• 한국음향학회지
• /
• 제15권6호
• /
• pp.5-11
• /
• 1996

본 논문은 불특정 화자의 단모음 인식에 관한 연구로써, fuzzy개념를 이용한 VQ(Vector Quantization)/NN(Neural Network)에 의한 음성 인식 방법을 제안한다. 이 방법은 fuzzy를 이용하여 VQ codebook에 의해 다중 관측열(multi-observation sequence)을 구해 각 symbol이 데이타로부터 가질 수 있는 확률값을 계산하여 이 값을 신경 회로망의 입력으로 사용하는 방법이다. 인식 대상어로는 한국어 단모음을 선정하였으며 10명의 남성 화자가 8개의 단모음을 10번씩 발음한 음성 데이터베이스를 이용하여 fuzzy를 이용하지 않은 VQ/NN과 fuzzy를 이용한 VQ/HMM(hidden Markov model)에 의한 인식률과 비교 실험한다. 실험 결과에 의하며, VQ/NN에 의한 인식률은 92.3%이며, fuzzy를 이용한 VQ/HMM에 의한 인식률은 93.8%이고, fuzzy를 이용한 VQ/Nn에 의한 인식률은 95.7%이다. 그러므로, 본 연구의 fuzzy를 이용한 VQ/NN이 학습 능력이 뛰어난 관계로 fuzzy를 이용한 VQ/HMM과 일반적인 VQ/NN 보다 인식률이 향상됨을 보여준다.

• 한국통신학회논문지
• /
• 제17권11호
• /
• pp.1199-1205
• /
• 1992

본 논문에서는 HMM(Hidden Markov Models)에서 문제점이 되는 개인차에의한 변동을 흡수하고, 적은 학습 데이타로서 인식률을 향상시키기 위하여 신경회로망을 이용한 NN-HMM(Neural Network Hidden Makov Models)에 의해 한국어 인식에 관하여 연구하였다. 이 방법은 HMM과 신경회로망의 출력을 각각 독립적인 인식값으로 가정하여 두 시스템의 확률곱으로 서로 보정되어 최대 인식확률의 음성모델을 인식하는 음성인식 시스템이다. 본 방법의 타당성을 평가하기 위하여 남, 여화자가 28개의 DDD 지역명을 발성한 음성데이타로 실험한 결과, 이산분포 HMM에 의한 방법에서는 91[%], 신경회로망에 의한 방법에서는 89[%], 제안된 방법에서는 95[%]의 향상된 인식률을 얻으므로써 인식성능의 우수함을 확인하였다.

• 대한토목학회논문집
• /
• 제29권3C호
• /
• pp.115-125
• /
• 2009

지반의 응력이력을 정의하는데 이용되는 선행압밀하중은 일반적으로 일차원 실내압밀실험으로부터 결정되어져 왔으나 피에조콘과 같은 원위치 시험의 관측값을 이용한 이론적인 방법과 경험적인 상관관계를 통한 결정도 가능하다. 최근 선행압밀하중을 결정하기 위한 인공신경망 모델들이 제안된 바 있으며, 기존의 이론적 경험적 선행압밀하중 추정 방법들이 갖는 지역의존성의 문제를 극복하고 예측 정확도 면에서도 크게 개선된 것으로 보고되었다. 그러나 인공신경망 모델은 모델구조와 학습과정에서 초기에 무작위로 부여되는 연결강도에 영향을 받아 예측에 변동성이 존재한다. 본 연구에서는 기존의 피에조콘 결과를 이용한 선행압밀하중 추정 인공신경망 모델이 연약지반에서 선행압밀하중 예측 시 보이는 변동성을 개선하기 위하여 신경망 모델의 구조 최적화를 수행하고 군집신경망 모델을 구축하였다. 제안된 군집신경망 모델을 이용한 예측결과는 기존의 다층신경망 모델 및 이론적 경험적 모델들과 비교되었다. 연구결과, 최적화된 구조를 갖는 다층신경망 모델일지라도 초기 연결강도에 따라 최종 학습 후 예측결과의 변동성이 여전히 존재하나, 다층신경망을 네트워크로 연결하여 제안된 군집신경망 모델은 기존의 다층신경망 모델들이 갖는 초기 연결강도 의존성을 개선하여 다층신경망 모델에 비해 일관성 있으며 보다 정확한 예측이 가능한 것으로 나타났다.

• 방송공학회논문지
• /
• 제27권7호
• /
• pp.1021-1033
• /
• 2022

After the Versatile Video Coding (VVC)/H.266 standard was completed, the Joint Video Exploration Team (JVET) began to investigate new technologies that could significantly increase coding gain for the next generation video coding standard. One direction is to investigate signal processing based tools, while the other is to investigate Neural Network based technology. Neural Network based Video Coding (NNVC) has not been studied previously, and this is the first trial of such an approach in the standard group. After two years of research, JVET produced the first common software called Neural Compression Software (NCS) with two NN-based in-loop filtering tools at the 27th meeting and began to maintain NN-based technologies for the common experiment. The coding performances of the two filters in NCS-1.0 are shown to be 8.71% and 9.44% on average in a random access scenario, respectively. All the material related to NCS can be found in the repository of the JVET. In this paper, we provide a brief overview and review of the NNVC activity studied in JVET in order to provide trend and insight for the new direction of video coding standard.

