• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.867-871
• /
• 2022

Amid the recent rapid trend change, the change in design has a great impact on the sales of fashion companies, so it is inevitable to be careful in choosing new designs. With the recent development of the artificial intelligence field, various machine learning is being used a lot in the fashion market to increase consumers' preferences. To contribute to increasing reliability in the development of new products by quantifying abstract concepts such as preferences, we generate new images that do not exist through three adversarial generative neural networks (GANs) and numerically compare abstract concepts of preferences using pre-trained convolution neural networks (CNNs). Deep convolutional generative adversarial networks (DCGAN), Progressive growing adversarial networks (PGGAN), and Dual Discriminator generative adversarial networks (DANs), which were trained to produce comparative, high-level, and high-level images. The degree of similarity measured was considered as a preference, and the experimental results showed that D2GAN showed a relatively high similarity compared to DCGAN and PGGAN.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.555-558
• /
• 2020

본 논문에서는 입력 영상에 담긴 다양한 물체들과 그들 간의 관계를 효과적으로 탐지하여, 하나의 장면 그래프로 표현해내는 새로운 심층 신경망 모델을 제안한다. 제안 모델에서는 물체와 관계의 효과적인 탐지를 위해, 합성 곱 신경망 기반의 시각 맥락 특징들뿐만 아니라 언어 맥락 특징들을 포함하는 다양한 멀티 모달 맥락 정보들을 활용한다. 또한, 제안 모델에서는 관계를 맺는 두 물체 간의 상호 의존성이 그래프 노드 특징값들에 충분히 반영되도록, 그래프 신경망을 이용해 맥락 정보를 임베딩한다. 본 논문에서는 Visual Genome 벤치마크 데이터 집합을 이용한 비교 실험들을 통해, 제안 모델의 효과와 성능을 입증한다.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.243-250
• /
• 2022

The purpose of this study was to propose technology to detect the wave in the image in real-time, and calculate the height of the wave-overtopping through image analysis using artificial intelligence. It was confirmed that the proposed wave overtopping detection system proposed in this study could detect the occurring of wave overtopping, even in severe weather and at night in real-time. In particular, a filtering algorithm for determining if the wave overtopping event was used, to improve the accuracy of detecting the occurrence of wave overtopping, based on a convolutional neural networks to catch the wave overtopping in CCTV images in real-time. As a result, the accuracy of the wave overtopping detection through AP50 was reviewed as 59.6%, and the speed of the overtaking detection model was 70fps based on GPU, confirming that accuracy and speed are suitable for real-time wave overtopping detection.

• Smart Media Journal
• /
• v.10 no.4
• /
• pp.45-54
• /
• 2021

The skin is the body's first line of defense against external infection. When a skin disease strikes, the skin's protective role is compromised, necessitating quick diagnosis and treatment. Recently, as artificial intelligence has advanced, research for technical applications has been done in a variety of sectors, including dermatology, to reduce the rate of misdiagnosis and obtain quick treatment using artificial intelligence. Although previous studies have diagnosed skin diseases with low incidence, this paper proposes a method to classify common illnesses such as warts and corns using a convolutional neural network. The data set used consists of 3 classes and 2,515 images, but there is a problem of lack of training data and class imbalance. We analyzed the performance using a deep metric loss function and a cross-entropy loss function to train the model. When comparing that in terms of accuracy, recall, F1 score, and accuracy, the former performed better.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.17-25
• /
• 2023

In this paper, we propose a model that can perform human pose estimation through a MobileViT-based model with fewer parameters and faster estimation. The based model demonstrates lightweight performance through a structure that combines features of convolutional neural networks with features of Vision Transformer. Transformer, which is a major mechanism in this study, has become more influential as its based models perform better than convolutional neural network-based models in the field of computer vision. Similarly, in the field of human pose estimation, Vision Transformer-based ViTPose maintains the best performance in all human pose estimation benchmarks such as COCO, OCHuman, and MPII. However, because Vision Transformer has a heavy model structure with a large number of parameters and requires a relatively large amount of computation, it costs users a lot to train the model. Accordingly, the based model overcame the insufficient Inductive Bias calculation problem, which requires a large amount of computation by Vision Transformer, with Local Representation through a convolutional neural network structure. Finally, the proposed model obtained a mean average precision of 0.694 on the MS COCO benchmark with 3.28 GFLOPs and 9.72 million parameters, which are 1/5 and 1/9 the number compared to ViTPose, respectively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.898-900
• /
• 2019

