• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.758-768
• /
• 2017

In this paper, we present a novel method to extract face representation based on multi-resolution spatial pyramid. In our method, a face is subdivided into increasingly finer sub-regions (local regions) and represented at multiple levels of histogram representations. To cope with misaligned problem, patch-based local descriptor extraction has been also developed in a novel way. To preserve multiple levels of detail in local characteristics and also encode holistic spatial configuration, histograms from all levels of spatial pyramid are integrated by using dimensionality reduction and feature combination, leading to our spatial-pyramid face feature representation. We incorporate our proposed face features into general face recognition pipeline and achieve state-of-the-art results on challenging face recognition problems.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.29.1-29
• /
• 2001

Neuro-fuzzy systems are multi-layered connectionist networks that realize the elements and functions of traditional fuzzy logic control/decision systems. A trained neuro-fuzzy system is isomorphic to a fuzzy logic system, and fuzzy IF-THEN rule knowledge can be explicitly extracted from the network. This talk presents a brief introduction to self-adaptive neuro-fuzzy systems and addresses some recent research results and applications. Most of the existing neuro-fuzzy systems exhibit several major drawbacks that lead to performance degradation. These drawbacks are the curse of dimensionality (i.e., fuzzy rule explosion), inability to re-structure their internal nodes in a changing environment, and their lack of ability to extract knowledge from a given set of training data. This talk focuses on our investigation of network architectures, self-adaptation algorithms, and efficient learning algorithms that will enable existing neuro-fuzzy systems to self-adapt themselves in an unstructured and uncertain environment.

• Nuclear Engineering and Technology
• /
• v.54 no.12
• /
• pp.4522-4533
• /
• 2022

For severe accident assessment of reactor pressure vessel (RPV), it is important to develop an accurate model that can predict transient thermo-mechanical behavior of the RPV lower head under the given condition. The present study revisits the lower head failure with two- and three-dimensional finite element models. In particular, we aim to give clear insight regarding the effect of the three-dimensionality present in the distribution of the thickness and thermal load of the lower head. For a rigorous validation of the result, both the OLHF-1 and the OLHF-2 tests are considered in this study. The result suggests that the three-dimensional effect is not negligible as far as the failure location is concerned. The non-uniformity of the thickness distribution is found to affect the failure location and time. The thermal load, which may not be axisymmetric in general, has the most significant effect on the failure assessment. We also observe that the creep property can affect the global deformation of the lower head, depending on the applied mechanical load.

• Korean Journal of Social Welfare Studies
• /
• v.41 no.2
• /
• pp.247-278
• /
• 2010

There are three main purposes of this study: (a) to investigate the developmental trajectories of psychological resilience, social resilience, and school resilience of adolescents in poverty, (b) to identify the longitudinal relationship of three resiliences and (c) to examine the protective factors that help adolescents to develop successfully in the face of poverty. Data were drawn from Korea Youth Panel Survey(KYPS), a longitudinal panel study on Middle school students in the second grade. Sample consists of 648 adolescents in poverty who particiipated in the KYPS. Latent Growth Curve Model(LGM) was used to analyze intraindividual changes in resiliences and interindividual differences in these changes. And AMOS 7.0 and SPSS 15.0 were used. In this study, it is concluded that the resilience of adolescents in poverty is the construct that has uni-dimensionality and multi-dimensionality at the same time. Therefore, in order to improve resilience of adolescents in poverty, protective factors associated with each resilience have to be increased. Those findings have provided various theoretical and practical implications for social workers and professionals helping adolescents in poverty.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.6
• /
• pp.899-905
• /
• 2013

In this paper, we focus on how to calibrate multi-cameras easily and how to efficiently detect quad-copters with small-numbered particles. Each particle is a six dimensional vector that is composed of 3D position and 3D orientation of a quad-copter in the space. Due to curse of dimensionality, that leads to explosive computational costs with a large amount of high-dimensioned particles. To detect efficiently, we need to put more particles in very promising spaces and few particles in other spaces. Though computational cost is lowered by minimizing particles, in order to track a quad-copter with multiple cameras in real-time, multiple images from the cameras should be synchronized and analyzed. Therefore, lots of the computations still need to be done. Because of this, GPGPU(General-Purpose computing on Graphics Processing Units) is implemented for parallel computing. This method has been successfully tested and gives accurate results in practical situations.

• Journal of KIISE:Databases
• /
• v.32 no.5
• /
• pp.509-525
• /
• 2005

In this paper, we propose the index structure based on a vector approximation for efficiently supporting the similarity search of multi-dimensional data. The proposed index structure splits a region with the space partition method and allocates to the split region dynamic bits according to the distribution of data. Therefore, the index structure splits a region to the unoverlapped regions and can reduce the depth of the tree by storing the much region information of child nodes in a internal node. Our index structure represents the child node more exactly and provide the efficient search by representing the region information of the child node relatively using the region information of the parent node. We show that our proposed index structure is better than the existing index structure in various experiments. Experimental results show that our proposed index structure achieves about $40\%$ performance improvements on search performance over the existing method.

• Journal of Digital Convergence
• /
• v.15 no.1
• /
• pp.247-253
• /
• 2017

Feature selection or variable selection is a data mining scheme for selecting highly relevant features with target concept from high dimensional data. It decreases dimensionality of data, and makes it easy to analyze clusters or classification. A feature selection scheme requires an evaluation function. Most of current evaluation functions are based on statistics or information theory, and they can evaluate only for single feature (one-dimensional data). However, features have interactions between them, and require evaluation function for multi-dimensional data for efficient feature selection. In this study, we propose modification of FSDD evaluation function for utilizing evaluation of multiple features using extended distance function. Original FSDD is just possible for single feature evaluation. Proposed approach may be expected to be applied on other single feature evaluation method.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.15-24
• /
• 2008

For high-dimensional classification tasks, such as face recognition, the number of samples is smaller than the dimensionality of the samples. In such cases, a problem encountered in linear discriminant analysis-based methods for dimension reduction is what is known as the small sample size (SSS) problem. Recently, to solve the SSS problem, a way of employing a dissimilarity-based classification(DBC) has been investigated. In DBC, an object is represented based on the dissimilarity measures among representatives extracted from training samples instead of the feature vector itself. In this paper, we propose a new method of optimizing DBCs using multi-level fusion strategies(MFS), in which fusion strategies are employed to represent features as well as to design classifiers. Our experimental results for benchmark face databases demonstrate that the proposed scheme achieves further improved classification accuracies.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.39 no.2
• /
• pp.27-38
• /
• 2002

A new self-consistent mathematical model for semiconductor quantum well device was developed. The model was based on the direct solution of the Boltzmann transport equation, coupled to the Schrodinger and Poisson equations. The solution yielded the distribution function for a two-dimensional electron gas(2DEG) in quantum well devices. To solve the Boltzmann equation, it was transformed into a tractable form using a Legendre polynomial expansion. The Legendre expansion facilitated analytical evaluation of the collision integral, and allowed for a reduction of the dimensionality of the problem. The transformed Boltzmann equation was then discretized and solved using sparce matrix algebra. The overall system was solved by iteration between Poisson, Schrodinger and Boltzmann equations until convergence was attained.