• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.868-870
• /
• 2005

스크래치는 오래된 필름에서 가장 많이 나타나는 손상 요인이다. 고화질의 멀티미디어 서비스를 제공하기 위해서는 이러한 스크래치들은 반드시 검출 및 복원되어야 한다. 이러한 중요성 때문에 지금까지 많은 복원 알고리즘이 개발되어 왔으나, 스크래치 영역의 자동검출에 대한 연구는 거의 이루어지지 않은 실정이다. 따라서 본 논문에서는 자동으로 스크래치영역을 추출할 수 있는 신경망 기반의 검출 방법을 제안한다. 다층 퍼셉트론 (Multi-layer perceptron: MLP)을 이용하여 스크래치영역과 비 스크래치영역을 구분하는데, 이 MLP는 다양한 크기의 스크래치를 검출하기 위해 다양한 크기의 입력 영상에 대해 적용된다. 제안된 방법의 평가를 위해 principal/ secondary 스크래치, alone/not-alone 스크래치, moving/static 스크래치등의 다양한 종류의 스크래치를 가진 영상에 대해 실험이 이루어졌고, 그 결과 제안된 방법의 강건함과 효율성을 입증되었다.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2755-2757
• /
• 2002

In this paper, we propose a now architecture for hardware implementation of digital neural network. By adopting flexible ladder-style bus and internal connection network into traditional SIMD-type digital neural network architecture, the proposed architecture enables fast processing that is based on parallelism, while does not abandon the flexibility and extensibility of the traditional approach. In the proposed architecture, users can change the network topology by setting configuration registers. Such reconfigurability on hardware allows enough usability like software simulation. We implement the proposed design on real FPGA, and configure the chip to multi-layer perceptron with back propagation for alphabet recognition problem. Performance comparison with its software counterpart shows its value in the aspect of performance and flexibility.

• Journal of the Korea Society of Computer and Information
• /
• v.1 no.1
• /
• pp.83-94
• /
• 1996

The test statistic in ANOVA tests has a single or doubly noncentral F distribution and the noncentral F distribution is applied to the calculation of the power functions of tests of general linear hypotheses. In this paper. the evaluation of the cumulative function of the single noncentral F distribution is applied to the neural network theory. The neural network consists of the multi-layer perceptron structure and learning process has the algorithm of the backpropagation. Numerical comparisons are made between the results obtained by neural network theory and the Patnaik's values.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.631-633
• /
• 2005

유비쿼터스 시대가 다가오면서, 많은 사람들은 모르는 장소에서 자신의 위치와 목적지까지의 경로에 대한 정보를 알고 싶어할 것이다. 기존의 네비게이션(navigation)을 위한 비전기술은 고차원과 저차원 특징값을 이용하였다. 텍스춰 정보, 색상 히스토그램과 같은 저차원 특징값은 영상의 특징을 정확하게 표현하기 어려우며, 마커와 같은 고차원 정보는 실험환경을 구축하는데 어려움이 있다. 우리는 기존 저/고차원의 특징값 대신, 영상의 특징을 표현하고 인덱싱(indexing)하기 위한 유용한 정보를 많이 포함하고 있으며, 실제환경에서 널리 분포되어있는 중차원 특징값인 문자영상을 이용한다. 문자영상추출은 MLP(Multi-layer perceptron)와 CAMShift알고리즘을 결합한 방법을 이용하며, 서로 다른 장소지만 같은 문자를 가진 곳에서 인식을 수행하기 위해 문자영상의 크기와 기울기를 기반으로 한 영상 검색공간을 대상으로 영상매칭을 수행한다. 실험에서 문자영상을 포함하는 직사각형 검색공간으로 인해 다양한 크기와 기울기에서 높은 인식률을 보이며, 간단한 계산으로 빠른 수행시간을 가진다.

