Claim Missing Document
Check
Articles

Found 4 Documents
Search

PEMANTAUAN KASUS PENYEBARAN COVID-19 BERBASIS WEBSITE MENGGUNAKAN FRAMEWORK REACT JS DAN API Tri Sulistyorini; Erma Sova; Rafli Ramadhan
Jurnal Ilmiah Multidisiplin Vol. 1 No. 04 (2022): Juli : Jurnal Ilmiah Multidisiplin
Publisher : Asosiasi Dosen Muda Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (814.632 KB) | DOI: 10.56127/jukim.v1i04.137

Abstract

The world has been attacked by the pandemic of coronavirus, starts from 2019 until this day, 2022. Coronavirus was detected in Indonesia started from 2020, specifically on March, 2020. The coronavirus or severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is the virus which attacks human’s respiratory system. It is also known as COVID-19. The virus may cause mild illnesses of human’s respiratory system, severe lung infections, and even death. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is categorized as the new infectious disease to human. The virus attacks anyone, such as elderly, adult, children, toddler, pregnant women, and breastfeeding mothers. Utilization of information technology that continues to develop can be felt in various fields. Such as the fields of education, government, health, social culture and so on. Information about COVID-19 is always needed by the people of Indonesia, even abroad. Utilization of this website-based technology can help the public in obtaining up to date information. Website application built using React JS framework and API. According to the problems experienced now, a website was created to monitor and provide accessible information to the public regarding the spread of COVID-19 virus cases in Indonesia and the entire world as well. People could approach the website called Covices which was created in programming languages, such as React Js and API.
PEMANFAATAN NODEMCU ESP8266 BERBASIS ANDROID (BLYNK) SEBAGAI ALAT ALAT MEMATIKAN DAN MENGHIDUPKAN LAMPU Tri Sulistyorini; Nelly Sofi; Erma Sova
Jurnal Ilmiah Teknik Vol. 1 No. 3 (2022): September : Jurnal Ilmiah Teknik
Publisher : Asosiasi Dosen Muda Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56127/juit.v1i3.334

Abstract

Internet of Things (IoT) is a concept that aims to expand the benefits of continuously connected internet connectivity. This study aims to utilize IoT in home automation and remote light control systems that can be operated with a smartphone application via an internet connection (WiFi). This system uses the NodeMCU ESP8266 module as a microcontroller, a light emitting diode (LDR) sensor as a controller for automating lights according to environmental conditions, and the Blynk smartphone application as a remote control for lights. The light control process can be carried out specifically on certain lamps and can be controlled by changes in ambient light in the morning and evening. The results show that when the LDR sensor gets minimal light, the light will be ON and vice versa the light will be OFF when more light intensity is received by the LDR. In addition, the Blynk application is able to control the lights remotely when connected to the internet network and, in this study, has been tested up to a distance of 2.7 km. It can be concluded that as long as the system is connected to WiFi stably and continuously, this control system can perform the task of turning on and off the lights independently when the owner is not at home.
Analisis Sentimen Masyarakat Pengguna Media Sosial Twitter Terhadap Motogp Mandalika Lombok Menggunakan Metode Bidirectional Encoder Representation From Transformers (BERT) Nelly Sofi; Tri Sulistyorini; Muhammad Nazaruddin
Jurnal Informasi, Sains dan Teknologi Vol. 6 No. 1 (2023): Juni: Jurnal Informasi Sains dan Teknologi
Publisher : Politeknik Negeri FakFak

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/isaintek.v6i1.103

Abstract

The MotoGP One race in West Nusa Tenggara Lombok, Mandalika which was held on March 18 2022, received many responses or reactions from the public on social media, especially Twitter. There are those who agree and disagree about the holding of MotoGP in Mandalika, to find out the responses of the people who agree or disagree is needed that can process tweets data using the sentiment analysis method. The use of BERT (Bidirectional Encoder Representations from Transformers) for sentiment analysis produces a bidirectional language model that can understand the context of all words from a sentence. The dataset used goes through preprocessing stages such as case folding, data cleaning, tokenization, normalization, and removal of stopwords before sentiment analysis is carried out. This study uses several hyperparameters, namely a batch size of 32, the optimizer uses Adam with a learning rate of 3e-6 or 0.000003, and an epoch of 25. The evaluation results of the model obtain an accuracy of 55%. Precision for positive by 56%, neutral by 59%, and negative by 44%. Recall for positive is 74%, neutral is 29%, and negative is 54%. F1-score for positive is 64%, neutral is 38%, and negative is 48%.
PENERAPAN HYPERPARAMETER CONVOLUTIONAL NEURAL NETWORK (CNN) DALAM MEMBANGUN MODEL SEGMENTASI GAMBAR MENGGUNAKAN ARSITEKTUR U-NET DENGAN TENSORFLOW Tri Sulistyorini; Erma Sova; Nelly Sofie; Revida Iriana Napitupulu
Jurnal Ilmiah Informatika Komputer Vol 28, No 2 (2023)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2023.v28i2.6959

Abstract

Teknologi canggih membutuhkan keterampilan atau performa yang baik untuk memudahkan sebagian pekerjaan di era modern, yaitu dengan menggunakan pendekatan machine learning. Bidang machine learning telah mengalami perubahan yang impresif dengan adanya kemunculan Artificial Neural Network (ANN). Model komputasi ini terinspirasi oleh jaringan saraf biologis yang telah melampaui bentuk kecerdasan buatan pada machine learning pada umumnya. Salah satu arsitektur Artificial Neural Network (ANN) yang paling unggul yaitu Convolutional Neural Network (CNN). CNN pada umumnya digunakan untuk memecahkan masalah pengenalan pola berbasis gambar yang kemudian menghasilkan output yang cukup baik dalam hal kompleksitas sederhana. Tujuan penelitian  adalah untuk Menerapkan convolutional neural network yaitu U-NET dan penerapannya pada TensorFlow, pembuatan segmentasi gambar dengan deep learning yang diterapkan seperti pada Oxford-IIIT Pet Dataset, melakukan pencarian prediksi yang dilakukan dengan arsitektur U-Net untuk menghasilkan hasil yang baik atau malah sebaliknya, melihat perbandingan Predicted Mask dengan True Mask pada kelas kucing yang munculkan dalam bentuk skor IOU dan penerapannya menggunakan nilai batas bawah pada IOU. Metode penelitian adalah untuk mengenalkan machine learning, CNN, dan arsitektur U-NET yang awalnya dirancang untuk segmentasi gambar biomedis. Hasil prediksi yang dilakukan dengan arsitektur U-Net menghasilkan hasil yang baik, perbandingan Predicted Mask dengan True Mask pada kelas kucing yang mendapatkan skor IOU sebesar 0.933. Pada penerapan ini menggunakan batas bawah 0.5 pada IOU sehingga model ini dapat berjalan dengan baik