• 문화기술의 융합
• /
• 제10권2호
• /
• pp.465-470
• /
• 2024

인공지능(Artificial Intelligence, AI) 기반 이미지 생성 기술의 발달로 다양한 이미지가 생성되고 있으며, 이를 정확하게 판별하는 기술이 필요하다. 생성된 이미지 데이터의 양에는 한계가 있으며, 한정된 데이터로 높은 성능을 내기 위해 본 연구에서는 전이 학습(Transfer Learning)을 활용한 생성 이미지를 판별하는 모델을 제안한다. ImageNet 데이터 셋으로 사전학습 된 모델을 입력 데이터 셋인 CIFAKE 데이터 셋에 그대로 적용하여 학습의 시간 비용을 줄인 후, 3개의 은닉층과 1개의 출력층을 더해 모델을 튜닝한다. 모델링 결과, 최종 레이어를 조정한 모델의 성능이 높아짐을 확인하였다. 딥러닝에서 전이 학습을 통해 학습한 후 출력층과 가까운 레이어를 데이터의 특성에 맞게 추가 및 조정하는 과정을 통해 적은 이미지 데이터로 인한 학습 정확도 이슈를 줄이고 생성된 이미지 판별을 할수 있다는 데 의의가 있다.

• 한국시뮬레이션학회논문지
• /
• 제33권2호
• /
• pp.27-35
• /
• 2024

본고에서는 인공지능 모델 학습에 사용하는 데이터셋에 내재한 편향성이 인공지능 예측 결과에 미치는 영향을 분석함으로써, 위의 경우가 사회적 격차를 고착화시키는 문제를 조명하고자 하였다. 따라서 데이터 편향성이 인공지능 모델에 끼치는 영향을 분석하기 위해, 성별 임금 격차에 관한 편향이 포함된 원본 데이터셋을 제작하였으며 해당 데이터셋을 비식별 처리한 데이터셋을 만들었다. 또한 의사결정트리 알고리즘을 통해 원본 데이터셋과 비식별화 된 데이터셋을 학습한 각각의 인공지능 모델 간의 산출물을 비교함으로써, 데이터 비식별화가 인공지능 모델이 산출한 결과의 편향에 어떠한 영향을 미치는지 분석하였다. 이를 통해 데이터 비식별화가 개인정보 보호뿐만 아니라, 데이터의 편향에도 중요한 역할을 할 수 있음을 도출하고자 하였다.

• 지능정보연구
• /
• 제28권3호
• /
• pp.23-43
• /
• 2022

AI(Artificial Intelligence)를 다양한 산업에서 접목하기 위해 알고리즘 선택에 대한 관심이 증가하고 있다. 알고리즘 선택은 대부분 데이터 과학자의 경험에 의해 결정되는 경우가 많다. 하지만 경험이 부족한 데이터 과학자의 경우 데이터셋 특성 기반의 메타학습(meta learning) 을 통해 알고리즘을 선택한다. 기존의 알고리즘 추천은 선정 과정이 블랙박스이기 때문에 어떠한 근거에 의해 도출되는지 알 수 없었다. 이에 따라 본 연구에서는 k-평균 군집분석을 활용하여 데이터셋 특성에 따라 유형을 나누고 적합한 분류 알고리즘과 클래스 불균형 해소 방법을 탐색한다. 본 연구 결과 네 가지 유형을 도출하였으며 데이터셋 유형에 따라 적합한 클래스 불균형 해소 방법과 분류 알고리즘을 추천하였다.

• 대한원격탐사학회지
• /
• 제38권4호
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.

• 인터넷정보학회논문지
• /
• 제25권1호
• /
• pp.189-198
• /
• 2024

민간에서뿐 아니라 국방분야에서도 인공지능은 국방의 발전을 위해 꼭 도입되어야 하는 첨단기술로 받아들여지고 있으며, 특히 국방과학기술혁신의 핵심 과제로 인공지능이 선정되고, 데이터의 중요성이 확대되고 있다. 국방은 폐쇄적인 데이터 정책에서 데이터 공유·활성화로 방향을 전환하고 있으며, 국방의 발전을 위해 필요한 양질의 데이터를 확보하기 위한 노력을 기울이고 있다. 특히 AI·빅데이터의 고유한 특성이 반영될 수 있도록 관련 절차 개선 및 대량·양질의 데이터가 충분히 확보된 상태에서 연구개발이 시작될 수 있도록 데이터 확보를 위한 사업예산과 제도 검토를 추진하고 있다. 그러나 국방 차원의 정형데이터 및 비정형 데이터의 표준화·품질 기준 마련이 필요한 상황이나 지금까지 국방은 정형데이터의 표준화·품질 기준을 제안하고 있는 수준으로 이에 대한 보완이 필요하다. 본 논문에서는 국방 인공지능에서 가장 필요한 국방 비정형 데이터셋을 위한 비정형 데이터셋 표준포맷을 제안하고, 이를 바탕으로 국방 비정형 데이터셋 표준화 방안을 제안한다.

