• The Journal of the Acoustical Society of Korea
• /
• v.21 no.5
• /
• pp.430-437
• /
• 2002

Having a variety of good characteristics against other pattern recognition techniques, the multilayer perceptron (MLP) has been widely used in speech recognition and speaker recognition. But, it is known that the error backpropagation (EBP) algorithm that MLP uses in learning has the defect that requires restricts long learning time, and it restricts severely the applications like speaker recognition and speaker adaptation requiring real time processing. Because the learning data for pattern recognition contain high redundancy, in order to increase the learning speed it is very effective to use the online-based learning methods, which update the weight vector of the MLP by the pattern. A typical online EBP algorithm applies the fixed learning rate for each update of the weight vector. Though a large amount of speedup with the online EBP can be obtained by choosing the appropriate fixed rate, firing the rate leads to the problem that the algorithm cannot respond effectively to different learning phases as the phases change and the number of patterns contributing to learning decreases. To solve this problem, this paper proposes a Changing rate and Omitting patterns in Instant Learning (COIL) method to apply the variable rate and the only patterns necessary to the learning phase when the phases come to change. In this paper, experimentations are conducted for speaker verification and speech recognition, and results are presented to verify the performance of the COIL.

• Journal of Korea Multimedia Society
• /
• v.21 no.7
• /
• pp.779-786
• /
• 2018

In this paper, we are applied a nerve network to allow for the reflection of data learning methods in their overall forms by using cluster data rather than data learning by the stages and then selected a nerve network model and analyzed its variables through learning by the cluster. The CkLR algorithm was proposed to analyze the reaction variables of clustering outcomes through an approach to the initialization of K-means clustering and build a model to assess the prediction rate of clustering and the accuracy rate of prediction in case of new data inputs. The performance evaluation results show that the accuracy rate of test data by the class was over 92%, which was the mean accuracy rate of the entire test data, thus confirming the advantages of a specialized structure found in the proposed learning nerve network by the class.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.4
• /
• pp.363-372
• /
• 1997

In this paper, the design and the implementation of the adaptive learning rate neural network controller for an articulate robot, which is being developed (or) has been developed in our Automatic Control Laboratory, are mainly discussed. The controller reduces software computational load via distributed processing method using multiple CPU's, and simplifies hardware structures by the time-division control with TMS32OC31 DSP chip. Proposed neural network controller with adaptive learning rate structure using expert's heuristics can improve learning speed. The proposed controller verifies its superiority by comparing response characteristics of conventional controller with those of the proposed controller that are obtained from the experiments for the 5 axis vertical articulated robot. We, also, present the generalization property of proposed controller for unlearned trajectory and the change of load through experimental data.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.550-554
• /
• 1992

In this paper the issue of convergence rate is introduced for a learning control scheme we have developed and applied for tracking of unknown linear systems. A sufficient condition under which the output trajectory converges exponentially fast is obtained using the controllability grammian of controllable linear systems. Under the same condition it is also shown that the learning control input converges exponentially with the same rate as the rate of output convergence. A numerical example with computer simulation results is presented to show the feasibility of the scheme.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.401-403
• /
• 2021

본 연구는 한국지능정보사회진흥원에서 제공한 2018년 스마트폰 과의존 실태조사에서 사용된 11개 변수와 스마트폰 과의존과의 관계를 탐색하고, 이를 통해 딥러닝 기반 스마트폰 과의존 분류 분석 모델을 개발하고자 시행되었다. 학습데이터셋은 전국 10,000개 가구내 만 3-69세 스마트폰 이용자 25,465명의 스마트폰 이용 형태 및 개인적 특성에 관한 데이터이다. 딥러닝은 심층신경망(DNN)을 설계하였으며, 은닉층(hidden layer)은 4개층으로 구성하였다. 입력한 데이터는 각각 200개, 150개, 100개, 50개, 2개 노드를 거치면서 최종 출력 정보인 스마트폰 과의존 분류율로 나타나는 모델이다. 이때 스마트폰 과의존 분류률을 높이기 위해 학습률(learning rate)과 같은 하이퍼 파라미터를 활용하여 세부조정하면서 가장 잘 학습하는 값을 찾아내었다. 연구결과, 학습횟수가 300번으로 학습율(learning.rate)이 0.01일때 훈련데이터에서 97.43%, 검증데이터에서 98.06%로 가장 높게 나타났다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.4
• /
• pp.309-314
• /
• 2007

This paper presents an adaptive neural computation algorithm for multi-layered neural networks which are applied to identify the characteristic function of dynamic systems. The main feature of the proposed algorithm is that the initial learning rate for the employed neural network is assigned systematically, and also the assigned learning rate can be adjusted empirically for effective neural leaning. By employing the approach, enhanced modeling of dynamic systems is possible. The effectiveness of this approach is veri tied by simulations.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.37-44
• /
• 2020

AI technology has developed in the form of decision support technology in law, patent, finance and national defense and is applied to disease diagnosis and legal judgment. To search real-time information with Deep Learning, Big data Analysis and Deep Learning Algorithm are required. In this paper, we try to predict the entrance rate to high-ranking universities using a Deep Learning model, RNN(Recurrent Neural Network). First, we analyzed the current status of private academies in administrative districts and the number of students by age in administrative districts, and established a socially accepted hypothesis that students residing in areas with a high educational fever have a high rate of enrollment in high-ranking universities. This is to verify based on the data analyzed using the predicted hypothesis and the government's public data. The predictive model uses data from 2015 to 2017 to learn to predict the top enrollment rate, and the trained model predicts the top enrollment rate in 2018. A prediction experiment was performed using RNN, a Deep Learning model, for the high-ranking enrollment rate in the special education zone. In this paper, we define the correlation between the high-ranking enrollment rate by analyzing the household income and the participation rate of private education about the current status of private institutes in regions with high education fever and the effect on the number of students by age.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• pp.503-511
• /
• 1995

A batch-mode algorithm is proposed to increase the speed of learning in the error backpropagation algorithm with variable learning rate and variable momentum parameters in classification problems. The objective function is normalized with respect to the number of patterns and output nodes. Also the gradient of the objective function is normalized in updating the connection weights to increase the effect of its backpropagated error. The learning rate and momentum parameters are determined from a function of the gradient norm and the number of weights. The learning rate depends on the square rott of the gradient norm while the momentum parameters depend on the gradient norm. In the two typical classification problems, simulation results demonstrate the effectiveness of the proposed algorithm.

• Journal of Sensor Science and Technology
• /
• v.33 no.3
• /
• pp.119-124
• /
• 2024

Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensing method for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step, fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256 values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with different parameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increased the recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. This is a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In our experiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.

• Journal of information and communication convergence engineering
• /
• v.19 no.1
• /
• pp.1-7
• /
• 2021

Reinforcement learning is an area of machine learning that studies how an intelligent agent takes actions in a given environment to maximize the cumulative reward. In this paper, we propose a new MAC protocol based on the Q-learning technique of reinforcement learning to improve the performance of the IEEE 802.11 wireless LAN CSMA/CA MAC protocol. Furthermore, the operation of each access point (AP) and station is proposed. The AP adjusts the value of the contention window (CW), which is the range for determining the backoff number of the station, according to the wireless traffic load. The station improves the performance by selecting an optimal backoff number with the lowest packet collision rate and the highest transmission success rate through Q-learning within the CW value transmitted from the AP. The result of the performance evaluation through computer simulations showed that the proposed scheme has a higher throughput than that of the existing CSMA/CA scheme.