• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.154-157
• /
• 2003

In order for testing faults of combinatorial logic circuit, the authors have developed a new diagnosis method: "Neural Network (NN) fault diagnosis", based on fm error back propagation functions. This method has proved the capability to test gate faults of wider range including so called SSA (single stuck-at) faults, without assuming neither any set of test data nor diagnosis dictionaries. In this paper, it is further shown that what kind of fault models can be detected in the NN fault diagnosis, and the simply modified one can extend to test delay faults, e.g. logic hazard as long as the delays are confined to those due to gates, not to signal lines.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.223-229
• /
• 2021

Classification of different blood cell types is an essential task for human's medical treatment. The white blood cells have different types of cells. Counting total White Blood Cells (WBC) and differential of the WBC types are required by the physicians to diagnose the disease correctly. This paper used transfer learning methods to the pre-trained deep learning models to classify different WBCs. The best pre-trained model was Inception ResNetV2 with Adam optimizer that produced classification accuracy of 98.4% for the dataset comprising four types of WBCs.

• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.200-206
• /
• 2021

Fraud in e-commerce transaction increased in the last decade especially with the increasing number of online stores and the lockdown that forced more people to pay for services and groceries online using their credit card. Several machine learning methods were proposed to detect fraudulent transaction. Neural networks showed promising results, but it has some few drawbacks that can be overcome using optimization methods. There are two categories of learning optimization methods, first-order methods which utilizes gradient information to construct the next training iteration whereas, and second-order methods which derivatives use Hessian to calculate the iteration based on the optimization trajectory. There also some training refinements procedures that aims to potentially enhance the original accuracy while possibly reduce the model size. This paper investigate the performance of several NN models in detecting fraud in e-commerce transaction. The backpropagation model which is classified as first learning algorithm achieved the best accuracy 96% among all the models.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제62차 하계학술대회논문집 28권2호
• /
• pp.301-302
• /
• 2020

The number of abandoned dogs were increasing every year in South Korea. However, many dogs are euthanized in the shelter because of the lack of budget. This project predicts euthanasia of abandoned dogs using machine learning algorithm. It collects data from the public data portal where Korea government provides a public dataset as a form of open API. This project uses recent three-year data 2017 to 2019 and 263371 cases were founded. This project implements random forest and logistic regression models. This project attained an average 72% of prediction accuracy.

• International Journal of Computer Science & Network Security
• /
• 제24권4호
• /
• pp.211-221
• /
• 2024

Pakistan is a top producer and exporter of high-quality rice, but traditional methods are still being used for detecting rice diseases. This research project developed an automated rice blast disease diagnosis technique based on deep learning, image processing, and transfer learning with pre-trained models such as Inception V3, VGG16, VGG19, and ResNet50. The modified connection skipping ResNet 50 had the highest accuracy of 99.16%, while the other models achieved 98.16%, 98.47%, and 98.56%, respectively. In addition, CNN and an ensemble model K-nearest neighbor were explored for disease prediction, and the study demonstrated superior performance and disease prediction using recommended web-app approaches.

• 치위생과학회지
• /
• 제14권1호
• /
• pp.15-21
• /
• 2014

본 연구에서는 구강으로부터 채득된 인상체를 스캐닝하여 디지털 모형을 제작하였을 때 제작된 디지털 모형의 체적 안정성을 평가하고자 하였다. 그리하여 환자의 구강을 가정한 상악 모형을 본 모형으로 채택하였다. 본 모형과 동일한 증례의 연구 모형을 치과용 석고를 이용하여 총 20개의 석고 모형을 제작하였다. 제작된 연구 모형 20개를 치과용 기성 트레이와 두 종류의 치과용 인상재를 이용하여 20개 연구 모형을 대상으로 20개의 인상을 채득하였다. 채득된 20개의 인상체를 치과용 스캐너로 스캐닝하는 방식으로 디지털 모형으로 변환하였다. 체적 안정성을 평가하기 위하여 6개의 대표 지점을 선정한 뒤 디지털 모형과 함께 디지털 모형의 근간인 석고 모형을 계측하였다. 그 결과 계측된 모든 부위에서 디지털 모형이 석고 모형보다 체적이 작은 것으로 조사되었고, 이는 통계적으로 유의하였다(p<0.05). 이러한 결과들로 추론하여 보았을 때 환자의 구강으로부터 채득된 인상체를 스캐닝하여 제작한 디지털 모형의 체적은 환자의 구강보다 작다는 것을 알 수 있었다. 그러나 이 차이는 미비한 것으로 여러 선행 연구 결과들을 근거로 하였을 때 임상적으로 허용이 가능한 것으로 생각된다.

