• Smart Media Journal
• /
• 제1권1호
• /
• pp.36-41
• /
• 2012

Feature selection is the important technique of selecting a subset of relevant features for building robust pattern recognition systems. Various methods have been studied for feature selection from sequential search algorithms to stochastic algorithms. In this work, we adopted a Quantum-inspired Genetic Algorithm (QGA) which is based on the concept and principles of quantum computing such as Q-bits and superposition of state for feature selection. The performance of QGA is compared to that of the Conventional Genetic Algorithm (CGA) with respect to the classification rates and the number of selected features. The experimental result using UCI data sets shows that QGA is superior to CGA.

• The Journal of the Korea institute of electronic communication sciences
• /
• 제17권4호
• /
• pp.703-708
• /
• 2022

K-means clustering is a representative clustering technique. However, there is a limitation in not being able to integrate the performance evaluation scale and the method of determining the minimum number of clusters. In this paper, a method for numerically determining the minimum number of clusters is introduced. The explained variance is presented as an integrated measure. We propose that the k-means clustering method should be performed in the subspace of the PCA in order to simultaneously satisfy the minimum number of clusters and the threshold of the explained variance. It aims to present an explanation in principle why principal component analysis and k-means clustering are sequentially performed in pattern recognition and machine learning.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• 제28권3호
• /
• pp.186-194
• /
• 2017

In this paper, we analyze the main performance of satellite's Synthetic Aperture Radar system for high resolution and wide swath. We have used the radiation pattern of reflector antenna with array feed and comparison between the conventional ScanSAR mode and SweepSAR mode has been carried out. The SweepSAR mode is a high-resolution wide-swath mode that transmits beams over a wide range and receives echo signals through sequential beamforming based on SCORE(SCan On REceive). In this paper, we analyzed the operating principle and characteristics of satellite's SweepSAR mode and simulate system performances. In addition, in order to increase the utilization of image, performances analysis for multiple frequency bands(C-band, X-band) has been considered.

• The KIPS Transactions:PartD
• /
• 제9D권3호
• /
• pp.365-380
• /
• 2002

Temporal data mining, the incorporation of temporal semantics to existing data mining techniques, refers to a set of techniques for discovering implicit and useful temporal knowledge from large quantities of temporal data. Temporal knowledge, expressible in the form of rules, is knowledge with temporal semantics and relationships, such as cyclic pattern, calendric pattern, trends, etc. There are many examples of temporal data, including patient histories, purchaser histories, and web log that it can discover useful temporal knowledge from. Many studies on data mining have been pursued and some of them have involved issues of temporal data mining for discovering temporal knowledge from temporal data, such as sequential pattern, similar time sequence, cyclic and temporal association rules, etc. However, all of the works treated data in database at best as data series in chronological order and did not consider temporal semantics and temporal relationships containing data. In order to solve this problem, we propose a theoretical framework for temporal data mining. This paper surveys the work to date and explores the issues involved in temporal data mining. We then define a model for temporal data mining and suggest SQL-like mining language with ability to express the task of temporal mining and show architecture of temporal mining system.

• Journal of Korea Technology Innovation Society
• /
• 제21권1호
• /
• pp.92-129
• /
• 2018

In general, a technology and innovation strategy has been established first. Then, the technology and innovation activities are conducted accordingly. The literature on the technology management process points out that the technology and innovation activities exist in some sequences, nonlinear or linear pattern. However, it is also argued that a certain technology and innovation activity can be occurred or disappeared at certain timing. In this paper, it has been analyzed and clarified how the technology and innovation activities are performed and working together with the technology and innovation strategies in certain context especially when the handset market moves from feature phone to smartphone during a last decade. Empirical results show that the starting point of the technology and innovation activity changes according to the technology and innovation strategies. And, technology innovation activities exhibit multi-layer architecture types. It is confirmed that technology and innovation activities follow a specific pattern. However, if there are some changes in the technology and innovation strategy due to the external environment change, some technology and innovation activities can be skipped because the priority of the technology and innovation activities would be changed. If the firm which has the strategy type of 'innovators' fails to adapt to the fast changing external environment and has the inadequate technology and innovation activities, it is required to change the technology and innovation strategy. It will have a huge impact on the firm's survival.

• Journal of the Korean Magnetics Society
• /
• 제18권2호
• /
• pp.49-53
• /
• 2008

Magnetic and crystallographic properties of patterned media fabricated by nanoimprint lithography and Co-Pt electroplating were studied. Thin films of Ru(20 nm)/Ta(5 nm)/$SiO_2$(100 nm) were deposited on Si(100) wafer and then 25 nm hole pattern was fabricated by nanoimprint lithography on substrate. The electroplated Co-Pt nano-dots have the diameter of 35 nm and the height of 27 nm. Magnetic dot patterns of Co-Pt alloy were created using electroplated Co-Pt alloy and then their properties were measured by MFM, SQUID, SEM, TEM and AFM. We observed single domain with perendicular anisotropy for each dot and achieved optimum coercivity of 2900 Oe. These results mean that patterned media fabricated by nanoimprint lithography and electroplating have good properties in view of extending superparamagnetic limit while satisfying the writability requirements with the present write heads.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 한국농업기계학회 2017년도 춘계공동학술대회
• /
• pp.166-166
• /
• 2017

