Garuda - Garba Rujukan Digital

Comparison of Fine-tuned CNN Architectures for COVID-19 Infection Diagnosis Jonathan, Jonathan; Widjaja, Moeljono; Suryadibrata, Alethea
ULTIMATICS Vol 16 No 1 (2024): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v16i1.3652

SARS-CoV-2 (COVID-19) virus spread quickly worldwide affects a variety of industries. The government took preventive steps to control the infection, such as diagnosing the human's lung by taking an X-Ray to see if the lungs were infected with COVID-19 or not. Using several pre-trained Convolutional Neural Network models as the basic model, this research deconstructs the comparison of fine-tuned architecture to identify which pre-trained model delivers the best outcomes in diagnosis by applying machine learning. Comparison is conducted using two scenarios that use batch sizes 64 and 32. Accuracy and f1 score are two evaluation metrics used to justify the model's good performance because the images in the real world, especially for positive classes, are scarce. According to the study, EfficientNetB0 outperforms other pre-trained models, namely ResNet50V2 and Xception, which achieved an accuracy of 0.895 and f1 score of 0.8871.

Automatic detection of dress-code surveillance in a university using YOLO algorithm Tantra, Benjamin Jason; Widjaja, Moeljono
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i2.pp1568-1575

Dress-code surveillance is a field that utilizes an object detection model to en- sure that people wear the proper attire in workplaces and educational institutions. The case is the same within universities, where students and staff must adhere to campus clothing guidelines. However, campus security still enforces univer- sity student clothing manually. Thus, this experiment creates an object detection model that can be used in the campus environment to detect if students are wear- ing appropriate clothing. The model developed for this research has reached an f1-score of 45% with an overall 51.8% mean accuracy precision. With this, the model has reached a satisfactory state with room for further improvements.

Beyond Traditional Methods: The Power of Bi-LSTM in Transforming Customer Review Sentiment Analysis Tjiptadjaja, Casey; Widjaja, Moeljono
IJNMT (International Journal of New Media Technology) Vol 12 No 1 (2025): Vol 12 No 1 (2025): IJNMT (International Journal of New Media Technology)
Publisher : Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ijnmt.v12i1.3775

In the current generation, many large and small companies compete fiercely to create things better than those on the market, such as smartphones, TVs, and many other things. One way they can do this is by guaranteeing the quality of services or goods that are better than others. The provider must investigate the feedback of their users or customers to improve the quality of service of the goods or services offered. Most medium and small companies, such as Micro, Small, and Medium enterprises (MSMEs), online stores, and so on, conduct research on customer feedback manually by looking at one-by-one feedback from customers, which is very ineffective and inefficient if a lot of customer feedback is obtained. Therefore, this research is conducted with the intention and purpose of helping medium and small companies analyze their customer sentiment, as well as trends over a certain period. This research will apply the Bidirectional Long Short-Term Memory (Bi-LSTM) algorithm to perform sentiment analysis on customer feedback. This research also compares other deep learning methods with the proposed method, namely the Uni-LSTM, GRU, CNN, and Simple-RNN algorithms. After testing, the accuracy results of the Uni-LSTM, Bi-LSTM, GRU, CNN, and Simple-RNN algorithms are 52.2%, 92.4%, 52.2%,

Comparison of Fine-tuned CNN Architectures for COVID-19 Infection Diagnosis Jonathan, Jonathan; Widjaja, Moeljono; Suryadibrata, Alethea
ULTIMATICS Vol 16 No 1 (2024): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v16i1.3652

SARS-CoV-2 (COVID-19) virus spread quickly worldwide affects a variety of industries. The government took preventive steps to control the infection, such as diagnosing the human's lung by taking an X-Ray to see if the lungs were infected with COVID-19 or not. Using several pre-trained Convolutional Neural Network models as the basic model, this research deconstructs the comparison of fine-tuned architecture to identify which pre-trained model delivers the best outcomes in diagnosis by applying machine learning. Comparison is conducted using two scenarios that use batch sizes 64 and 32. Accuracy and f1 score are two evaluation metrics used to justify the model's good performance because the images in the real world, especially for positive classes, are scarce. According to the study, EfficientNetB0 outperforms other pre-trained models, namely ResNet50V2 and Xception, which achieved an accuracy of 0.895 and f1 score of 0.8871.

Title

Found 4 Documents
Search

Abstract

Abstract

Abstract

Abstract

Title Search

Found 4 Documents Search

Abstract

Abstract

Abstract

Abstract

Title

Found 4 Documents
Search