• Biomolecules & Therapeutics
• /
• v.30 no.2
• /
• pp.179-183
• /
• 2022

Traditionally, pathologists microscopically examine tissue sections to detect pathological lesions; the many slides that must be evaluated impose severe work burdens. Also, diagnostic accuracy varies by pathologist training and experience; better diagnostic tools are required. Given the rapid development of computer vision, automated deep learning is now used to classify microscopic images, including medical images. Here, we used a Inception-v3 deep learning model to detect mouse lung metastatic tumors via whole slide imaging (WSI); we cropped the images to 151 by 151 pixels. The images were divided into training (53.8%) and test (46.2%) sets (21,017 and 18,016 images, respectively). When images from lung tissue containing tumor tissues were evaluated, the model accuracy was 98.76%. When images from normal lung tissue were evaluated, the model accuracy ("no tumor") was 99.87%. Thus, the deep learning model distinguished metastatic lesions from normal lung tissue. Our approach will allow the rapid and accurate analysis of various tissues.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.557-560
• /
• 2023

In this paper, we introduce a pre-training method leveraging the capabilities of the Vision Transformer (ViT) for disease diagnosis in conventional Fundus images. Recognizing the need for effective representation learning in medical images, our method combines the Vision Transformer with a Masked Autoencoder to generate meaningful and pertinent image augmentations. During pre-training, the Masked Autoencoder produces an altered version of the original image, which serves as a positive pair. The Vision Transformer then employs contrastive learning techniques with this image pair to refine its weight parameters. Our experiments demonstrate that this dual-model approach harnesses the strengths of both the ViT and the Masked Autoencoder, resulting in robust and clinically relevant feature embeddings. Preliminary results suggest significant improvements in diagnostic accuracy, underscoring the potential of our methodology in enhancing automated disease diagnosis in fundus imaging.

• Journal of Information Processing Systems
• /
• v.19 no.4
• /
• pp.540-553
• /
• 2023

The hollow letter CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) is an optimized version of solid CAPTCHA, specifically designed to weaken characteristic information and increase the difficulty of machine recognition. Although convolutional neural networks can solve CAPTCHA in a single step, a good attack result heavily relies on sufficient training data. To address this challenge, we propose a seed filling algorithm that converts hollow characters to solid ones after contour line restoration and applies three rounds of detection to remove noise background by eliminating noise blocks. Subsequently, we utilize a support vector machine to construct a feature vector for recognition. Security analysis and experiments show the effectiveness of this algorithm during the pre-processing stage, providing favorable conditions for subsequent recognition tasks and enhancing the accuracy of recognition for hollow CAPTCHA.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.55 no.10
• /
• pp.410-417
• /
• 2006

Generally, the training set of maximum $m{\times}L(m+f)$ patterns in the pattern recognition method is required for the real-time bus reconfiguration strategy when a main transformer fault occurs in the distribution substation. Accordingly, to make the application of pattern recognition method possible, the size of the training set must be reduced as efficient level. This Paper proposes a methodology which obtains the minimized training set by applying the pattern clustering method to load patterns of the main transformers and feeders during selected period and to obtain bus reconfiguration strategy based on it. The MaxMin distance clustering algorithm is adopted as the pattern clustering method. The proposed method reduces greatly the number of load patterns to be trained and obtain the satisfactory pattern matching success rate because that it generates the typical pattern clusters by appling the pattern clustering method to load patterns of the main transformers and feeders during selected period. The proposed strategy is designed and implemented in Visual C++ MFC. Finally, availability and accuracy of the proposed methodology and the design is verified from diversity simulation reviews for typical distribution substation.

• Journal of East-West Nursing Research
• /
• v.19 no.2
• /
• pp.96-103
• /
• 2013

Purpose: The purpose of this study was to identify the factors influencing hospital staffs' performance ability of Cardiopulmonary resuscitation (CPR). Methods: The study was conducted with 250 hospital staffs in B hospital located in Busan. The survey data were collected from August 1 to September 15, 2012 and were analyzed using frequencies, percentages, means, t-test, ANOVA, Pearson correlation coefficient and stepwise multiple regression with the SPSS WIN 19.0 program. Results: There were statistically significant differences in performance ability of CPR depending on occupations, CPR experience, CPR situations, identification of Automated external defibrillator (AED) location within the hospital, AED use experience, CPR training experience and AED training experience. A significant positive correlation was found between CPR knowledge and performance ability in addition to a significant positive correlation between CPR attitude and to performance ability. The significant factors influencing performance ability of CPR were CPR attitude, occupations, CPR training experience, knowledge and identification of AED location within the hospital. Those factors explained about 40.1% of the variance. Conclusion: It is necessary to develop a strategy for hospital staff to improve the levels of performance ability of CPR.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.21-26
• /
• 2006

This paper focuses on modeling and predicting differential GPS corrections transmitted by marine radio-beacon systems using artificial neural networks. Various neural network structures with various training algorithms were examined, including Linear, Radial Biases, and Feedforward. Matlab Neural Network toolbox is used for this purpose. Data sets used in building the model are the transmitted pseudorange corrections and broadcast navigation message. Model design is passed through several stages, namely data collection, preprocessing, model building, and finally model validation. It is found that feedforward neural network with automated regularization is the most suitable for our data. In training the neural network, different approaches are used to take advantage of the pseudorange corrections history while taking into account the required time for prediction and storage limitations. Three data structures are considered in training the neural network, namely all round, compound, and average. Of the various data structures examined, it is found that the average data structure is the most suitable. It is shown that the developed model is capable of predicting the differential correction with an accuracy level comparable to that of beacon-transmitted real-time DGPS correction.