모돈의 건강 상태를 정량 지수화 하기 위한 연구를 수행 중이다. 지제이상, 섭식 불량, 수면 패턴 등의 운동 특성 분석을 위하여 복수의 초음파 센서를 이용하였다. 시계열 계측 신호를 분석하여 정량 지수화를 수행하는 과정에서 주파수 도메인 분석을 시도하였다. 이 과정에서 주파수 도메인의 분해능에 따른 편차 극복을 위한 비선형 모델링을 수행하였다. 또한 인접한 시계열 데이터 구간 간의 상관성 분석이 가능하면 대용량 데이터의 실시간 처리로 인한 지연 시간 극복 및 기대되는 예후에 대한 조기 진단이 가능할 것이다. 본 연구에서는 구글에서 제공하는 Tensorflow와 NVIDIA에서 제공하는 CUDA 엔진을 동시 적용한 심층 학습 시스템을 이용하였다. 전 처리를 위하여 주파수 분해능 (2분, 3분, 5분, 7분, 11분, 13분, 17분, 19분)에 따른 데이터 집합을 1단계로 두고, 상위 10 순위 안에 드는 파워 스펙트럼 밀도의 크기를 2단계로 하여, 총 2~10개의 입력 노드를 순차적으로 선정하였고, 동일한 방식으로 인접한 시계열의 파워 스펙터럼 밀도를 순위를 변화시켜 지정하였다. 대표적인 심층학습 모델인 Softmax regression with a multilayer convolutional network를 이용하여 Recursive feature selection 경우의 수를 $8{\times}9{\times}9$로 총 648 가지 선정하고, Epoch는 10,000회로 지정하였다. Calibration 모델링의 경우 Cost function이 10% 이하인 경우 해당 경우의 학습을 중단하였으며, 모델 간 상호 교차 검증을 수행하기 위하여 $_8C_2{\times}_8C_2{\times}_8C_2$ 경우의 수에 대한 Verification test를 수행하였다. Calibration 과정 상 모든 경우에 대하여 10% 이하의 Cost function 값을 보였으나, 검증 테스트 과정에서 모든 경우에 대하여 $r^2$ < 0.5 인 결정 계수 값이 나타났다. 단적으로 심층학습 모델의 과도한 적합(Over fitting) 방식의 한계를 보인 것이라 판단할 수 있다. 적합한 Feature selection 및 심층 학습 모델에 대한 지속적이고 추가적인 고려를 통해 과도적합을 해소함과 동시에 실효적이고 활용 가능한 Classification을 위한 입, 출력 노드 단의 전후 Indexing, Quantization에 대한 고려가 필요할 것이다. 이를 통해 모돈 생체 정보 정량화를 위한 지능형 현장 진단 기술 연구를 지속할 것이다.

• Journal of Korean Society of Transportation
• /
• 제24권6호
• /
• pp.103-117
• /
• 2006

This study develops an agent-based simulation model to evaluate tourist information systems under ubiquitous environment. In this study, individual tourist's activity chaining behavior is formulated as a utility maximization problem. The underlying assumption of the model is that tourists increase their activities within their time and budget constraints to maximize their utilities. The model seeks individual's optimal tour schedule by solving Prize-Collecting Multiple-Day Traveling Salesman Problem(PC MD TSP). The simulation-based evaluation framework allows investigating individual utility gains by their information type and the total expenditure at each tour attractions. The real-time tour activity scheduling system enables tourists to optimize their tour activities by minimizing their time loss and maximizing their opportunity to use high utility facilities.

• Analytical Science and Technology
• /
• 제24권2호
• /
• pp.78-84
• /
• 2011

The fragmentation patterns of a serine protease inhibitor, camostat, and its degradation product, 4-(4-guanidinobenzoyloxy)phenylacetic acid (GBPA), were for the first time investigated by a triple quadrupole tandem mass spectrometry equipped with an electrospray source (ESI-MS/MS) in positive and/or negative ion mode under collision-induced dissociation (CID). The positive CID spectrum of camostat showed distinctly that the single bond (C-O) cleavage between carbonyl group and oxygen atom of the ester bonds of the compound favorably occurred and then the loss of N,N-dimethylcarbamoylmethyl group was more susceptible than that of guanidine moiety. In the positive ion CID spectrum of GBPA, the initial cleavage between the carbonyl group and oxygen atom of 4-guanidinobenzoyloxy group also occurred, yielding the most abundant fragment ion at m/z 145. On the other hand, the negative CID spectrum of GBPA characteristically showed the occurrence of the most abundant peak at m/z 226 resulting from the sequential neutral losses of $CO_2$ and HN=C=NH from the parent ion at m/z 312.

• The Transactions of the Korea Information Processing Society
• /
• 제6권6호
• /
• pp.1656-1666
• /
• 1999

The more complex and large digital circuits become, the more important delay test becomes which guarantees that circuits operate in time. In this paper, the proposed algorithm is developed, which enable the fast indirect implication for efficient test pattern generation in sequential circuits of standard scan environment. Static learning algorithm enables application of a new implication value using contrapositive proposition. The static learning procedure found structurally, analyzes the gate structure in the preprocessing phase and store the information of learning occurrence so that it can be used in the test pattern generation procedure if it satisfies the implication condition. If there exists a signal line which include all paths from some particular primary inputs, it is a partitioning point. If paths passing that point have the same partial path from primary input to the signal or from the signal to primary output, they will need the same primary input values which separated by the partitioning point. In this paper test pattern generation can be more effective by using this partitioning technique. Finally, an efficient delay fault test pattern generator using indirect implication is developed and the effectiveness of these algorithms is demonstrated by experiments.