• Journal of Digital Convergence
• /
• v.11 no.12
• /
• pp.295-302
• /
• 2013

Many reported methods assume that the people in an image or an image sequence have been identified and localization. People detection is one of very important variable to affect for the system's performance as the basis technology about the detection of other objects and interacting with people and computers, motion recognition. In this paper, we present an efficient linear discriminant for multi-view people detection. Our approaches are based on linear discriminant. We define training data with fisher Linear discriminant to efficient learning method. People detection is considerably difficult because it will be influenced by poses of people and changes in illumination. This idea can solve the multi-view scale and people detection problem quickly and efficiently, which fits for detecting people automatically. In this paper, we extract people using fisher linear discriminant that is hierarchical models invariant pose and background. We estimation the pose in detected people. The purpose of this paper is to classify people and non-people using fisher linear discriminant.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.3
• /
• pp.62-67
• /
• 1999

In this paper, we investigates a reliable model of the Predictive Recurrent Neural Network for the speech recognition. Predictive Neural Networks are modeled by syllable units. For the given input syllable, then a model which gives the minimum prediction error is taken as the recognition result. The Predictive Neural Network which has the structure of recurrent network was composed to give the dynamic feature of the speech pattern into the network. We have compared with the recognition ability of the Recurrent Network proposed by Elman and Jordan. ETRI's SAMDORI has been used for the speech DB. In order to find a reliable model of neural networks, the changes of two recognition rates were compared one another in conditions of: (1) changing prediction order and the number of hidden units: and (2) accumulating previous values with self-loop coefficient in its context. The result shows that the optimum prediction order, the number of hidden units, and self-loop coefficient have differently responded according to the structure of neural network used. However, in general, the Jordan's recurrent network shows relatively higher recognition rate than Elman's. The effects of recognition rate on the self-loop coefficient were variable according to the structures of neural network and their values.

• Journal of Digital Convergence
• /
• v.14 no.10
• /
• pp.375-380
• /
• 2016

This study aimed to evaluate the possibility for assessment of binocular visual function about alteration for near point of convergence (NPC). Study subjects were total 30 (emmetropia 16, myopia 14), who had no eye disease except for the phoria and monocular corrected vision 1.0 and over. Near point of accommodation (NPA), NPC and phoria test were measured both at ordinary and stimulation of +1D. Ordinary NPC was 1.77cm shorter than NPC stimulated +1D and the NPC of emmetropia was shorter than that of myopia. The difference between NPC stimulated +1D and ordinary were increased in the emmetropia. As the NPC increased, the AC/A ratio was elevated and the feature of near exophoria appeared. The results suggested that the alteration of NPC might substitute AC/A ratio for reference variable of binocular vision. If converged and analyzed comparatively with another binocular visual evaluation test, the alteration of NPC could be developed for substitution of evaluation test.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.3
• /
• pp.244-248
• /
• 2013

In this paper, we describe the smart metal casting processing management system, in which we applied case-based reasoning on the window environment. Metal casting is one of the most common casting processes. The metal casting processing is complex and variable depends on a kind of metal casting products. Especially, the metal casting industry has a feature which produces small quantities but produces a lot of different types of metal casting products. And we developed the smart metal casting processing management system which could show the processing route according to the product cases intelligently using the result of case-based reasoning. The experimental result shows that our metal casting processing management system schemes achieves more productivity than manual management schemes.

• Culinary science and hospitality research
• /
• v.17 no.3
• /
• pp.65-75
• /
• 2011

The purpose of the study was to explore the relationship between satisfaction and future behavior intention of cafeteria users. Respondents of the research were cafeteria users in major colleges in Kyunggi province. A total of 300 questionnaires were distributed between October 1, 2010 and October 20, 2010 but only281 questionnaires were used for the analysis. Based on 14 selection attributes, factor analysis showed that the KMO value of 0.634, which was extracted by Verimax vertical rotation, and=610.084(p<0.001). In addition, the distributional explanation showed a total of 61.685%. Five factors were obtained as ingredients, food, menu, maintenance, and internal environment factors according to the feature of each variable. The Cronbach value according to confidence and validity tests was 0.703. The explanation was 16.3% and the influence on satisfaction included ingredients, maintenance, and internal environment. The effect on future behavior intention was significant at the level of p<0.001. This study has limitations in that it has generalized the findingson consumers of university cafeterias; therefore, follow-up studies must be conducted.

