• 전자공학회논문지B
• /
• 제31B권9호
• /
• pp.159-165
• /
• 1994

In this paper, we propose a multi-layer associative neural network structure suitable for hardware implementaion with the function of performance refinement and improved robutst capability. Unlike other methods which reduce network complexity by putting restrictions on synaptic weithts, we are imposing a requirement of hidden layer neurons for the function. The proposed network has synaptic weights obtainted by Hebbian rule between adjacent layer's memory patterns such as Kosko's BAM. This network can be extended to arbitary multi-layer network trainable with Genetic algorithm for getting hidden layer memory patterns starting with initial random binary patterns. Learning is done to minimize newly defined network error. The newly defined error is composed of the errors at input, hidden, and output layers. After learning, we have bidirectional recall process for performance improvement of the network with one-shot recall. Experimental results carried out on pattern recognition problems demonstrate its performace according to the parameter which represets relative significance of the hidden layer error over the sum of input and output layer errors, show that the proposed model has much better performance than that of Kosko's bidirectional associative memory (BAM), and show the performance increment due to the bidirectionality in recall process.

• 한국정보통신학회논문지
• /
• 제25권12호
• /
• pp.1770-1776
• /
• 2021

손 표현 인식을 위해서는 손의 정적인 형태를 기반으로 하는 손 자세 인식과 손의 움직임을 기반으로 하는 손 동작 인식이 함께 사용된다. 본 논문에서는 가상의 칠판 위에서 움직이는 손의 궤적을 기반으로 기호를 인식하는 손 표현인식 방법을 제안하였다. 손으로 가상의 칠판에 그린 기호를 인식하기 위해서는 손의 움직임으로부터 기호를 인식하는 방법은 물론, 데이터 입력의 시작과 끝을 찾아내기 위한 손 자세 인식 역시 필요하다. 본 논문에서는 손 자세 인식을 위해 미디어파이프를, 시계열 데이터에서 손 동작을 인식하기 위해 순환 신경망의 한 종류인 LSTM(Long Short Term Memory)을 사용하였다. 제안하는 방법의 유효성을 보이기 위해 가상 칠판에 쓰는 숫자 인식에 제안하는 방법을 적용하였을 때 약 94%의 인식률을 얻을 수 있었다.

• 정보처리학회논문지B
• /
• 제8B권6호
• /
• pp.699-704
• /
• 2001

본 논문에서는 혼성 모듈 구조의 recurrent 시간지연신경회로망(time-delay neural network)과 HMM(hidden Markov model)을 결합한 음성인식을 위한 새로운 구조에 대해 연구하였다. 시간지연신경회로망에서는 윈도우 크기를 확장하는 것이 인식률 향상에 유리하므로 이를 위해 첫 번째 은닉층에 궤환 구조를 사용하여 윈도우 크기를 실제로 크게 하지 않고도 동일한 효과를 얻을 수 있도록 하였다. 다음 이 시간지연신경망에서 입력된 음소의 특징 벡터의 시간에 따라 변화하는 성질을 잘 처리 할 수 있도록 시간지연신경회로망의 입력층을 복수의 상태로 나누어 음소특징의 시간축에 대한 각 상태마다 특징 감지기를 갖도록 하였다. 이때 시간지연신경회로망은 전체 음성인식 영역에 적용될 수 있도록 모듈 방식의 구조로 구성되었다. 그리고 이 모듈 구조 시간지연신경망의 출력 벡터를 HMM에 연결하여 서로 결합 하므로써 양 구조의 장점을 취하는 혼성 구조의 인식시스템을 구성하였고 이때 이 혼성 구조에서 효율적으로 적용할 수 있는 HMM 파라미터 smoothing 방법을 제시하였다.

• International Journal of Computer Science & Network Security
• /
• 제22권8호
• /
• pp.1-6
• /
• 2022

In this paper, we will present the realization of a facial recognition system using the ESP32-CAM board controlled by an Arduino board. The goal is to monitor a remote location in real time via a camera that is integrated into the ESP32 IOT board. The acquired images will be recorded on a memory card and at the same time transmitted to a pc (a web server). The development of this remote monitoring system is to create an alternative between security, reception, and transmission of information to act accordingly. The simulation results of our proposed application of the facial recognition domain are very efficient and satisfying in real time.

