• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.3
• /
• pp.669-675
• /
• 2005

This paper proposes coordinates transformation and calibration algorithm using 3D parabolic coordinate transformation and delta-bar-delta neural algorithm for the omni-directional image captured by catadioptric camera. Experimental results shows that the proposed algorithm has accuracy and confidence in coordinate transformation which is sensitive to environmental variables.

• Journal of Korea Multimedia Society
• /
• v.9 no.3
• /
• pp.369-376
• /
• 2006

In this paper, we propose an improved fuzzy RBF network which dynamically adjusts the rate of learning by applying the Delta-bar-Delta algorithm in order to improve the learning performance of fuzzy RBF networks. The proposed learning algorithm, which combines the fuzzy C-Means algorithm with the generalized delta learning method, improves its learning performance by dynamically adjusting the rate of learning. The adjustment of the learning rate is achieved by self-generating middle-layered nodes and by applying the Delta-bar-Delta algorithm to the generalized delta learning method for the learning of middle and output layers. To evaluate the learning performance of the proposed RBF network, we used 40 identifiers extracted from a container image as the training data. Our experimental results show that the proposed method consumes less training time and improves the convergence of teaming, compared to the conventional ART2-based RBF network and fuzzy RBF network.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.4
• /
• pp.19-27
• /
• 2002

We proposed an auto-tuning method of learning rate for performance improvement of backpropagation algorithm. Proposed method is used a fuzzy logic system for automatic tuning of learning rate. Instead of choosing a fixed learning rate, the fuzzy logic system is used to dynamically adjust learning rate. The inputs of fuzzy logic system are ${\Delta}$ and $\bar{{\Delta}}$, and the output is the learning rate. In order to verify the effectiveness of the proposed method, we performed simulations on a N-parity problem, function approximation, and Arabic numerals classification. The results show that the proposed method has considerably improved the performance compared to the backpropagation, the backpropagation with momentum, and the Jacobs' delta-bar-delta.

• East Asian mathematical journal
• /
• v.18 no.2
• /
• pp.271-282
• /
• 2002

Let R be a ring with an endomorphism $\sigma$ and a derivation $\delta$. An ideal I of R is ($\sigma,\;\delta$)-ideal of R if $\sigma(I){\subseteq}I$ and $\delta(I){\subseteq}I$. An ideal P of R is a ($\sigma,\;\delta$)-prime ideal of R if P(${\neq}R$) is a ($\sigma,\;\delta$)-ideal and for ($\sigma,\;\delta$)-ideals I and J of R, $IJ{\subseteq}P$ implies that $I{\subseteq}P$ or $J{\subseteq}P$. An ideal Q of R is ($\sigma,\;\delta$)-semiprime ideal of R if Q is a ($\sigma,\;\delta$)-ideal and for ($\sigma,\;\delta$)-ideal I of R, $I^2{\subseteq}Q$ implies that $I{\subseteq}Q$. The ($\sigma,\;\delta$)-prime radical (resp. prime radical) is defined by the intersection of all ($\sigma,\;\delta$)-prime ideals (resp. prime ideals) of R and is denoted by $P_{(\sigma,\delta)}(R)$(resp. P(R)). In this paper, the following results are obtained: (1) $P_{(\sigma,\delta)}(R)$ is the smallest ($\sigma,\;\delta$)-semiprime ideal of R; (2) For every extended endomorphism $\bar{\sigma}$ of $\sigma$, the $\bar{\sigma}$-prime radical of an Ore extension $P(R[x;\sigma,\delta])$ is equal to $P_{\sigma,\delta}(R)[x;\sigma,\delta]$.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 1996.05a
• /
• pp.209-216
• /
• 1996

The shape variation of billet was investigated by numerical method and spray forming work with variation of average substrate withdrawal velocity$\bar{V}$, withdrawal velocity change interval $\Delta$t and velocity deviation from average velocity $V_{dev}$. The shape and diameter with large$\bar{V}$, $\Delta$t, $V_{dev}$ vary seriously. When $\bar{V}$, $\Delta$t, $V_{dev}$ are smaller, the shape of billet is more simillar to that of the billet with constant withdrawal velocity. The average diameter of billet is determined by only $\bar{V}$, independent of $\Delta$t, $V_{dev}$. With $\bar{V}$, : 0.2 mm/sec $\Delta$t: 200 sec and $V_{dev}$. : 0.2mm/sec billet of constant diameter 230mm$\times$ height 1000mm were manufactured.

