• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1724-1733
• /
• 2014

This paper presents a pattern recognition analysis of two spirals problem and optimization of Cascade Correlation learning algorithm using in combination with a non-monotone function as CosExp(cosine-modulated symmetric exponential function) and a monotone function as sigmoid function. In addition, the algorithm's optimization is attempted. By using genetic algorithms the optimization of the algorithm will attempt. In the first experiment, by using CosExp activation function for candidate neurons of the learning algorithm is analyzed the recognized pattern in input space of the two spirals problem. In the second experiment, CosExp function for output neurons is used. In the third experiment, the sigmoid activation functions with various parameters for candidate neurons in 8 pools and CosExp function for output neurons are used. In the fourth experiment, the parameters are composed of 8 pools and displacement of the sigmoid function to determine the value of the three parameters is obtained using genetic algorithms. The parameter values applied to the sigmoid activation functions for candidate neurons are used. To evaluate the performance of these algorithms, each step of the training input pattern classification shows the shape of the two spirals. In the optimizing process, the number of hidden neurons was reduced from 28 to15, and finally the learning algorithm with 12 hidden neurons was optimized.

• Korean Journal of Cognitive Science
• /
• v.26 no.3
• /
• pp.301-322
• /
• 2015

This study examined the effect of emotional sounds on satisfaction of search (SOS). SOS occurs when detection of a target results in a lesser chance of finding subsequent targets when searching for an unknown number of targets. Previous studies have examined factors that may influence the phenomenon, but the effect of emotional sounds is yet to be identified. Therefore, the current study investigated how emotional sound affects magnitude of the SOS effect. In addition, participants' eye movements were recorded to determine the source of SOS errors. The search display included abstract T and L-shaped items on a cloudy background and positive and negative sounds. Results demonstrated that negative sounds produced the largest SOS effect by definition, but this was due to superior accuracy in low-salient single target trials. Response time, which represents efficiency, was consistently faster when negative sounds were provided, in all target conditions. On-target fixation classification revealed scanning error, which occurs because targets are not fixated, as the most prominent type of error. These results imply that the two dimensions of emotion - valence and arousal - interactively affect cognitive performance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.6
• /
• pp.545-550
• /
• 2013

In pattern recognition field, data classification is an essential process for extracting meaningful information from data. Adaptive boosting algorithm, known as AdaBoost algorithm, is a kind of improved boosting algorithm for applying to real data analysis. It consists of weak classifiers, such as random guessing or random forest, which performance is slightly more than 50% and weights for combining the classifiers. And a strong classifier is created with the weak classifiers and the weights. In this paper, a research is performed using AdaBoost algorithm for detecting chaff echo which has similar characteristics to precipitation echo and interrupts weather forecasting. The entire process for implementing chaff echo classifier starts spatial and temporal clustering based on similarity with weather radar data. With them, learning data set is prepared that separated chaff echo and non-chaff echo, and the AdaBoost classifier is generated as a result. For verifying the classifier, actual chaff echo appearance case is applied, and it is confirmed that the classifier can distinguish chaff echo efficiently.

• Korean Journal of Food Science and Technology
• /
• v.45 no.3
• /
• pp.279-284
• /
• 2013

A quantitative method using ultra performance liquid chromatography with a photodiode array detector (UPLCPDA) was established for the analysis of 2 major plant metabolites: ${\beta}$-asarone and ${\alpha}$-asarone from Acorus gramineus, A. tatarinowii, A. calamus and Anemone altaica, and their contents are compared with other herbs of Acorus species. The method was validated according to the International Conference on harmonization (ICH) guideline for validation of analytical procedures with respect to precision, accuracy, and linearity. The average content of ${\beta}$-asarone in Acorus gramineus was significantly higher than that in others, with the second highest concentration observed in A. tatarinowii, and only a trace amounts found in A. calamus and Anemone altaica. In contrast, the average content of ${\alpha}$-asarone in A. calamus was the highest, followed by that in Acorus gramineus and A. tatarinowii. principle component analysis (PCA) confirmed that ${\beta}$-asarone and ${\alpha}$-asarone content differed among the species. These results suggest that this UPLC-PDA method can be considered as good quality control criteria for Acorus gramineus.

