• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.187-194
• /
• 1996

In this paper, we propose regression neural networks based on regression trees. We map regression trees into three layered feedforward networks. We put multi feature split functions in the first layer so that the networks have a better chance to get optimal partitions of input space. We suggest two supervised learning algorithms for the network training and test both in single feature split and multifeature split functions. In experiments, the proposed regression neural networks is proved to have the better learning performance than those of the single feature split regression trees and the single feature split regression networks. Furthermore, we shows that the proposed learning schemes have an effect to prune an over-grown tree without degrading the learning performance.

• The KIPS Transactions:PartA
• /
• v.13A no.6 s.103
• /
• pp.555-560
• /
• 2006

In contrast with the earlier remote education that simply recorded off-line classes, modern remote education emphasizes on offering additional functions that could maximize learning efficiency. Usage of such multimedia information as the texts, graphics, sounds, animations is considered fundamental element in offering the additional functions. This paper designs and implements an encoder/decoder that could accommodate the multimedia information with emphasis on demonstrating execution files. Instructors can demonstrate my type of execution files or application data files, and the remote learners can freely try running the corresponding execution files by themselves. Consequently, a high-level of learning efficiency can be achieved by the proposed encoder/decoder.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1380-1390
• /
• 2021

The video face recognition (FR) is one of the most popular researches in the field of computer vision due to a variety of applications. In particular, research using the attention mechanism is being actively conducted. In video face recognition, attention represents where to focus on by using the input value of the whole or a specific region, or which frame to focus on when there are many frames. In this paper, we propose a novel attention based deep learning method. Main novelties of our method are (1) the use of combining two loss functions, namely weighted Softmax loss function and a Triplet loss function and (2) the feasibility of end-to-end learning which includes the feature embedding network and attention weight computation. The feature embedding network has a positive effect on the attention weight computation by using combined loss function and end-to-end learning. To demonstrate the effectiveness of our proposed method, extensive and comparative experiments have been carried out to evaluate our method on IJB-A dataset with their standard evaluation protocols. Our proposed method represented better or comparable recognition rate compared to other state-of-the-art video FR methods.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.170-175
• /
• 1998

Transporting a large table using multiple robotic agents requires at least two group behaviors of homing and herding which are to bo coordinated in a proper sequence. Existing GP methods for multi-agent learning are not practical enough to find an optimal solution in this domain. To evolve this kind of complex cooperative behavior we use a novel method called fitness switching. This method maintains a pool of basis fitness functions each of which corresponds to a primitive group behavior. The basis functions are then progressively combined into more complex fitness functions to co-evolve more complex behavior. The performance of the presented method is compared with that of two conventional methods. Experimental results show that coevolutionary fitness switching provides an effective mechanism for evolving complex emergent behavior which may not be solved by simple genetic programming.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.45-49
• /
• 1997

In this paper, we controlled a Rotary Inverted Pendulum System using Neuro-Fuzzy Controller(NFC). The inverted pendulum system is widely used as a typical example of an unstable nonlinear control system which is difficult to control. Fuzzy theory have been because membership functions and rules of a fuzzy controller are often given by experts or a fuzzy logic control system. This controller is a feedforward multilayered network which integrates the basic elements and functions of a tradtional fuzzy logic controller into a connectionist structure which has distributed learning abilities. Such NFC can be constructed from training examples by learning rule, and the structure can be trained to develop fuzzy logic rules and find optimal input/output membership functions. Using this controller, we presented the results that controlled a Rotary Inverted Pendulum System and the associated algorithms.

• Research in Mathematical Education
• /
• v.16 no.3
• /
• pp.177-194
• /
• 2012

What strategies are used to help students understand quadratic functions in mathematics classroom? In specific, how does Chinese teacher highlight a connection between algebraic representation and graphic representation? From October to November 2009, an experienced teacher classroom was observed. It was found that when students started learning a new type of quadratic function in lessons, the teacher used two different teaching strategies for their learning: (1) Eliciting students to plot the graphs of quadratic functions with pointwise approaches, and then construct the function image in their minds with global approaches; and (2) Presenting a specific mathematical problem, or introducing conception to elicit students to conjecture, and then encouraging them to verify it with appoint approaches.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.34 no.4
• /
• pp.189-196
• /
• 2011

In this paper, we propose a logical control-based actor-critic algorithm as an efficient approach for the approximation of the capacitated fab scheduling problem. We apply the average reward temporal-difference learning method for estimating the relative value functions of system states, while avoiding deadlock situation by Banker's algorithm. We consider the Intel mini-fab re-entrant line for the evaluation of the suggested algorithm and perform a numerical experiment by generating some sample system configurations randomly. We show that the suggested method has a prominent performance compared to other well-known heuristics.

• Smart Structures and Systems
• /
• v.26 no.6
• /
• pp.797-807
• /
• 2020

Due to the influence of nonlinearity and time-variation, it is difficult to establish an accurate model of concrete frame structures that adopt active controllers. Fuzzy theory is a relatively appropriate method but susceptible to human subjective experience to decrease the performance. This paper proposes a novel artificial intelligence based EBA (Evolved Bat Algorithm) controller with machine learning matched membership functions in the complex nonlinear system. The proposed affine transformed membership functions are adopted and stabilization and performance criterion of the closed-loop fuzzy systems are obtained through a new parametrized linear matrix inequality which is rearranged by machine learning affine matched membership functions. The trajectory of the closed-loop dithered system and that of the closed-loop fuzzy relaxed system can be made as close as desired. This enables us to get a rigorous prediction of stability of the closed-loop dithered system by establishing that of the closed-loop fuzzy relaxed system.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.194-207
• /
• 2022

In the last decade, substantial progress has been achieved in intelligent traffic control technologies to overcome consistent difficulties of traffic congestion and its adverse effect on smart cities. Edge computing is one such advanced progress facilitating real-time data transmission among vehicles and roadside units to mitigate congestion. An edge computing-based deep reinforcement learning system is demonstrated in this study that appropriately designs a multiobjective reward function for optimizing different objectives. The system seeks to overcome the challenge of evaluating actions with a simple numerical reward. The selection of reward functions has a significant impact on agents' ability to acquire the ideal behavior for managing multiple traffic signals in a large-scale road network. To ascertain effective reward functions, the agent is trained withusing the proximal policy optimization method in several deep neural network models, including the state-of-the-art transformer network. The system is verified using both hypothetical scenarios and real-world traffic maps. The comprehensive simulation outcomes demonstrate the potency of the suggested reward functions.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.11
• /
• pp.76-88
• /
• 1998

While most of the research on reinforcement learning assumed a discrete control space, many of the real world control problems need to have continuous output. This can be achieved by using continuous mapping functions for the value and action functions of the reinforcement learning architecture. Two questions arise here however. One is what sort of function representation to use and the other is how to determine the amount of noise for search in action space. The ubiquitous neural network is used here to learn the value and policy functions. Next, the reinforcement predictor that is intended to predict the next reinforcement is introduced that also determines the amount of noise to add to the controller output. The proposed reinforcement learning architecture is found to have a sound on-line learning control performance especially at high-speed road following of high curvature road. Both computer simulation and actual experiments on a test vehicle have been performed and their efficiency and effectiveness has been verified.