• Structural Engineering and Mechanics
• /
• 제12권5호
• /
• pp.527-540
• /
• 2001

A new sort of learning algorithm named whole learning algorithm is proposed to simulate the nonlinear and dynamic behavior of RC members for the estimation of structural integrity. A mathematical technique to solve the multi-objective optimization problem is applied for the learning of the feedforward neural network, which is formulated so as to minimize the Euclidean norm of the error vector defined as the difference between the outputs and the target values for all the learning data sets. The change of the outputs is approximated in the first-order with respect to the amount of weight modification of the network. The governing equation for weight modification to make the error vector null is constituted with the consideration of the approximated outputs for all the learning data sets. The solution is neatly determined by means of the Moore-Penrose generalized inverse after summarization of the governing equation into the linear simultaneous equations with a rectangular matrix of coefficients. The learning efficiency of the proposed algorithm from the viewpoint of computational cost is verified in three types of problems to learn the truth table for exclusive or, the stress-strain relationship described by the Ramberg-Osgood model and the nonlinear and dynamic behavior of RC members observed under an earthquake.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권7호
• /
• pp.3333-3350
• /
• 2019

The smart jammer launches jamming attacks which degrade the transmission reliability. In this paper, smart jamming attacks based on the communication probability over different channels is considered, and an anti-jamming Q learning algorithm (AQLA) is developed to obtain anti-jamming knowledge for the local region. To accelerate the learning process across multiple regions, a multi-regional intelligent anti-jamming learning algorithm (MIALA) which utilizes transferred knowledge from neighboring regions is proposed. The MIALA algorithm is evaluated through simulations, and the results show that the it is capable of learning the jamming rules and effectively speed up the learning rate of the whole communication region when the jamming rules are similar in the neighboring regions.

• Korean Journal of Radiology
• /
• 제21권7호
• /
• pp.891-899
• /
• 2020

Objective: To assess the diagnostic performance of a deep learning-based algorithm for automated detection of acute and chronic rib fractures on whole-body trauma CT. Materials and Methods: We retrospectively identified all whole-body trauma CT scans referred from the emergency department of our hospital from January to December 2018 (n = 511). Scans were categorized as positive (n = 159) or negative (n = 352) for rib fractures according to the clinically approved written CT reports, which served as the index test. The bone kernel series (1.5-mm slice thickness) served as an input for a detection prototype algorithm trained to detect both acute and chronic rib fractures based on a deep convolutional neural network. It had previously been trained on an independent sample from eight other institutions (n = 11455). Results: All CTs except one were successfully processed (510/511). The algorithm achieved a sensitivity of 87.4% and specificity of 91.5% on a per-examination level [per CT scan: rib fracture(s): yes/no]. There were 0.16 false-positives per examination (= 81/510). On a per-finding level, there were 587 true-positive findings (sensitivity: 65.7%) and 307 false-negatives. Furthermore, 97 true rib fractures were detected that were not mentioned in the written CT reports. A major factor associated with correct detection was displacement. Conclusion: We found good performance of a deep learning-based prototype algorithm detecting rib fractures on trauma CT on a per-examination level at a low rate of false-positives per case. A potential area for clinical application is its use as a screening tool to avoid false-negative radiology reports.

• 한국경영과학회지
• /
• 제31권2호
• /
• pp.69-85
• /
• 2006

Transductive Support Vector Machine(TSVM) is one of semi-supervised learning algorithms which exploit the domain structure of the whole data by considering labeled and unlabeled data together. Although it was proposed several years ago, there has been no efficient algorithm which can handle problems with more than hundreds of training examples. In this paper, we propose an efficient branch-and-bound algorithm which can solve large-scale TSVM problems with thousands of training examples. The proposed algorithm uses two bounding techniques: min-cut bound and reduced SVM bound. The min-cut bound is derived from a capacitated graph whose cuts represent a lower bound to the optimal objective function value of the dual problem. The reduced SVM bound is obtained by constructing the SVM problem with only labeled data. Experimental results show that the accuracy rate of TSVM can be significantly improved by learning from the optimal solution of TSVM, rather than an approximated solution.

• 한국정보통신학회논문지
• /
• 제25권11호
• /
• pp.1486-1494
• /
• 2021

문자 인식은 스마트 주차, text to speech 등 최근 다양한 플랫폼에서 필요로 하는 기술로써, 기존의 방법과 달리 새로운 시도를 통하여 그 성능을 향상시키려는 연구들이 진행되고 있다. 그러나 문자 인식에 사용되는 이미지의 품질이 낮을 경우, 문자 인식기 학습용 이미지와 테스트 이미지간에 해상도 차이가 발생하여 정확도가 떨어지는 문제가 발생된다. 이를 해결하기 위해 본 논문은 문자 인식 모델 성능이 다양한 품질 데이터에 대하여 강인하도록 이미지 초해상도 및 문자 인식을 결합한 통째학습 신경망을 설계하고, 대안적 통째학습 알고리즘을 구현하여 통째 신경망 학습을 수행하였다. 다양한 문자 이미지 중 차량 번호판 이미지를 이용하여 대안적 통째학습 및 인식 성능 테스트를 진행하였고, 이를 통해 제안하는 알고리즘의 효과를 검증하였다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.65-70
• /
• 2001

