• 인터넷정보학회논문지
• /
• 제25권1호
• /
• pp.79-90
• /
• 2024

본 연구는 대표적인 생성형 AI 기술인 ChatGPT의 이용자 신뢰를 중심으로 이용실태와 지속사용의도에 영향을 미치는 요인, 그리고 신뢰의 영향력이 목적에 따라 달라지는지를 탐색적으로 살펴보았다. 이를 위해 ChatGPT를 많이 이용하는 20대와 30대를 대상으로 설문조사를 실시하였으며 통계 패키지 프로그램인 IBM SPSS 27과 SmartPLS 4.0을 적용하여 분석을 수행하였다. Bhattacherjee의 기대충족모델(ECM)을 기반으로 구조방정식 모델을 구축하고, 경로분석과 다중그룹분석(MGA)를 실시하여 가설을 검증하였다. 본 연구의 결과는, 첫째, ChatGPT 이용자들은 일상적인 도구로 사용하기보다 특정 목적이나 필요에 따라 사용하고 있으며, 대부분의 사용자가 ChatGPT의 환각효과(Hallucination)에 대해 인지하고 있으나 이는 사용을 저해하는 요인은 아니었다. 둘째, 가설검정 결과 독립변수인기대충족, 인지된 유용성, 사용자 만족 요인 모두가 종속변수인 지속이용의도에 긍정적 영향을 미치고 있음을 확인하였다. 셋째, 이용자가 ChatGPT를 이용하는 목적에 따라 신뢰의 영향력이 달라짐이 확인되었다. 이용자가 정보 검색 목적으로 ChatGPT를 활용하는 경우에는 신뢰가 사용자 만족에 영향을 미친 반면, 창작 목적으로 사용하는 경우 영향을 미치지 않는 것으로 나타났다. 본 연구의 결과가 향후 사회와 기업에 있어 생성형 AI의 도입 과정에서 신뢰성의 문제를 해결하고 성공적인 도입을 위한 정책 수립 및 개선방안 도출을 위해 활용될 수 있기를 기대한다.

• 대한원격탐사학회지
• /
• 제38권1호
• /
• pp.111-126
• /
• 2022

Land use and land cover (LULC) mapping is an important factor in geospatial analysis. Although highly precise ground-based LULC monitoring is possible, it is time consuming and costly. Conversely, because the synthetic aperture radar (SAR) sensor is an all-weather sensor with high resolution, it could replace field-based LULC monitoring systems with low cost and less time requirement. Thus, LULC is one of the major areas in SAR applications. We developed a LULC model using only KOMPSAT-5 single co-polarized data and digital elevation model (DEM) data. Twelve HH-polarized images and 18 VV-polarized images were collected, and two HH-polarized images and four VV-polarized images were selected for the model testing. To train the LULC model, we applied the conditional generative adversarial network (cGAN) method. We used U-Net combined with the residual unit (ResUNet) model to generate the cGAN method. When analyzing the training history at 1732 epochs, the ResUNet model showed a maximum overall accuracy (OA) of 93.89 and a Kappa coefficient of 0.91. The model exhibited high performance in the test datasets with an OA greater than 90. The model accurately distinguished water body areas and showed lower accuracy in wetlands than in the other LULC types. The effect of the DEM on the accuracy of LULC was analyzed. When assessing the accuracy with respect to the incidence angle, owing to the radar shadow caused by the side-looking system of the SAR sensor, the OA tended to decrease as the incidence angle increased. This study is the first to use only KOMPSAT-5 single co-polarized data and deep learning methods to demonstrate the possibility of high-performance LULC monitoring. This study contributes to Earth surface monitoring and the development of deep learning approaches using the KOMPSAT-5 data.

• 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.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 추계학술대회
• /
• pp.58-60
• /
• 2019

Double JPEG compression detection is one of the most important ways of exposing the integrity of the JPEG image in image forensics. Several methods have been proposed for discriminating against the double JPEG image. In this paper, we propose a new method for restoring the JPEG compressed image and making the detector confused by introducing a Generative Adversarial Network (GAN). First, a generator network is designed for restoring the JPEG compressed image and analyzed the quality. Then, the restored image is tested with the double compression detector for evaluating the robustness of the proposed GAN model. The detection accuracy reduces from 98% to 58%.

