• International Journal of Computer Science & Network Security
• /
• 제24권7호
• /
• pp.143-147
• /
• 2024

Image noise classification is a classical problem in the field of image processing, machine learning, deep learning and computer vision. In this paper, image noise classification is performed using deep learning. Keras deep learning library of TensorFlow is used for this purpose. 6900 images images are selected from the Kaggle database for the classification purpose. Dataset for labeled noisy images of multiple type was generated with the help of Matlab from a dataset of non-noisy images. Labeled dataset comprised of Salt & Pepper, Gaussian and Sinusoidal noise. Different training and tests sets were partitioned to train and test the model for image classification. In deep neural networks CNN (Convolutional Neural Network) is used due to its in-depth and hidden patterns and features learning in the images to be classified. This deep learning of features and patterns in images make CNN outperform the other classical methods in many classification problems.

• The KIPS Transactions:PartB
• /
• 제14B권4호
• /
• pp.311-320
• /
• 2007

This paper presents vision-based 3D facial expression animation technique and system which provide the robust 3D head pose estimation and real-time facial expression control. Many researches of 3D face animation have been done for the facial expression control itself rather than focusing on 3D head motion tracking. However, the head motion tracking is one of critical issues to be solved for developing realistic facial animation. In this research, we developed an integrated animation system that includes 3D head motion tracking and facial expression control at the same time. The proposed system consists of three major phases: face detection, 3D head motion tracking, and facial expression control. For face detection, with the non-parametric HT skin color model and template matching, we can detect the facial region efficiently from video frame. For 3D head motion tracking, we exploit the cylindrical head model that is projected to the initial head motion template. Given an initial reference template of the face image and the corresponding head motion, the cylindrical head model is created and the foil head motion is traced based on the optical flow method. For the facial expression cloning we utilize the feature-based method, The major facial feature points are detected by the geometry of information of the face with template matching and traced by optical flow. Since the locations of varying feature points are composed of head motion and facial expression information, the animation parameters which describe the variation of the facial features are acquired from geometrically transformed frontal head pose image. Finally, the facial expression cloning is done by two fitting process. The control points of the 3D model are varied applying the animation parameters to the face model, and the non-feature points around the control points are changed by use of Radial Basis Function(RBF). From the experiment, we can prove that the developed vision-based animation system can create realistic facial animation with robust head pose estimation and facial variation from input video image.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• 제35권2호
• /
• pp.161-168
• /
• 2011

The heating, ventilating, air conditioning (HVAC) system is a very important part of an automotive vehicle: it controls the microclimate inside the passenger's compartment and removes the frost or mist that is produced in cold/rainy weather. In this study, the numerical analysis of the defrost duct in an HVAC system and the de-icing pattern is carried out using commercial CFX-code. The mass flow distribution and flow structure at the outlet of the defrost duct satisfied the duct design specification. For analyzing the de-icing pattern, additional grid generation of solid domain of ice and glass is pre-defined for conductive heat transfer. The flow structure near the windshield, streakline, and temperature fields clearly indicate that the de-icing capacity of the given defrost duct configuration is excellent and that it can be operated in a stable manner. In this paper, the unsteady changes in temperature, water volume fraction, and static enthalpy at four monitoring points are discussed.

