• 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 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.

• Journal of Environmental Science International
• /
• v.11 no.3
• /
• pp.201-207
• /
• 2002

This study was carried out to evaluate the artificial neural network algorithm for water quality forecasting in Chungju lake, north Chungcheong province. Multi-layer perceptron(MLP) was used to train artificial neural networks. MLP was composed of one input layer, two hidden layers and one output layer. Transfer functions of the hidden layer were sigmoid and linear function. The number of node in the hidden layer was decided by trial and error method. It showed that appropriate node number in the hidden layer is 10 for pH training, 15 for DO and BOD, respectively. Reliability index was used to verify for the forecasting power. Considering some outlying data, artificial neural network fitted well between actual water quality data and computed data by artificial neural networks.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.778-780
• /
• 2019

본 논문은 네트워크 트래픽에 대한 동적인 변화에 대응하기위해 기존의 네트워크 트래픽 데이터를 이용하여 기계 학습을 사용하여 학습시킴으로써 이후 네트워크 트래픽 동향에 대해 분류하여 예측하는 연구에 관한 논문으로, 기계 학습의 종류 중 MLP(Multi-Layer Perceptron)를 이용하여 실험하였는데 MLP 의 구조와 학습 반복 횟수에 따른 정확도의 차이와 테스트 데이터 실험 결과를 정리하였다. 또한 이를 통해 얻어진 결과는 어떻게 사용 될 지와 정확도를 높이기 위해서는 어떤 요소가 영향을 끼치는지에 대해 논문의 방식과 비교하여 설명한다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.86-86
• /
• 2016

본 연구는 가뭄 예측에 대한 오차를 알고리즘과 결합하여 다층 퍼셉트론 (Multi-layer Perceptron, MLP) 네트워크 구조를 인공신경망 모형에 적용하고, 표준강수지수(Standard Precipitation Index, SPI)를 입 력 및 출력 변수로 구성하여 가뭄예측을 시도하였다. 예측모델을 평가하기 위해 기상청 산하의 59개 관측소에 대한 1980년부터 2015년까지의 기상자료를 적용하였으며, 수립된 자료를 활용하여 한반도 전역의 가뭄에 대한 시공간적인 분석을 수행하였다. 단기가뭄 예측성능을 평가하기 위해 2000년에서 2015년까지 16년간의 모의결과를 ROC 분석을 통하여 시공간적 단기가뭄 예측성능을 평가하고 혼동행렬(Conversion Matrix) 구성에 대한 조건적 확률의 다각적 검토를 통해 모델 예측에 대한 정확성(Accuracy), 신뢰성(Precision) 등 다양한 예측성능에 대한 평가를 수행하고 2016년 가뭄전망을 제시하고자 한다.

• Annual Conference of KIPS
• /
• 2007.05a
• /
• pp.457-458
• /
• 2007

Clustering plays an indispensable role for data analysis. Many clustering algorithms have been developed. However, most of them suffer poor performance of learning. To archive good clustering performance, we develop a hybrid neural network model. It is the combination of Multi-Layer Perceptron (MLP) and Adaptive Resonance Theory 2 (ART2). It inherits two distinct advantages of stability and plasticity from ART2. Meanwhile, by combining the merits of MLP, it improves the performance for clustering. Experiment results show that our model can be used for clustering with promising performance.

• Journal of Advanced Navigation Technology
• /
• v.5 no.1
• /
• pp.1-10
• /
• 2001

Speech has a good characteristics of which car drivers busy to concern with miscellaneous operation can make use in convenient handling and manipulating of devices. By utilizing this, this works proposes a speaker verification method for protecting cars from being stolen and identifying a person trying to access critical on-line services. In this, continuant phonemes recognition which uses language information of speech and MLP(mult-layer perceptron) which has some advantages against previous stochastic methods are adopted. The recognition method, though, involves huge computation amount for learning, so it is somewhat difficult to adopt this in speaker verification application in which speakers should enroll themselves at real time. To relieve this problem, this works presents a solution that introduces speaker cohort models from speaker verification score normalization technique established before, dividing background speakers into small cohorts in advance. As a result, this enables computation burden to be reduced through classifying the enrolling speaker into one of those cohorts and going through enrollment for only that cohort.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.280-285
• /
• 1991

Neural network control has many innovative potentials for fast, accurate and intelligent adaptive control. In this paper, a learning control architecture for the dynamic control of a robot manipulator is developed using inverse dynamic neurocontroller and linear neurocontroher. The inverse dynamic neurocontrouer consists of a MLP (multi-layer perceptron) and the linear neurocontroller consists of SLPs (single layer perceptron). Compared with the previous type of neurocontroller which is using an inverse dynamic neurocontroller and a fixed PD gain controller, proposed architecture shows the superior performance over the previous type of neurocontroller because linear neurocontroller can adapt its gain according to the applied task. This superior performance is tested and verified through the control of PUMA 560. Without any knowledge on the dynamic model, its parameters of a robot , (The robot is treated as a complete black box), the neurocontroller, through practice, gradually and implicitly learns the robot's dynamic properties which is essential for fast and accurate control.

• Science of Emotion and Sensibility
• /
• v.27 no.1
• /
• pp.59-68
• /
• 2024

This study aimed to develop a soft fabric-based elbow-bending angle sensor that can replace conventional hard-type inertial sensors and a system for estimating bending angles using it. To enhance comfort during exercise, this study treated four fabrics (Bergamo, E-band, span cushion, and polyester) by single-walled carbon nanotube dip coating to create conductive textiles. Subsequently, one fabric was selected based on performance evaluations, and an elbow flexion angle sensor was fabricated. Gauge factor, hysteresis, and sensing range were employed as performance evaluation metrics. The data obtained using the fabricated sensor showed different trends in sensor values for the changes in the angle during bending and extending movements. Because of this divergence, the two movements were separated, and this constituted the one-step process. In the two-step process, multilayer perceptron (MLP) was employed to handle the complex nonlinear relationships and achieve high data accuracy. Based on the results of this study, we anticipate effective utilization in various smart wearable and healthcare domains. Consequently, a soft- fabric bending angle sensor was developed, and using MLP, nonlinear relationships can be addressed, enabling angle estimation. Based on the results of this study, we anticipate the effective utilization of the developed system in smart wearables and healthcare.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.135-144
• /
• 2003

A method for the automatic segmentation of speech signals is described. The method is dedicated to the construction of a large database for a Text-To-Speech (TTS) synthesis system. The main issue of the work involves the refinement of an initial estimation of phone boundaries which are provided by an alignment, based on a Hidden Market Model(HMM). Multi-layer perceptron (MLP) was used as a phone boundary detector. To increase the performance of segmentation, a technique which individually trains an MLP according to phonetic transition is proposed. The optimum partitioning of the entire phonetic transition space is constructed from the standpoint of minimizing the overall deviation from hand labelling positions. With single speaker stimuli, the experimental results showed that more than 95% of all phone boundaries have a boundary deviation from the reference position smaller than 20 ms, and the refinement of the boundaries reduces the root mean square error by about 25%.