• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 추계학술발표대회
• /
• pp.763-766
• /
• 2018

표정은 사람들 사이에서 감정을 표현하는 강력한 비언어적 수단이다. 표정 인식은 기계학습에서 아주 중요한 분야 중에 하나이다. 표정 인식에 사용되는 기계학습 모델들은 사람 수준의 성능을 보여준다. 하지만 좋은 성능에도 불구하고, 기계학습 모델들은 표정 인식 결과에 대한 근거나 설명을 제공해주지 못한다. 이 연구는 표정 인식의 근거로서 Facial Action Coding Unit(AUs)을 사용하기 위해서 CK+ Dataset을 사용하여 표정 인식을 학습한 Convolutional Neural Network(CNN) 모델이 추출한 특징들을 t-distributed stochastic neighbor embedding(t-SNE)을 사용하여 시각화한 뒤, 인식된 표정과 AUs 사이의 분포의 연관성을 확인하는 연구이다.

• 정보처리학회논문지B
• /
• 제10B권7호
• /
• pp.777-784
• /
• 2003

본 논문에서는 다중 신경망을 이용한 인식단위 결합 기반의 인쇄체 문자인식 방법을 제안한다. 입력 문자영상은 한글 문자 형식 6가지와 한글 이외의 기타 문자 형식의 전체 7가지 형식으로 분류되어 인식된다. 한글 문자는 2단계의 MLP 신경망 인식기에 의해 인식된다. 첫째 단계에서는 한글 문자를 자소의 조합 형태에 따라 2개 또는 3개의 인식단위로 나누고, 각 인식단위에서 추출된 방향각도 특징 벡터를 입력으로 하는 MLP 신경망으로 1차 인식한다. 둘째 단계에서는 첫째 단계의 인식단위별 MLP 신경망 인식기의 인식양상 특징을 추출하고 다른 MLP 신경망에 입력하여 최종 한글 문자인식을 한다. 한글 이외의 기타 문자의 인식을 위해서는 단일 MLP 신경망을 사용한다. 인식 실험에서는 실제 우편물 50,000통 영상으로부터 추출한 문자영상 데이터베이스를 이용하였는데, 실험 결과 본 논문에서 제안한 방법이 매우 우수함을 알 수 있었다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제7권7호
• /
• pp.259-266
• /
• 2018

본 논문에서는 단어의 순서와 문맥을 고려하는 특징을 추출하여 순환신경망(Recurrent Neural Network)으로 문서를 분류하는 방법을 제안한다. 단어의 의미를 고려한 word2vec 방법으로 문서내의 단어를 벡터로 표현하고, 문맥을 고려하기 위해 doc2vec으로 입력하여 문서의 특징을 추출한다. 문서분류 방법으로 이전 노드의 출력을 다음 노드의 입력으로 포함하는 RNN 분류기를 사용한다. RNN 분류기는 신경망 분류기 중에서도 시퀀스 데이터에 적합하기 때문에 문서 분류에 좋은 성능을 보인다. RNN에서도 그라디언트가 소실되는 문제를 해결해주고 계산속도가 빠른 GRU(Gated Recurrent Unit) 모델을 사용한다. 실험 데이터로 한글 문서 집합 1개와 영어 문서 집합 2개를 사용하였고 실험 결과 GRU 기반 문서 분류기가 CNN 기반 문서 분류기 대비 약 3.5%의 성능 향상을 보였다.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제23권12호
• /
• pp.698-702
• /
• 2017

자연 언어 처리(Natural Language Processing) 분야에 심층 신경망(Deep Neural Network)이 소개된 이후, 단어, 문장 등의 의미를 나타내기 위한 분산 표상인 임베딩(Embedding)을 학습하기 위한 연구가 활발히 진행되고 있다. 임베딩 학습을 위한 방법으로는 크게 문맥 기반의 텍스트 모델링 방법과, 기학습된 임베딩을 결합하여 더 긴 텍스트의 분산 표상을 계산하고자 하는 결합 기반의 텍스트 모델링 방법이 있다. 하지만, 기존 결합 기반의 텍스트 모델링 방법은 최적 결합 단위에 대한 고찰 없이 단어를 이용하여 연구되어 왔다. 본 연구에서는 비교 실험을 통해 문서 임베딩 생성에 적합한 결합 기법과 최적 결합 단위에 대해 알아본다. 또한, 새로운 결합 방법인 담화 분석 기반의 결합 방식을 제안하고 실험을 통해 기존의 순차적 결합 기반 신경망 모델 대비 우수성을 보인다.

