No 1 (2018) More Issue