• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2000년도 추계학술발표논문집 (상)
• /
• pp.247-250
• /
• 2000

본 논문에서는 다양한 배경을 가지는 연속적인 얼굴 영상에서 실시간으로 눈의 위치를 자동적으로 추출하는 방법에 대하여 제시한다. 얼굴 요소 중에서 눈은 얼굴 인식 분야에 있어서 중요한 특징을 나타내는 주 요소로써 주로 히스토그램 분석과 색상 정보를 이용하여 눈 영역의 윤곽을 추출하는 방법이 제기되고 있다. 본 논문에서는 명암의 변화에도 비교적 적응력이 강한 이진화 기법을 사용하여 원영상을 이진화하고, 가변 템플릿(Deformable Template)방법을 사용하여 후보 영역을 추출한다. 이러한 후보영역들은 ART2 신경회로망을 이용하여 병합되며, 병합된 후보 영역들은 얼굴 요소의 기하학적 사전지식을 기반으로 검증되어, 시간에 따라 모양변화가 급변하는 눈 영역에 대한 실시간 추출을 가능하게 한다. 이상의 연구 결과는 교통사고 방지를 위한 눈의 졸림감지 등의 응용 시스템에 이용될 수 있다.

• 제어로봇시스템학회논문지
• /
• 제9권7호
• /
• pp.536-546
• /
• 2003

We propose an object extraction technique adequate for the radial shape's radar signal structure for the purpose of implementing ARPA(Automatic Radar Plotting Aid) installed in the vessel. The radar signal data are processed by interpolation and accumulation to acquire a qualified image. The objects of the radar image have characteristics of having different shape and size as it gets far from the center, and it is not adequate for clustering generally. Therefore, this study designs a new vigilance distance model of elliptical shape and adopts this model in the ART2 neural network. We prove that the proposed clustering method makes it possible to extract objects adaptively and to separate the connected objects effectively.

• ETRI Journal
• /
• 제43권2호
• /
• pp.288-298
• /
• 2021

Abstractive text summarization is a process of making a summary of a given text by paraphrasing the facts of the text while keeping the meaning intact. The manmade summary generation process is laborious and time-consuming. We present here a summary generation model that is based on multilayered attentional peephole convolutional long short-term memory (MAPCoL; LSTM) in order to extract abstractive summaries of large text in an automated manner. We added the concept of attention in a peephole convolutional LSTM to improve the overall quality of a summary by giving weights to important parts of the source text during training. We evaluated the performance with regard to semantic coherence of our MAPCoL model over a popular dataset named CNN/Daily Mail, and found that MAPCoL outperformed other traditional LSTM-based models. We found improvements in the performance of MAPCoL in different internal settings when compared to state-of-the-art models of abstractive text summarization.

• 한국컴퓨터정보학회논문지
• /
• 제24권8호
• /
• pp.87-93
• /
• 2019

These days, as interest in the recommendation system with deep learning is increasing, a number of related studies to develop a performance for collaborative filtering through autoencoder, a state-of-the-art deep learning neural network architecture has advanced considerably. The purpose of this study is to propose autoencoder which is used by the recommendation system to predict ratings, and we added more hidden layers to the original architecture of autoencoder so that we implemented deep autoencoder with 3 to 5 hidden layers for much deeper architecture. In this paper, therefore we make a comparison between the performance of them. In this research, we use 2-dimensional arrays and 3-dimensional tensor as the input dataset. As a result, we found a correlation between matrix entry of the 3-dimensional dataset such as item-time and user-time and also figured out that deep autoencoder with extra hidden layers generalized even better performance than autoencoder.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권1호
• /
• pp.182-190
• /
• 2024

Various artificial intelligence neural network models that have emerged since 2014 enable the creation of new content beyond the existing level of information discrimination and withdrawal, and the recent generative artificial intelligences such as ChatGPT and Gall-E2 create and present new information similar to actual data, enabling natural interaction because they create and provide verbal expressions similar to humans, unlike existing chatbots that simply present input content or search results. This study aims to present a model that can improve the ChatGPT communication skills of university students through curriculum research on ChatGPT, which can be participated by students from all departments, including engineering, humanities, society, health, welfare, art, tourism, management, and liberal arts. It is intended to design a way to strengthen competitiveness to embody the practical ability to solve problems through ethical attitudes, AI-related technologies, data management, and composition processes as knowledge necessary to perform tasks in the artificial intelligence era, away from simple use capabilities. It is believed that through creative education methods, it is possible to improve university awareness in companies and to seek industry-academia self-reliant courses.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.1989-2011
• /
• 2019

Vehicle detection based on aerial images is an interesting and challenging research topic. Most of the traditional vehicle detection methods are based on the sliding window search algorithm, but these methods are not sufficient for the extraction of object features, and accompanied with heavy computational costs. Recent studies have shown that convolutional neural network algorithm has made a significant progress in computer vision, especially Faster R-CNN. However, this algorithm mainly detects objects in natural scenes, it is not suitable for detecting small object in aerial view. In this paper, an accurate and effective vehicle detection algorithm based on Faster R-CNN is proposed. Our method fuse a hyperactive feature map network with Eltwise model and Concat model, which is more conducive to the extraction of small object features. Moreover, setting suitable anchor boxes based on the size of the object is used in our model, which also effectively improves the performance of the detection. We evaluate the detection performance of our method on the Munich dataset and our collected dataset, with improvements in accuracy and effectivity compared with other methods. Our model achieves 82.2% in recall rate and 90.2% accuracy rate on Munich dataset, which has increased by 2.5 and 1.3 percentage points respectively over the state-of-the-art methods.