• Journal of Veterinary Science
• /
• 제23권1호
• /
• pp.17.1-17.10
• /
• 2022

Background: Inspection of livestock farms using surveillance cameras is emerging as a means of early detection of transboundary animal disease such as African swine fever (ASF). Object tracking, a developing technology derived from object detection aims to the consistent identification of individual objects in farms. Objectives: This study was conducted as a preliminary investigation for practical application to livestock farms. With the use of a high-performance artificial intelligence (AI)-based 3D depth camera, the aim is to establish a pathway for utilizing AI models to perform advanced object tracking. Methods: Multiple crossovers by two humans will be simulated to investigate the potential of object tracking. Inspection of consistent identification will be the evidence of object tracking after crossing over. Two AI models, a fast model and an accurate model, were tested and compared with regard to their object tracking performance in 3D. Finally, the recording of pig pen was also processed with aforementioned AI model to test the possibility of 3D object detection. Results: Both AI successfully processed and provided a 3D bounding box, identification number, and distance away from camera for each individual human. The accurate detection model had better evidence than the fast detection model on 3D object tracking and showed the potential application onto pigs as a livestock. Conclusions: Preparing a custom dataset to train AI models in an appropriate farm is required for proper 3D object detection to operate object tracking for pigs at an ideal level. This will allow the farm to smoothly transit traditional methods to ASF-preventing precision livestock farming.

• ETRI Journal
• /
• 제42권6호
• /
• pp.815-826
• /
• 2020

We propose a two-dimensional (2D) scattering-center-extraction (SCE) method using sparse recovery based on the compressive-sensing theory, even with data missing from the received radar cross-section (RCS) dataset. First, using the proposed method, we generate a 2D grid via adaptive discretization that has a considerably smaller size than a fully sampled fine grid. Subsequently, the coarse estimation of 2D scattering centers is performed using both the method of iteratively reweighted least square and a general peak-finding algorithm. Finally, the fine estimation of 2D scattering centers is performed using the orthogonal matching pursuit (OMP) procedure from an adaptively sampled Fourier dictionary. The measured RCS data, as well as simulation data using the point-scatterer model, are used to evaluate the 2D SCE accuracy of the proposed method. The results indicate that the proposed method can achieve higher SCE accuracy for an incomplete RCS dataset with missing data than that achieved by the conventional OMP, basis pursuit, smoothed L0, and existing discrete spectral estimation techniques.

• 한국군사과학기술학회지
• /
• 제25권4호
• /
• pp.381-389
• /
• 2022

Detecting partially occluded objects is difficult due to the appearances and shapes of occluders are highly variable. These variabilities lead to challenges of localizing accurate bounding box or classifying objects with visible object parts. To address these problems, we propose a two-stage part-based attention approach for robust object detection under partial occlusion. First, our part attention network(PAN) captures the important object parts and then it is used to generate weighted object features. Based on the weighted features, the re-weighted object features are produced by our reinforced PAN(RPAN). Experiments are performed on our collected military vehicle dataset and synthetic occlusion dataset. Our method outperforms the baselines and demonstrates the robustness of detecting objects under partial occlusion.

• 아시아태평양코퍼스연구
• /
• 제1권1호
• /
• pp.95-125
• /
• 2020

This paper aims to inform people how to support each other on social media. It alludes to an architecture for social media discourse and proposes a novel theory of support in social media discourse. It makes a methodological contribution. It combines predominately artificial intelligence with corpus linguistics analysis. It is on a large-scale dataset of anonymised diabetes-related user's posts from the Facebook platform. Log-likelihood and precision measures help with validation. A multi-method approach with Discourse Analysis helps in understanding any potential patterns. People living with Diabetes are found to employ sophisticated high-frequency patterns of device-enabled categories of purpose and content. It is with, for example, linguistic forms of Advice with stance-taking and targets such as Diabetes amongst other interactional ways. There can be uncertainty and variation of effect displayed when sharing information for support. The implications of the new theory aim at healthcare communicators, corpus linguists and with preliminary work for AI support-bots. These bots may be programmed to utilise the language patterns to support people who need them automatically.

• Korean Journal of Radiology
• /
• 제23권3호
• /
• 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.