• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.294-297
• /
• 2017

SNS와 스마트기기의 발전으로 온라인을 통한 뉴스 배포가 용이해지면서 악의적으로 조작된 뉴스가 급속도로 생성되어 확산되고 있다. 뉴스 조작은 다양한 형태로 이루어지는데, 이 중에서 정상적인 기사 내에 광고나 낚시성 내용을 포함시켜 독자가 의도하지 않은 정보에 노출되게 하는 형태는 독자가 해당 내용을 진짜 뉴스로 받아들이기 쉽다. 본 논문에서는 뉴스 기사 내에 포함된 문단 중에서 부적합한 문단이 포함 되었는지를 판정하기 위한 방법을 제안한다. 제안하는 방식에서는 자연어 처리에 유용한 Convolutional Neural Network(CNN)모델 중 Word2Vec과 tf-idf 알고리즘, 로지스틱 회귀를 함께 이용하여 뉴스 부적합 문단을 검출한다. 본 시스템에서는 로지스틱 회귀를 이용하여 문단의 카테고리를 분류하여 본문의 카테고리 분포도를 계산하고 Word2Vec을 이용하여 문단간의 유사도를 계산한 결과에 가중치를 부여하여 부적합 문단을 검출한다.

• Communications for Statistical Applications and Methods
• /
• v.27 no.3
• /
• pp.313-326
• /
• 2020

Deep Learning is the most important key to the development of Artificial Intelligence (AI). There are several distinguishable architectures of neural networks such as MLP, CNN, and RNN. Among them, we try to understand one of the main architectures called Recurrent Neural Network (RNN) that differs from other networks in handling sequential data, including time series and texts. As one of the main tasks recently in Natural Language Processing (NLP), we consider Neural Machine Translation (NMT) using RNNs. We also summarize fundamental structures of the recurrent networks, and some topics of representing natural words to reasonable numeric vectors. We organize topics to understand estimation procedures from representing input source sequences to predict target translated sequences. In addition, we apply multiple translation models with Gated Recurrent Unites (GRUs) in Keras on English-Korean sentences that contain about 26,000 pairwise sequences in total from two different corpora, colloquialism and news. We verified some crucial factors that influence the quality of training. We found that loss decreases with more recurrent dimensions and using bidirectional RNN in the encoder when dealing with short sequences. We also computed BLEU scores which are the main measures of the translation performance, and compared them with the score from Google Translate using the same test sentences. We sum up some difficulties when training a proper translation model as well as dealing with Korean language. The use of Keras in Python for overall tasks from processing raw texts to evaluating the translation model also allows us to include some useful functions and vocabulary libraries as well.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.729-732
• /
• 2018

모바일 게임 산업의 발달로 많은 사용자들이 게임을 이용하면서, 그들의 만족감을 사용리뷰를 통해 드러낸다. 실제로 각 리뷰의 범주가 모두 다르지만 현재 구글 플레이 앱스토어(Google Play App Store)의 게임 리뷰 범주는 3가지로 매우 제한적이다. 따라서 본 연구에서는 빠르고 정확한 고객의 요구를 필요로 하는 게임 소프트웨어의 특성을 고려하여 게임 리뷰를 입력했을 때, 게임의 운영 및 시스템에 맞도록 리뷰의 카테고리를 세분화하고 만족도를 분석하는 시스템을 개발한다. 제안 시스템은 인공신경망 모델인 CNN을 평점을 기반으로 훈련시켜 리뷰에 대한 만족도를 도출한다. 또한 Word2Vec을 이용해 단어들 간의 유사도를 구하고, 이를 활용한 단어 배열을 이용하여 가장 스코어가 높은 카테고리로 배정한다. 본 논문은 제안한 리뷰 만족도 및 카테고리 분류 시스템이 실제 효과적으로 리뷰를 보다 의미 있는 정보로써 제공할 수 있음을 보인다.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.835-843
• /
• 2017

Humans have often been used gesture to communicate with each other. The communication between computer and person was also not different. To interact with a computer, we command with gesture, keyboard, mouse and extra devices. Especially, the gesture is very useful in many environments such as gaming and VR(Virtual Reality), which requires high specification and rendering time. In this paper, we propose a gesture recognition method based on CNN model to apply to gaming and real-time applications. Deep learning for gesture recognition is processed in a separated server and the preprocessing for data acquisition is done a client PC. The experimental results show that the proposed method is in accuracy higher than the conventional method in game environment.

• Annual Conference of KIPS
• /
• 2018.05a
• /
• pp.447-448
• /
• 2018

라벨인식과 같은 광학 문자 인식은 영상처리를 활용한 컴퓨터 비전의 대표적인 연구분야이다. 본 연구에서는 딥러닝 기반의 라벨인식 시스템을 고안하였다, 생산 라인에 적용되는 라벨인식 시스템은 인식 속도가 중요하기 때문에 기존의 R-CNN기반의 딥러닝 신경망보다 월등히 빠른 오브젝트 검출 시스템 YOLO를 활용하여 문자를 학습 및 인식 시스템을 개발하였다. 본 시스템은 기존 시스템에 근접하는 문자인식 정확도를 제공하고 자동으로 문자영역을 검출 가능하며, 라벨의 인쇄불량을 판독하도록 하였다. 또한 개발, 배포, 적용이 한번에 가능한 프레임워크를 통하여 생산현장에서 발생하는 다양한 이미지 처리에 활용될 전망이다.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.589-591
• /
• 2019