• Proceedings of the KOR-KST Conference
• /
• 1998.10b
• /
• pp.149-149
• /
• 1998

차종구분의 필요성은 교통공학 및 계획분야에서 교통패턴을 파악할 필요가 있으며 도로의 포장설계와 같은 구조적 측면, 교통관련자료구축 등에서도 중요하다. 현재 국내에서 운영중에 있는 각종검지기 체계들은 외국에서 개발한 체계로서 여러 가지 다양한 센서를 복합구성하여 차종을 구분하는 고가의 장비들이다. 이에 대한 국내의 연구사례는 극히 드물다고 볼 수 있다. 지금까지 주를 이룬 국내 연구사례를 보면 루프검지기를 이용한 차종구분이 주를 이루고 있다. 현재 루프검지기의 대체검지기(영상검지기, 자석검지기)개발이 활발히 진행되고 있으며 본 연구에서 이용되는 검지기는 자석검지기로서 루프검지기에 비하여 설치가 간단하고 파손의 우려가 적으며 유지관리 및 보수가 손쉽고 비용면에서도 저렴하다는 것이 장점이라 하겠다. 이에 최근에 개발되어진 단일 자석검지기를 이용한 실시간 차종인식 알고리즘을 개발하고, 현장실험을 통한 현장 적용성을 검토한다. 고속도로에 설치되어 있는 자석검지기를 이용하여 자료를 수집하며 분석에 이용되는 자료는 개별차량에 대하여 자속밀도의 변화를 주파수값으로 변환한 Digital Data값이다. 그 수치를 토대로 각 차량의 점유시간을 파악하여 각 차량의 점유시간동안 파형의 특징을 추출하여 각 특징들을 기초로 하여 각 차량이 나타내는 고유의 파형을 식별하는 패턴인식 방법으로 접근한다. 본 연구에서는 검지기 매설장소의 유한성 및 연구대상 도로의 특성으로 인하여 다양한 차종의 자료수집이 용이하지 못하여 시험가능한 자료수가 많은 차종을 대상으로 분석한다. 차종인식 알고리즘상의 차종분류는 건설교통부 차종분류기준에 따라 우선 구분이 확실한 차종으로 나눈후 단계적으로 세부적 차종분류로 접근한다.의 영향들을 고려함으로써 가로망 설계 과정에서 가로망의 상반된 역할인 이동성과 접근성의 비교가 가능한 보다 현실적인 가로망 설계 모형을 구축하고자 한다. 지금까지 소개된 가로망 설계모형들은 용량변화에 대한 설계변수의 형태에 따라 이산적 가로망 설계 모형과 연속적 가로망 설계모형으로 나뉘어지게 된다. 본 논문의 경우, 계산속도의 향상 측면에서는 연속적 가로망 설계 모형을 도입할 수 있지만, 이때 요구되는 도로용량이 이산적인 변수(차선 수)로 결정되어야만 신호제어 변수를 결정할 수 있기 때문에, 이산적 가로망 설계 모형이 사용된다. 하지만, 이산적 설계모형의 경우 조합최적화 문제이므로 정확한 최적해를 구하기 위해서는 상당한 시간이 소요되며, 경우에 따라서는 국부 최적해에 빠지게 된다. 이러한 문제를 극복하기 위해, 우선 이상적 모형의 근사화, 혹은 조합최적화문제를 위해 개발된 Simulated Annealing기법의 적용, 연속적 모형의 변수를 이산화하는 방법 등 다양한 모형들을 고려해 본 뒤, 적절한 모형을 적용할 것이다. 가로망 설계 모형에서 신호제어를 고려하기 위해서는 주어진 가로망에 대한 통행 배정과정에서 고려되는 통행시간을 링크통행시간과 교차로 지체시간을 동시에 고려해야 하는데, 이러한 문제의 해결을 위해서 최근 활발히 논의되고 있는 교차로에서의 신호제어에 대응하는 통행배정 모형을 도입하여 고려하고자 한다. 이를 위해서 지금까지 연구되어온 Global Solution Approach와 Iterative Approach를 비교, 검토한 뒤 모형에 보다 알맞은 방법을 선택한다. 차량의 교차로 통행을 고려하는 performance function의 경우 비신호 교차로와 신호교차로에 대

