Setia Budi
Universitas Kristen Maranatha

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

Found 4 Documents
Search

Pengaruh Preprocessing Terhadap Klasifikasi Diabetic Retinopathy dengan Pendekatan Transfer Learning Convolutional Neural Network Juan Elisha Widyaya; Setia Budi
Jurnal Teknik Informatika dan Sistem Informasi Vol 7 No 1 (2021): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v7i1.3327

Abstract

Diabetic retinopathy (DR) is eye diseases caused by diabetic mellitus or sugar diseases. If DR is detected in early stage, the blindness that follow can be prevented. Ophthalmologist or eye clinician usually decide the stage of DR from retinal fundus images. Careful examination of retinal fundus images is time consuming task and require experienced clinicians or ophthalmologist but a computer which has been trained to recognize the DR stages can diagnose and give result in real-time manner. One approach of algorithm to train a computer to recognize an image is deep learning Convolutional Neural Network (CNN). CNN allows a computer to learn the features of an image, in our case is retinal fundus image, automatically. Preprocessing is usually done before a CNN model is trained. In this study, four preprocessing were carried out. Of the four preprocessing tested, preprocessing with CLAHE and unsharp masking on the green channel of the retinal fundus image give the best results with an accuracy of 79.79%, 82.97% precision, 74.64% recall, and 95.81% AUC. The CNN architecture used is Inception v3.
Form Recognition dan Character Mapping Menggunakan Image Segmentation dan Optical Character Recognition Christian Wibisono; Setia Budi
Jurnal Teknik Informatika dan Sistem Informasi Vol 7 No 1 (2021): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v7i1.3340

Abstract

Industry 4.0 revolve the way of thinking in manufacturing factory business. Speed and accuracy become the main focus to survive and To growth. This study aims to build a blue print of an system that will increase both speed and accuracy in form input. This research will use several computer vision technologies like CNN that will used to do form classification and image segmentation, there is also OCR that will take specific information from a document that have been classified with CNN and then transform it into a JSON format which have more generic format and can be used in most common platform.
Analisis Persepsi Risiko Pekerja di Indonesia Terhadap COVID-19 Dzikri Robbi; Mewati Ayub; Setia Budi
Jurnal Teknik Informatika dan Sistem Informasi Vol 8 No 2 (2022): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v8i2.5056

Abstract

Since August 2020, the COVID-19 pandemic has affected more than 29 million workers in Indonesia. Therefore, worker protection and job creation must be an important priority to emerge more resilient and productive after the COVID-19 crisis. Threat assessment and risk perception are core features of protective-motivation theory and understanding workers' perceptions of COVID-19 risk is expected to help navigate and manage the impact of this pandemic on workers. This study assesses workers' risk perceptions of COVID-19 using a national sample of size N=1,900 of workers in Indonesia. The level of employee risk perception of COVID-19 is relatively high in all workplaces and the workplace also influences the level of risk perception. From all respondents, it is known that the respondent's knowledge about COVID-19, the respondent's behavior towards COVID-19 and the social environmental conditions at the respondent's workplace are all significant predictors of the perceived risk of COVID-19. Age group and type of workplace were found to be significant determinants of perceived risk, compared to the sex and employment status of the examined workers. In all workplaces, respondents stated that the risk of spreading COVID-19 was at a moderate level and the work area was considered an area that had a higher risk of spreading COVID-19 compared to smoking areas and the canteen or pantry.
Ekstraksi Perilaku Komuter Pada Commuter Line Menggunakan Rule-Based Machine Learning Albertus Indarko Wiyogo; Setia Budi; Hapnes Toba
Jurnal Teknik Informatika dan Sistem Informasi Vol 9 No 1 (2023): JuTISI (in progress)
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v9i1.6133

Abstract

The application of Automatic Fare Collection (AFC) on Commuter Line trains can provide new knowledge in navigating between Commuter Line train lines and real commuter travel data. The AFC system allows management to obtain large amounts of detailed data regarding the routes of each commuter daily. One of the challenges faced in using big data at AFC is the extraction of data on the behavior of transporting passengers. Commuter Line passenger behavior is a very important factor for operators to make the right decision. This study uses the association rules method to extract AFC data to produce good information and understand Jabodetabek commuter behavior. The results showed that the association rules method could extract AFC data and produce strong association rules on commuter behavior.