Coronavirus Disease-2019 (COVID-19) is a new type of coronavirus that has become a pandemic in various countries. The large number of people exposed to COVID-19 at the same time makes it difficult for hospitals to accommodate all patients so that they must determine the priority scale which patients should get treatment first. In this study, we designed a decision-making system that was used to determine which patients were prioritized for treatment. In addition, we integrate with AI to quickly detect someone exposed to covid or not from X Ray images. The X Ray image detection model that we use is based on VGG16. Obtained f1-score in testing the Covid-19 and non-Covid-19 label dataset by 99.4%. Then in the normal label dataset, covid-19, and pneumonia obtained f1score 96.5%. In the covid-19 dataset and pneumonia an f1score of 98.7% was obtained. In addition, our model also beats other pretrain models such as densenet, resnet, squeezenet, and inception with a range of around 4%. This study also provides the same results between manual calculations and decision support systems that are built.
The development of educational facilities in an area must be considered optimally in accordance with national regulatory standards so that it makes it easier for the community to access these facilities. This study aims to understand and describe affordability, the distribution pattern of location points for SMA/SMK/MA Negeri in Tangerang Regency and to find out the relationship between the population aged 15-19 years for each sub-district in Tangerang Regency using a quantitative descriptive research method with a spatial approach. The affordability analysis resulted in 76.05% of residential areas not being reached, with a random pattern of location points and no correlation between the location points of State SMA/SMK/MA and the population aged 15-19 years with a correlation index value of 0.106.
Social distancing includes strategies to ban public gatherings and advise individuals to stay at their home or maintain distance to one another by at least 1-2 meters. This study aims to intend to assess all the available evidence of social distancing in decreasing COVID-19 transmission in the general population. We conducted an electronic search of published literature using MEDLINE/Pubmed, Science direct, PMC, Wiley, and Google Scholar and we use Joanna Briggs Institute (JBI) critical appraisal checklist to assess methodological qualities. A total of 7 articles were decided to be included in this study. Social distancing has curb down the number and saved approximately 10 thousand Brazilian lives. A study by VoPham et al on the association of social distancing and COVID-19 incidence found higher social distancing was associated with a 29% reduction of COVID-19 incidence (adjusted IRR 0.71;95% CI (0,57-0,87) and 35% reduction of COVID-19 mortality (adjusted IRR 0,65; 95% CI 0,55-0,76). Social distancing is one of the major policies implemented for long-term behavioral adjustment in managing the COVID-19 pandemic. Passive social distancing is not enough to drag down the number, there needs to be large scale testing, isolation, and contact tracing. However, we believe we have illuminated the impact of social distancing on the COVID-19 pandemic and add to the available literature the basis of social distancing in reducing transmission of COVID-19.
Part of Speech Tagging atau POS Tag merupakan salah satu proses untuk mengelompokkan kata berdasarkan kelas kata seperti: kata benda, kata kerja, atau kata sambung. Kegunaan POS Tag antara lain dapat bermanfaat pada analisis sentimen, pengenalan entitas bernama, dan konversi teks ke suara. Dalam melakukan POS Tag, jika dilakukan secara manual dapat menghabiskan banyak waktu, oleh karena itu dibuatlah sistem berbasis machine learning untuk mengotomatisasi proses ini. Pada penelitian ini, dilakukan POS Tag dengan menerapkan transfer learning dengan model Embedding from Language Model (ELMo). Model ELMo cukup populer digunakan pada dataset bahasa Inggris karena dapat memberi hasil akurasi yang memuaskan namun pada dataset bahasa Indonesia belum ada paper yang membahas tentang model ini. Melalui penelitian ini ingin dilihat bagaimana performa ELMo pada dataset bahasa Indonesia. Model yang digunakan untuk menyelesaikan masalah POS Tag adalah model berbasis BiLSTM. Pada penelitian ini, juga ingin dilihat bagaimana performa model jika ditambahkan CNN setelah BiLSTM. Selain itu, juga diteliti bagaimana performa dari tiap lapisan ELMo. Dari penelitian ini diperoleh bahwa metode BiLSTM + CNN + CRF dengan embedding ELMo lapisan pertama memiliki akurasi terbaik, dengan nilai 95.62%. Selain itu, diperoleh bahwa penambahan CNN setelah BiLSTM dapat meningkatkan akurasi serta mengurangi overfitting pada masalah POS Tag bahasa Indonesia.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.