• 한국컴퓨터정보학회논문지
• /
• 제29권7호
• /
• pp.11-20
• /
• 2024

본 논문에서는 생성 모델을 이용한 데이터 프리 양자화에서 발생할 수 있는 지식 격차를 줄이기 위하여 BAG (Bit-width Aware Generator)와 채널 어텐션 기반 중간 레이어 지식 증류를 제안한다. 생성 모델을 이용한 데이터 프리 양자화의 생성자는 오직 원본 네트워크의 피드백에만 의존하여 학습하기 때문에, 양자화된 네트워크의 낮은 bit-width로 인한 감소된 수용 능력 차이를 학습에 반영하지 못한다. 제안한 BAG는 양자화된 네트워크와 동일한 bit-width로 양자화하여, 양자화된 네트워크에 맞는 합성 이미지를 생성하여 이러한 문제를 완화한다. 또한, 양자화된 네트워크와 원본 모델 간의 지식 격차를 줄이는 것 역시 양자화에서 매우 중요한 문제이다. 이를 완화하기 위해 제안한 채널 어텐션 기반 중간 레이어 지식 증류는 학생 모델이 교사 모델로부터 어떤 채널에 더 집중해서 학습해야 하는지를 가르친다. 제안한 기법의 효율성을 보이기 위해, CIFAR-100에서 학습한 원본 네트워크를 가중치와 활성값을 각각 3-bit로 양자화하여 학습을 수행하였다. 그 결과 56.14%의 Top-1 Accuracy를 달성하였으며, 베이스라인 모델인 AdaDFQ 대비 3.4% 정확도를 향상했다.

• Journal of Information Processing Systems
• /
• 제20권3호
• /
• pp.375-390
• /
• 2024

Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reduced network bandwidth consumption, and improved the quality of service for user experience; however, it has also introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud-edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing with complex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deep-learning network models. A lightweight deep-learning model was proposed to address these challenges. First, normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wasserstein generative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviates the imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessed and expanded local data are used to fine-tune the trained model. This ensures that the data of each edge node are more consistent with the local characteristics, effectively improving the system's detection ability. In the designed lightweight deep learning network model, two sets of convolutional pooling layers of convolutional neural networks (CNN) were used to extract spatial features. The bidirectional long short-term memory network (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjusted through the attention mechanism, improving the model's ability to identify abnormal traffic features. The proposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018 datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953, respectively, showing superior accuracy to other comparative models. The proposed lightweight deep learning network model has good application prospects for anomaly traffic detection in cloud-edge collaborative computing architectures.

• Wind and Structures
• /
• 제36권4호
• /
• pp.237-247
• /
• 2023

The emergence of high-rise buildings has necessitated frequent structural health monitoring and maintenance for safety reasons. Wind causes damage and structural changes on tall structures; thus, safe structures should be designed. The pressure developed on tall buildings has been utilized in previous research studies to assess the impacts of wind on structures. The wind tunnel test is a primary research method commonly used to quantify the aerodynamic characteristics of high-rise buildings. Wind pressure is measured by placing pressure sensor taps at different locations on tall buildings, and the collected data are used for analysis. However, sensors may malfunction and produce erroneous data; these data losses make it difficult to analyze aerodynamic properties. Therefore, it is essential to generate missing data relative to the original data obtained from neighboring pressure sensor taps at various intervals. This study proposes a deep learning-based, deep convolutional generative adversarial network (DCGAN) to restore missing data associated with faulty pressure sensors installed on high-rise buildings. The performance of the proposed DCGAN is validated by using a standard imputation model known as the generative adversarial imputation network (GAIN). The average mean-square error (AMSE) and average R-squared (ARSE) are used as performance metrics. The calculated ARSE values by DCGAN on the building model's front, backside, left, and right sides are 0.970, 0.972, 0.984 and 0.978, respectively. The AMSE produced by DCGAN on four sides of the building model is 0.008, 0.010, 0.015 and 0.014. The average standard deviation of the actual measures of the pressure sensors on four sides of the model were 0.1738, 0.1758, 0.2234 and 0.2278. The average standard deviation of the pressure values generated by the proposed DCGAN imputation model was closer to that of the measured actual with values of 0.1736,0.1746,0.2191, and 0.2239 on four sides, respectively. In comparison, the standard deviation of the values predicted by GAIN are 0.1726,0.1735,0.2161, and 0.2209, which is far from actual values. The results demonstrate that DCGAN model fits better for data imputation than the GAIN model with improved accuracy and fewer error rates. Additionally, the DCGAN is utilized to estimate the wind pressure in regions of buildings where no pressure sensor taps are available; the model yielded greater prediction accuracy than GAIN.