본 논문에서는 고도장비의 운용 및 정비를 위한 교육훈련 시스템 개발을 위해 자연어 처리와 딥러닝 기술을 이용하여 항공정비와 관련된 전문분야의 문서 분류가 가능한 방법을 제안하고자 한다. 문서 분류 모델의 개발을 위해 항공정비 교범을 텍스트 파일로 변환하여 총 4917개의 문서를 생성하였으며, 정비사 개인별 정비능력 관리(IMQC)를 기준으로 12개의 범주로 구분하였다. 수집된 문서는 전문분야의 문서인 점을 고려하여 전문용어 사전을 추가하였으며, KoNLPy를 이용하여 전처리를 수행하였다. 전문분야의 문서는 범주에 상관없이 문서 내용의 유사도가 매우 높은 특징을 가지고 있어, 특정 범주내에서 중요한 정도를 잘 표현 할 수 있는 TF-ICF를 이용하여 특징 추출을 하였다. 이후 합성곱 신경망(CNN)을 이용하여 특징 맵을 생성한 후 완전 결합 계층을 통하여 분류하였으며, 테스트 문서 983건을 분류한 결과 평균 73.6%의 분류성능을 보여주었다.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1425-1430
• /
• 2018

In this paper, we propose a CNN based deep learning algorithm for semantic segmentation of images. In order to improve the accuracy of semantic segmentation, we combined pixel level object classification and image level object classification. The image level object classification is used to accurately detect the characteristics of an image, and the pixel level object classification is used to indicate which object area is included in each pixel. The proposed network structure consists of three parts in total. A part for extracting the features of the image, a part for outputting the final result in the resolution size of the original image, and a part for performing the image level object classification. Loss functions exist for image level and pixel level classification, respectively. Image-level object classification uses KL-Divergence and pixel level object classification uses cross-entropy. In addition, it combines the layer of the resolution of the network extracting the features and the network of the resolution to secure the position information of the lost feature and the information of the boundary of the object due to the pooling operation.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.113-116
• /
• 2021

As artificial intelligence technologies, including deep learning, develop, these technologies are being introduced to code similarity analysis. In the traditional analysis method of calculating the graph edit distance (GED) after converting the source code into a control flow graph (CFG), there are studies that calculate the GED through a trained graph neural network (GNN) with the converted CFG, Methods for analyzing code similarity through CNN by imaging CFG are also being studied. In this paper, to determine which approach will be effective and efficient in researching code similarity analysis methods using artificial intelligence in the future, code similarity is measured through funcGNN, which measures code similarity using GNN, and Siamese Network, which is an image similarity analysis model. The accuracy was compared and analyzed. As a result of the analysis, the error rate (0.0458) of the Siamese network was bigger than that of the funcGNN (0.0362).

• International journal of advanced smart convergence
• /
• v.9 no.4
• /
• pp.132-138
• /
• 2020

Worldwide, the number of corona virus disease 2019 (COVID-19) confirmed cases is rapidly increasing. Although vaccines and treatments for COVID-19 are being developed, the disease is unlikely to disappear completely. By attaching a smart sensor to the respirator worn by medical staff, Internet of Things (IoT) technology and artificial intelligence (AI) technology can be used to automatically detect the medical staff's infection symptoms. In the case of medical staff showing symptoms of the disease, appropriate medical treatment can be provided to protect the staff from the greater risk. In this study, we design and develop a system that detects cough, a typical symptom of respiratory infectious diseases, by applying IoT technology and artificial technology to respiratory protection. Because the cough sound is distorted within the respirator, it is difficult to guarantee accuracy in the AI model learned from the general cough sound. Therefore, coughing and non-coughing sounds were recorded using a sensor attached to a respirator, and AI models were trained and performance evaluated with this data. Mel-spectrogram conversion method was used to efficiently classify sound data, and the developed cough recognition system had a sensitivity of 95.12% and a specificity of 100%, and an overall accuracy of 97.94%.

• Korean Journal of Materials Research
• /
• v.31 no.12
• /
• pp.719-726
• /
• 2021

Through the process of chemical vapor deposition, Tungsten Hexafluoride (WF₆) is widely used by the semiconductor industry to form tungsten films. Tungsten Hexafluoride (WF₆) is produced through manufacturing processes such as pulverization, wet smelting, calcination and reduction of tungsten ores. The manufacturing process of Tungsten Hexafluoride (WF₆) is required thorough quality control to improve productivity. In this paper, a real-time detection system for oxidation defects that occur in the manufacturing process of Tungsten Hexafluoride (WF₆) is proposed. The proposed system is implemented by applying YOLOv5 based on Convolutional Neural Network (CNN); it is expected to enable more stable management than existing management, which relies on skilled workers. The implementation method of the proposed system and the results of performance comparison are presented to prove the feasibility of the method for improving the efficiency of the WF₆ manufacturing process in this paper. The proposed system applying YOLOv5s, which is the most suitable material in the actual production environment, demonstrates high accuracy (mAP@0.5 99.4 %) and real-time detection speed (FPS 46).