• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.9
• /
• pp.3243-3257
• /
• 2021

Deep neural networks provide excellent performance in pattern recognition, audio classification, and image recognition. It is important that they accurately recognize input data, particularly when they are used in autonomous vehicles or for medical services. In this study, we propose a data correction method for increasing the accuracy of an unknown classifier by modifying the input data without changing the classifier. This method modifies the input data slightly so that the unknown classifier will correctly recognize the input data. It is an ensemble method that has the characteristic of transferability to an unknown classifier by generating corrected data that are correctly recognized by several classifiers that are known in advance. We tested our method using MNIST and CIFAR-10 as experimental data. The experimental results exhibit that the accuracy of the unknown classifier is a 100% correct recognition rate owing to the data correction generated by the proposed method, which minimizes data distortion to maintain the data's recognizability by humans.

• Language and Information
• /
• v.9 no.1
• /
• pp.69-92
• /
• 2005

Pattern recognition in cognitive agents is based on (i) the uninterpreted input data (e.g. parameter values) provided by the agent's hardware devices and (ii) and interpreted patterns (e.g. templates) provided by the agent's memory. Computationally, the task consists in finding the memory data corresponding best to the input data, for any given input. Once the best fitting memory data have been found, the input is recognized by applying to it the interpretation which happens to be stored with the memorized pattern. This paper presents a fast converging procedure which starts from a few initially recognized items and then analyzes the remainder of the input by systematically checking for items shown by memory to have been related to the initial items in previous encounters. In this way, known patterns are tried first, and only when they have been exhausted, an elementary exploration of the input is commenced. Efficiency is improved further by choosing the candidate to be tested next according to frequency.

• Spatial Information Research
• /
• v.20 no.1
• /
• pp.27-38
• /
• 2012

The recent development of CFD techniques are being involved w ith Environmental Impact Assessment and Environmental DesignroThey are being applied to the Site Planning and Engineering Design works as a new trendroHowever, CFD laboratory works are not extended to the field works in Industrial Project due to inaccuracy of the data input process that is cause by absence of regional height informationsroHence, in this study, we promote to build a new initial input data processing steps and algorithms for CFD Model generation. ENVI-met model is very popular, efficient, and freely downloadable CFD model. Light Detection And Ranging (LiDAR) are well known state of art technology and dataset proving a reliable accuracy for CFD. We use LiDAR data as a input source for CFD input producing process and algorithm development and evaluation. CFD initial input data generation process and results derived from am development and set is very useful and efficient for rapid CFD input data producing and maklomore reliable CFD Model forec st for atmospheric and climatic analysis for planning and design engineering industry.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.680-684
• /
• 2005

This paper presents a data-based stability analysis of a MIMO linear time-invariant discrete-time system, as an extension of the previous results for a SISO system. In the MIMO case, a similar discussion as in the case of a SISO system is also applied, except that an augmented input and output space is considered whose dimension is determined in relation to both the orders of the input and output vectors and the numbers of inputs and outputs. As certain subspaces of the input and output space, both output data space and closed-loop data space are defined, which contain all the behaviors of a system, respectively, with zero input in open-loop and with a control input in closed-loop. Then, we can derive the data-based stability conditions, in which the open-loop stability can be checked by using a data matrix whose column vectors span the output data space and the closed-loop stability can also be checked by using a data matrix whose column vectors span the closed-loop data space.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.4
• /
• pp.58-66
• /
• 1998

In many situations, it is very important to identify a certain unkown system, it from its input-output data. For this purpose, several system modeling algorithms have been suggested heretofore, and studies regarding the fuzzy modeling based on its nonlinearity get underway as well. Generatlly, fuzzy models have the capability of dividing input space into several subspaces, compared to linear ones. But hitherto subggested fuzzy modeling algorithms do not take into consideration the correlations between components of sample input data and address them independently of each other, which results in ineffective partition of input space. Therefore, to solve this problem, this letter proposes a new fuzzy modeling algorithm which partitions the input space more efficiently that conventional methods by taking into consideration correlations between components of sample data. As a way to use correlation and divide the input space, the method of principal component is ued. Finally, the results of computer simulation are given to demonstrate the validity of this algorithm.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.11a
• /
• pp.230-234
• /
• 2006

This study review about input data needing for noise mapping through the process for noise mapping to the Cheong-Ju on a middle-small scale city. Typically a technician know a input data in noise mapping but it is difficult to get the data. Even if we get the data, it is not regular type. So it take a long time to work out. This study is presented the guideline to solve this problems and indicate about getting data a scheme. and as it make a comparative study of the Europe case.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.273-275
• /
• 2006

In this paper, we introduce a new design of fuzzy neural networks using input-output data information of target system. The proposed fuzzy neural networks is constructed by input-output data information and used the center of data distance by HCM clustering to obtain the characteristics of data. A membership function is defined by HCM clustering and is applied input-output dat included each rule to conclusion polynomial functions. We use triangular membership functions and simplified fuzzy inference, linear fuzzy inference, and modified quadratic fuzzy inference in conclusion. In the networks learning, back propagation algorithm of network is used to update the parameters of the network. The proposed model is evaluated with benchmark data.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.37 no.5
• /
• pp.35-42
• /
• 1995

his paper is to develop a GIS application model (GISCELWAB) for the spatial simulation of surface runoff from a small watershed. The model was constituted by three submodels : The input data extraction model (GISINDATA) which prepares cell-based input data automatically for a given watershed, the cell water balance model (CELWAB) which calculates the water balance for a cell and simulates surface runoff of watershed simultaneously by the interaction of cells, and the output data management model (GISOUTDISP) which visualize the results of temporal and spatial variation of surface runoff. The input data extraction model was developed to solve the time-consuming problems for the input-data preparation of distributed hydrologic model. The input data for CELWAB can be obtained by extracting ASCII data from a vector map. The output data management model was developed to convert the storage depth and discharge of cells into grid map. This model enables to visualize the spatial formulation process of watershed storage depth and surface runoff wholly with time increment.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.6
• /
• pp.39-46
• /
• 2004

One of the significant issues in cluster analysis is to identify a proper number of clusters hidden under given data. In this paper we propose a novel approach to systematically determine the number of clusters based on Input Representation Coverage (IRC), which is newly defined as a quantified value of how well original input data in Gaussian feature space can be captured with a certain number of clusters. Furthermore, its usability and applicability is also investigated via experiments with synthetic data. Our experiment results show that the proposed approach is quite useful in approximately finding the real number of clusters implicitly contained in the data.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.101.5-101
• /
• 2001

A linear input/output data-based predictive control with integral action is developed. The control input is obtained directly from the input/output data in a single step. However, the state estimation in subspace identification gives a biased estimate and there is model mismatch when the controller is applied to a nonlinear process. To overcome such difficulties, we add integral action to a linear input/output data-based predictive controller by augmenting the integrated white noise disturbance model and use each of best linear unbiased estimation(BLUE) filter and Kalman filter as a stochastic observer for the unmeasured disturbance. When applied to a continuous styrene polymerization reactor the proposed controller demonstrates.