• Journal of Technology Innovation
• /
• v.21 no.2
• /
• pp.285-317
• /
• 2013

This paper delineates dynamic capabilities, which can be measured by internal capability and external knowledge, and also, in the shape of dynamic capabilities, bases on that corporate actions are expatiated by fitness and rent of evolutionary perspective. To achieve the goal of this study, classifying types of Nano-technology enterprise and suggesting analytical pattern based on dynamic capabilities, this thesis substantially analyzes how to categorize a type of enterprise and gauge a result through a survey of 359 domestic companies producing goods concerned with Nano-technology. This paper analyzes whether or not the internal capability and external knowledge affect the outcome of a certain enterprise. Moreover, in according to the results of practical analysis, it deducts 2 new variables by applying principal component analysis on four previous variables showing the internal capability and external knowledge. By classifying four types of enterprises with criterion of these two factors based on a relative extent and comparing each typical financial result, this paper suggests that the companies with relatively higher level of the internal capability and external knowledge surpass the lower ones at the financial outcome. Not only this, but also the technology-level analysis shows the same result, the higher capability and knowledge the higher performance. However, the analysis based on the difference of the four types of financial outcomes reveals that technological and evolutionary fitness can determine financial achievement.

• Ecology and Resilient Infrastructure
• /
• v.7 no.2
• /
• pp.114-125
• /
• 2020

Despite the various artificial neural networks that have been developed, most of the discharge models in previous studies have been developed using deep neural networks. This study aimed to develop a discharge model using a convolution neural network (CNN), which was used to solve classification problems. Furthermore, the applicability of CNN was evaluated. The photographs (pictures or images) for input data to CNN could not clearly show the characteristics of the study area as well as precipitation. Hence, the model employed in this study had to use numerical images. To solve the problem, the CN of NRCS was used to generate images as input data for the model. The generated images showed a good possibility of applicability as input data. Moreover, a new application of CN, which had been used only for discharge prediction, was proposed in this study. As a result of CNN training, the model was trained and generalized stably. Comparison between the actual and predicted values had an R² of 0.79, which was relatively high. The model showed good performance in terms of the Pearson correlation coefficient (0.84), the Nash-Sutcliffe efficiency (NSE) (0.63), and the root mean square error (24.54 ㎥/s).

• Clinics in Shoulder and Elbow
• /
• v.9 no.1
• /
• pp.50-59
• /
• 2006

Purpose: The nonoperative outcome of elbow dislocations with associated radial head and coronoid fractures are often unsatisfactory because of chronic instability and stiffness from proloned immobilization, Therefore we managed these injuries with well programed surgical appproaches. Method: Ten patients with this injury were evaluated retrospectively from May 1998 to June 2004 after a minimum of 12 months. These injuries include elbow dislocation and associated fractures of both the radial head and the coronoid process. All ten patients were treated by one clinic operatively with similar scheduled surgical methods which started on the lateral side and terminated on the medial side of the elbow. Radial head and neck fractures were classified Mason types, as two and three types respectively with six and four cases and six cases were fixated. Coronoid process were fixated with screws anteroposterior directly or anchor suture in all cases, each type was classified one, two and three. where were three type one, four type two, and three type three were according to Regan and Morrey classification. Results: The outcome was three resulting in excellent, four good, two normaland and the remaining case was one poor according to the Mayo Elbow Performance score. At a terminal follow up, the range of motion of the elbow averaged flection contracture, $6^{\circ}(0{\sim}20^{\circ})$ and further flection, $129^{\circ}(115{\sim}140^{\circ})$. Two patients had complications requiring additional care. One, displaced coronoid process which was repaired with capsule and the other patient experienced, palsy of ulnar nerve and contracted elbow joint. Conclusions: Usage of early operation as the minimum injury of medial ligaments complex and the rigid fixation of fractures to prompt motion with our scheduled management for elbow dislocations with associated radial head and coracoid fractures provided excellent results.