• ETRI Journal
• /
• v.40 no.5
• /
• pp.643-652
• /
• 2018

Dysarthria is a degenerative disorder of the central nervous system that affects the control of articulation and pitch; therefore, it affects the uniqueness of sound produced by the speaker. Hence, dysarthric speaker recognition is a challenging task. In this paper, a feature-extraction method based on deep belief networks is presented for the task of identifying a speaker suffering from dysarthria. The effectiveness of the proposed method is demonstrated and compared with well-known Mel-frequency cepstral coefficient features. For classification purposes, the use of a multi-layer perceptron neural network is proposed with two structures. Our evaluations using the universal access speech database produced promising results and outperformed other baseline methods. In addition, speaker identification under both text-dependent and text-independent conditions are explored. The highest accuracy achieved using the proposed system is 97.3%.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2000.11a
• /
• pp.36-44
• /
• 2000

The purpose of this study is to introduce a more efficient forecasting technique, which could help result the reduction of cost in removing the waste of airline in-flight meals. We will use a neural network approach known to many researchers as the “Outstanding Forecasting Technique”. We employed a multi-layer perceptron neural network using a backpropagation algorithm. We also suggested using other related information to improve the forecasting performances of neural networks. We divided the data into three sets, which are training data set, cross validation data set, and test data set. Time lag variables are still employed in our model according to the general view of time series forecasting. We measured the accuracy of our model by “Mean Square Error”(MSE). The suggested model proved most excellent in serving economy class in-flight meals. Forecasting the exact amount of meals needed for each airline could reduce the waste of meals and therefore, lead to the reduction of cost. Better yet, it could enhance the cost competition of each airline, keep the schedules on time, and lead to better service.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.261-262
• /
• 2006

According to the previous work, various well known methods including maximum a posteriori probability classifier (MAP) and multi layer perceptron networks classifier (MLP) showed competitive results. Since even the small errors often leads to a fatal result, we investigated the method that reduces classification error perfectly by screening out some ambiguous patterns. Those ambiguous patterns can be examined by routine biopsy. We incorporated an ambiguous category in MAP and MLP. Classification results involving 216 spectra gave 100% sensitivity for the case of MLP.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.255-256
• /
• 2006

Raman spectroscopy has strong potential for providing noninvasive dermatological diagnosis of skin cancer. In this study, we investigated two classification methods with maximum a posteriori (MAP) probability and multi-layer perceptron (MLP) classification. The classification framework consists of preprocessing of Raman spectra, feature extraction, and classification. In the preprocessing step, a simple windowing method is proposed to obtain robust features. Classification results with MLP involving 216 spectra preprocessed with the proposed method gave 97.3% sensitivity, which is very promising results for automatic Basal Cell Carcinoma (BCC) detection.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.114-117
• /
• 2000

In this paper, Fuzzy Self-organizing Neural Networks(FSONN) based on Fuzzy Neural Networks(FNN) is proposed to overcome some problems, such as the conflict between ovefitting and good generation, and low reliability. The proposed FSONN consists of FNN and SONN. Here, FNN is used as the premise part of FSONN and SONN is the consequnt part of FSONN. The FUN plays the preceding role of FSONN. For the fuzzy reasoning and learning method in FNN, Simplified fuzzy reasoning and backpropagation learning rule are utilized. The number of layers and the number of nodes in each layers of SONN that is based on the GMDH method are not predetermined, unlike in the case of the popular multi layer perceptron structure and can be generated. Also the partial descriptions of nodes can use various forms such as linear, modified quadratic, cubic, high-order polynomial and so on. In this paper, the optimal design procedure of the proposed FSONN is shown in each step and performance index related to approximation and generalization capabilities of model is evaluated and also discussed.

• 한국HCI학회:학술대회논문집
• /
• 2007.02c
• /
• pp.322-325
• /
• 2007

Graphics processing unit (GPU) is used for a faster artificial neural network. It is used to implement the matrix multiplication of a neural network to enhance the time performance of a text detection system. Preliminary results produced a 20-fold performance enhancement using an ATI RADEON 9700 PRO board. The parallelism of a GPU is fully utilized by accumulating a lot of input feature vectors and weight vectors, then converting the many inner-product operations into one matrix operation. Further research areas include benchmarking the performance with various hardware and GPU-aware learning algorithms. (c) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.