• Journal of KIISE:Software and Applications
• /
• v.31 no.5
• /
• pp.537-542
• /
• 2004

Multi-Layer Perceptron network has been mainly applied to many practical problems because of its nonlinear mapping ability. However the generalization ability of MLP networks may be affected by the number of hidden nodes, the initial values of weights and the training errors. These factors, if improperly chosen, may result in poor generalization ability of MLP networks. It is important to identify these factors and their interaction in order to control effectively the generalization ability of MLP networks. In this paper, we have empirically identified the factors that affect the generalization ability of MLP networks, and compared their relative effects on the generalization performance for the conventional and visualized weight selecting methods using the controller box.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1624-1631
• /
• 2021

With the continued development of image processing technology, we live in a time when it is difficult to visually discriminate processed (or tampered) images from real images. However, as the risk of fake images being misused for crime increases, the importance of image forensic science for identifying fake images is emerging. Currently, various deep learning-based identifiers have been studied, but there are still many problems to be used in real situations. Due to the inherent characteristics of deep learning that strongly relies on given training data, it is very vulnerable to evaluating data that has never been viewed. Therefore, we try to find a way to improve generalization ability of deep learning-based fake image identifiers. First, images with various contents were added to the training dataset to resolve the over-fitting problem that the identifier can only classify real and fake images with specific contents but fails for those with other contents. Next, color spaces other than RGB were exploited. That is, fake image identification was attempted on color spaces not considered when creating fake images, such as HSV and YCbCr. Finally, dropout, which is commonly used for generalization of neural networks, was used. Through experimental results, it has been confirmed that the color space conversion to HSV is the best solution and its combination with the approach of increasing the training dataset significantly can greatly improve the accuracy and generalization ability of deep learning-based identifiers in identifying fake images that have never been seen before.

• Journal of Information Processing Systems
• /
• v.15 no.2
• /
• pp.422-432
• /
• 2019

A hybrid kernel function of support vector machine is proposed to improve the classification performance of power quality disturbances. The kernel function mathematical model of support vector machine directly affects the classification performance. Different types of kernel functions have different generalization ability and learning ability. The single kernel function cannot have better ability both in learning and generalization. To overcome this problem, we propose a hybrid kernel function that is composed of two single kernel functions to improve both the ability in generation and learning. In simulations, we respectively used the single and multiple power quality disturbances to test classification performance of support vector machine algorithm with the proposed hybrid kernel function. Compared with other support vector machine algorithms, the improved support vector machine algorithm has better performance for the classification of power quality signals with single and multiple disturbances.

• Journal of Advanced Marine Engineering and Technology
• /
• v.21 no.1
• /
• pp.66-70
• /
• 1997

In this paper a new learning algorithm for curvature smoothing and improved generalization for multi-layer neural networks is proposed. To enhance the generalization ability a constraint term of hidden neuron activations is added to the conventional output error, which gives the curvature smoothing characteristics to multi-layer neural networks. When the total cost consisted of the output error and hidden error is minimized by gradient-descent methods, the additional descent term gives not only the Hebbian learning but also the synaptic weight decay. Therefore it incorporates error back-propagation, Hebbian, and weight decay, and additional computational requirements to the standard error back-propagation is negligible. From the computer simulation of the time series prediction with Santafe competition data it is shown that the proposed learning algorithm gives much better generalization performance.

• Research in Mathematical Education
• /
• v.9 no.4 s.24
• /
• pp.329-333
• /
• 2005

Based on author's practice of instructing Chinese gifted students to join the Chinese Mathematics Olympic (CMO), the paper adopted test analysis model of the Scholastic Aptitude Test of Mathematics (SAT-M), tested mathematics ability of 212 mathematical gifted students to join the CMO, applied correlation analysis and factor analysis and proposed the mathematics ability structure in Chinese gifted students including comprehensive operation ability, logic thinking ability, abstract generalization ability, spatial imagination ability, memory ability, transfer ability and intuition thinking ability. And it analyzed the expression form of these abilities respectively and gave some suggestion on mathematics teaching about gifted Chinese students.

