The COVID-19 pandemic has induced many problems in various sectors of human life. After more than one year of the pandemic, many studies have been conducted to discover various technological innovations and applications to combat the virus that has claimed many lives. The use of Big Data technology to mitigate the threats of the pandemic has been accelerated. Therefore, this survey aims to explore Big Data technology research in fighting the pandemic. Furthermore, the relevance of Big Data technology was analyzed while technological contributions to five main areas were highlighted. These include healthcare, social life, government policy, business and management, and the environment. The analytical techniques of machine learning, deep learning, statistics, and mathematics were discussed to solve issues regarding the pandemic. The data sources used in previous studies were also presented and they consist of government officials, institutional service, IoT generated, online media, and open data. Therefore, this study presents the role of Big Data technologies in enhancing the research relative to COVID-19 and provides insights into the current state of knowledge within the domain and references for further development or starting new studies are provided.
31 January 2021 in ACM Transactions on Asian and Low-Resource Language Information Processing
A novel Indonesian sentiment lexicon (SentIL -- Sentiment Indonesian Lexicon) is created with an automatic pipeline; from creating sentiment seed words, adding new words with slang words, emoticons, and from the given dictionary and sentiment corpus, until tuning sentiment value with tagged sentiment corpus. It begins by taking seed words from WordNet Bahasa that mapped with sentiment value from English SentiWordNet . The seed words are enriched by combining the dictionary-based method with words’ synonyms and antonyms, and corpus-based methods with word embedding for word similarity that trained in positive and negative sentiment corpus from online marketplaces review and Twitter data. The valence score of each lexicon is recalculated based on its relative occurrence in the corpus. We also add some famous slang words and emoticons to enrich the lexicon. Our experiment shows that the proposed method can provide an increase of 3.5 times lexicon number as well as improve the accuracy of 80.9% for online review and 95.7% for Twitter data, and they are better than other published and available Indonesian sentiment lexicons.
Ionospheric disturbances caused by the 2016 West Sumatra earthquake have been studied using total electron content (TEC) measurements by Global Navigation Satellite System (GNSS) observation stations evenly distributed in Sumatra and Java, Indonesia. Previous observation focused on the coseismic ionospheric disturbances (CID) detected 11–16 min after the earthquake. The maximum TEC amplitude measured was 2.9 TECU (TEC Unit) with speed between 1 and 1.72 km/s. A comprehensive analysis needs to be done to see how the growth and direction of the movement of the CID due to the earthquake is using the 3D tomography method. The dimensions of 3D tomographic model are setup to 1° × 1.2° × 75 km. The continuity constraints were used to stabilize the solution, and multiple resolution tests with synthetic data were conducted to evaluate the precision of the results. This research focuses on the anomalous movement of the ionosphere observed in three dimensions. From the model, the positive anomaly initially appeared 11 min after the earthquake at the altitude of 300 km, which is the highest ionization layer and correspond to the electron density profile using IRI model. The anomalous movement appeared 12 min after the mainshock and moved 1° toward the geomagnetic field every minute. The density anomaly of the ionosphere began to weaken 8 min after the appearance of CID. To check the accuracy of the 3D tomography model, we carried out two types of tests, namely checkerboard resolution test and the second resolution test.
An ensemble of machine learning approach is presented to detect the sentiment polarity in Indonesian user-generated text. We use TF-IDF, term presence, and valence score of sentiment lexicon as features in learning process for classifier model generation. The valence score is resulted from a system which considers the negation and booster words as well. Our experiments with ensemble approach for sentiment polarity analysis on Indonesian user generated text slightly better than single classifier approach and outperform the baseline methods, which gives 91.59% accuracy and 91.59% F1-score.
1 February 2023 in International Journal of Electrical and Computer Engineering (IJECE)
Even though coronavirus disease 2019 (COVID-19) vaccination has been done, preparedness for the possibility of the next outbreak wave is still needed with new mutations and virus variants. A near real-time surveillance system is required to provide the stakeholders, especially the public, to act in a timely response. Due to the hierarchical structure, epidemic reporting is usually slow particularly when passing jurisdictional borders. This condition could lead to time gaps for public awareness of new and emerging events of infectious diseases. Online news is a potential source for COVID-19 monitoring because it reports almost every infectious disease incident globally. However, the news does not report only about COVID-19 events, but also various information related to COVID-19 topics such as the economic impact, health tips, and others. We developed a framework for online news monitoring and applied sentence classification for news titles using deep learning to distinguish between COVID-19 events and non-event news. The classification results showed that the fine-tuned bidirectional encoder representations from transformers (BERT) trained with Bahasa Indonesia achieved the highest performance (accuracy: 95.16%, precision: 94.71%, recall: 94.32%, F1-score: 94.51%). Interestingly, our framework was able to identify news that reports the new COVID strain from the United Kingdom (UK) as an event news, 13 days before the Indonesian officials closed the border for foreigners.
2 May 2025 in Bulletin of Electrical Engineering and Informatics
Recognizing chili plant varieties through chili leaf image samples automatically at low costs represents an intriguing area of study. While maintaining and protecting the quality of chili plants is a priority, classifying leaf images captured randomly requires considerable effort. The quality of the captured leaf images significantly impacts the development of the model. This study applies a meta-learning approach to chili leaf image data, creating a dataset and classifying leaf images captured using mobile devices with varying camera specifications. The images were organized into 14 experimental groups to assess accuracy. The approach included 2-way and 3-way classification tasks, with 3-shot, 5-shot, and 10-shot learning scenarios, to analyze the influence of various chili leaf image factors and optimize the classification and segmentation model's accuracy. The findings demonstrate that a minimum of 10 shots from the meta-test dataset is sufficient to achieve an accuracy of 84.87% using 2-way classification meta-learning combined with the mix-up augmentation technique.