• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.785-804
• /
• 2017

Due to various factors such as postures, facial expressions and illuminations, face recognition by videos often suffer from poor recognition accuracy and generalization ability, since the within-class scatter might even be higher than the between-class one. Herein we address this problem by proposing a hierarchical cascaded classifier for video face recognition, which is a multi-layer algorithm and accounts for the misclassified samples plus their similar samples. Specifically, it can be decomposed into single classifier construction and multi-layer classifier design stages. In single classifier construction stage, classifier is created by clustering and the number of classes is computed by analyzing distance tree. In multi-layer classifier design stage, the next layer is created for the misclassified samples and similar ones, then cascaded to a hierarchical classifier. The experiments on the database collected by ourselves show that the recognition accuracy of the proposed classifier outperforms the compared recognition algorithms, such as neural network and sparse representation.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• The Journal of Korean Association of Computer Education
• /
• v.20 no.3
• /
• pp.13-23
• /
• 2017

There have been many researches on educational effects and efficient education methods related to Informatics education for computational thinking. However, while the one of the human models specified in the national curriculum focuses on self-directed career development ability, research on Informatics education from the viewpoint of career education is deficient. This study aimed to analyze the effects of Informatics education on science high school students' career development ability and suggest implications. As a result, not the students' career recognition and career search ability, but also career choice and preparation also improved. However, it was analyzed that there is a significant difference according to the gender and the completion of the middle school Informatics education. This study is expected to contribute to the necessity of Informatics education and the direction of Informatics education research from the viewpoint of career education.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.20 no.1
• /
• pp.17-22
• /
• 2009

Objectives : A higher level of aggression has been reported for children with attention-deficit/hyperactivity disorder (ADHD) than for non-ADHD children. Aggression was shown to have a negative effect on the social functioning of children with ADHD. The ability to recognize facial emotion expression has also been related to aggression. In this study, we examined whether impulsivity and dysfunctional recognition of facial emotion expression could explain the aggressiveness of children with ADHD. Methods : 67 children with ADHD participated in this study. We measured the ability to recognize facial emotion expression by using the Emotion Recognition Test (ERT) and we measured aggression by the T score of the aggression subscale of the Child Behavior Checklist (CBCL). Impulsivity was measured by the ADHD diagnostic system (ADS). Results : The teacher rated level of aggression was related to the score of recognizing negative affect. After controlling for the effect of impulsivity, this relationship is not significant. Only the score of the visual commission errors ex plained the level of aggression of children with ADHD. Conclusion : Impulsivity seems to have a major role in explaining the aggression of children with ADHD. The clinical implication of this study is that effective intervention for controlling impulsivity may be expected to reduce the aggression of children with ADHD.

• The Journal of the Korea Contents Association
• /
• v.17 no.11
• /
• pp.364-370
• /
• 2017

Creative thinking and fusion diversity of the performing arts pursue the settlement of empirical value realization by assuming new communication by genre. This new value and communication can create a type of collective intelligence with a different attempt based on the individual communication and horizontal thinking of the masses. Therefore, the empirical value and communication of the 21st century convergence(fusion) performing arts is possible through new types and analysis, and also were understood as the horizontal creation structure of the artist. As a result, first, the concept of the right value of 'convergence' was perceived as empirical communication depending on the empirical thinking ability of genre artists. Second, off-genre and collaborative tendencies are due to cooperation based on intellectual ability and recognition of horizontal communication by genre. Third, in the collaboration, the public's individualized communication ability and universal communication recognition should be premised and perceived the empirical definition about the collective intelligence. In conclusion, it is concluded that empirical value and communication of convergence performing arts enable to the experimental creation of collective intelligence, and that the relationship structure extends to a meaningful transition of convergence interpretation and expression of performing arts.