• 한국정보처리학회논문지
• /
• 제4권7호
• /
• pp.1749-1758
• /
• 1997

전력수요의 예측은 예측기간에 따라 중장기 전력수요 예측과 단기 부하 예측으로 구분할 수 있다. 기존의 단기 부하예측은 주로 역전파 알고리즘(back propagation algorithm)다층퍼셉트론을 이용하여 예측을 하였으나 이는 학습시간이 많이 걸릴 뿐만 아니라 학습도중에 지역최소점(local minima)에 빠져 학습이 계속되지 못한다는 문제가 있다. 본 논문은 이러한 역전파 알고리즘의 문제점을 해결할 수 있는 방법으로 Radial Basis 함수(Radial Basis Function)를 이용하여 동적 단기부하 예측 모형을 제안한다. Radial Basis 함수는 하나의 은닉층(hidden layer)을 갖고 있으며, 전방향(feed-forward)학습을 한다는 특징이 있다. 본 논문에서 제안한 단기 부하 예측모형은 학습을 하기 위하여 시간대별 부하량을 클러스터링 하고, 이 클러스터의 중심값을 Radial Basis 함수의 은닉층으로 하여 학습을 한 다음 예측하고자 하는 패턴을 한 단위로 하여 시단대별로 예측하였다. 기존의 연구에서의 클러스터링 방법으로는 통계학의 K-Means 방법이나 Kohonen의 LVQ(Learning Vector Quantization)을 주로 이용하였으나 본 논문에서는 패턴의 분류에 있어서 다른 알고리즘보다 편차가 작은 Pal, et. al.의 GLVQ(Generalized LVQ) 알고리즘을 이용하였다. 본 논문에서 이용한 데이타는 1995년 3월 1일-3일, 6월 1일-3일, 7월 1일-3일, 9월 1일-3일, 11월 1일-3일의 72시간 데이타를 입력하여 월별 4일의 24시간의 예측시간으로 예측하였다. 실험결과 월별 1일과 3일까지의 학습데이타로 1시간 후의 부하량을 24시간동안 예측한 결과 1.3795%의 평균 오차율로 예측하였다.

• 산업경영시스템학회지
• /
• 제46권1호
• /
• pp.55-67
• /
• 2023

Lightweight face recognition models, as one of the most popular and long-standing topics in the field of computer vision, has achieved vigorous development and has been widely used in many real-world applications due to fewer number of parameters, lower floating-point operations, and smaller model size. However, few surveys reviewed lightweight models and reimplemented these lightweight models by using the same calculating resource and training dataset. In this survey article, we present a comprehensive review about the recent research advances on the end-to-end efficient lightweight face recognition models and reimplement several of the most popular models. To start with, we introduce the overview of face recognition with lightweight models. Then, based on the construction of models, we categorize the lightweight models into: (1) artificially designing lightweight FR models, (2) pruned models to face recognition, (3) efficient automatic neural network architecture design based on neural architecture searching, (4) Knowledge distillation and (5) low-rank decomposition. As an example, we also introduce the SqueezeFaceNet and EfficientFaceNet by pruning SqueezeNet and EfficientNet. Additionally, we reimplement and present a detailed performance comparison of different lightweight models on the nine different test benchmarks. At last, the challenges and future works are provided. There are three main contributions in our survey: firstly, the categorized lightweight models can be conveniently identified so that we can explore new lightweight models for face recognition; secondly, the comprehensive performance comparisons are carried out so that ones can choose models when a state-of-the-art end-to-end face recognition system is deployed on mobile devices; thirdly, the challenges and future trends are stated to inspire our future works.

• Journal of information and communication convergence engineering
• /
• 제2권2호
• /
• pp.132-137
• /
• 2004

Most of the current computer vision theories are based on hypotheses that are difficult to apply to the real world, and they simply imitate a coarse form of the human visual system. As a result, they have not been showing satisfying results. In the human visual system, there is a mechanism that processes information due to memory degradation with time and limited storage space. Starting from research on the human visual system, this study analyzes a mechanism that processes input information when information is transferred from the retina to ganglion cells. In this study, a model for the characteristics of ganglion cells in the retina is proposed after considering the structure of the retina and the efficiency of storage space. The MNIST database of handwritten letters is used as data for this research, and ART2 and SOM as recognizers. The results of this study show that the proposed recognition model is not much different from the general recognition model in terms of recognition rate, but the efficiency of storage space can be improved by constructing a mechanism that processes input information.

• 한국정보처리학회논문지
• /
• 제5권8호
• /
• pp.1951-1959
• /
• 1998

본 논문에서는 내용기반 접근 방법에 의한 보다 효율적인 특징 추출 및 이를 이용한 영상 검색 시스템을 Oracle 데이터베이스상에서 구현하였다. 먼저, 다양한 입력 영상에 대하여 기존 Stricker 방법을 수정하여 영상의 칼라 특징을 추출하고, 추출된 칼라 특징과 ART2 신경만을 이용하여 영상들을 개략 분류한다. 다음, wavelet 변환을 이용하여 변환 영역상에서 영상의 질감 특징을 추출하고, 이를 이용하여 전 단계에서 칼라 특징으로 개략 분류된 영상들의 최종적인 상세 분류를 수행한다. 연구된 특징 추출 방법들을 기반으로 하여, 관계형 데이터베이스상에서 확장된 SQL문을 사용하여 영상 검색 시스템을 구현하였다. 제안된 영상 검색 시스템은 Oracle DBMS상에서 구현되었고, 200개의 시험 영상으로 실험한 결과, Recall과 Precision에서 90%, 81%의 만족한 검색 효율을 보였다.