• 한국인터넷방송통신학회논문지
• /
• 제20권3호
• /
• pp.171-179
• /
• 2020

최근 연구 결과에 따르면, 컨볼루션 신경 회로망은 이미지 분류, 객체 검출, 이미지 생성 등의 문제에서 최고의 성능을 보여주고 있다. 비전 카메라를 사용한 결함 검사는 다른 결함 검사보다 경제적이기 때문에 공장 자동화에 있어서 아주 중요하고, 딥러닝의 지도학습은 전통 기계학습 방식의 결함 검사 성능을 월등히 뛰어넘었다. 하지만, 딥러닝의 지도학습은 엄청난 양의 데이터 주석 작업을 요구하기 때문에, 이를 실제 산업 현장에 적용하는 것은 효율적이지 않다. 따라서 본 연구는 최근 이미지 생성 과업에서 큰 성공을 보여주고 있는 변분 오토인코더와 적대적 생성 신경망을 활용하여 비지도 방식의 비정상 검출을 위한 신경망 회로 구조를 제안하였고, 이를 MNIST, 용접 결함 데이터에 적용하여 비정상 검출 성능을 검증하였다.

• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.1-9
• /
• 2022

Ship detection in synthetic aperture radar (SAR) images is an important application in marine monitoring for the military and civilian domains. Over the past decade, object detection has achieved significant progress with the development of convolutional neural networks (CNNs) and lot of labeled databases. However, due to difficulty in collecting and labeling SAR images, it is still a challenging task to solve SAR ship detection CNNs. To overcome the problem, some methods have employed conventional data augmentation techniques such as flipping, cropping, and affine transformation, but it is insufficient to achieve robust performance to handle a wide variety of types of ships. In this paper, we present a novel and effective approach for deep SAR ship detection, that exploits label-rich Electro-Optical (EO) images. The proposed method consists of two components: a data augmentation network and a ship detection network. First, we train the data augmentation network based on conditional generative adversarial network (cGAN), which aims to generate additional SAR images from EO images. Since it is trained using unpaired EO and SAR images, we impose the cycle-consistency loss to preserve the structural information while translating the characteristics of the images. After training the data augmentation network, we leverage the augmented dataset constituted with real and translated SAR images to train the ship detection network. The experimental results include qualitative evaluation of the translated SAR images and the comparison of detection performance of the networks, trained with non-augmented and augmented dataset, which demonstrates the effectiveness of the proposed framework.

• 한국지구과학회지
• /
• 제44권6호
• /
• pp.675-692
• /
• 2023

This study used a Chatbot, a generative artificial intelligence (AI), to analyze the interaction between the Chatbot and students when exploring critical minerals from an epistemological aspect. The results, issues to be kept in mind in the teaching and learning process using AI were discussed in terms of the role of the teacher, the goals of education, and the characteristics of knowledge. For this study, we conducted a three-session science education program using a Chatbot for 19 high school students and analyzed the reports written by the students. As a result, in terms of form, the students' questions included search-type questions and non-search-type questions, and in terms of content, in addition to various questions asking about the characteristics of the target, there were also questions requiring a judgment by combining various data. In general, students had a questioning strategy that distinguished what they should aim for and what they should avoid. The Chatbot's answer had a certain form and consisted of three parts: an introduction, a body, and a conclusion. In particular, the conclusion included commentary or opinions with opinions on the content, and in this, value judgments and the nature of science were revealed. The interaction between the Chatbot and the student was clearly evident in the process in which the student organized questions in response to the Chatbot's answers. Depending on whether they were based on the answer, independent or derived questions appeared, and depending on the direction of comprehensiveness and specificity, superordinate, subordinate, or parallel questions appeared. Students also responded to the chatbot's answers with questions that included critical thinking skills. Based on these results, we discovered that there are inherent limitations between Chatbots and students, unlike general classes where teachers and students interact. In other words, there is 'limited interaction' and the teacher's role to complement this was discussed, and the goals of learning using AI and the characteristics of the knowledge they provide were also discussed.

• 융합보안논문지
• /
• 제24권2호
• /
• pp.9-17
• /
• 2024

본 논문은 기업 내 생성형 AI(Generative Artificial Intelligence) 시스템의 보안 위협과 대응 방안을 제시한다. AI 시스템이 방대한 데이터를 다루면서 기업의 핵심 경쟁력을 확보하는 한편, AI 시스템을 표적으로 하는 보안 위협에 대비해야 한다. AI 보안 위협은 기존 사람을 타겟으로 하는 사이버 보안 위협과 차별화된 특징을 가지므로, AI에 특화된 대응 체계 구축이 시급하다. 본 연구는 AI 시스템 보안의 중요성과 주요 위협 요인을 분석하고, 기술적/관리적 대응 방안을 제시한다. 먼저 AI 시스템이 구동되는 IT 인프라 보안을 강화하고, AI 모델 자체의 견고성을 높이기 위해 적대적 학습 (adversarial learning), 모델 경량화(model quantization) 등 방어 기술을 활용할 것을 제안한다. 아울러 내부자 위협을 감지하기 위해, AI 질의응답 과정에서 발생하는 이상 징후를 탐지할 수 있는 AI 보안 체계 설계 방안을 제시한다. 또한 사이버 킬 체인 개념을 도입하여 AI 모델 유출을 방지하기 위한 변경 통제와 감사 체계 확립을 강조한다. AI 기술이 빠르게 발전하는 만큼 AI 모델 및 데이터 보안, 내부 위협 탐지, 전문 인력 육성 등에 역량을 집중함으로써 기업은 안전하고 신뢰할 수 있는 AI 활용을 통해 디지털 경쟁력을 제고할 수 있을 것이다.