• Journal of Korean society of Dental Hygiene
• /
• v.15 no.1
• /
• pp.11-17
• /
• 2015

Objectives: The purpose of the study is to investigate the relationship between noise awareness, hearing ability, and dental hygiene performance in dental hygienists. Methods: The subjects were 234 dental hygienists in Seoul, Gyeonggi-do, and Incheon. The questionnaire consisted of 3 questions of general characteristics of the subjects, 1 question of noise awareness, 3 questions of hearing ability, 5 questions of dental hygiene performance, 1 question of noise reduction necessity, and 2 questions of noise control. Noise awareness, dental hygiene performance, and noise reduction necessity were measured by Likert 5 scale. Cronbach's alpha was 0.825 in dental hygiene performance reliability. Results: There was a significant difference in noise recognition by age(p<0.01) and working career(p<0.05). Those who pumped up the higher TV volume accounted for 31.6% and 3.0% had hearing impairment in the regular health checkup. 3.4% of the respondents complained of hearing loss, ear fluid, and equilibrium problem diagnosed by the doctors. The relationship between the type of workplace environment and task performance showed a significant difference. Those who work in the dental hospitals had high score of 3.43, while those who work in dental clinics had 3.20(p<0.05). The increased level of noise recognition affected the task performance and it is necessary to reduce the noise level. More try must be focused on the noise exposure prevention. Conclusions: In order to reduce the problems due to noise and improve their quality of life, it is necessary to change the noise recognition in the work place.

• Journal of Technologic Dentistry
• /
• v.35 no.4
• /
• pp.367-376
• /
• 2013

Purpose: The purpose of this study is to investigate self management and subjective chewing ability and provide the basic information to research of healthy life of old people from development of education and method for dental health of denture patient. Methods: From 15th or August to 15th of September in Daegu and Gyeong-buk, denture patients were targeted for a survey. Data from 295 people were analyzed. Results: Adjusted $R^2$ of oral health and denture satisfaction of an object of study increased to 24.9%(F=20.460, p<.001). Adjusted $R^2$ of denture custody and method of sterilization was 37.8% and Adjusted $R^2$ of recognition denture satisfaction of chewing effect was 14.4% which affect to most(F=9.274, p<.001). Conclusion: In conclusion denture condition, denture custody, method of sterilization, chewing effect influence oral health, healthy life of patients who have denture.

• Fire Science and Engineering
• /
• v.23 no.4
• /
• pp.154-164
• /
• 2009

The administration of Korean local governments in charge of natural disaster management and manmade disaster management has been completely or partially integrated to the fire fighting headquarters since 1990's. Therefore the relationship between the fire fighters and the regular officers has been more important. So in this study, I made a questionnaire about management ability, rescue activities, disaster, business efficiency of the disaster management organization. And then I did a question research to the comparison analysis of recognition between fire fighter and regular officers of Seoul disaster management organization. As a result of the comparative analysis of understanding, there is a meaningful difference among facilities of management ability, man-made disaster of disaster, business cooperation and business connection of business efficiency. Through the comparison analysis of recognition, I tried to present the improvement of Seoul disaster management organization.

• Korean Journal of Child Studies
• /
• v.32 no.1
• /
• pp.1-11
• /
• 2011

This aim of this study was to investigate the effects of the music appreciation teaching-learning method on the musical ability of young children. The music appreciation activities were developed firstly in consideration of the 4 steps of the learning cycle (recognition, exploration, inquiry, application). One group was then taught music appreciation, taking into account the learning cycle. The results were then compared with another comparative group in terms of musical ability. The results indicated that the musical ability sum of the treatment groups improved more than the comparative group. More specifically, the treatment group for four-year-olds was seen to have improved significantly more than the comparative group in terms of musical ability. These results indicate that this music appreciation teaching-learning method has a number of positive effects upon young children`s musical ability. Therefore, it is suggested that kindergarten teachers conduct instruction with an appropriate accompanying learning cycle as part of the teaching-learning method when it comes to improving the musical ability of young children.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.5
• /
• pp.421-427
• /
• 2004

In order to exploit underwater resources successfully, the first step would be a marine environmental research and exploration in the seafloor. Generally one sets up a long-term underwater experimental unit in the seafloor and retrieves the unit later after a certain period time. Essential to these applications is the reliable teleoperation and telemetering of the unit. In this paper we presents a robust underwater sound recognition algorithm by which we can identify the sound signal without the influence of disturbances due to underwater environmental changes. The proposed method provides a means suitable for the acoustic releaser which requires low power dissipation and long-time underwater operation. We demonstrate its ability of securing stability and fast sound recognition through simulation methods.