• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 2005.11a
• /
• pp.355-358
• /
• 2005

This study investigates both the dissatisfaction evaluation of residents in Kangseo Permanant Rental Housing(PRH) complex managed by SH corporation and their neighborhood's recognition on the PRH complex in terms of questionnaires divided by two groups. The result shows that the residents in PRH complex are especially dissatisfied with lining space and number of rooms, parking capacity, outmoded building, and incidence of crime.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.223-228
• /
• 2009

We propose an on-line machine learning approach for object recognition, where new images are continuously added and the recognition decision is made without delay. Random forest (RF) classifier has been extensively used as a generative model for classification and regression applications. We extend this technique for the task of building incremental component-based detector. First we employ object descriptor model based on bag of covariance matrices, to represent an object region then run our on-line RF learner to select object descriptors and to learn an object classifier. Experiments of the object recognition are provided to verify the effectiveness of the proposed approach. Results demonstrate that the propose model yields in object recognition performance comparable to the benchmark standard RF, AdaBoost, and SVM classifiers.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.2
• /
• pp.5-12
• /
• 1994

This paper proposes One Stage MSVQ/DP method for word recognition system university administration branch names are selected for the recognition experiment and 10 LPC cepstrum coefficients is used as the feature parameter. Besides the speech recognition experiments by proposed method, for comparision with it, we perform the experiments on the same data by Level Building DTW and One Stage DP method. The Recognition rates with the LBDTW and the One Stage method are $83.3\%$ and $87.5\%$, but the recognition rate with the proposed method is $91.6\%$.

• Korean Institute of Interior Design Journal
• /
• v.16 no.1 s.60
• /
• pp.126-134
• /
• 2007

This study researches the effectiveness of virtual experiences as an evaluation method in design. For the study, I researched the result on the spatial recognition before, abstracted visual objects and factors in recognition process and made up 43 inquiries for the evaluation through the experts group. Besides, set the analytical code between recognition factor and spatial constituents, made analysis the result from it. From April 1st to June 30th in 2004, the virtual model of educational place, college main building and city library was established as a subject of the research and studied the result. The methods that are used for the study are frequent analysis, T-test, reliability analysis, factor analysis etc. and SPSSWIN Package is used for the statistic analysis. There were two times of analysis on the evaluation to analyze the effect of virtual models on the web basis, one group evaluated the virtual building same as real and the other group evaluated the building site. Then analyzed the differences and correlation between the two. In result, college building, the first subject of study, and the second city library shows that made little differences between on the spot evaluation and virtual evaluation. Therefore, it is considered that the design evaluation with virtual model on the web basis has a vantage. But some problems founded that solved between preceding and present research through the feedback. It is as follows, 1. detection of problems that insufficience validity in the first survey. 2. found some not-validity inquiries. 3. detection of necessities that qualitative improvement and technical repletion in virtual environment.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.87-95
• /
• 2020

Generally, occupational safety and particularly construction safety is an intricate phenomenon. Industry professionals have devoted vital attention to enforcing Occupational Safety and Health (OHS) from the last three decades to enhance safety management in construction. Despite the efforts of the safety professionals and government agencies, current safety management still relies on manual inspections which are infrequent, time-consuming and prone to error. Extensive research has been carried out to deal with high fatality rates confronting by the construction industry. Sensor systems, visualization-based technologies, and tracking techniques have been deployed by researchers in the last decade. Recently in the construction industry, computer vision has attracted significant attention worldwide. However, the literature revealed the narrow scope of the computer vision technology for safety management, hence, broad scope research for safety monitoring is desired to attain a complete automatic job site monitoring. With this regard, the development of a broader scope computer vision-based risk recognition system for correlation detection between the construction entities is inevitable. For this purpose, a detailed analysis has been conducted and related rules which depict the correlations (positive and negative) between the construction entities were extracted. Deep learning supported Mask R-CNN algorithm is applied to train the model. As proof of concept, a prototype is developed based on real scenarios. The proposed approach is expected to enhance the effectiveness of safety inspection and reduce the encountered burden on safety managers. It is anticipated that this approach may enable a reduction in injuries and fatalities by implementing the exact relevant safety rules and will contribute to enhance the overall safety management and monitoring performance.

