• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.11-20
• /
• 2024

In this paper, we propose the BAG (Bit-width Aware Generator) and the Intermediate Layer Knowledge Distillation using Channel-wise Attention to reduce the knowledge gap between a quantized network, a full-precision network, and a generator in GDFQ (Generative Data-Free Quantization). Since the generator in GDFQ is only trained by the feedback from the full-precision network, the gap resulting in decreased capability due to low bit-width of the quantized network has no effect on training the generator. To alleviate this problem, BAG is quantized with same bit-width of the quantized network, and it can generate synthetic images, which are effectively used for training the quantized network. Typically, the knowledge gap between the quantized network and the full-precision network is also important. To resolve this, we compute channel-wise attention of outputs of convolutional layers, and minimize the loss function as the distance of them. As the result, the quantized network can learn which channels to focus on more from mimicking the full-precision network. To prove the efficiency of proposed methods, we quantize the network trained on CIFAR-100 with 3 bit-width weights and activations, and train it and the generator with our method. As the result, we achieve 56.14% Top-1 Accuracy and increase 3.4% higher accuracy compared to our baseline AdaDFQ.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• 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
• /
• v.36 no.4
• /
• 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.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.3
• /
• pp.171-179
• /
• 2020

Recently, studies have shown that convolution neural networks are achieving the best performance in image classification, object detection, and image generation. Vision based defect inspection which is more economical than other defect inspection, is a very important for a factory automation. Although supervised anomaly detection algorithm has far exceeded the performance of traditional machine learning based method, it is inefficient for real industrial field due to its tedious annotation work, In this paper, we propose ADGAN, a unsupervised anomaly detection architecture using the variational autoencoder and the generative adversarial network which give great results in image generation task, and demonstrate whether the proposed network architecture identifies anomalous images well on MNIST benchmark dataset as well as our own welding defect dataset.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• 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.

• Journal of the Korean earth science society
• /
• v.44 no.6
• /
• 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.

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.9-17
• /
• 2024

This paper examines the security threats to enterprise Generative Artificial Intelligence systems and proposes countermeasures. As AI systems handle vast amounts of data to gain a competitive edge, security threats targeting AI systems are rapidly increasing. Since AI security threats have distinct characteristics compared to traditional human-oriented cybersecurity threats, establishing an AI-specific response system is urgent. This study analyzes the importance of AI system security, identifies key threat factors, and suggests technical and managerial countermeasures. Firstly, it proposes strengthening the security of IT infrastructure where AI systems operate and enhancing AI model robustness by utilizing defensive techniques such as adversarial learning and model quantization. Additionally, it presents an AI security system design that detects anomalies in AI query-response processes to identify insider threats. Furthermore, it emphasizes the establishment of change control and audit frameworks to prevent AI model leakage by adopting the cyber kill chain concept. As AI technology evolves rapidly, by focusing on AI model and data security, insider threat detection, and professional workforce development, companies can improve their digital competitiveness through secure and reliable AI utilization.

• Journal of Practical Engineering Education
• /
• v.16 no.3_spc
• /
• pp.275-282
• /
• 2024

This study studied a teaching model for software education using generative AI. The purpose of the study is to use ChatGPT as an instructor's assistant in programming classes for non-major students by using ChatGPT in software education. In addition, we designed ChatGPT to enable individual learning for learners and provide immediate feedback when students need it. The research method was conducted using ChatGPT as an assistant for non-computer majors taking a liberal arts Python class. In addition, we confirmed whether ChatGPT has the potential as an assistant in programming education for non-major students. Students actively used ChatGPT for writing assignments, correcting errors, writing coding, and acquiring knowledge, and confirmed various advantages, such as being able to focus on understanding the program rather than spending a lot of time resolving errors. We were able to see the potential for ChatGPT to increase students' learning efficiency, and we were able to see that more research is needed on its use in education. In the future, research will be conducted on the development, supplementation, and evaluation methods of educational models using ChatGPT.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.133-139
• /
• 2024

In response to the challenges posed by a super-aged society, local authorities are conducting educational programs on smartphone usage tailored for the elderly. However, obstacles such as the limitations of one-to-many education and suboptimal learning outcomes for the elderly have hindered the efficacy of smartphone education. This study suggests an educational service intended for direct application in offline settings, considering the identified problems. Through the utilization of generative AI, the proposed app identifies specific challenges encountered by users during actual smartphone use, offering personalized exercises to facilitate customized and repetitive learning experiences for individual users. When integrated with existing local government education initiatives, this app is anticipated to enhance the efficiency of smartphone education by providing personalized, one-on-one training that is efficient in terms of time and content.

• Korean Journal of Radiology
• /
• v.23 no.1
• /
• 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.