• The Journal of Information Systems
• /
• v.19 no.4
• /
• pp.183-206
• /
• 2010

The technology acceptance model (TAM) is a lot of cited in information technology adoption and usage researches. But TAM has been conducted primarily in volitional environments of the adoption of new technology. This paper discusses technology acceptance in accounting information systems to examine TAM with Characteristics of Organizations and Individuals in mandated using Combined Guard System. Combined Guard System is a scientific guard system that is composed of automated surveillance system, automated sensing system and control system. GOP Scientific Guard System is operated by GOP unit in Korean Army O Division from 2006. In this study, using the extended technology acceptance model, we have analyzed factors which affect the usage intention of GOP Scientific Guard System in mandated using environment. Based upon previous researches, we have selected Support of management unit, Training, Perceived Risk, Subjective Knowledge and Computer Self-efficacy, perceived usefulness, perceived ease of use, and usage intention as variables and proposed a research model. We collected 253 survey questionnaires from Korean army officer and soldier who are serviced at GOP unit in O Division, and analyzed the data using SPSS 12.0 and SmartPLS 2.0M3. According to the results by PLS analysis, According to the results by PLS analysis, Training and Subjective Knowledge did not affect Perceived usefulness, but the other hypotheses were accepted. And Perceived usefulness, and Ease of use influenced the Usage intention. The results of this study will increase Characteristics of Organizations and Individuals on GOP Scientific Guard System and eventually contribute to establishing the activation of Combined Guard System.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.350-352
• /
• 2017

Virtual reality technology was initially developed for entertainment purposes such as games, movies, sports, and theme parks, but gradually expanded to a number of industries such as education, e-commerce, and health care,. Therefore, safety education content incorporating VR is also rising rapidly. However, the program activity on safety education in our country is still insignificant. Although rescue of patients with acute cardiac arrest using defibrillators is one of the most representative safety education, in 2014, defibrillators are rarely used in Korea to save the lives of patients and there are very few cases of using defibrillators. The use of automatic defibrillators and the importance of knowing how to use them for expanding accessibility are necessary. However, it is not easy to provide experience education only after completing the safety education in simple theoretical education. In this paper, we propose a automatic defibrillator training simulation system using virtual reality that can be freelu trained at any time.

• Journal of Platform Technology
• /
• v.11 no.3
• /
• pp.56-67
• /
• 2023

Recently, de-identification of personal information, which has been a long-cherished desire of the data-based industry, was revised and specified in August 2020. It became the foundation for activating data called crude oil[2] in the fourth industrial era in the industrial field. However, some people are concerned about the infringement of the basic rights of the data subject[3]. Accordingly, a development study was conducted on the Batch De-Identification Tool, a personal information de-identification automation tool. In this study, first, we developed an image labeling tool to label human faces (eyes, nose, mouth) and car license plates of various resolutions to build data for training. Second, an object recognition model was trained to run the object recognition module to perform de-identification of personal information. The automated personal information de-identification tool developed as a result of this research shows the possibility of proactively eliminating privacy violations through online services. These results suggest possibilities for data-based industries to maximize the value of data while balancing privacy and utilization.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.1
• /
• pp.1-13
• /
• 2024

This study assessed the efficacy of improving the accuracy of reservoir water level prediction models by employing automated machine learning models and efficient cross-validation methods for time-series data. Considering the inherent complexity and non-linearity of time-series data related to reservoir water levels, we proposed an optimized approach for model selection and training. The performance of twelve models was evaluated for the Obong Reservoir in Gangneung, Gangwon Province, using the TPOT (Tree-based Pipeline Optimization Tool) and four cross-validation methods, which led to the determination of the optimal pipeline model. The pipeline model consisting of Extra Tree, Stacking Ridge Regression, and Simple Ridge Regression showed outstanding predictive performance for both training and test data, with an R² (Coefficient of determination) and NSE (Nash-Sutcliffe Efficiency) exceeding 0.93. On the other hand, for predictions of water levels 12 hours later, the pipeline model selected through time-series split cross-validation accurately captured the change pattern of time-series water level data during the test period, with an NSE exceeding 0.99. The methodology proposed in this study is expected to greatly contribute to the efficient generation of reservoir water level predictions in regions with high rainfall variability.