• Korean Journal of Cognitive Science
• /
• v.6 no.2
• /
• pp.27-45
• /
• 1995

In this paper, we suggest the "Fuzzy Behavior Knowledge Space(FBKS)" and explain how to utilize the FBKS when aggregating decisions of individual classifiers. The concept of "Behavior Knowledge Space(BKS)" is known to be the best method in the context that each classifier offers only one class label as its decision. However. the BKS does not considers measurement value of class label. Furthermore, it does not allow the heuristic knowledge of human experts to be embedded when combining multiple decisions. The FBKS eliminates such drawbacks of the BKS by adapting the fwzy concepts. Our method applies to the classification results that contain both class labels and associated measurement values. Experimental results confirm that the FBKS could be a very promising tool in pattern recognition areas.

• Journal of Korean Society of Water and Wastewater
• /
• v.23 no.1
• /
• pp.57-67
• /
• 2009

Under the supply-oriented policy, efficiency and rationale have not been fully considered in planning of water supply facilities in Korea. As a case, this study shows that large-size systems are suffering from overcapacity problem of water treatment plants, and thus discusses what options should be applied to deal with inefficiency. Water demand of large-size systems has suddenly decreased for the last 10 years while water demand has been often assumed to increase at a regular rate in planning of plants according to excess capacity hypothesis. This inconsistency led to a serious overcapacity. In 2006, total excess capacity of nine large-size systems was more than 1.2 times as large as maximum daily demand of total customers in Seoul. However, their options are expected to stay ex post facto. To prepare the risk of overcapacity, and draw large benefits out of the plants, the authors and other professionals in Korea should further discuss the more adaptive method for prediction of water demand, and systems integration between a large-size system and adjoining systems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.2
• /
• pp.92-99
• /
• 2014

This paper proposes the method of facial expression recognition based on decision tree structure. In the image of facial expression, ASM(Active Shape Model) and LBP(Local Binary Pattern) make the local features of a facial expressions extracted. The discriminant features gotten from local features make the two facial expressions of all combination classified. Through the sum of true related to classification, the combination of facial expression and local region are decided. The integration of branch classifications generates decision tree. The facial expression recognition based on decision tree shows better recognition performance than the method which doesn't use that.

• International Journal of Automotive Technology
• /
• v.3 no.2
• /
• pp.63-70
• /
• 2002

Future on-board vehicle control systems can be further improved through new types of mechatronic systems. In particular, these systems' capacities for interaction enhance safety, comfort and economic viability. The Automotive Engineering Department (fzd) of darmstadt University of Technology is engaged in research of the mechatronic vehicle corner, which consists of three subsystems: sensor tire, electrically actuated wheel brake and smart suspension. By intercommunication of these three systems, the brake controller receives direct, fast and permanent information about dynamic events in the tire contact area provided by the tire sensor as valuable control input. This allows to control operation conditions of each wheel brake. The information provided by the tire sensor for example help to distinguish between staightline driving and cornering as well as to determine $\mu$-split conditions. In conjunction with current information of dynamic wheel loads, tire pressures and friction tyre/road, the ideal brake force distribution can be achieved. Alike through integration of adaptive suspension bushings, elastokinematic behaviour and wheel positions can be adapted to manoeuver-oriented requirements.

• Advances in aircraft and spacecraft science
• /
• v.3 no.2
• /
• pp.149-170
• /
• 2016

Multi-Disciplinary Optimization (MDO) is widely used to handle the advanced design in several engineering applications. Such applications are commonly simulation-based, in order to capture the physics of the phenomena under study. This framework demands fast optimization algorithms as well as trustworthy numerical analyses, and a synergic integration between the two is required to obtain an efficient design process. In order to meet these needs, an adaptive Computational Fluid Dynamics (CFD) solver and a fast optimization algorithm have been developed and combined by the authors. The CFD solver is based on a high-order discontinuous Galerkin discretization while the optimization algorithm is a high-performance version of the Artificial Bee Colony method. In this work, they are used to address a typical aero-mechanical problem encountered in turbomachinery design. Interesting achievements in the considered test case are illustrated, highlighting the potential applicability of the proposed approach to other engineering problems.

