• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.313-321
• /
• 2017

One of the most frequently performed tasks in human-robot interaction (HRI), intelligent vehicles, and security systems is face related applications such as face recognition, facial expression recognition, driver state monitoring, and gaze estimation. In these applications, accurate head pose estimation is an important issue. However, conventional methods have been lacking in accuracy, robustness or processing speed in practical use. In this paper, we propose a novel method for estimating head pose with a monocular camera. The proposed algorithm is based on a deep neural network for multi-task learning using a small grayscale image. This network jointly detects multi-view faces and estimates head pose in hard environmental conditions such as illumination change and large pose change. The proposed framework quantitatively and qualitatively outperforms the state-of-the-art method with an average head pose mean error of less than $4.5^{\circ}$ in real-time.

• Archives of design research
• /
• v.16 no.2
• /
• pp.301-310
• /
• 2003

The interface design of mobile products has become a hot issue recently as a variety of products are being developed for extended usages. There have been two different views on interface design of mobile products like PDAs(personal digital assistants) or cellular phone. One 치aims that the current interface design of PC cannot be directly applied because mobile products have their own specific functions and requirements. On the meantime, the other argues that an extended application of PC metaphors to mobile products can have advantages because users'PC experiences can reduce the learning efforts and thus contribute to intuitive understanding mobile products. In this research, two types of PDAs, developed according to the aforementioned conflicting philosophies were compared and evaluated, based on laboratory-based usability testing conducted by novice users. The experiment consists of asking subjects to perform identical tasks for the two different types of products. The interaction data collected during usability testing were analyzed in terms of time taken, rate of success of tasks and errors. The experiment shows that there were some meaningful effects of users'experience of PC on the usability of PDAs.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.671-674
• /
• 2018

In this study, we implement a YOLO driving assistance system using a model car. The YOLO is an object detection and recognition algorithm using deep running which is becoming an issue recently. The system alerts the lane departure by applying the image processing technology to the image acquired through the camera, recognizes the objects using the YOLO, and performs various functions according to the type of the object and the distance between the vehicle. the YOLO, which is superior to the existing object detection and recognition algorithm, improves the performance of the driving assist system without additional equipment. The driving assist system using the YOLO will ensure the safety of the driver with low cost.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.24 no.2
• /
• pp.7-14
• /
• 2018

Purpose: The outbreak of Middle East Respiratory Syndrome(MERS) in KOREA has brought up the demands for ventilation guideline and regulations for healthcare facilities since most of the infection was spreaded inside healthcare facility. Currently KOREA has no ventilation guideline or regulations covering entire section of healthcare facility. The purpose of this study is to investigate current ventilation methods in KOREA healthcare facilities to in future, propose ventilation guideline. Methods: Research of foreign counties ventilation guideline and regulation for healthcare facilities were conducted for reference. Field investigation with survey of 21 healthcare were conducted to identify the ventilation system and operating methods. Additionally survey for healthcare workers were conducted to observe the recognition related to ventilation system in healthcare facility. Results: The result showed that most of foreign countries ventilation guideline and regulation suggests similar items to reduce the spread of infection and maintain good indoor air quality. The investigation results indicated that fixed guideline for ventilation in healthcare facility were required due to different ventilation operating methods. Survey result of healthcare workers has told us that ventilation guideline and regulation is needed to prevent further infection. Implications: Absence of ventilation guideline and regulations for healthcare facility in KOREA is an urgent issue.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.4
• /
• pp.138-144
• /
• 2014

Now, Autonomous unmanned vehicle has become an issue in next generation technology. 2D Laser scanner as the distance measurement sensor is used. 2D Laser scanner detects the distance of 80m, measured angle is -5 to 185 degree. Laser scanner detects only the plane, but using motor swings. As a result, traffic signs detect and analyze patterns. Traffic signs when driving at low speed, shape of the detected pattern is very similar. By shaking the laser scanner, traffic signs and other obstacles became clear distinction.