SPARQL(SPARQL Protocol and RDF Query Language)은 지식 베이스를 위한 표준 시맨틱 질의 언어이다. 최근 인공지능 분야에서 지식 베이스는 질의 응답 시스템, 시맨틱 검색 등 그 활용성이 커지고 있다. 그러나 SPARQL 과 같은 질의 언어를 사용하기 위해서는 질의 언어의 문법을 이해하기 때문에, 일반 사용자의 경우에는 그 활용성이 제한될 수밖에 없다. 이에 본 논문은 신경망 기반 기계 번역 기술을 활용하여 자연어 질의로부터 SPARQL 을 생성하는 방법을 제안한다. 우리는 제안하는 방법을 대규모 공개 지식 베이스인 Wikidata 를 사용해 검증하였다. 우리는 실험에서 사용할 Wikidata 에 존재하는 영화 지식을 묻는 자연어 질의-SPARQL 질의 쌍 20,000 건을 생성하였고, 여러 sequence-to-sequence 모델을 비교한 실험에서 합성곱 신경망 기반의 모델이 BLEU 96.8%의 가장 좋은 결과를 얻음을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.586-589
• /
• 2024

본 실험 연구에서는 주의 메커니즘과 컨볼루션 신경망을 결합하여 모델을 개선하는 방법을 탐색하는 딥 러닝 기술을 소개한다. 이 기술은 지도 학습 방식을 위해 공개 데이터 세트의 쓰레기 분류 데이터를 사용하고, Grad-CAM 기술과 채널 주의 메커니즘 SE 를 적용하여 모델의 분류 의사 결정 과정을 더 잘 이해하기 위해 히트 맵을 생성한다. Grad-CAM 기술을 사용하여 히트 맵을 생성하면 분류 중에 모델이 집중하는 영역을 시각화할 수 있다. 이는 모델의 분류 결정을 설명하는 방법을 제공하여 다양한 이미지 카테고리에 대한 모델 결정의 기초를 더 잘 이해할 수 있다. 실험 결과는 전통적인 합성곱 신경망과 비교하여 제안한 방법이 쓰레기 분류 작업에서 더나은 성능을 달성한다는 것을 보여준다. 주의 메커니즘과 히트맵 해석을 결합함으로써 우리 모델은분류 정확도를 향상시킬 수 있다. 이는 실제 응용 분야의 이미지 분류 작업에 큰 의미가 있으며 해석 가능성에 대한 딥 러닝 연구 진행을 촉진하는 데 도움이 된다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.470-471
• /
• 2019

서로 다른 음성 데이터 분류를 위한 연구는 많이 진행되고 있지만 개인이 갖고 있는 목소리 또는 각 악기들이 갖고 있는 음색 러닝 연구는 부족한 실정이다. 본 논문에서는 음색 러닝을 위한 합성 곱 신경망 분석 연구를 진행한다. 음색이란 음정과 세기가 같을 경우에도 두 소리를 구분할 수 있는 복합적인 요소이다.

• Journal of The Korean Association For Science Education
• /
• v.43 no.3
• /
• pp.237-251
• /
• 2023

This study explores the possibility of automated scoring for scientific graph answers by designing an automated scoring model using convolutional neural networks and applying it to students' kinematics graph answers. The researchers prepared 2,200 answers, which were divided into 2,000 training data and 200 validation data. Additionally, 202 student answers were divided into 100 training data and 102 test data. First, in the process of designing an automated scoring model and validating its performance, the automated scoring model was optimized for graph image classification using the answer dataset prepared by the researchers. Next, the automated scoring model was trained using various types of training datasets, and it was used to score the student test dataset. The performance of the automated scoring model has been improved as the amount of training data increased in amount and diversity. Finally, compared to human scoring, the accuracy was 97.06%, the kappa coefficient was 0.957, and the weighted kappa coefficient was 0.968. On the other hand, in the case of answer types that were not included in the training data, the s coring was almos t identical among human s corers however, the automated scoring model performed inaccurately.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.1
• /
• pp.19-26
• /
• 2019

In this paper, the classification performance of learning algorithms is compared for TAB digit recognition. The TAB digits that are segmented from TAB musical notes contain TAB lines and musical symbols. The labeling method and non-linear filter are designed and applied to extract fret digits only. The shift operation of the 4 directions is applied to generate more data. The selected models are Bayesian classifier, support vector machine, prototype based learning, multi-layer perceptron, and convolutional neural network. The result shows that the mean accuracy of the Bayesian classifier is about 85.0% while that of the others reaches more than 99.0%. In addition, the convolutional neural network outperforms the others in terms of generalization and the step of the data preprocessing.