• ETRI Journal
• /
• v.37 no.4
• /
• pp.752-765
• /
• 2015

We propose a novel post-processing algorithm and its very-large-scale integration architecture that simultaneously uses the passive and active stereo vision information to improve the reliability of the three-dimensional disparity in a hybrid stereo vision system. The proposed architecture consists of four steps - left-right consistency checking, semi-2D hole filling, a tiny adaptive variance checking, and a 2D weighted median filter. The experimental results show that the error rate of the proposed algorithm (5.77%) is less than that of a raw disparity (10.12%) for a real-world camera image having a $1,280{\times}720$ resolution and maximum disparity of 256. Moreover, for the famous Middlebury stereo image sets, the proposed algorithm's error rate (8.30%) is also less than that of the raw disparity (13.7%). The proposed architecture is implemented on a single commercial field-programmable gate array using only 13.01% of slice resources, which achieves a rate of 60 fps for $1,280{\times}720$ stereo images with a disparity range of 256.

• Journal of Information Processing Systems
• /
• v.8 no.4
• /
• pp.621-652
• /
• 2012

Software Estimations provide an inclusive set of directives for software project developers, project managers, and the management in order to produce more realistic estimates based on deficient, uncertain, and noisy data. A range of estimation models are being explored in the industry, as well as in academia, for research purposes but choosing the best model is quite intricate. Estimation by Analogy (EbA) is a form of case based reasoning, which uses fuzzy logic, grey system theory or machine-learning techniques, etc. for optimization. This research compares the estimation accuracy of some conventional data mining models with a hybrid model. Different data mining models are under consideration, including linear regression models like the ordinary least square and ridge regression, and nonlinear models like neural networks, support vector machines, and multivariate adaptive regression splines, etc. A precise and comprehensible predictive model based on the integration of GRA and regression has been introduced and compared. Empirical results have shown that regression when used with GRA gives outstanding results; indicating that the methodology has great potential and can be used as a candidate approach for software effort estimation.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.394-399
• /
• 2002

In this paper, Multisource data classification methods based on Bayesian formula are considered. For this decision fusion scheme, the individual data sources are handled separately by statistical classification algorithms and then Bayesian fusion method is applied to integrate from the available data sources. This method includes the combination of each expert decisions where the weights of the individual experts represent the reliability of the sources. The reliability measure used in the statistical approach is common to all pixels in previous work. In this experiment, the weight factors have been assigned to have different value for all pixels in order to improve the integrated classification accuracies. Although most implementations of Bayesian classification approaches assume fixed a priori probabilities, we have used adaptive a priori probabilities by iteratively calculating the local a priori probabilities so as to maximize the posteriori probabilities. The effectiveness of the proposed method is at first demonstrated on simulations with artificial and evaluated in terms of real-world data sets. As a result, we have shown that Bayesian statistical fusion scheme performs well on multispectral data classification.

• International Journal of High-Rise Buildings
• /
• v.8 no.2
• /
• pp.95-100
• /
• 2019

Whilst most research focuses on the reduction of operative energy use in buildings, the aspect of which (and how many) materials are used is often neglected and poorly explored. However, considering the continuous growth of the global population and the limited availability of resources, it is clear that focusing on operative energy alone is too short-sighted. The tasks lying ahead for architects and engineers cannot be accomplished with conventional methods of construction. With a share of 50-60% of global resource consumption, the building industry has a decisive impact on our environment. If business as usual continues, resources will be significantly depleted in a matter of decades. Therefore, researchers of the University of Stuttgart are investigating the concept of adaptivity as a promising method for saving resources in the built environment. The term adaptivity in the context of building structures was first introduced by Werner Sobek. It describes a method where sensors, actuators and control units are implemented in systems or facades in order to oppose physical impacts in an ideal way. The applicability of this method will be verified on an experimental high-rise building at the University campus in Stuttgart. Thus, this paper describes this innovative research project and depicts the concept of adaptivity in high-rise structures. Furthermore, it gives an overview of potential actuation concepts and the interdisciplinary challenges behind them.

• Advances in aircraft and spacecraft science
• /
• v.9 no.2
• /
• pp.95-102
• /
• 2022

The paper investigates the process of pulsation of a spherical cavity (bubble) in a liquid under the influence of a source of ultrasonic vibrations. The process of pulsation of a cavitation pocket in liquid is investigated. The Kirkwood-Bethe model was used to describe the motion. A numerical solution algorithm based on the Runge-Kutta-Felberg method of 4-5th order with adaptive selection of the integration step has been developed and implemented. It was revealed that if the initial bubble radius exceeds a certain value, then the bubble will perform several pulsations until the moment of collapse. The same applies to the case of exceeding the amplitude of ultrasonic vibrations of a certain value. The proposed algorithm makes it possible to fully describe the process of cavitation pulsations, to carry out comprehensive parametric studies and to evaluate the influence of various process parameters on the intensity of cavitation.