• Korean Journal of Radiology
• /
• v.23 no.3
• /
• pp.343-354
• /
• 2022

Objective: To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children. Materials and Methods: This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs). Results: The AI model showed an AUROC of 0.922 (95% CI, 0.842-0.969) in the internal test set and 0.870 (95% CI, 0.785-0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%-92.0%) and specificity of 91.3% (95% CI, 79.2%-97.6%) for the internal test set and 78.9% (95% CI, 54.4%-93.9%) and 88.2% (95% CI, 78.7%-94.4%), respectively, for the external test set. With the model's assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020-0.168; p = 0.012) and 0.069 (95% CI, 0.002-0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074-0.090; p = 0.850). Conclusion: A deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.12
• /
• pp.919-936
• /
• 2003

Nowadays Electronic Commerce shopping mall is welcomed more and more on the Internet. It is expected that Shopping mall systems come to be various and adaptable to complex requirements according to customers who have these various needs, but just show products list, instead. This thesis suggests various structures of shopping malls showing interface agent model using Case-Based Reasoning one of reasoning method of Artificial Intelligence instead of the method of prior EC shopping mall. 1 constructed case base by making index with shopping mall members and customers' private informations, and pursued difference from prior EC shopping malls by proposing to customers cases of other users' selection of products who have similar private informations with them.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.3
• /
• pp.100-107
• /
• 2002

In this paper, we propose an expert system for electronic interlocking which enhances the safty, efficiency and expanability of the existing system by designing real-time interlocking control based on the interlocking table automatically generated using artificial intelligence approach. The expert system consists of two parts; an interlocking table generation part and a real-time interlocking control part. The former generates automatically the interlocking relationship of all possible routes by searching dynamically the station topology which is obtained from station database. On the other hand, the latter controls the status of station facilities in real-time by applying the generated interlocking relationship to the signal facilities such as signal devices, points, track circuits for a given route. The expert system is implemented in C language which is suitable to implement the interlocking table generation part using the dynamic memory allocation technique. Finally, the effectiveness of the expert system is proved by simulating for the typical station model.

• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 1995.10a
• /
• pp.85-93
• /
• 1995

Recently, the development of Artificial Intelligence(AI) and Expert System has caused some interest in the possibility of developing an intelligent CAD system. However, these development and possibility are in an extremenly early stage for Architectural design. In this study, the design process of Residence being recognized as a Constraints-satisfied model, a part of these constraints used in the Architectural design of Residence are being systematized and sorted by the design process. Those regulations and planning items to be considered in the basic planning stage are being systematized as a knowledge base system. The possibility of this knowledge-based system as an effective design tool is studied and an integrated form of Architectural design system is proposed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2115-2127
• /
• 2021

Although significant progress has been made in synthesizing visually realistic face images by Generative Adversarial Networks (GANs), there still lacks effective approaches to provide fine-grained control over the generation process for semantic facial attribute editing. In this work, we propose a novel cross channel self-attention based generative adversarial network (CCA-GAN), which weights the importance of multiple channels of features and archives pixel-level feature alignment and conversion, to reduce the impact on irrelevant attributes while editing the target attributes. Evaluation results show that CCA-GAN outperforms state-of-the-art models on the CelebA dataset, reducing Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) by 15~28% and 25~100%, respectively. Furthermore, visualization of generated samples confirms the effect of disentanglement of the proposed model.

• Electronics and Telecommunications Trends
• /
• v.38 no.1
• /
• pp.46-54
• /
• 2023

The announcement of the US Environmental Protection Agency that it will stop conducting or funding experimental studies on mammals by 2035 should prioritize ongoing efforts to develop and use alternative toxicity screening methods to animal testing. Toxicity screening is likely to be further developed considering the combination of human-induced pluripotent-stem-cell-derived organ-on-a-chip and multielectrode array (MEA) technologies. We briefly review the current status of MEA technology and MEA-based neuropharmacological drug screening using various cellular model systems. Highlighting the coronavirus disease pandemic, we shortly comment on the importance of early prediction of toxicity by applying artificial intelligence to the development of rapid screening methods.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.665-666
• /
• 2023