• Journal of Information Processing Systems
• /
• 제9권1호
• /
• pp.117-140
• /
• 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document's textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.730-744
• /
• 2023

The topic of this paper is the recognition of human activities using egocentric vision, particularly captured by body-worn cameras, which could be helpful for video surveillance, automatic search and video indexing. This being the case, it could also be helpful in assistance to elderly and frail persons for revolutionizing and improving their lives. The process throws up the task of human activities recognition remaining problematic, because of the important variations, where it is realized through the use of an external device, similar to a robot, as a personal assistant. The inferred information is used both online to assist the person, and offline to support the personal assistant. With our proposed method being robust against the various factors of variability problem in action executions, the major purpose of this paper is to perform an efficient and simple recognition method from egocentric camera data only using convolutional neural network and deep learning. In terms of accuracy improvement, simulation results outperform the current state of the art by a significant margin of 61% when using egocentric camera data only, more than 44% when using egocentric camera and several stationary cameras data and more than 12% when using both inertial measurement unit (IMU) and egocentric camera data.

• The Journal of the Acoustical Society of Korea
• /
• 제17권4E호
• /
• pp.28-34
• /
• 1998

In most switching system, the processing unit is designed to work efficiently even at relatively high loads, but when the offered traffic exceeds a particular level, the rate of completed calls can fall drastically. A single call handled by the switching system consists of a sequence of events or messages that has to be processed by the control unit. The control unit is not only incapable of handling all of the offered calls, but also its call handling capability can drop as the offered load increases. The real time available for call processing is a critical resource that requires careful management. Therefore, the overloading of this resource must be detected by a subscriber in the from of a dial tone delay or an uncompleted call which is either blocked or mishandled. The subscriber may respond by either dialing prematurely or by re-attempting a call. This action can further escalate the processors load, which is spent for uncompleted calls. Unless a proper control is used, the switching system can finally break down. In this paper, we paper, we propose a fuzzy overload detection and control method for switching systems, which can by generating fuzzy rules via fuzzy aggregation networks. Simulation results involving a switching system is given.

• 전자통신동향분석
• /
• 제32권6호
• /
• pp.57-65
• /
• 2017

Neural network based AI computing is a promising technology that reflects the recognition and decision operation of human beings. Early AI computing processors were composed of GPUs and CPUs; however, the dramatic increment of a floating point operation requires an energy efficient AI processor with a highly parallelized architecture. In this paper, we analyze the trends in processor architectures for AI computing. Some architectures are still composed using GPUs. However, they reduce the size of each processing unit by allowing a half precision operation, and raise the processing unit density. Other architectures concentrate on matrix multiplication, and require the construction of dedicated hardware for a fast vector operation. Finally, we propose our own inAB processor architecture and introduce domestic cutting-edge processor design capabilities.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권3호
• /
• pp.193-199
• /
• 2017

Instead of using only spatial features from a single frame for person re-identification, a combination of spatial and temporal factors boosts the performance of the system. A recurrent neural network (RNN) shows its effectiveness in generating highly discriminative sequence-level human representations. In this work, we implement RNN, three Long Short Term Memory (LSTM) network variants, and Gated Recurrent Unit (GRU) on Caffe deep learning framework, and we then conduct experiments to compare performance in terms of size and accuracy for person re-identification. We propose using GRU for the optimized choice as the experimental results show that the GRU achieves the highest accuracy despite having fewer parameters than the others.

• 전기학회논문지P
• /
• 제58권4호
• /
• pp.511-515
• /
• 2009

For detecting of the faulty insulator, Correlation Propagation Neural Networks(CPNN) has been proposed. Faulty insulator is reduced the rate of insulation extremely, and taken the results dirty and injured. It is necessary to detect the faulty insulator and exchange the new one. And thus, we have designed the CPNN to be detected that insulators by the real time computation method through the inter-node diffusion. In the network, a node corresponds to a state in the quantized input space. Each node is composed of a processing unit and fixed weights from its neighbor nodes as well as its input terminal. Information propagates among neighbor nodes laterally and inter-node interpolation is achieved. 1-D CPNN hardware has been implemented with general purpose. Experiments with static and dynamic signals have been done upon the CPNN hardware. Through the results of simulation experiments, we define the ability of real-time detecting the faulty insulators.