22 April 2024 in IEEE Access
AAAmelia Devi Putri Ariyanto
Amelia Devi Putri Ariyanto
Challenges in the big data phenomenon arise due to the existence of unstructured text data, which is very large, comes from various sources, has various formats, and contains much noise. The complexity of unstructured text data makes it difficult to extract useful information. Therefore, a process is needed to transform it into structured data to be processed further. The information Extraction (IE) process helps to extract relationships, entities, semantic roles, and events from unstructured text data by converting them into structured output. One of IE’s tasks is Semantic Role Labeling (SRL), which has a crucial function in identifying semantic roles in a sentence so that it can enrich the understanding of the text. However, much of SRL development focuses on high-resource data, especially in English. The limited development of SRL in specific low-resource languages or domains is a complex challenge. This research aims to conduct a systematic study on the development of SRL for low-resource data, both in low-resource language or domain-specific contexts. The review process was carried out systematically using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) model, and 54 quality papers were obtained from the filtering process (from 2018 to 2023). We review several essential points, including (1) datasets that are often used for SRL tasks and their labeling strategies for low-resource data, (2) methods that have currently been developed for SRL tasks and learning scenarios when dealing with low-resource data, (4) evaluation metrics, (5) application of SRL tasks. This review is complemented by a discussion of issues and potential solutions for developing SRL on low-resource data to help researchers develop SRL more effectively in dealing with the challenges faced with low-resource data.
14 January 2020 in Scientometrics
1 January 2017 in Procedia Computer Science
ESEsther Irawati Setiawan
Biomedical engineering research trend can be healthcare models with unobtrusive smart systems for monitoring vital signs and physical activity. Detecting infant facial cry because of inability to communicate pain, recognizing facial emotion to understand dysfunction mechanisms through micro expression or transform captured human expression with motion device into three-dimensional objects are some of the applied systems. Nowadays, collaborated with biomedical research, mining and analyzing social network can improve public and private health care sectors as well such as research health news shared on social media about pharmaceutical drugs, pandemics, or viral outbreaks. Due to the vast amount of shared news, there is an urgency to select and filter information to prevent the spread of hoax or fake news. We explored in depth some steps to classify hoaxes written as news articles. This discussion also encourages on how technologies of social network analysis could be used to make new kinds improvement in health care sectors. Then close with a description of limitless future possibilities of biomedical engineering research in social media.
1 September 2014 in International Journal on Smart Sensing and Intelligent Systems
Overlapping white blood cell identification on microscopic blood cell images is proposed for increasing the accuracy of white blood cell segmentation and counting. The accurate identification of overlapping cells can increase the accuracy of cell counting system for diagnosing diseases. The overlapping cells have different characteristic such as area and shape with a single cell of microscopic cell images therefore the overlapping cell identification based on geometric feature is preferred. As a result, the proposed method identifies and counts the number of overlapping cells similar with manual white blood cell counting. In addition, the proposed method segment nucleus and cytoplasm of white blood cell with average of accuracy 85.22% and 70.27% from the manual segmented respectively. For future work, the results can be extended to separate the identified overlapping cell therefore it can applied for differential white blood cell counting for diagnosing diseases.
26 April 2022 in Journal of Information Systems Engineering and Business Intelligence
NRNarandha Arya Ranggianto
Background: Twitter is one of the most used social media, with 310 million active users monthly and 500 million tweets per day. Twitter is not only used to talk about trending topics but also to share information about accidents, fires, traffic jams, etc. People often find these updates useful to minimize the impact. Objective: The current study compares the effectiveness of three deep learning methods (CNN, RCNN, CLSTM) combined with neuroNER in classifying multi-label incidents. Methods: NeuroNER is paired with different deep learning classification methods (CNN, RCNN, CLSTM). Results: CNN paired with NeuroNER yield the best results for multi-label classification compared to CLSTM and RCNN. Conclusion: CNN was proven to be more effective with an average precision value of 88.54% for multi-label incidents classification. This is because the data we used for the classification resulted from NER, which was in the form of entity labels. CNN immediately distinguishes important information, namely the NER labels. CLSTM generates the worst result because it is more suitable for sequential data. Future research will benefit from changing the classification parameters and test scenarios on a different number of labels with more diverse data. Keywords: CLSTM, CNN, Incident Classification, Multi-label Classification, RCNN