딥러닝은 인간이 탐지하기 어려운 데이터의 특징 및 패턴을 인지하고, 이들을 학습하여 데이터를 분류 및 예측할 수 있는 기술이다. 그러나 딥러닝 모델을 잘 학습시키기 위해서는 고품질의 대용량 데이터와 이들을 처리할 수 있는 방대한 컴퓨터 자원이 요구되는 것이 일반적이다. 따라서 소량의 데이터만이 존재하는 분야나 컴퓨터 자원이 한정되어 있는 상황에서는 딥러닝을 적용하기 어렵다. 본 논문에서는, 소량의 데이터로도 모델을 자신들의 태스크에 맞게 최적화시킬 수 있는 메타러닝에 대해 소개하고, 메타 러닝 기법들의 방향에 따른 Metric-Based, Model-Based 및 Optimization 기반 모델들에 대해 소개하고, 앞으로 나아가야 할 연구 방향에 대해 제시한다.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.678-680
• /
• 2023

본 논문은 정확하면서도 효율적인 한국어 문장 분류 기법에 대해서 논의한다. 최근 자연어처리 분야에서 사전 학습된 언어 모델(Pre-trained Language Models, PLM)은 미세조정(fine-tuning)을 통해 문장 분류 하위 작업(downstream task)에서 성공적인 결과를 보여주고 있다. 하지만, 이러한 미세조정은 하위 작업이 바뀔 때마다 사전 학습된 언어 모델의 전체 매개변수(model parameters)를 학습해야 한다는 단점을 갖고 있다. 본 논문에서는 이러한 문제를 해결할 수 있도록 도메인 적응기(domain adapter)를 활용한 한국어 문장 분류 프레임워크인 DAKS(Domain Adaptation-based Korean Sentence classification framework)를 제안한다. 해당 프레임워크는 학습되는 매개변수의 규모를 크게 줄임으로써 효율적인 성능을 보였다. 또한 문장 분류를 위한 특징(feature)으로써 한국어 사전학습 모델(KLUE-RoBERTa)의 다양한 은닉 계층 별 은닉 상태(hidden states)를 활용하였을 때 결과를 비교 분석하고 가장 적합한 은닉 계층을 제시한다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.166-171
• /
• 2023

With significant advancements in the field of artificial intelligence, many novel algorithms and technologies have emerged. Currently, AI painting can generate high-quality images based on textual descriptions. However, it is often challenging to control details when generating images, even with complex textual inputs. Therefore, there is a need to implement additional control mechanisms beyond textual descriptions. Based on ControlNet, this passage describes a combined utilization of various local controls (such as edge maps and depth maps) and global control within a single model. It provides a comprehensive exposition of the fundamental concepts of ControlNet, elucidating its theoretical foundation and relevant technological features. Furthermore, combining methods and applications, understanding the technical characteristics involves analyzing distinct advantages and image differences. This further explores insights into the development of image generation patterns.

• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.170-178
• /
• 2024

Through the growth of the fifth-generation networks and artificial intelligence technologies, new threats and challenges have appeared to wireless communication system, especially in cybersecurity. And IoT networks are gradually attractive stages for introduction of DDoS attacks due to integral frailer security and resource-constrained nature of IoT devices. This paper emphases on detecting DDoS attack in wireless networks by categorizing inward network packets on the transport layer as either "abnormal" or "normal" using the integration of machine learning algorithms knowledge-based system. In this paper, deep learning algorithms and CNN were autonomously trained for mitigating DDoS attacks. This paper lays importance on misuse based DDOS attacks which comprise TCP SYN-Flood and ICMP flood. The researcher uses CICIDS2017 and NSL-KDD dataset in training and testing the algorithms (model) while the experimentation phase. accuracy score is used to measure the classification performance of the four algorithms. the results display that the 99.93 performance is recorded.