• 정보관리학회지
• /
• 제34권4호
• /
• pp.59-79
• /
• 2017

본 연구는 Figshare를 통해 공유되고 있는 문헌정보학분야 연구데이터의 유형, 주제, 공개 수준 등을 분석하고 재사용성이 상대적으로 높은 데이터의 특성을 통계적으로 해석해 보았다. 분석 결과 데이터의 유형은 dataset과 paper 유형이, 주제 분야는 open access와 research data가 가장 많은 비중을 차지하였으며, 70%에 가까운 연구데이터가 pdf와 같이 편집과 재사용이 원활하지 않은 형태로 공개되어 있는 것으로 조사되었다. 또한 연구데이터의 특성과 활용 정도간의 관계 분석 결과, 주제에 있어서는 APC(Article Processing Charge)를 비롯한 open access 영역이 가장 많이 활용되고 있는 것으로 나타났으며, 데이터 유형에 있어서는 paper의 활용도가 가장 높은 것으로 나타났다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권9호
• /
• pp.2589-2604
• /
• 2024

Brain tumors, characterized by uncontrollable cellular growths, are a significant global health challenge. Navigating the complexities of tumor identification due to their varied dimensions and positions, our research introduces enhanced methods for precise detection. Utilizing advanced learning techniques, we've improved early identification by preprocessing clinical dataset-derived images, augmenting them via a Generative Adversarial Network, and applying an Improved Privacy-Preserving Collaborative Convolutional Neural Network (IPC-CNN) for segmentation. Recognizing the critical importance of data security in today's digital era, our framework emphasizes the preservation of patient privacy. We evaluated the performance of our proposed model on the Figshare and BRATS 2018 datasets. By facilitating a collaborative model training environment across multiple healthcare institutions, we harness the power of distributed computing to securely aggregate model updates, ensuring individual data protection while leveraging collective expertise. Our IPC-CNN model achieved an accuracy of 99.40%, marking a notable advancement in brain tumor classification and offering invaluable insights for both the medical imaging and machine learning communities.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1233-1241
• /
• 2022

Tumors of the brain are the deadliest, with a life expectancy of only a few years for those with the most advanced forms. Diagnosing a brain tumor is critical to developing a treatment plan to help patients with the disease live longer. A misdiagnosis of brain tumors will lead to incorrect medical treatment, decreasing a patient's chance of survival. Radiologists classify brain tumors via biopsy, which takes a long time. As a result, the doctor will need an automatic classification system to identify brain tumors. Image classification is one application of the deep learning method in computer vision. One of the deep learning's most powerful algorithms is the convolutional neural network (CNN). This paper will introduce a novel deep learning structure and image gradient to classify brain tumors. Meningioma, glioma, and pituitary tumors are the three most popular forms of brain cancer represented in the Figshare dataset, which contains 3,064 T1-weighted brain images from 233 patients. According to the numerical results, our method is more accurate than other approaches.

• International Journal of Knowledge Content Development & Technology
• /
• 제8권1호
• /
• pp.25-36
• /
• 2018

Research data must be testable. Science is all about verification and testing. To make data testable, tools used to produce, collect, and examine data during the research must be available. Quite often, however, these data become inaccessible once the work is over and the results being published. Hence, information and the related context must be provided on how research data are preserved and how they can be reproduced. Open Science is the international movement for making scientific research data properly accessible for research community. One of its major goals is building data repositories to foster wide dissemination of open data. The objectives of this research are to examine the features of research data, common repository platforms, and community requests for the purpose of designing functional requirements for research data repositories. To analyze the features of the research data, we use data curation profiles available from the Data Curation Center of the Purdue University, USA. For common repository platforms we examine Fedora Commons, iRODS, DataONE, Dataverse, Open Science Data Cloud (OSDC), and Figshare. We also analyze the requests from research community. To design a technical solution that would meet public needs for data accessibility and sharing, we take the requirements of RDA Repository Interest Group and the requests for the DataNest Community Platform developed by the Korea Institute of Science and Technology Information (KISTI). As a result, we particularize 75 requirement items grouped into 13 categories (metadata; identifiers; authentication and permission management; data access, policy support; publication; submission/ingest/management, data configuration, location; integration, preservation and sustainability, user interface; data and product quality). We hope that functional requirements set down in this study will be of help to organizations that consider deploying or designing data repositories.