• East Asian mathematical journal
• /
• v.38 no.1
• /
• pp.1-12
• /
• 2022

Let R be a ring with an endomorphism σ and a σ-derivation δ. R is called (σ, δ)-Baer (resp. (σ, δ)-quasi-Baer, (σ, δ)-p.q.-Baer, (σ, δ)-p.p.) if the right annihilator of every right (σ, δ)-set (resp., (σ, δ)-ideal, principal (σ, δ)-ideal, (σ, δ)-element) of R is generated by an idempotent of R. In this paper, for a given Ore extension A = R[x; σ, δ] of R, the following properties are investigated: If R is a σ-rigid ring in which σ and δ commute, then (1) R is (σ, δ)-Baer if and only if R is (σ, δ)-quasi-Baer if and only if A is (${\bar{\sigma}},\;{\bar{\delta}}$)-Baer if and only if A is (${\bar{\sigma}},\;{\bar{\delta}}$)-quasi-Baer; (2) R is (σ, δ)-p.p. if and only if R is (σ, δ)-p.q.-Baer if and only if A is (${\bar{\sigma}},\;{\bar{\delta}}$)-p.p. if and only if A is (${\bar{\sigma}},\;{\bar{\delta}}$)-p.q.-Baer.

• Journal of information and communication convergence engineering
• /
• v.1 no.3
• /
• pp.157-162
• /
• 2003

We propose a learning method for improving the performance of the backpropagation algorithm. The proposed method is using a fuzzy logic system for automatic tuning of the learning rate of each weight. Instead of choosing a fixed learning rate, the fuzzy logic system is used to dynamically adjust the learning rate. The inputs of fuzzy logic system are delta and delta bar, and the output of fuzzy logic system is the learning rate. In order to verify the effectiveness of the proposed method, we performed simulations on the XOR problem, character classification, and function approximation. The results show that the proposed method considerably improves the performance compared to the general backpropagation, the backpropagation with momentum, and the Jacobs'delta-bar-delta algorithm.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.10
• /
• pp.1231-1238
• /
• 1999

This paper presents an approach for the optimal heating load Identification using Diagonal Recurrent Neural Networks(DRNN). In this paper, the DRNN captures the dynamic nature of a system and since it is not fully connected, training is much faster than a fully connected recurrent neural network. The architecture of DRNN is a modified model of the fully connected recurrent neural network with one hidden layer. The hidden layer is comprised of self-recurrent neurons, each feeding its output only into itself. In this study, A dynamic backpropagation (DBP) with delta-bar-delta learning method is used to train an optimal heating load identifier. Delta-bar-delta learning method is an empirical method to adapt the learning rate gradually during the training period in order to improve accuracy in a short time. The simulation results based on experimental data show that the proposed model is superior to the other methods in most cases, in regard of not only learning speed but also identification accuracy.

• Journal of the Korean Chemical Society
• /
• v.42 no.2
• /
• pp.150-155
• /
• 1998

Kinetic studies on the reaction of isoquinoline with para-substituted benzylbromides were conducted under various pressures (1 ~1000 bar) in acetonitrile. From the rate constants obtained, the activation parameters such as$\DeltaV^{\neq}, \Delta\beta^{\neq}, \DeltaH^{\neq}, \DeltaS^{\neq}, \DeltaG^{\neq}$ and Ea were evaluated. Reaction rate increasing the pressure and temperature. The activation compressibility coefficient and the activation entropy showed negative values. From the substituent effect and the results, it was found that the reaction proceeds through $S_N2$ mechanism, but the structure of transition state was slightly changed with substituents and pressure.

• Journal of the Korean Chemical Society
• /
• v.36 no.2
• /
• pp.180-184
• /
• 1992

Kinetic studies for the reaction of pyridine with substituted benzoyl chlorides were conducted under various pressures (1-1000 bar) in acetonitrile. From rate constants, the activation parameters (${\Delta}V^{\neq}$, ${\Delta}{\beta}^{\neq}$,${\Delta}H^{\neq}$, ${\Delta}S^{\neq}$ and ${\Delta}G^{\neq}$) were evaluated. Rates of these reaction increased with an increase in the pressure. The activation volume, the activation compressibility coefficient and the activation entropy were negative. From substituents effect and these results, it was found that these reactions proceed through $S_N2$ mechanism, but the structure of transition state was slightly changed with substituents and pressure.