• Journal of Biomedical Engineering Research
• /
• v.44 no.4
• /
• pp.255-263
• /
• 2023

Clinical ultrasound (US) is a widely used imaging modality with various clinical applications. However, capturing a large field of view often requires specialized transducers which have limitations for specific clinical scenarios. Panoramic imaging offers an alternative approach by sequentially aligning image sections acquired from freehand sweeps using a standard transducer. To reconstruct a 3D volume from these 2D sections, an external device can be employed to track the transducer's motion accurately. However, the presence of optical or electrical interferences in a clinical setting often leads to incorrect measurements from such sensors. In this paper, we propose a deep learning (DL) framework that enables the prediction of scan trajectories using only US data, eliminating the need for an external tracking device. Our approach incorporates diverse data types, including correlation volume, optical flow, B-mode images, and rawer data (IQ data). We develop a DL network capable of effectively handling these data types and introduce an attention technique to emphasize crucial local areas for precise trajectory prediction. Through extensive experimentation, we demonstrate the superiority of our proposed method over other DL-based approaches in terms of long trajectory prediction performance. Our findings highlight the potential of employing DL techniques for trajectory estimation in clinical ultrasound, offering a promising alternative for panoramic imaging.

• Journal of Digital Contents Society
• /
• v.12 no.4
• /
• pp.501-510
• /
• 2011

Most of electronic medical record systems which have been built in Korean hospitals are based on source oriented medical record approach. These systems hardly satisfy diverse objectives owing to the innate imperfections in system architecture and development methodology. Thus, the hybrid of source oriented and problem oriented approach is highly desirable. The purpose of this study is to present an architecture and methodology required to construct hybrid electronic medical record system and to develop a prototype based on them. Analyzing the clinical processes and data requirements of problem oriented medical record approach we developed a software process model as weel as an architecture model which consists of legacy system, clinical data repository, problem list database, prospective plan database, user interface, and synchronization procedures.

• Journal of Korea Multimedia Society
• /
• v.19 no.7
• /
• pp.1107-1115
• /
• 2016

Efficient Market Hypothesis (EMH), states that at any point in time in a liquid market security prices fully reflect all available information. This paper presents a study of proving the hypothesis through daily Twitter sentiments using the hybrid approach of the lexicon-based approach and the naïve Bayes classifier. In this research we analyze the currency exchange rate movement of Indonesia Rupiah vs US dollar as a way of testing the Efficient Market Hypothesis. In order to find a correlation between the prediction sentiments from Twitter data and the actual currency exchange rate trends we collect Twitter data every day and compute the overall sentiment to label them as positive or negative. Experimental results have shown 69% correct prediction of sentiment analysis and 65.7% correlation with positive sentiments. This implies that EMH is semi-strong Efficient Market Hypothesis, and that public information provide by Twitter sentiment correlate with changes in the exchange market trends.

• Journal of Information Technology Services
• /
• v.9 no.4
• /
• pp.231-242
• /
• 2010

The emergence of convergence has been the cause of development of the industry more complex and difficult by continually changing business environment and the destruction of the business area. The government-initiatives approach shows the limits to foster the new industries in needs of service-oriented ecosystem. In this study, we propose the service model as service-based approach for the development of new industries derived through the convergence inter-industry. While business model is defined based on the company's temporary and piecemeal activities, service model is the concept of dynamic and continuous that includes national, industrial, corporate level. In order to derive the service model, to identify current problems and issues with the public and the private sector is first. Then design the roadmap for the implementation of the desired shape through strategy from optimal rationality and long-term strategy. In this study, we define a service model, and consider when establishing a service model for three dimensional(national, industrial, corporate level) through analyzed by 3Level Service Model. And we also consider characteristics of the service model and approach, present the case of 'New Transit Card Services in Seoul'.

• Journal of Korean Society for Quality Management
• /
• v.49 no.3
• /
• pp.405-420
• /
• 2021

Purpose: This study started with the question of how to use Virtual Reality (VR) contents as a part of the non-face-to-face education tool that has recently attracted attention. Methods: In this paper, the use of VR contents as an educational tool is explained as a process of 'new media access dimension'. The question was explored on why Virtual Reality (or Augmented Reality) contents are not used as educational tools in the educational field. Results: As a result, the lack of 'material access' such as devices and infrastructure affects 'motivational access' approach stage, which is the previous stage. Again, it has a negative effect on literacy, which is 'skill access' approach stage. As it was found that it was not circulating to the level of "motive-material-skill-usage", it was discussed that it was taking a different step from the past adoption process of ICT and smart media. Conclusion: Based on this, it is believed that immersive content will contribute to arousing interest that can be applied and spread in the educational field, and it is also thought that it will be possible to derive academic interest in the educational effect according to the characteristics of immersive content such as VR.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1000-1011
• /
• 2021

