• The Journal of Korean Institute of Information Technology
• /
• v.17 no.12
• /
• pp.81-92
• /
• 2019

Weeds are a major object which is very harmful to crops. To remove the weeds effectively, we have to classify them accurately and use herbicides. As computing technology has developed, image-based machine learning methods have been studied in this field, specially convolutional neural network(CNN) based models have shown good performance in public image dataset. However, CNN with numerous training parameters and high computational amount. Thus, it works under high hardware condition of expensive GPUs in real application. To solve these problems, in this paper, a hierarchical architecture based deep-learning model is proposed. The experimental results show that the proposed model successfully classify 21 species of the exotic weeds. That is, the model achieve 97.2612% accuracy with a small number of parameters. Our proposed model with a few parameters is expected to be applicable to actual application of network based classification services.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.87-93
• /
• 2023

In this paper, we propose a system that accurately and efficiently determines forward head posture based on network learning by analyzing the user's skeletal posture. Forward head posture syndrome is a condition in which the forward head posture is changed by keeping the neck in a bent forward position for a long time, causing pain in the back, shoulders, and lower back, and it is known that daily posture habits are more effective than surgery or drug treatment. Existing methods use convolutional neural networks using webcams, and these approaches are affected by the brightness, lighting, skin color, etc. of the image, so there is a problem that they are only performed for a specific person. To alleviate this problem, this paper extracts the skeleton from the image and learns the data corresponding to the side rather than the frontal view to find the forward head posture more efficiently and accurately than the previous method. The results show that the accuracy is improved in various experimental scenes compared to the previous method.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.65-73
• /
• 2023

In this paper, we propose a data augmentation method based on CNN(Convolutional Neural Network) learning for efficiently obtaining concrete crack image datasets. Real concrete crack images are not only difficult to obtain due to their unstructured shape and complex patterns, but also may be exposed to dangerous situations when acquiring data. In this paper, we solve the problem of collecting datasets exposed to such situations efficiently in terms of cost and time by using vector and thickness-based data augmentation techniques. To demonstrate the effectiveness of the proposed method, experiments were conducted in various scenes using U-Net-based crack detection, and the performance was improved in all scenes when measured by IoU accuracy. When the concrete crack data was not augmented, the percentage of incorrect predictions was about 25%, but when the data was augmented by our method, the percentage of incorrect predictions was reduced to 3%.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.252-254
• /
• 2019

본 논문은 합성곱 기반의 Single Shot Multibox Detector(SSD) [1] 의 구조를 이용하여 다양한 스케일의 얼굴들을 잘 검출하도록 하였다. 얼굴 검출은 물체 검출과는 다르게 얼굴의 높이와 너비의 비율이 다소 일정하고 크기가 작은 경우가 많은데, 이에 맞게 얼굴 검출이 용이하도록 anchor의 스케일, 비율, 크기를 변경하였다. 특징점 추출 네트워크는 깊은 네트워크의 최적화를 용이하게 하는 skip connection을 이용한 ResNet-50 [2] 기반을 사용하였다. 다양한 크기, 조명, 환경, 각도의 얼굴들을 포함하는 영상들로 이뤄진 Wider Face[3] 데이터 셋의 easy validation set으로 실험한 결과 0.782과 hard validation set에서 0.611의 average precision을 보였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.253-256
• /
• 2021

본 논문에서는 합성곱 신경망을 통해 학습된 DoF(피사계 심도, Depth of field) 네트워크 아키텍처를 이용하여 객체 인식, 시점 추적, 문자 인식, 비사실적 렌더링 등 다양한 애플리케이션에 적용할 수 있는 사후 필터링 기법에 대해 살펴본다. 일반적으로 영상은 포커싱과 아웃포커싱에 의해 사용자의 관심표현이 결정되며, 이를 이용하여 영상 내 중요도를 판단한다. 영상 내에는 수많은 콘텐츠들이 혼재되어 있기 때문에 사용자가 집중적으로 보고 있는 콘텐츠를 찾아내기 어렵다. 본 논문에서는 사용자가 흥미롭고 집중적으로 보고 있는 영역을 DoF 네트워크로 학습시키고, 이를 통해 이전 기법으로는 표현할 수 없었던 DoF 기반 객체 인식, 시점 추적, 문자 인식, 비사실적 렌더링을 효율적으로 표현해낸다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.355-364
• /
• 2023