• The Journal of the Acoustical Society of Korea
• /
• v.5 no.4
• /
• pp.27-36
• /
• 1986

본 논문은 특정 화자에 대한 하국어 연속음의 효율적인 인식을 위하여, 구문분석과 OGS기법으 로 변형시킨 Level Building을 이용한 인식시스템에 대해서 제안하고 있다. 본 시스템에서 사용하는 template는 연속음을 분할시킨 단독음이며 소구간 경로 및 본 논문에서 제안한 전체 경로 제약에 의해 거리 계산값이 최소인 super reference를 구함으로써 인식된다. 본 연구에서 사용한 연속음은 단독음 11 자로 구성된 13개의 전철역명으로서 2인의 남성과 1인의 여성화자에 의해 10번씩 발음한 130단어를 테 스트하였는데 97.7%의 단어인식을 보였다.

• KIEAE Journal
• /
• v.8 no.4
• /
• pp.37-42
• /
• 2008

In the case that high-rise building is constructed, the surrounding wind velocity increase more than 50~100%. From this cause, many wind environmental problems can be occurred. For example, ordinary wind environmental disaster may be occurred in a region, or walking disturbed. In developed countries including USA, EU, and Japan, many efforts have been made for building wind prevention by grasping previously the effects before building constructed. But, We are bearing risk of wind environmental disaster because we have not enough recognition about building wind, and have not architectural prevention counterplans. This study aims to examine wind environmental characteristics of domestic apartment complex, and effective architectural counterplans. As the basic stage for this, we investigated pre-estimate tools and risk assessment methods of building wind in apartment complex, applied to two apart complex in Cheon-An region by CFD. As the result, serious damages were not presented. But, it is obvious that various architectural counterplans will be presented by this example researches.

• Proceedings of the KIEE Conference
• /
• 2002.11c
• /
• pp.313-316
• /
• 2002

The need to protect a main information and control a personal access using Biometrics in the intelligent building system is extended with growing the information and communication technologies in recent years. The fingerprint recognition technology is one of the biometrics methods available that has been widely used in various applications. But the present architecture of fingerprint recognition system has many of the problems because of centralized control network architecture. But we can solve the problems with distributed control network architecture. In this paper, the fingerprint recognition system uses the merit of the LonWorks. it is able to easily modularize the system and make up for the weak points in the typical fingerprint recognition system.

• Journal of Integrative Natural Science
• /
• v.5 no.2
• /
• pp.120-126
• /
• 2012

This paper describes the algorithm that lowers the dimension, maintains the gesture recognition and significantly reduces the eigenspace configuration time by combining the higher correlation feature information and Principle Component Analysis. Since the suggested method doesn't require a lot of computation than the method using existing geometric information or stereo image, the fact that it is very suitable for building the real-time system has been proved through the experiment. In addition, since the existing point to point method which is a simple distance calculation has many errors, in this paper to improve recognition rate the recognition error could be reduced by using several successive input images as a unit of recognition with K-Nearest Neighbor which is the improved Class to Class method.

• Fire Science and Engineering
• /
• v.18 no.3
• /
• pp.25-29
• /
• 2004

The purpose of this study is to supply basis data that can improve the recognition of Daegu citizens on fire safety through the investigation of their recognition on fire safety. To achieve the purpose, 553 Daegu citizens in Daegu city were interviewed from Oct. 2 to 15, 2003. The results of this study are as follows; Citizens had thought little the recognition of our society on fire safety and Daegu subway fire accident caused very big effect in citizens' fire safety recognition. Citizens did not trust about fire fighting facilities that is established in the building. Method to elevate recognition for citizens' fire safety recognition appeared by TV, newspaper, etc public information reinforcement (30.7%), establishment and operation of the fire safety experience center (24.6%), fire safety education reinforcement in school (20.8%).