• 한국생물공학회:학술대회논문집
• /
• 한국생물공학회 2000년도 춘계학술발표대회
• /
• pp.173-176
• /
• 2000

A neural network based controller (NN controller) was studied for the control of ammonia concentrations in biological processes. An ammonia FIA has been employed to on-line monitor the concentrations of ammonia in a bioreactor. The optimal neural network structure was investigated by computer simulation and found to be a 3(inputlayer)-2(hidden layer)-1(output layer). The NN controller had advantage over the PID controller, even though the former is more time consuming. The 3-2-1 NN controller has been used to control the ammonia concentrations in a simulated bioprocess and also in a real cultivation process of yeast, and its performance were investigated.

• 한국항해항만학회지
• /
• 제31권4호
• /
• pp.289-293
• /
• 2007

In this paper, new application of adaptive neural network to design a ship's Rudder-Roll Damping(RRD) control system is presented Firstly, the ANNAI neural network controller is presented. Secondly, new RRD control system using this neural network approach is developed. It uses two neural network controllers for heading control and roll damping control separately. Finally, Computer simulation of this RRD control system is carried out to compare with a linear quadratic optimal RRD control system; discussions and conclusions are provided. The simulation results show the feasibility of using ANNAI controller for RRD. Also, the necessity of mathematical ship model in designing RRD control system is removed by using NN control technique.

• 산업공학
• /
• 제24권2호
• /
• pp.97-104
• /
• 2011

Research for multi-variate classification has been studied through two kinds of procedures which are feature selection and classification. Feature Selection techniques have been applied to select important features and the other one has improved classification performances through classifier applications. In general, each technique has been independently studied, however consideration of the interaction between both procedures has not been widely explored which leads to a degraded performance. In this paper, through integrating these two procedures, classification performance can be improved. The proposed model takes advantage of KBANN (Knowledge-Based Artificial Neural Network) which uses prior knowledge to learn NN (Neural Network) as training information. Each NN learns characteristics of the Feature Selection and Classification techniques as training sets. The integrated NN can be learned again to modify features appropriately and enhance classification performance. This innovative technique is called ALBNN (Algorithm Learning-Based Neural Network). The experiments' results show improved performance in various classification problems.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.993-996
• /
• 1993

This paper addresses the structure and its associated learning algorithms of a feedforward multi-layered connectionist network, which has distributed learning abilities, for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed neural-network-based fuzzy logic control system (NN-FLCS) can be contrasted with the traditional fuzzy logic control system in their network structure and learning ability. An on-line supervised structure/parameter learning algorithm dynamic learning algorithm can find proper fuzzy logic rules, membership functions, and the size of output fuzzy partitions simultaneously. Next, a Reinforcement Neural-Network-Based Fuzzy Logic Control System (RNN-FLCS) is proposed which consists of two closely integrated Neural-Network-Based Fuzzy Logic Controllers (NN-FLCS) for solving various reinforcement learning problems in fuzzy logic systems. One NN-FLC functions as a fuzzy predictor and the other as a fuzzy controller. As ociated with the proposed RNN-FLCS is the reinforcement structure/parameter learning algorithm which dynamically determines the proper network size, connections, and parameters of the RNN-FLCS through an external reinforcement signal. Furthermore, learning can proceed even in the period without any external reinforcement feedback.

• 한국멀티미디어학회논문지
• /
• 제25권6호
• /
• pp.783-792
• /
• 2022

Versatile Video Coding (VVC) is the latest video coding standard, which had been developed by the Joint Video Experts Team (JVET) of ITU-T Video Coding Experts Group (VCEG) and ISO/IEC Moving Picture Experts Group (MPEG) in 2020. Although VVC can provide powerful coding performance, it requires tremendous computational complexity to determine the optimal block structures during the encoding process. In this paper, we propose a fast ternary tree decision method using two neural networks with 7 nodes as input vector based on the multi-layer perceptron structure, names STH-NN and STV-NN. As a training result of neural network, the STH-NN and STV-NN achieved accuracies of 85% and 91%, respectively. Experimental results show that the proposed method reduces the encoding complexity up to 25% with unnoticeable coding loss compared to the VVC test model (VTM).

• Animal cells and systems
• /
• 제16권2호
• /
• pp.121-126
• /
• 2012

In this study, a neural network (NN) modeling approach has been used to predict the mechanical and geometrical behaviors of mouse embryo cells. Two NN models have been implemented. In the first NN model dimple depth (w), dimple radius (a) and radius of the semi-circular curved surface of the cell (R) were used as inputs of the model while indentation force (f) was considered as output. In the second NN model, indentation force (f), dimple radius (a) and radius of the semi-circular curved surface of the cell (R) were considered as inputs of the model and dimple depth was predicted as the output of the model. In addition, sensitivity analysis has been carried out to investigate the influence of the significance of input parameters on the mechanical behavior of mouse embryos. Experimental data deduced by Fl$\ddot{u}$ckiger (2004) were collected to obtain training and test data for the NN. The results of these investigations show that the correlation values of the test and training data sets are between 0.9988 and 1.0000, and are in good agreement with the experimental observations.