• The KIPS Transactions:PartA
• /
• v.14A no.7
• /
• pp.399-408
• /
• 2007

Currently various techniques for efficiently developing sensor network applications are developed. However, these techniques provide the method for developing only single sensor network application easily and rapidly. Since sensor network applications control various sensor nodes based on core components of operating system, the technique to develop applications by defining common functionalities of various applications and selecting variable functionalities according to the work flow of specific application is efficient. Accordingly, this paper presents an experimental study that identifies commonality of sensor network application domain and supports optional development according to the variability of application by applying product line approach to developing sensor network application. Through the experimental study, we describe the characteristics of sensor network application domain compared with general business domain for product line development. Also, we show the effectiveness of the proposed approach by presenting that core assets designed using the proposed variability feature model and VEADL are reused according to the functionalities of each sensor node.

• Journal of KIISE:Software and Applications
• /
• v.28 no.9
• /
• pp.681-687
• /
• 2001

In order to raise a class discrimination power by combining multiple classifiers under the Bayesian decision theory, the upper bound of a Bayes error rate bounded by the conditional entropy of a class variable and decision variables obtained from training data samples should be minimized. Wang and Wong proposed a tree dependence first-order approximation scheme of a high order probability distribution composed of the class and multiple feature pattern variables for minimizing the upper bound of the Bayes error rate. This paper presents an extended high order product approximation scheme dealing with higher order dependency more than the first-order tree dependence, based on the minimization of the upper bound of the Bayes error rate. Multiple recognizers for unconstrained handwritten numerals from CENPARMI were combined by the proposed approximation scheme using the Bayesian formalism, and the high recognition rates were obtained by them.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.3
• /
• pp.259-266
• /
• 2011

We present a new dual sequential approximate optimization (SAO) algorithm called SD-TDQAO (sequential dual two-point diagonal quadratic approximate optimization). This algorithm solves engineering optimization problems with a nonlinear objective and nonlinear inequality constraints. The two-point diagonal quadratic approximation (TDQA) was originally non-convex and inseparable quadratic approximation in the primal design variable space. To use the dual method, SD-TDQAO uses diagonal quadratic explicit separable approximation; this can easily ensure convexity and separability. An important feature is that the second-derivative terms of the quadratic approximation are approximated by TDQA, which uses only information on the function and the derivative values at two consecutive iteration points. The algorithm will be illustrated using mathematical and topological test problems, and its performance will be compared with that of the MMA algorithm.

• Annals of Clinical Neurophysiology
• /
• v.10 no.1
• /
• pp.43-47
• /
• 2008

Background: Acute brachial plexitis is an acute idiopathic inflammatory disease affecting brachial plexus, which is characterized by initial severe pain in shoulder followed by profound weakness of affected arm. This is a retrospective study to evaluate the clinical and electrophysiological profile of acute brachial plexitis. Methods: Sixteen patients with acute brachial plexitis were sampled. The electrodiagnostic studies included motor and sensory nerve conduction studies (NCSs) of the median and ulnar, sensory NCSs of medial and lateral antebrachial cutaneous nerves, and needle electromyography (EMG) of selected muscles of upper extremities and cervical paraspinal muscles. The studies were performed on both sides irrespective of the clinical involvement. Results: In most of our patient, upper trunk was predominantly affected (14 patients, 87.50%). Only two patients showed either predominant lower trunk affection or diffuse affection of brachial plexus. All had an acute pain followed by the development of muscle weakness of shoulder girdle after a variable interval ($7{\pm}8.95$ days). Ten patients (62.50%) had severe disability. In NCSs, the most frequent abnormality was abnormal lateral antebrachial cutaneous sensory nerve action potentials (SNAPs). On needle EMG, all the patients showed abnormal EMG findings in affected muscles. Conclusions: In this study, pain was the presenting feature in all patients, and the territory innervated by upper trunk of the brachial plexus was most frequently involved. The most common NCS abnormality was abnormal SNAP in lateral antebrachial cutaneous nerve. Our findings support that the electrodiagnostic test is useful in localizing the trunk involvement in acute brachial plexitis.

• The Journal of the Korea Contents Association
• /
• v.13 no.12
• /
• pp.62-69
• /
• 2013

A great many researches on affordance in HCI(Human Computer Interaction), product design, and cognitive science has been done investigated currently. In addition, the concept of affordances has been applied to games in the incremental trying to understand the relationship between gamers and systems. However, there are some problems to apply them to games because many researchers take ease to use, consistency, and usefulness to handle mainly in HCI rather than the property of the game into account. Consequently, the objective of the study is to investigate affordances in consideration of the features of the game, such as fantasy, variety, and fun based on the concept of them suggested in ecological psychology. A protocol analysis was conducted through the think-aloud method on the full gameplay session to platform action game as the basic genre of many game. The result of this research reveals that a static and movable affordances as a fixed state are discovered and transforming continously, appearing, and disappearing affordances as variable states are uncovered, and physical and cognitive affordances are observed. The result of this research is expected to propose the essential design guideline on the methodology of game design.