• Journal of Fisheries and Marine Sciences Education
• /
• v.21 no.4
• /
• pp.508-522
• /
• 2009

A teacher evaluation system is a hot issue of educational policy these days. Many teachers have opposed teacher evaluation system, but government and many parents have agreed teacher evaluation system. And some people agree teacher evaluation system, but some people disagree teacher evaluation system. The approvers of teacher evaluation system insist that teacher evaluation system can provide the quality of instruction, satisfaction of schooling, and nation's competition capacity. But opponents of teacher evaluation system insist that teacher evaluation system can provide dissatisfaction of teachers' job, excessive competition among teachers, and the failure of educational policy. So, comprehensive studies about teacher evaluation system are needed. The purpose of this study was to investigate that elementary and secondary teachers' recognition about teacher evaluation system. The tool of this study was used questionnaire which was made by researcher of this study. This study indicates as follows. Many teachers opposed teacher evaluation system, because of deficit of validity and reliability of teacher evaluation system. Also, many teachers indicated instruction ability as the most important evaluation standard of teacher evaluation system. And many teachers predicted the dissatisfaction of teachers' job and excessive competition among teachers as a result of teacher evaluation system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.4
• /
• pp.109-114
• /
• 2009

Recently, web 2.0 is becoming issue can provide a web based services and the technology is developing rapidly. In addition a variety of platforms on the web and SDK(Software Development Kit) is available from various aspects, web services, a trend that is rapidly growing user. But the development of security systems cannot follow the speed and These weaknesses are provided in the Web service by using illegal methods of information acquisition. Therefore, in this paper, we analyzed information for checking a variety of illegal access on Web services. Also, we designed and implemented Web Service-Hacking Pattern Recognition System for which warns the dangerous fact that as recognized hacking through comparisons the hacking patterns which have classified from the hacking method of existing system.

• Hwankyungkyoyuk
• /
• v.21 no.2
• /
• pp.11-24
• /
• 2008

This research verifies the effect on environmental attitude and knowledge accomplishment by t-test as producing and running programs regarding global warming which is raised as a representative environmental issue subject to 6th grade-elementary students. For this, environmental education programs about global warming for elementary students are developed and applied 15 times by reconstituting classes based on the contents regarding global warming from the text books revised as of 7th course of study. The result is as below. First, some part of contents from social study and science of 6th grade elementary curriculum of 7th course of study was able to be reconstituted to 15 education programs. Secondly, the programs about global warming improved students' environmental attitude Application of the programs about global warming showed significant difference(p<.05) on building environmental attitude as it proved those are effective on both area of recognition level and practice level. The method used on the test had .866's Cronbach alpha modulus value therefore, it obtained reliability. Thirdly, the programs regarding global warming improved students' knowledge accomplishment. As a result of test for knowledge accomplishment which was executed with same method for attitude test, the application of the programs about global warming showed significant difference(p<.05) on improving students' knowledge accomplishment on the global warming therefore, it resulted that the application of the program is effective on knowledge acquirement.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.137-142
• /
• 2021

Machine-learning systems have proven their worth in various industries, including healthcare and banking, by assisting in the extraction of valuable inferences. Information in these crucial sectors is traditionally stored in databases distributed across multiple environments, making accessing and extracting data from them a tough job. To this issue, we must add that these data sources contain sensitive information, implying that the data cannot be shared outside of the head. Using cryptographic techniques, Privacy-Preserving Machine Learning (PPML) helps solve this challenge, enabling information discovery while maintaining data privacy. In this paper, we talk about how to keep your data mining private. Because Data mining has a wide variety of uses, including business intelligence, medical diagnostic systems, image processing, web search, and scientific discoveries, and we discuss privacy-preserving in deep learning because deep learning (DL) exhibits exceptional exactitude in picture detection, Speech recognition, and natural language processing recognition as when compared to other fields of machine learning so that it detects the existence of any error that may occur to the data or access to systems and add data by unauthorized persons.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.147-153
• /
• 2023

In recent times, an absence of effective crowd management has led to numerous stampede incidents in crowded places. A crucial component for enhancing on-site crowd management effectiveness is the utilization of crowd counting technology. Current approaches to analyzing congested scenes have evolved beyond simple crowd counting, which outputs the number of people in the targeted image to a density map. This development aligns with the demands of real-life applications, as the same number of people can exhibit vastly different crowd distributions. Therefore, solely counting the number of crowds is no longer sufficient. CSRNet stands out as one representative method within this advanced category of approaches. In this paper, we propose a crowd counting network which is adaptive to the change in the density of people in the scene, addressing the performance degradation issue observed in the existing CSRNet(Congested Scene Recognition Network) when there are changes in density. To overcome the weakness of the CSRNet, we introduce a system that takes input from the image's information and adjusts the output of CSRNet based on the features extracted from the image. This aims to improve the algorithm's adaptability to changes in density, supplementing the shortcomings identified in the original CSRNet.