We consider a hyper-redundant system that consists of many uniform units. The hyper-redundant system has many degrees of freedom and it can accomplish various tasks. Applysing the reinforcement learning to the hyper-redundant system is very attractive because it is possible to acquire various behaviors for various tasks automatically. In this paper we present a new reinforcement learning algorithm "Q-learning with propagation of motion". The algorithm is designed for the multi-agent systems that have strong connections. The proposed algorithm needs only one small Q-table even for a large scale system. So using the proposed algorithm, it is possible for the hyper-redundant system to learn the effective behavior. In this algorithm, only one leader agent learns the own behavior using its local information and the motion of the leader is propagated to another agents with time delay. The reward of the leader agent is given by using the whole system information. And the effective behavior of the leader is learned and the effective behavior of the system is acquired. We apply the proposed algorithm to a snake-like hyper-redundant robot. The necessary condition of the system to be Markov decision process is discussed. And the computer simulation of learning the locomotion is demonstrated. From the simulation results we find that the task of the locomotion of the robot to the desired point is learned and the winding motion is acquired. We can conclude that our proposed system and our analysis of the condition, that the system is Markov decision process, is valid.

• 전자공학회논문지B
• /
• 제31B권7호
• /
• pp.170-178
• /
• 1994

The nearest neighbor classification rule is widely used because it is not only simple but the error rate is asymptotically less than twice Bayes theoretical minimum error. But the method basically use the whole training patterns as the reference vectors. so that both storage and classification time increase as the number of training patterns increases. LVQ(Learning Vector Quantization) resolved this problem by training the reference vectors instead of just storing the whole training patterns. But it is a heuristic algorithm which has no theoretic background there is no terminating condition and it requires a lot of iterations to get to meaningful result. This paper is to propose a new training method of the reference vectors. which minimize the given error function. The nearest neighbor network,the network version of the nearest neighbor classification rule is proposed. The network is funtionally identical to the nearest neighbor classification rule is proposed. The network is funtionally identical to the nearest neighbor classification rule and the reference vectors are represented by the weights between the nodes. The network is trained to minimize the error function with respect to the weights by the steepest descent method. The learning algorithm is derived and it is shown that the proposed method can adjust more reference vectors than LVQ in each iteration. Experiment showed that the proposed method requires less iterations and the error rate is smaller than that of LVQ2.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제51권2호
• /
• pp.69-77
• /
• 2002

Speaker verification can be classified in two categories, text-dependent speaker verification and text-independent speaker verification. In this paper, we discuss text-dependent speaker verification. Text-dependent speaker verification system determines whether the sound characteristics of the speaker are equal to those of the specific person or not. In this paper we obtain the speaker data using a sound card in various noisy conditions, apply a new Hidden LMS (Least Mean Square) adaptive algorithm to it, and extract LPC (Linear Predictive Coding)-cepstrum coefficients as feature vectors. Finally, we use a competitive learning neural network for speaker verification. The proposed hidden LMS adaptive filter using a neural network reduces noise and enhances features in various noisy conditions. We construct a separate neural network for each speaker, which makes it unnecessary to train the whole network for a new added speaker and makes the system expansion easy. We experimentally prove that the proposed method improves the speaker verification performance.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.203-211
• /
• 2022

Multi-objective optimization problems (MOPs) arise in many real-world applications. MOPs involve two or more objectives with the aim to be optimized. With these problems improvement of one objective may led to deterioration of another. The primary goal of most multi-objective evolutionary algorithms (MOEA) is to generate a set of solutions for approximating the whole or part of the Pareto optimal front, which could provide decision makers a good insight to the problem. Over the last decades or so, several different and remarkable multi-objective evolutionary algorithms, have been developed with successful applications. However, MOEAs are still in their infancy. The objective of this research is to study how to use and apply machine learning (ML) to improve evolutionary multi-objective optimization (EMO). The EMO method is the multi-objective evolutionary algorithm based on decomposition (MOEA/D). The MOEA/D has become one of the most widely used algorithmic frameworks in the area of multi-objective evolutionary computation and won has won an international algorithm contest.

• 로봇학회논문지
• /
• 제14권2호
• /
• pp.122-130
• /
• 2019

Collecting a rich but meaningful training data plays a key role in machine learning and deep learning researches for a self-driving vehicle. This paper introduces a detailed overview of existing open-source simulators which could be used for training self-driving vehicles. After reviewing the simulators, we propose a new effective approach to make a synthetic autonomous vehicle simulation platform suitable for learning and training artificial intelligence algorithms. Specially, we develop a synthetic simulator with various realistic situations and weather conditions which make the autonomous shuttle to learn more realistic situations and handle some unexpected events. The virtual environment is the mimics of the activity of a genuine shuttle vehicle on a physical world. Instead of doing the whole experiment of training in the real physical world, scenarios in 3D virtual worlds are made to calculate the parameters and training the model. From the simulator, the user can obtain data for the various situation and utilize it for the training purpose. Flexible options are available to choose sensors, monitor the output and implement any autonomous driving algorithm. Finally, we verify the effectiveness of the developed simulator by implementing an end-to-end CNN algorithm for training a self-driving shuttle.