• 한국인터넷방송통신학회논문지
• /
• 제24권1호
• /
• pp.133-139
• /
• 2024

초고령사회로 인한 정보격차를 줄이기 위해 지자체에서 고령자를 대상으로 스마트폰 사용법 교육을 진행하고 있다. 하지만 1 대 다수 교육의 한계, 고령자의 학습 효과 미비 등의 문제점이 있어 스마트폰 교육에 어려움을 겪고 있다. 본 연구는 이러한 문제점을 바탕으로 고령자 대상으로 반복적으로 학습할 수 있는 교육환경 등을 고려하여 오프라인 교육 현장에서 직접 사용할 수 있는 교육용 서비스를 제안하였다. 해당 연구의 앱은 생성형 AI를 이용하여 사용자가 실제 사용에서 어려워하는 부분을 파악해 사용자별로 다른 문제를 제공해 개인 맞춤형 실습이 이루어질 수 있도록 설계하였다. 기존의 지자체 교육과 연계해 사용한다면 1:1 교육, 시간, 그리고 내용 면에서 효율적인 스마트폰 교육이 이루어질 것으로 기대된다.

• Korean Journal of Radiology
• /
• 제23권1호
• /
• pp.139-149
• /
• 2022

Objective: To compare the effects of bone suppression imaging using deep learning (BSp-DL) based on a generative adversarial network (GAN) and bone subtraction imaging using a dual energy technique (BSt-DE) on radiologists' performance for pulmonary nodule detection on chest radiographs (CXRs). Materials and Methods: A total of 111 adults, including 49 patients with 83 pulmonary nodules, who underwent both CXR using the dual energy technique and chest CT, were enrolled. Using CT as a reference, two independent radiologists evaluated CXR images for the presence or absence of pulmonary nodules in three reading sessions (standard CXR, BSt-DE CXR, and BSp-DL CXR). Person-wise and nodule-wise performances were assessed using receiver-operating characteristic (ROC) and alternative free-response ROC (AFROC) curve analyses, respectively. Subgroup analyses based on nodule size, location, and the presence of overlapping bones were performed. Results: BSt-DE with an area under the AFROC curve (AUAFROC) of 0.996 and 0.976 for readers 1 and 2, respectively, and BSp-DL with AUAFROC of 0.981 and 0.958, respectively, showed better nodule-wise performance than standard CXR (AUAFROC of 0.907 and 0.808, respectively; p ≤ 0.005). In the person-wise analysis, BSp-DL with an area under the ROC curve (AUROC) of 0.984 and 0.931 for readers 1 and 2, respectively, showed better performance than standard CXR (AUROC of 0.915 and 0.798, respectively; p ≤ 0.011) and comparable performance to BSt-DE (AUROC of 0.988 and 0.974; p ≥ 0.064). BSt-DE and BSp-DL were superior to standard CXR for detecting nodules overlapping with bones (p < 0.017) or in the upper/middle lung zone (p < 0.017). BSt-DE was superior (p < 0.017) to BSp-DL in detecting peripheral and sub-centimeter nodules. Conclusion: BSp-DL (GAN-based bone suppression) showed comparable performance to BSt-DE and can improve radiologists' performance in detecting pulmonary nodules on CXRs. Nevertheless, for better delineation of small and peripheral nodules, further technical improvements are required.

• 실천공학교육논문지
• /
• 제16권3_spc호
• /
• pp.275-282
• /
• 2024

본 연구는 생성형 AI를 활용한 소프트웨어교육에 관한 수업모델을 연구하였다. 연구 목적은 ChatGPT를 소프트웨어교육에 활용함으로써 비전공학생들의 프로그래밍 수업에서 교수자의 보조자 역할로 ChatGPT를 활용하기 위함이다. 또한, ChatGPT를 이용해 학습자 개별 교육이 가능하도록 설계하고, 학생들이 필요로 한 시점에 즉각적인 피드백을 제공하고자 하였다. 연구 방법은 교양과목의 파이썬 수업을 듣는 컴퓨터 비전공자를 대상으로 ChatGPT를 보조자로 활용하여 수업을 진행하였다. 그리고 비전공학생의 프로그래밍 교육에서 ChatGPT가 보조자로서 가능성이 있는지 확인하였다. 학생들은 ChatGPT를 과제작성, 오류수정, 코딩 작성 및 지식 습득에 활발히 사용하였으며, 오류 해결에 많은 시간이 걸리는 것을 프로그램을 이해하는데 집중할 수 있는 등 다양한 이점을 확인하였다. ChatGPT가 학생들의 학습 효율을 높일 수 있는 가능성 볼 수 있었으며, 교육에 활용하는 데 있어서 더 많은 연구가 필요함을 알 수 있었다. 향후에는 ChatGPT를 활용한 교육 모델의 발전과 보완, 평가 방법에 관한 연구가 이루어질 것이다.