• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.6
• /
• pp.86-96
• /
• 2010

In this paper, we propose stereo vision-based obstacle detection and vehicle verification methods using U-disparity map and bird's-eye view mapping. First, we extract a road feature using maximum frequent values in each row and column. And we extract obstacle areas on the road using the extracted road feature. To extract obstacle areas exactly we utilize U-disparity map. We can extract obstacle areas exactly on the U-disparity map using threshold value which consists of disparity value and camera parameter. But there are still multiple obstacles in the extracted obstacle areas. Thus, we perform another processing, namely segmentation. We convert the extracted obstacle areas into a bird's-eye view using camera modeling and parameters. We can segment obstacle areas on the bird's-eye view robustly because obstacles are represented on it according to ranges. Finally, we verify the obstacles whether those are vehicles or not using various vehicle features, namely road contacting, constant horizontal length, aspect ratio and texture information. We conduct experiments to prove the performance of our proposed algorithms in real traffic situations.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.3 s.309
• /
• pp.25-33
• /
• 2006

This paper proposed device-independent color matching algorithm based on the 3D RGB lookup table (LUT) between mobile camera and mobile LCD (Liquid Crystal Display) to improve the color-fidelity. Proposed algorithm is composed of thee steps, which is device characterization, gamut mapping, 3D RGB-LUT design. First, the characterization of mobile LCD is executed using the sigmoidal function, different from conventional method such as GOG (Gain Offset Gamma) and S-curve modeling, based on the observation of electro-optical transfer function of mobile LCD. Next, mobile camera characterization is conducted by fitting the digital value of GretagColor chart captured under the daylight environment (D65) and tristimulus values (CIELAB) using the polynomial regression. However, the CIELAB values estimated by polynomial regression exceed the maximum boundary of the CIELAB color space. Therefore, these values are corrected by linear compression of the lightness and chroma. Finally, gamut mapping is used to overcome the gamut difference between mobile camera and moible LCD. To implement the real-time processing, 3D RGB-LUT is designed based on the 3D RGB-LUT and its performance is evaluated and compared with conventional method.

• Journal of the Korea Institute of Building Construction
• /
• v.14 no.6
• /
• pp.561-569
• /
• 2014

In construction site, BIM is used in part of construct-ability review and design mistake checking. However, in a current domestic construction site, except public order project, most of work in private order project has been processing based on 2D work. As an expert resists to certain point in introduction of new technique, it may be shown in the introduction of BIM. For this, We need to analysis construct-ability of introducing BIM, work field of introducing and operational capability about present domestic construction engineers. Therefore, this study solves the problem of existing construct-ability analysis, and it visualizes the various information and objects for an effective job performance. Furthermore, construct-ability analysis by BIM that can use an intergrated management is theoretically examined and practical field-application priority among conclusions is proposed through a survey targeting on the hand-on worker. Therefore, this study suggests a factor supplying for a business-centric introduction plan and support condition.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.18-31
• /
• 2002

In this study, we introduce a concept of advanced neurofuzzy polynomial networks(ANFPN), a hybrid modeling architecture combining neurofuzzy networks(NFN) and polynomial neural networks(PNN). These networks are highly nonlinear rule-based models. The development of the ANFPN dwells on the technologies of Computational Intelligence(Cl), namely fuzzy sets, neural networks and genetic algorithms. NFN contributes to the formation of the premise part of the rule-based structure of the ANFPN. The consequence part of the ANFPN is designed using PNN. At the premise part of the ANFPN, NFN uses both the simplified fuzzy inference and error back-propagation learning rule. The parameters of the membership functions, learning rates and momentum coefficients are adjusted with the use of genetic optimization. As the consequence structure of ANFPN, PNN is a flexible network architecture whose structure(topology) is developed through learning. In particular, the number of layers and nodes of the PNN are not fixed in advance but is generated in a dynamic way. In this study, we introduce two kinds of ANFPN architectures, namely the basic and the modified one. Here the basic and the modified architecture depend on the number of input variables and the order of polynomial in each layer of PNN structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the ANFPN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed ANFPN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• Fire Science and Engineering
• /
• v.15 no.1
• /
• pp.55-65
• /
• 2001

This paper's purpose is three-folded: modeling the self-regulating fire prevention system, developing a packet of practical fire prevention measures and regulations, and reviewing the applicability of fire insurance system in Korea as a main components of the self-regulating fore prevention system. The so called self-regulating fire prevention system is defined as a grand national fire prevention framework based on and promoted by the vitality and creativeness of the market (or private sector). This drastically contrasts with the existing government-led fire prevention system in Korea. The self-regulating fire prevention system has three grounds: the principle of self-responsibility, the redefinition of the fire service as a public goods, and the principle of self-selection. It seems natural that the self-regulating fire prevention system requires the function of fire insurance institution as a pivoting mechanism providing individual decision makers with a system of incentives, resulting in rational behaviors in the part of each individuals and in the well-balanced fire prevention network in the part of the overall public. In this regard, this pilfer examines the institutions and performance of the fire insurance industry in Korea and reviews the limitation of the industry as an instant replacement mechanism of the current government-led fire prevention system in Korea.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.185-192
• /
• 2012