• 대한가정학회지
• /
• 제37권12호
• /
• pp.91-102
• /
• 1999

The purpose of this study was to investigate the father-child relationship. The final sample for the data analyses included 83 three-year old children and their lathers. The instrument of study was the 'generative fathering'(by Yee et al, 1999). This measurement consisted two areas, first is the father's involvement in child rearing, and second is the responsibility on child rearing. And the child attachment security was observed through Attachment Q-Set(Waters, 1987) in the child's home. The results were following: 1. The mean of the child's attachment security was .33 and the range of attachment security was from -.07 to .79. 2. Father had higher responsibility on rearing, more involved in the child care. 3. The child's attachment security was predicted by the father's involvement in rearing. The father's responsibility didn't show the relationship with the child's attachment security. Especially among the subcategories of involvement, the activity with child had a significant relation to attachment security. So the father's interaction with child was meaningful for the child to develop the internal working model.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.401-403
• /
• 2019

In this paper, we propose a generative adversarial networks (GAN) based text-to-image generating method. In many natural language processing tasks, which word expressions are determined by their term frequency -inverse document frequency scores. Word2Vec is a type of neural network model that, in the case of an unlabeled corpus, produces a vector that expresses semantics for words in the corpus and an image is generated by GAN training according to the obtained vector. Thanks to the understanding of the word we can generate higher and more realistic images. Our GAN structure is based on deep convolution neural networks and pixel recurrent neural networks. Comparing the generated image with the real image, we get about 88% similarity on the Oxford-102 flowers dataset.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.522-524
• /
• 2019

In spite of a rapid development in the quality of built-in mobile cameras, their some physical restrictions hinder them to achieve the satisfactory results of digital single lens reflex (DSLR) cameras. In this work we propose an end-to-end deep learning method to translate ordinary images by mobile cameras into DSLR-quality photos. The method is based on the framework of generative adversarial networks (GANs) with several improvements. First, we combined the U-Net with DenseNet and connected dense block (DB) in terms of U-Net. The Dense U-Net acts as the generator in our GAN model. Then, we improved the perceptual loss by using the VGG features and pixel-wise content, which could provide stronger supervision for contrast enhancement and texture recovery.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.871-891
• /
• 2019

Visual tracking is a challenging task that needs learning an effective model to handle the changes of target appearance caused by factors such as pose variation, illumination change, occlusion and motion blur. In this paper, a novel tracking algorithm based on weighted local sub-space reconstruction error is presented. First, accounting for the appearance changes in the tracking process, a generative weight calculation method based on structural reconstruction error is proposed. Furthermore, a template update scheme of occlusion-aware is introduced, in which we reconstruct a new template instead of simply exploiting the best observation for template update. The effectiveness and feasibility of the proposed algorithm are verified by comparing it with some state-of-the-art algorithms quantitatively and qualitatively.

• Journal of Multimedia Information System
• /
• 제8권2호
• /
• pp.85-92
• /
• 2021

In a face, there is much information of person's identity. Because of this property, various tasks such as expression recognition, identity recognition and deepfake have been actively conducted. Most of them use the exact frontal view of the given face. However, various directions of the face can be observed rather than the exact frontal image in real situation. The profile (side view) lacks information when comparing with the frontal view image. Therefore, if we can generate the frontal face from other directions, we can obtain more information on the given face. In this paper, we propose a combined style model based the conditional generative adversarial network (cGAN) for generating the frontal face from multi-view images that consist of characteristics that not only includes the style around the face (hair and beard) but also detailed areas (eye, nose, and mouth).

• Journal of Semiconductor Engineering
• /
• 제2권1호
• /
• pp.125-129
• /
• 2021

As the interest of deep learning, techniques to control the color of images in image processing field are evolving together. However, there is no clear standard for color, and it is not easy to find a way to represent only the color itself like the color-palette. In this paper, we propose a novel color palette extraction system by chroma fine-tuning with reinforcement learning. It helps to recognize the color combination to represent an input image. First, we use RGBY images to create feature maps by transferring the backbone network with well-trained model-weight which is verified at super resolution convolutional neural networks. Second, feature maps are trained to 3 fully connected layers for the color-palette generation with a generative adversarial network (GAN). Third, we use the reinforcement learning method which only changes chroma information of the GAN-output by slightly moving each Y component of YCbCr color gamut of pixel values up and down. The proposed method outperforms existing color palette extraction methods as given the accuracy of 0.9140.