As advanced cyber threats continue to increase in recent years, it is difficult to detect new types of cyber attacks with existing pattern or signature-based intrusion detection method. Therefore, research on anomaly detection methods using data learning-based artificial intelligence technology is increasing. In addition, supervised learning-based anomaly detection methods are difficult to use in real environments because they require sufficient labeled data for learning. Research on an unsupervised learning-based method that learns from normal data and detects an anomaly by finding a pattern in the data itself has been actively conducted. Therefore, this study aims to extract a latent vector that preserves useful sequence information from sequence log data and develop an anomaly detection learning model using the extracted latent vector. Word2Vec was used to create a dense vector representation corresponding to the characteristics of each sequence, and an unsupervised autoencoder was developed to extract latent vectors from sequence data expressed as dense vectors. The developed autoencoder model is a recurrent neural network GRU (Gated Recurrent Unit) based denoising autoencoder suitable for sequence data, a one-dimensional convolutional neural network-based autoencoder to solve the limited short-term memory problem that GRU can have, and an autoencoder combining GRU and one-dimensional convolution was used. The data used in the experiment is time-series-based NGIDS (Next Generation IDS Dataset) data, and as a result of the experiment, an autoencoder that combines GRU and one-dimensional convolution is better than a model using a GRU-based autoencoder or a one-dimensional convolution-based autoencoder. It was efficient in terms of learning time for extracting useful latent patterns from training data, and showed stable performance with smaller fluctuations in anomaly detection performance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.64-67
• /
• 2021

가짜뉴스는 뉴스 기사 형식을 갖는 날조된 정보를 의미하며, 최근 모바일 인터넷 장치의 보급과 소셜 네트워크 서비스의 대중화로 온라인 확산이 가속화되고 있다. 기존 연구는 가짜뉴스의 탐지를 위해 뉴스의 주제목, 부제목, 리드, 본문 등 뉴스 기사를 이루는 구성요소를 비롯하여 언론사, 기자, 날짜, 확산 경로 등의 메타 데이터를 대상으로 분석하였다. 그러나 뉴스의 제목과 본문 및 메타 데이터 등은 내용 수정이 쉬워, 다량의 데이터를 학습한 모델이라 하더라도 높은 정확도를 장기간 유지하기 어려울 수 있다. 이러한 문제점을 해결하기 위하여 본 논문은 합성곱 신경망을 이용해 문맥 정보를 분석하고 장단기 메모리 기반의 감성분석을 추가로 수행한다. 문맥 정보와 가짜뉴스 유포자가 쉽게 수정할 수 없는 감성 변화 패턴을 활용하여 성능이 개선된 가짜뉴스 탐지 모델을 제안한다.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.45-52
• /
• 2021

In this paper, we propose a prediction model for osteopenia and osteoporosis based on a convolutional neural network(CNN) using computed tomography(CT) images. In a single CT image, CNN had a limitation in utilizing important local features for diagnosis. So we propose a compound model which has two identical structures. As an input, two different texture images are used, which are converted from a single normalized CT image. The two networks train different information by using dissimilarity loss function. As a result, our model trains various features in a single CT image which includes important local features, then we ensemble them to improve the accuracy of predicting osteopenia and osteoporosis. In experiment results, our method shows an accuracy of 77.11% and the feature visualize of this model is confirmed by using Grad-CAM.

• Prospectives of Industrial Chemistry
• /
• v.23 no.6
• /
• pp.3-13
• /
• 2020

저출산 고령화 사회로의 진입은 대한민국뿐만 아니라 전 세계적으로 많은 사회 문제를 야기하고 있다. 그 중에서 고령 인구 증가로 인한 의료 수요 증가와 이를 뒷받침 할 의료인력 부족은 곧 다가올 사회문제이다. 4차 산업 혁명으로 인해 다양한 사회문제에 대한 혁신적인 해법들이 제시되고 있는데, 본 기고문에서는 다가올 고령화 사회에서 의료인력 부족 등에 의한 해결법으로 원격의료 지원을 위한 인공지능 활용을 다루고자 한다. 병 진단 및 예측을 위한 여러 가지 인공지능 알고리즘은 이미 많이 개발 되어 있으나, 일반적으로 딥러닝에 많이 쓰이는 인공신경망 구조인 합성곱 뉴럴네트워크(convolution neural network)나 기존 퍼셉트론(perceptron) 구조에서 벗어나 확률론적 인공신경망 중에 하나인 베이지안 뉴럴네트워크(Bayesian neural network)를 다루고자 한다. 그중에서 연산효율적이며 뉴로모픽 하드웨어로 구현 가능성이 높고 실제 진단 예측(diagnosis prediction) 문제 해결에 강점을 보이는 알고리즘으로써 naive Bayes classifer를 활용한 연구를 소개하고자 한다.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.378-390
• /
• 2022

With the recent development of deep composite multiplication neural network learning, deep learning techniques applied to single-image super-resolution have shown good results, and the strong expression ability of deep networks has enabled complex nonlinear mapping between low-resolution and high-resolution images. However, there are limitations in applying it to real-time or low-power devices with increasing parameters and computational amounts due to excessive use of composite multiplication neural networks. This paper uses blocks that extract hierarchical characteristics little by little using information distillation and suggests the Recursive Distillation Super Resolution Network (RDSRN), a lightweight network that improves performance by making more accurate high frequency components through high frequency residual purification blocks. It was confirmed that the proposed network restores images of similar quality compared to RDN, restores images 3.5 times faster with about 32 times fewer parameters and about 10 times less computation, and produces 0.16 dB better performance with about 2.2 times less parameters and 1.8 times faster processing time than the existing lightweight network CARN.