• 대한전자공학회논문지
• /
• 제26권10호
• /
• pp.1576-1583
• /
• 1989

In this paper, we describe real-time optical implementation of the Hopfield neural network model for two-dimensional associative memory by using commercial LCTV and Multifocus For real-time processing capability, we use LCTV as a memory mask and a input spatial light modulator. Inner product between input pattern and memory matrix is processed by the multifocus holographic lens. The output signal is then electrically thresholded fed back to the system input by 2-D CCD camera. From the good experimental results, the proposed system can be applied to pattern recognition and machine vision in future.

• IMMUNE NETWORK
• /
• 제23권1호
• /
• pp.11.1-11.11
• /
• 2023

Memory T cells that mediate fast and effective protection against reinfections are usually generated upon recognition on foreign Ags. However, a "memory-like" T-cell population, termed virtual memory T (T_VM) cells that acquire a memory phenotype in the absence of foreign Ag, has been reported. Although, like innate cells, T_VM cells reportedly play a role in first-line defense to bacterial or viral infections, their protective or pathological roles in immune-related diseases are largely unknown. In this review, we discuss the current understanding of T_VM cells, focusing on their distinct characteristics, immunological properties, and roles in various immune-related diseases, such as infections and cancers.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권3호
• /
• pp.215-220
• /
• 2002

This paper proposes a method to apply the Backpropagation(BP) algorithm of MVL(Multi-Valued Logic) Neural Network to pattern recognition. It extracts the property of an object density about an original pattern necessary for pattern processing and makes the property of the object density mapped to MVL. In addition, because it team the pattern by using multiple valued logic, it can reduce time f3r pattern and space fer memory to a minimum. There is, however, a demerit that existed MVL cannot adapt the change of circumstance. Through changing input into MVL function, not direct input of an existed Multiple pattern, and making it each variable loam by neural network after calculating each variable into liter function. Error has been reduced and convergence speed has become fast.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.127-136
• /
• 2021

Real-time human recognition is a challenging task, as the images are captured in an unconstrained environment with different poses, makeups, and styles. This limitation is addressed by generating several facial images with poses, makeup, and styles with a single reference image of a person using Generative Adversarial Networks (GAN). In this paper, we propose deep learning-based human recognition using integration of GAN and Spatial Domain Techniques. A novel concept of human recognition based on face depiction approach by generating several dissimilar face images from single reference face image using Domain Transfer Generative Adversarial Networks (DT-GAN) combined with feature extraction techniques such as Local Binary Pattern (LBP) and Histogram is deliberated. The Euclidean Distance (ED) is used in the matching section for comparison of features to test the performance of the method. A database of millions of people with a single reference face image per person, instead of multiple reference face images, is created and saved on the centralized server, which helps to reduce memory load on the centralized server. It is noticed that the recognition accuracy is 100% for smaller size datasets and a little less accuracy for larger size datasets and also, results are compared with present methods to show the superiority of proposed method.

• 한국통신학회논문지
• /
• 제15권8호
• /
• pp.667-677
• /
• 1990

본 논문에서는 2차원 Hopfield 신경회로망 모델에 근거한 새로운 광 연산 메모리 시스템을 구현하였다. 2차원 영상의 실시간 처리를 위하여 입력 공간광변조기와 메모리 마스크는 상용 LCTV를 사용하고 특히, 4차원 메모리 행렬은 2차원 부행렬 마스크의 2차원적 배열로 구성하였으며 임의의 이력 패턴과 메모리 행렬간의 내적 계산은 multifocus hololens를 사용하여 처리하였다. 출력 영상은 전자적으로 thresholding 된 후 2차원 CCD 카메라를 사용하여 다시 연상 메모리 시스템의 입력으로 궤환되도록 루프를 구성하였다. 본 시스템의 연상 기억 및 오류 정정 능력에 대한 실험결과를 통해 본 논문에서 제시된 새로운 2차원 신경회로망 모델의 광학적 구현 시스템은 앞으로 패턴 인식, machine vision 등과 같은 분야에 실질적 응용이 가능하다.

• 한국정밀공학회지
• /
• 제10권1호
• /
• pp.77-88
• /
• 1993

In this paper, we propose a stereo vision system to solve correspondence problem with large disparity and sudden change in environment which result from small distance between camera and working objects. First of all, a specific feature is divided by predfined elementary feature. And then these are combined to obtain coded data for solving correspondence problem. We use Neural Network to extract elementary features from specific feature and to have adaptability to noise and some change of the shape. Fourier transformation and Log-polar mapping are used for obtaining appropriate Neural Network input data which has a shift, scale, and rotation invariability. Finally, we use associative memory to obtain coded data of the specific feature from the combination of elementary features. In spite of specific feature with some variation in shapes, we could obtain satisfactory 3-dimensional data from corresponded codes.