In recent years, using Deep Learning methods to apply for medical and biomedical image analysis has seen many advancements. In clinical, using Deep Learning-based approaches for cancer image analysis is one of the key applications for cancer detection and treatment. However, the scarcity and shortage of labeling images make the task of cancer detection and analysis difficult to reach high accuracy. In 2015, the Unet model was introduced and gained much attention from researchers in the field. The success of Unet model is the ability to produce high accuracy with very few input images. Since the development of Unet, there are many variants and modifications of Unet related architecture. This paper proposes a new approach of using Unet++ with pretrained EfficientNet as backbone architecture for breast tumor cell nuclei segmentation and uses the multi-organ transfer learning approach to segment nuclei of breast tumor cells. We attempt to experiment and evaluate the performance of the network on the MonuSeg training dataset and Triple Negative Breast Cancer (TNBC) testing dataset, both are Hematoxylin and Eosin (H & E)-stained images. The results have shown that EfficientUnet++ architecture and the multi-organ transfer learning approach had outperformed other techniques and produced notable accuracy for breast tumor cell nuclei segmentation.

• Journal of the Korea Convergence Society
• /
• v.12 no.3
• /
• pp.297-304
• /
• 2021

This study aims not only to access the visual thought-oriented approach that has been implemented in established art therapy and education but also to integrate language education and therapeutic approach to support the development of school-age children. Thus, text mining technique was applied to search for areas where different areas of language and art can be integrated. This research was conducted in accordance with the procedure of basic research, preliminary DB construction, text screening, DB pre-processing and confirmation, stop-words removing, text mining analysis and the deduction about the convergent areas. These results demonstrated that this study draws convergence areas related to regional, communication, and learning functions, areas related to problem solving and sensory organs, areas related to art and intelligence, areas related to information and communication, areas related to home and disability, topics, conceptualization, peer-related areas, integration, reorganization, attitudes. In conclusion, this study is meaningful in that it established a framework for designing an activity-centered convergence program of art and language in the future and attempted a holistic approach to support child development.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.180-180
• /
• 2012

• BMB Reports
• /
• v.57 no.1
• /
• pp.60-65
• /
• 2024

The CRISPR-Cas9 system has significantly advanced regenerative medicine research by enabling genome editing in stem cells. Due to their desirable properties, mesenchymal stem cells (MSCs) have recently emerged as highly promising therapeutic agents, which properties include differentiation ability and cytokine production. While CRISPR-Cas9 technology is applied to develop MSC-based therapeutics, MSCs exhibit inefficient genome editing, and susceptibility to plasmid DNA. In this study, we compared and optimized plasmid DNA and RNP approaches for efficient genome engineering in MSCs. The RNP-mediated approach enabled genome editing with high indel frequency and low cytotoxicity in MSCs. By utilizing Cas9 RNPs, we successfully generated B2M-knockout MSCs, which reduced T-cell differentiation, and improved MSC survival. Furthermore, this approach enhanced the immunomodulatory effect of IFN-r priming. These findings indicate that the RNP-mediated engineering of MSC genomes can achieve high efficiency, and engineered MSCs offer potential as a promising therapeutic strategy.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.11 no.4
• /
• pp.217-222
• /
• 2011

Genetic algorithms are one of the most important methods used to solve the Traveling Salesman Problem. Therefore, many researchers have tried to improve the Genetic Algorithm by using different methods and operations in order to find the optimal solution within reasonable time. This paper intends to find a new approach that adopts an improved genetic algorithm to solve the Traveling Salesman Problem, and compare with the well known heuristic method, namely, Kohonen Self-Organizing Map by using different data sets of symmetric TSP from TSPLIB. In order to improve the search process for the optimal solution, the proposed approach consists of three strategies: two separate tour segments sets, the improved crossover operator, and the improved mutation operator. The two separate tour segments sets are construction heuristic which produces tour of the first generation with low cost. The improved crossover operator finds the candidate fine tour segments in parents and preserves them for descendants. The mutation operator is an operator which can optimize a chromosome with mutation successfully by altering the mutation probability dynamically. The two improved operators can be used to avoid the premature convergence. Simulation experiments are executed to investigate the quality of the solution and convergence speed by using a representative set of test problems taken from TSPLIB. The results of a comparison between the new approach using the improved genetic algorithm and the Kohonen Self-Organizing Map show that the new approach yields better results for problems up to 200 cities.