• ETRI Journal
• /
• 제33권5호
• /
• pp.741-751
• /
• 2011

This paper focuses on online speaker tracking for telephone conversations and broadcast news. Since the online applicability imposes some limitations on the tracking strategy, such as data insufficiency, a reliable approach should be applied to compensate for this shortage. In this framework, a set of reference speaker models are used as side information to facilitate online tracking. To improve the indexing accuracy, adaptation approaches in eigenvoice decomposition space are proposed in this paper. We believe that the eigenvoice adaptation techniques would help to embed the speaker space in the models and hence enrich the generality of the selected speaker models. Also, an index structure of the reference models is proposed to speed up the search in the model space. The proposed framework is evaluated on 2002 Rich Transcription Broadcast News and Conversational Telephone Speech corpus as well as a synthetic dataset. The indexing errors of the proposed framework on telephone conversations, broadcast news, and synthetic dataset are 8.77%, 9.36%, and 12.4%, respectively. Using the index tree structure approach, the run time of the proposed framework is improved by 22%.

• 환경영향평가
• /
• 제9권1호
• /
• pp.25-37
• /
• 2000

This paper presents a study of hydrological and hydraulic model applications in environmental impact statements which were submitted during recent years in Korea. In many cases (almost 70 %), the hydrological and hydraulic changes were neglected from the impact identification processes, even if the proposed actions would cause significant impacts on those environmental items. In most cases where the hydrological and hydraulic impacts were predicted, simple equations were used as an impact prediction tool. Computer models were used in very few cases(5%). Even in these few cases, models were improperly applied and thus the predicted impacts would not be reliable. The improper applications and the impact neglections are attributed to the fact that there are no available model application guidelines as well as no requirements by the review agency. The effects of mitigation measures were not analyzed in most cases. Again, these can be attributed to no formal guidelines available for impact predictions until now. A brief guideline is presented in this paper. This study suggested that the model application should be required and guided in detail by the review agency. It is also suggested that the hydrological and hydraulic items shoud be integrated with the water quality predictions in future, since the non-point source pollution runoff is based on the hydrologic phenomena and the water quality reactions on the hydraulic nature.

• International Journal of Computer Science & Network Security
• /
• 제21권12호
• /
• pp.157-164
• /
• 2021

The aim of this study is to provide empirical evaluation of the accuracy of data-model fit using growing levels of invariance models. Overall model accuracy of factor solutions was evaluated by the examination of the order for testing three levels of measurement invariance (MIV) starting with configural invariance (model 0). Model testing was evaluated by the Chi-square difference test (∆𝛘²) between two groups, and root mean square error of approximation (RMSEA), comparative fit index (CFI), and Tucker-Lewis index (TLI) were used to evaluate the all-model fits. Factorial invariance result revealed that stability of the models was varying over increasing levels of measurement as a function of variable-to-factor ratio (VTF), subject-to-variable ratio (STV), and their interactions. There were invariant factor loadings and invariant intercepts among the groups indicating that measurement invariance was achieved. For VTF ratio (3:1, 6:1, and 9:1), the models started to show accuracy over levels of measurement when STV ratio was 6:1. Yet, the frequency of stability models over 1000 replications increased (from 69% to 89%) as STV ratio increased. The models showed more accuracy at or above 39:1 STV.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4625-4647
• /
• 2020

The Generative Adversarial Networks, as one of the most creative deep learning models in recent years, has achieved great success in computer vision and natural language processing. It uses the game theory to generate the best sample in generator and discriminator. Recently, many deep learning models have been applied to the security field. Along with the idea of "generative" and "adversarial", researchers are trying to apply Generative Adversarial Networks to the security field. This paper presents the development of Generative Adversarial Networks. We review traditional generation models and typical Generative Adversarial Networks models, analyze the application of their models in natural language processing and computer vision. To emphasize that Generative Adversarial Networks models are feasible to be used in security, we separately review the contributions that their defenses in information security, cyber security and artificial intelligence security. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.