• International Journal of Advanced Culture Technology
• /
• v.6 no.4
• /
• pp.80-86
• /
• 2018

The intervention of Autism Spectrum Disorder (ASD) is limited research focus on the effect of occupational-based intervention. This study sought to determine the effect of occupational-based intervention of chopstick skills for children with ASD. This study included a total of 3 children with ASD.Using single-subject study design, a changing criterion design and ABC design were implemented. The participants' behavior was observed and recorded throughout each session. In this study, the results were analyzed through visual graphs. The amount of food that was moved using the chopsticks was gradually increased. The results show that all participants significantly improved in their ability to use chopsticks in each intervention session. In addition, Assessment of Motor and Process Skills (AMPS) improved the generalization. According to the AMPS, both the overall motor and process skills increased from baseline an average of 0.7 logit. The results of this study showed occupational-based intervention on chopsticks skill to be effective in acquisition and generalization of chopstick skill in children with ASD.

• Journal of Power Electronics
• /
• v.17 no.5
• /
• pp.1288-1297
• /
• 2017

The estimation of the remaining useful life (RUL) of lithium-ion (Li-ion) batteries is important for intelligent battery management system (BMS). Data mining technology is becoming increasingly mature, and the RUL estimation of Li-ion batteries based on data-driven prognostics is more accurate with the arrival of the era of big data. However, the support vector machine (SVM), which is applied to predict the RUL of Li-ion batteries, uses the traditional single-radial basis kernel function. This type of classifier has weak generalization ability, and it easily shows the problem of data migration, which results in inaccurate prediction of the RUL of Li-ion batteries. In this study, a novel multi-kernel SVM (MSVM) based on polynomial kernel and radial basis kernel function is proposed. Moreover, the particle swarm optimization algorithm is used to search the kernel parameters, penalty factor, and weight coefficient of the MSVM model. Finally, this paper utilizes the NASA battery dataset to form the observed data sequence for regression prediction. Results show that the improved algorithm not only has better prediction accuracy and stronger generalization ability but also decreases training time and computational complexity.

• Journal of the Korean School Mathematics Society
• /
• v.16 no.4
• /
• pp.927-941
• /
• 2013

In this paper, we investigate and analysis high school students' generalization of cosine rule using analogy, and we study teaching and learning methods improving students' analogical thinking ability to improve mathematical thinking process. When students can reproduce what they have learned through inductive reasoning process or analogical thinking process and when they can justify their own mathematical knowledge through logical inference or deductive reasoning process, they can truly internalize what they learn and have an ability to use it in various situations.

• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.101-110
• /
• 2004

In dynamic systems, such as social and economic systems, complex interactions emerge among its members. In that case, their behaviors become adaptive according to Changing environment. In many cases, an individual's behaviors can be modeled by a stimulus-response system in a dynamic environment. In this paper, we use the Iterated Prisoner's Dilemma (IPD) game, which is simple yet capable of dealing with complex problems, to model the dynamic systems. We propose strategic coalition consisting of many agents and simulate their emergence in a co-evolutionary learning environment. Also we introduce the concept of confidence for agents in a coalition and show how such confidences help to improve the generalization ability of the whole coalition. Experimental results are presented to demonstrate that co-evolutionary learning with coalitions and confidence allows better performing strategies that generalize well.

• Education of Primary School Mathematics
• /
• v.17 no.2
• /
• pp.77-93
• /
• 2014

The purpose of this study was to investigate the relationships between thinking styles and the components of mathematical ability of elementary math gifted children. The results of this study were as follows: First, there were differences in thinking styles: The gifted students prefer legislative, judical, hierarchic, global, internal and liberal thinking styles. General students prefer oligarchic and conservative thinking styles. Second, there were differences in components of mathematical ability: The gifted students scored high in all sections. And if when they scored high in one section, then they most likely scored high in the other sections as well. But the spacial related lowly to the generalization and memorization. There is no significant relationship between memorization and calculation Third, there was a correlation between thinking styles and components of mathematical ability: Some thinking styles were related to components of mathematical ability. In functions of thinking styles, legislative style have higher effect on calculation. And executive, judical styles related negatively to the inference ability. In forms of thinking styles monarchic style had higher effect on space ability, hierarchic style had higher effect on calculation. Monarchic, hierarchic styles related negatively to inference ability. In level of thinking styles global, local styles have higher effect on calculation. Local styles related negatively to the inference ability. In the scope of thinking styles, internal style had a higher effect on generalization, and external style had a higher effect on calculation. And there is no significant relationship leaning of thinking styles.