• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.5 no.1
• /
• pp.33-44
• /
• 2012

A class of recurrent neural networks is proposed and proven to be capable of identifying any discrete-time dynamical system. The applications of the proposed network are addressed in the encoding, identification, and extraction of finite state automata. Simulation results show that the identification of finite state automata using the proposed network, trained by the hybrid greedy simulated annealing with a modified error function in the learning stage, exhibits generally better performance than other conventional identification schemes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.12
• /
• pp.5087-5102
• /
• 2015

Rapid popularization of smart cell phone equipped with camera has led to a number of new legal and criminal problems related to multimedia such as digital image, which makes cell phone source identification an important branch of digital image forensics. This paper proposes a classifier combination based source identification strategy for cell phone images. To identify the outlier cell phone models of the training sets in multi-class classifier, a one-class classifier is orderly used in the framework. Feature vectors including color filter array (CFA) interpolation coefficients estimation and multi-feature fusion is employed to verify the effectiveness of the classifier combination strategy. Experimental results demonstrate that for different feature sets, our method presents high accuracy of source identification both for the cell phone in the training sets and the outliers.

• Near Infrared Analysis
• /
• v.1 no.2
• /
• pp.29-33
• /
• 2000

The identification step of raw drug materials is an indispensible procedure in the GMP manufacturing process within the pharmaceutical industry. However, wet chemistry methods for identification of drug materials, used by the various Pharmacopeia are time-consuming and expensive steps. In this paper, near-infrared spectroscopy (NIRS) has been developed for identifying eleven drug substances including calcium pantothenate, cefaclor, cefoperazone, cephradine, dextromethorphan, ehtambutol, nicotinamide, pyrozinamide, tramadol, vitamin C, and vitamin E. Also the aim of ths work is to consturct a new algorithm for calibration model using soft independence modeling of class analogy (SIMCA) with Malinowskis Indicator Function (IND), which is used for finding the number of principal components of each class of the SIMACA model. The use of NIR technique with pattern recognition to qualify raw materials can make it possible to monitor process in real time as well as to control all procedures in the pharmaceutical industry. As the result, the samples identified of 183 different batches from 11 different compounds were separated clearly by SIMCA with 2nd derivative spectra in the NIR region of 1100∼2400 nm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.12
• /
• pp.2541-2546
• /
• 2009

In the anti-collision scheme proposed by EPCglobal Class-1 Gen-2 standard, the frame size for a query round is determined by Q-algorithm. In the Q-algorithm, the reader calculates a frame size without estimating the number of tags in it's identification range. It uses only the slot status. Therefore, the Q-algorithm has advantage that the reader's algorithm is simpler than other DFSA algorithms. However, the standard does not define an optimized parameter value for adjusting the frame size. In this paper, we propose the optimized parameter values for minimizing the identification time by various computer simulations.

• Journal of Digital Contents Society
• /
• v.9 no.2
• /
• pp.165-175
• /
• 2008

Currently, software development methods have been advanced to service-oriented from component-oriented, to component-oriented from object-oriented. The component-oriented and service-oriented software development methods are analyzed by object-oriented UML model. So, the efficient analysis method for object-oriented UML model needs. In this paper, we suggest the analysis guideline and process based on event using Input Data-Process-Output Data Table for identifying use cases and classes efficiently. And the suggested method complements the problems depending the developer's perspective and experience.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2006.07a
• /
• pp.556-556
• /
• 2006

• Journal of Sensor Science and Technology
• /
• v.24 no.6
• /
• pp.368-372
• /
• 2015

In this paper, we proposed a post-processing technique for improving classification performance of electronic nose (E-Nose) system which may be occurred drift signals from sensor array. An adaptive radial basis function network using stochastic gradient (SG) and singular value decomposition (SVD) is applied to process signals from sensor array. Due to drift from sensor's aging and poisoning problems, the final classification results may be showed bias and fluctuations. The predicted classification results with drift are quantized to determine which identification level each class is on. To mitigate sharp fluctuations moving-averaging (MA) technique is applied to quantized identification results. Finally, quantization and some edge correction process are used to decide levels of the fluctuation-smoothed identification results. The proposed technique has been indicated that E-Nose system was shown correct odor identification results even if drift occurred in sensor array. It has been confirmed throughout the experimental works. The enhancements have produced a very robust odor identification capability which can compensate for decision errors induced from drift effects with sensor array in electronic nose system.

• Journal of the Korea Safety Management & Science
• /
• v.8 no.4
• /
• pp.119-127
• /
• 2006

This paper deals with the middleware and S/W development of real time automatic attendance check management system using ubiquitous 900Mhz RFID(Radio Frequency Identification). This system supports the real time automatic attendance check and necessary data processing in class management. We expect to decrease the effort for class management and to upgrade the status of real time management of class.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.70-72
• /
• 2005

최근들어 Radio Frequency Identification (RFID) 태그가 다수의 상품에 부착되고 절러 분야에 적용되기 시작했지만, 비용문제로 인해 인증이나 암호화 같은 보안기능은 고려하지 않고 있다. 보안 기능이 없는 RFID시스템은 개인정보 노굴, 불법 리더의 접근, 위조 태그의 남용과 같은 심각한 부작용을 초래하지만 현 단계에서는 보안기능을 적용하기가 쉽지않다. 절러 기술을 따르는 수동형 태그중 EPCglobal의 EPC Class 1과 Class 1 Generation 2(C1G2)는 산업계의 여러 분야에서 특히, supply-chain 모델에서 사실상 국제표준으로 여겨진다. EPC Class1 수준의 태그는 자체 밧데리를 가지지 않는 수동형 태그이고, 암호 프리미티브를 적용한 알고리즘이나 프로토콜은 제공하지 않는다. EPC Class1 과 EPC C1G2의 유일한 보안 대책으로는 태그를 영원히 동작하지 못하게 하는 Kill 기능이 있다. Kill을 수행한 태그는 RFID 태그로서의 의미가 사라진다. 본 논문에서는 Kill 기능에 대한 EPC Class1 시스템의 취약성을 보이고 또한, EPC C1G2 시스템에서 Kill 관점에서의 보안성을 분석한다.

• Proceedings of the Zoological Society Korea Conference
• /
• 1994.10a
• /
• pp.261.1-261
• /
• 1994

No Abstract, See Full Text