• Journal of Distribution Science
• /
• 제12권6호
• /
• pp.81-88
• /
• 2014

Purpose - Entrepreneurship promotion is emerging as an important economic growth agenda. However, in Korea, entrepreneurship has weakened because of the collapse of the venture bubbles of the 2000s and the global economic recession in 2008, which have induced the business community to choose stability over risk. The Korean government has been implementing several support projects to inspire and promote youth entrepreneurship through various means including financial assistance; however, the perpetuation rate of young entrepreneurship is still low as compared to advanced economies such as the US and EU. This case study focuses on the Youth Start-Up Business Support Program of the Small & Medium Business Corporation, and explores practical alternatives. Further, it aims to suggest managerial factors and a conceptual model for change management factors affecting the business performance creation of a startup company, based on the Small and medium Business Corporation's young venture startup fund. Research design, data, and methodology - Many studies examine the current progress and issues of startup firms, for example, a lack of systematic cultivation of entrepreneurship and startup business training, lack of commercialization funding for youth startup businesses, lack of mentoring, and inadequate infrastructure. From prior research, we address four factors, namely, personal managerial capabilities, innovative business model, sufficient cash flow, and social network, affecting startup companies' business performance. This study involved a sample survey of 200 young entrepreneurs to investigate casual relations between the four factors and business performance. A regression analysis was used to verify the hypotheses. Results - First, in relation to differences in the founder's personal characteristics, age, sales amount, and number of employees significantly impact business performance. Second, regarding the causal relation between the four factors for creating business performance, an innovative business model and social networking have supported the hypotheses, revealing that the more that a start-up founder has an innovative business model and social networking, the more the start-up firms are likely to have better performance (e.g., sales volume, employment, ROE, ROI, etc.). Although the founder's competency and sufficient cash flow have no significant relationship with business performance, the mean value was higher performance for high founder's competency and sufficient cash flow. Conclusions - This study provides basic data on policy support strategies of the Small and Medium Business Corporation, to help young entrepreneurs achieve their start-up business goals. It shows that young entrepreneurship startup firms should strive to explore ideas to satisfy customers' needs, and that changes in customer value and the continuous innovation of business model differentiation are required to actively respond to change management. Moreover, at the infant startup stage, they should activate social network programs to share information, thereby offsetting resource scarcity and managing business risk. Further, the establishment of a long-term vision and the implementation of training programs in related specific fields should be supported to strengthen founders' personal capabilities.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제21권7호
• /
• pp.29-37
• /
• 2020

In the past, meta-heuristic optimization algorithms were developed to solve the problems caused by complex nonlinearities occurring in natural phenomena, and various studies have been conducted to examine the applicability of the developed algorithms. The self-adaptive vision correction algorithm (SAVCA) showed excellent performance in mathematics problems, but it did not apply to complex engineering problems. Therefore, it is necessary to review the application process of the SAVCA. The SAVCA, which was recently developed and showed excellent performance, was applied to the advanced Muskingum flood routing model (ANLMM-L) to examine the application and application process. First, initial solutions were generated by the SAVCA, and the fitness was then calculated by ANLMM-L. The new value selected by a local and global search was put into the SAVCA. A new solution was generated, and ANLMM-L was applied again to calculate the fitness. The final calculation was conducted by comparing and improving the results of the new solution and existing solutions. The sum of squares (SSQ) was used to calculate the error between the observed and calculated runoff, and the applied results were compared with the current models. SAVCA, which showed excellent performance in the Muskingum flood routing model, is expected to show excellent performance in a range of engineering problems.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제16권5호
• /
• pp.96-108
• /
• 2017

The current collision warning and avoidance system(CWAS) is one of the representative Advanced Driver Assistance Systems (ADAS) that significantly contributes to improve the safety performance of a vehicle and mitigate the severity of an accident. However, current CWAS mainly have focused on preventing a forward collision in an uninterrupted flow, and the prevention performance near intersections and other various types of accident scenarios are not extensively studied. In this paper, the safety performance of Vision-Sensor (VS) and Radar-Sensor(RS) - based collision warning systems are evaluated near an intersection area with the data from Naturalistic Driving Study(NDS) of Second Strategic Highway Research Program(SHRP2). Based on the VS and RS data, we newly derived sixteen vehicle-to-vehicle accident scenarios near an intersection. Then, we evaluated the detection performance of VS and RS within the derived scenarios. The results showed that VS and RS can prevent an accident in limited situations due to their restrained field-of-view. With an accident prevention rate of 0.7, VS and RS can prevent an accident in five and four scenarios, respectively. For an efficient accident prevention, a different system that can detect vehicles'movement with longer range than VS and RS is required as well as an algorithm that can predict the future movement of other vehicles. In order to further improve the safety performance of CWAS near intersection areas, a communication-based collision warning system such as integration algorithm of data from infrastructure and in-vehicle sensor shall be developed.

• Journal of the Korean housing association
• /
• 제21권2호
• /
• pp.101-109
• /
• 2010

Various environmental problems due to rapid industrialization and urbanization have worsened to such an extent that they threaten the environmental restitution of the globe and become a critical international issue. Korean government has presented the concept of green growth as a new state vision for the next 60 years and is making efforts to solve these environmental problems. Daegu Metropolitan City has faced various environmental problems including overpopulation of the city, traffic pollution, household waste accumulation and the green zone problem because of the increase of urbanization over the last few decades. As such urbanization continues, the quality of residential environments is rapidly deteriorating and the intensive use of the land leads to an increase of building area, raising the temperatures of cities. There have therefore been demands for healthy, pleasant and satisfying residential environments and for the improvement of existing residential environments, and this demand has been fully recognized by society. Nevertheless, current residential complex developments concentrate only on raising the efficiency of land use. In related laws of the past (Daegu Metropolitan City, Urban Planning Municipal Ordinance as of October 10, 2003) an attempt was made to impose a standard to segmentalize the building-to-land ratio, floor area ratio and regulations of number of floors vertically. However, these laws have now been abolished and the regulations are being eased. The purpose of this study was to analyze the characteristics of the floating wind before and after the vertical segmentation of residential areas (Daegu Metropolitan City, Urban Planning Municipal Ordinance as of October 10, 2003) by using KLAM_21, a model that enables analysis and prediction of the flow and generation of cold wind. The purpose is also to present a plan to improve the quality of residential areas when developing a building lot and redeveloping housing areas.

• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 한국주거학회 2009년도 추계학술발표대회 논문집
• /
• pp.109-112
• /
• 2009

Various environmental problems due to the rapid industralization and urbanization have been worsened as much as to threaten the environmental restitution of globe and become a critical international issue. Korean government presented the green growth as a new state vision for 60 years afterwards and is making efforts to solve the environmental problems. Daegu metropolitan city has faced various environmental problems including overpopulation of cities, traffic pollution, household wastes and green zone problem because of urbanization for the last decades. As such urbanism continues, the quality of residential environment is rapidly deteriorating and the intensive use of land leads to increase of building area raising the temperature of cities. Therefore there have been demands for the healthy, pleasant and satisfying residential environment and the improvement of residential environment and such recognition rises from society in full measure. Nevertheless the current residential complex concentrates only on raising the efficiency of land use. Related laws in the past(Daegu Metropolitan City, Urban Planning Municipal Ordinance as of October 10, 2003) tried to prepare a standard to segmentalize the building-to-land ratio, floor area ratio and regulations of number of floors vertically, but currently it is abolished and the regulations are becoming eased. The purpose of this study was to analyze the characteristics of the floating wind before and after the vertical segmentation of residential areas(Daegu Metropolitan City, Urban Planning Municipal Ordinance as of October 10, 2003) by using KLAM_21, a model that enables analysing and predicting the flow and generation of clod wind, and to present a plan to improve the quality of residential areas afterwards when developing building lot and re-developing housing areas.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• 제6권1호
• /
• pp.1-5
• /
• 2013

The number of pedestrians is considered essential information which can be used to control a person who makes a entrance or a exit into a building. The number of pedestrians, also, can be used to help to manage pedestrian traffic and the volume of pedestrian flow within the building. Due to the fact there is incorrect detection by occluded, shadows, and illumination, however, difficulty can arise in existing system which is for detection and counts of a person who makes a entrance or a exit into a building. In this paper, it is minimized that the change of illumination and the effect of shadow through the transmitted image from camera which is created and processed with great adaptability. The accuracy of the calculations can be increase as well by using Kalman Filter and Mean-Shift Algorithm in order to avoid overlapped counts. As a result of the test, it is proved that the count method that shows the accuracy of 95.4% should be effective for detection and counts.

• Journal of Pharmacopuncture
• /
• 제19권1호
• /
• pp.28-36
• /
• 2016

Objectives: The purpose of this study is to achieve a vision for autistic children and their parents aimed at generating interest in ideas such as "Sanitas Per Aquam" (SPA), massage and music therapy, which has begun to have widespread use and to attract attention. Methods: This cross-sectional, descriptive study was carried out with autistic children and their parents from February to April 2015 in $Mu{\breve{g}}la$, Turkey. The study was began by interviewing experts in the field and by developing a suitable assessment questionnaire. In order to direct the flow of conversation between the researchers and the autisitc children and their parents, the researchers conducted semi-structured face to face interviews in a form that had been determined by using reports in the literature and the opinions of experts in the field. Results: Forty two boys (84%) and eight girls (16%) with autism participated in our study. Children in the 0 - 7 age group spent long time in the bathroom (P = 0.001). Boys liked to be hugged more than girls (P = 0.01). Children ages 0 - 7 years liked bright lighting while those 15 years of age and older liked gloomy lighting (P = 0.009). Except for these statistically significant sex- and age-related differences, no other statistically significant differences were noted in the parameters of this study. Although the result was not statistically significant, more children with mild autism disorder obeyed commands like inhale or exhale (P = 0.051). Conclusion: Treatment for autism spectrum disorders is not yet fully possible, so many studies are being done to alleviate some symptoms and to improve the quality of life for individuals with autism and their families. As a result of our study, whether touching the areas the children want touched and listening to their favorite music are required to stimulate the brain remain as questions in our minds.