Call Center requires an ability of agents a lot more than face-to-face contact due to being achieved communication by non face-to face channel for contact with customers. In order to improve the ability of agents, Call Center carries out various educational training according to their work experience and function and with the accomplishment of educational training, Call Center is going to fulfill to develop its quality of counseling and productivity. On the other hand, due to investment of a lot of time and budget to educational training, it is needed to grasp and manage about its effectiveness that how helpful the training is for performance of work-site operations through evaluation of educational training. Having Seen researches about evaluation of educational training until these days, most researches have mainstream to measure satisfaction and a level of learning or degree that how the learning transfers to actions. It is found that a research about an entire evaluation model should be required. This study aims to investigate effectiveness of Call Center educational training from the level of recognition by reflecting Kirkpatrick's the four levels of learning evaluation. By the four levels, reaction, learning, behavior and results, the study found out a connection with standards of evaluation about each levels. In addition, by using structural equation modeling, it was examined goodness of fit about the entire model. Furthermore, by an alternative model, considering a direct relation between a factor of reaction and behavior, it was compared and examined goodness of fit of overall model of the study model and the alternative one.

• Horticultural Science & Technology
• /
• v.30 no.3
• /
• pp.270-277
• /
• 2012

Greenhouse industry has been growing in many countries due to both the advantage of stable year-round crop production and increased demand for fresh vegetables. In greenhouse cultivation, $CO_2$ concentration plays an essential role in the photosynthesis process of crops. Continuous and accurate monitoring of $CO_2$ level in the greenhouse would improve profitability and reduce environmental impact, through optimum control of greenhouse $CO_2$ enrichment and efficient crop production, as compared with the conventional management practices without monitoring and control of $CO_2$ level. In this study, a mathematical model was developed to estimate the $CO_2$ emission from soil as affected by environmental factors in greenhouses. Among various model types evaluated, a linear regression model provided the best coefficient of determination. Selected predictor variables were solar radiation and relative humidity and exponential transformation of both. As a response variable in the model, the difference between $CO_2$ concentrations at the soil surface and 5-cm depth showed are latively strong relationship with the predictor variables. Segmented regression analysis showed that better models were obtained when the entire daily dataset was divided into segments of shorter time ranges, and best models were obtained for segmented data where more variability in solar radiation and humidity were present (i.e., after sun-rise, before sun-set) than other segments. To consider time delay in the response of $CO_2$ concentration, concept of time lag was implemented in the regression analysis. As a result, there was an improvement in the performance of the models as the coefficients of determination were 0.93 and 0.87 with segmented time frames for sun-rise and sun-set periods, respectively. Validation tests of the models to predict $CO_2$ emission from soil showed that the developed empirical model would be applicable to real-time monitoring and diagnosis of significant factors for $CO_2$ enrichment in a soil-based greenhouse.

• Tunnel and Underground Space
• /
• v.30 no.5
• /
• pp.446-461
• /
• 2020

Numerical simulations of CIEMAT column test in Spain are performed to investigate the coupled thermo-hydro-mechanical (THM) behavior of MX80 bentonite pellets using TOUGH2-FLAC3D. The heater power and injection pressure of water in the numerical simulations are identical to those in the laboratory test. To investigate the applicability of the thermo-hydraulic (TH) model used in TOUGH2 code to prediction of the coupled TH behavior, the simulation results are compared with the observations of temperature and relative humidity with time. The tendencies of the coupled behavior observed in the test are well represented by the numerical models and the simulator in terms of temperature and relative humidity evolutions. Moreover, the performance of the models for the reproduction and prediction of the coupled TH behavior is globally satisfactory compared with the observations. However, the calculated stress change is relatively small and slow due to the limitations of the simple elastic and swelling pressure model used in numerical simulations. It seems that the two models are insufficient to realistically reproduce the complex coupled THM behavior in the bentonite pellets.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.1
• /
• pp.127-132
• /
• 2011

In this paper, we propose a novel method of adult image classification by combining skin color regions and edges in an input image. The proposed method consists of four steps. In the first step, initial skin color regions are detected by logical AND operation of all skin color regions detected by the existing methods of skin color detection. In the second step, a skin color probability map is created by modeling the distribution of skin color in the initial regions. Then, a binary image is generated by using threshold value from the skin color probability map. In the third step, after using the binary image and edge information, we detect final skin color regions using a region growing method. In the final step, adult image classification is performed by support vector machine(SVM). To this end, a feature vector is extracted by combining the final skin color regions and neighboring edges of them. As experimental results, the proposed method improves performance of the adult image classification by 9.6%, compared to the existing method.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.10
• /
• pp.217-230
• /
• 2012

This paper propose interacting test programming methods between test equipment and hardware unit to verify function and performance of the hardware unit under test. Proposed test program can minimizes the risk of failures when the unit is mounted on the aircraft by testing and verifying the unit under the worst stress condition. Also, Object oriented design using UML make it easy to apply in other equipments. Test program consists of architecture package and hardware package. Architecture package is in a role for system management, log analysis, message receiving and message analysis. Messages that are used by system management define messages for testing and defined messages is sent and received to test equipment through Ethernet. Hardware package is in a role for hardware management that is needed to be tested and is related to a system. Hardware to be tested is divided into internal test and transmission test. Internal test inspects hardware itself and reports the test results to the test equipment. Transmission test inspects communication device by sending or receiving data. All kinds of test is done in the worst condition of the test unit executing in parallel. Each device is tested at least 482 times and at most 15,003 times about one hour. Test program is utilized in hardware reliability test like as environmental test or EMI test.