• Clinics in Shoulder and Elbow
• /
• v.8 no.2
• /
• pp.97-104
• /
• 2005

Purpose: To report the results of surgical treatment of comminuted fractures of distal humerus and to identify factors that affect the results. Materials and Methods: Thirty-two patients who were treated with open reduction and internal fixation for comminuted fracture of distal humerus were enrolled. According to the AO classification, A2.3 was 1 case, A3.2, 2 cases, A3.3, 8 cases, B1.3, 1 case, B2.3, 1 case, C2.2, 5 cases, C2.3, 4 cases, C3.2, 3 cases and C3.3, 7 cases. As fixation technique, 17 cases were fixed by double plates, 4 cases by only K-wires, 4 cases by only screws, 3 cases by K-wires and screws and 4 cases by one plate and screws. The mean age at the time of the operation was 49 years(range, $19{\sim}77$ years). The mean follow-up period was 16 months(range, $8{\sim}51$ months). Results: At the last follow-up, the mean maximum flexion was $116.4^{\circ}\;(range,\;85{\sim}140^{\circ})$ and the mean loss of terminal extension was $11.8^{\circ}\;(range,\;0{\sim}40^{\circ})$. The average Mayo elbow performance score was $91.4^{\circ}\;(range,\;55{\sim}100^{\circ})$. Overall 29 cases(91%) showed good to excellent results. The mean range of motion of extraarticular and intraarticular fracture group was $105.5^{\circ}\;(range,\;65{\sim}140^{\circ})$ and $104^{\circ}\;(range,\;55{\sim}140^{\circ})$, respectively. The average elbow score of both groups was$93^{\circ}\;(range,\;70{\sim}100^{\circ})$ and $90.7^{\circ}\;(range,\;55{\sim}100^{\circ})$. Over 90% showed more than good results. 30 cases(94%) showed complete bony union but two cases, nonunion. One case of the nonunion cases underwent replating with bone graft as revision surgery and total elbow arthroplasty was performed in the other case. At the last follow-up, 27 patients(84.4%) showed subjective satisfaction. Conclusion: Open reduction and internal fixation with appropriate surgical technique for comminuted fractures of distal humerus showed good results, which were not affected by age at the time of operation, fixation methods and anterior transposition of the ulnar nerve. Transolecranon approach may be considered as good choice for intraarticular comminuted fractures of distal humerus.

• Journal of Digital Convergence
• /
• v.14 no.2
• /
• pp.183-190
• /
• 2016

This paper proposes algorithm to reduce the computing time in a neural network that reduces transmission of data for tracking mobile objects in surveillance networks in terms of detection and communication load. Object Detection can be defined as follows : Given image sequence, which can forom a digitalized image, the goal of object detection is to determine whether or not there is any object in the image, and if present, returns its location, direction, size, and so on. But object in an given image is considerably difficult because location, size, light conditions, obstacle and so on change the overall appearance of objects, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact object detection which overcomes some restrictions by using neural network. Proposed system can be object detection irrelevant to obstacle, background and pose rapidly. And neural network calculation time is decreased by reducing input vector size of neural network. Principle Component Analysis can reduce the dimension of data. In the video input in real time from a CCTV was experimented and in case of color segment, the result shows different success rate depending on camera settings. Experimental results show proposed method attains 30% higher recognition performance than the conventional method.