• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.52-56
• /
• 2004

The Information of classification and estimate about KOSPI200 index`s up and down in the stock market becomes an important standard of decision-making in designing portofolio in futures and option market. Because the coming trend of time series patterns, an economic indicator, is very subordinate to the most recent economic pattern, it is necessary to study the recent patterns most preferentially. This paper compares classification and estimated performance of SVM(Support Vector Machine) and Fuzzy SVM model that are getting into the spotlight in time series analyses, neural net models and various fields. Specially, it proves that Fuzzy SVM is superior by presenting the most suitable dimension to fuzzy membership function that has time series attribute in accordance with learning Data Base.

• Journal of Energy Engineering
• /
• v.17 no.2
• /
• pp.100-106
• /
• 2008

Flameless fiber mat catalytic burners have been known as an effective heat source in industrial drying processes since heat obtained from combustion can be transferred to absorptive body by far-infrared radiation. In order to extend the application of fiber mat catalytic burner, novel fiber mat catalytic burners were manufactured and combustion characteristics of them were investigated. For diffusive catalytic burners, the efficiency of combustion was significantly affected by the installation direction and the temperature of catalytic bed perimeter influenced on the diffusion rate of oxygen which determined the combustion efficiency of catalytic burner. It was seen in premixed catalytic combustion that air content in premixed fuel gas was optimized at slightly higher than theoretical amount of air. Combustion heat released higher than 70% by radiant heat in premixed catalytic combustion likewise diffusive catalytic combustion.

• Journal of Sensor Science and Technology
• /
• v.5 no.5
• /
• pp.55-62
• /
• 1996

This paper describes development of Polarized Stereo Monitoring System (KAERI-PSM) and compares the remote handling performance of KAERI-PSM with that of other monitoring systems, electric shutter type stereo monitoring system and general TV monitoring system. Remote handling performance is evaluated by total time and error number on remote operating experiments. Four kinds of remote handling experiments are carried out through 1) directly 2) general TV 3) electric shutter type monitor, and 4) KAERI-PSM. In these experiments six employees are participated and PUMA robot with force-torque reflectional joystic is used. The result of experiments show that camera angle against object is significant factor in monitoring and stereo monitoring system give more performance benifits in terms of accuracy and speed of remote handling operation than general TV monitoring system. In comparision of the polarized and electric shutter type stereo monitoring system, both have similar accuracy and speed for remote handling operation, but the former is superior in image quality and stability of the performance.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.2
• /
• pp.201-208
• /
• 2009

Recently, the wind energy has been widely used as a renewable energy resource due to lack and environmental issues of the mostly used fossil fuel. This work is to develop a 500W class small wind turbine blade which will be applicable to relatively low speed region like Korea and for the domestic use. For this blade a high efficiency wind turbine blade was designed with the proposing aerodynamic design procedure, and a light and low cost composite structure blade was designed considering fatigue life. Structural analyses including load case study, stress, deformation, buckling and vibration analysis were performed using the Finite Element Method. The fatigue life was estimated using the load spectrum analysis and the Miner rule. In order to evaluate the designed blade, the structural and aerodynamic performance tests were carried out, and the test results were compared with the analysis results.

• Journal of KIISE:Databases
• /
• v.30 no.4
• /
• pp.362-371
• /
• 2003

In this paper, we propose an optimal interest point extraction method to support shape-base image classification and indexing for image database by applying a dynamic threshold that reflects the characteristics of the shape contour. The threshold is determined dynamically by comparing the contour length ratio of the original shape and the approximated polygon while the algorithm is running. Because our algorithm considers the characteristics of the shape contour, it can minimize the number of interest points. For n points of the contour, the proposed algorithm has O(nlogn) computational cost on an average to extract the number of m optimal interest points. Experiments were performed on the 70 synthetic shapes of 7 different contour types and 1100 fish shapes. It shows the average optimization ratio up to 0.92 and has 14% improvement, compared to the fixed threshold method. The shape features extracted from our proposed method can be used for shape-based image classification, indexing, and similarity search via normalization.

• KIISE Transactions on Computing Practices
• /
• v.21 no.11
• /
• pp.733-738
• /
• 2015

User demographic information is necessary in order to improve the quality of personalized services such as recommendation systems. Mobile data, especially text data, is known to be effective for prediction of user demographic information. However, mobile text data has privacy issues so that its utilization is limited. In this regard, we introduce an on-device gender prediction framework utilizing mobile text data while minimizing the privacy issue. Discriminative word and emoticon sets of each gender are constructed from web documents written by authors of each gender. After gender prediction is performed by comparing discriminative word and emoticon sets with a user's mobile text data, an ensemble method that combines two prediction results draws a final result. From experiments conducted on real-world mobile text data, the proposed on-device framework shows promising results for gender prediction.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.1
• /
• pp.57-62
• /
• 2013

Because there is no suspension and differential devices at cart body, the deformation of the frame happened during kart driving affects the driving performance caused by the elastic deformation and the fatigue life of kart frame resulted from the permanent deformation. The dynamic behavior of kart caused by the torsional deformation during circular driving is the important factor of these two kinds of deformations. In order to analyze the dynamic behavior of kart at this curved section, GPS is used to trace the track of kart and the torsional stress at kart-frame has been measured with real time. The mechanical properties of kart-frames for leisure and racing are investigated through material property analysis and tensile test. Torsional stress concentration and frame distortion are investigated through stress analysis on frame on the basis of study result. The real karts for leisure and racing kart are also tested in each driving condition by using the driving analysis equipment. The driving behavior of kart at the curved section are investigated through this test. As the phenomenon of load movement due to centrifugal force at car is happened during circular driving, the torsional stress occurs at cart steel frame.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.9
• /
• pp.979-984
• /
• 2012

An antiroll-bar assembly is a precision component that is designed to control the rolling of railway cars. It is important for ensuring a safe and comfortable ride. A torsion bar is the main part of the antiroll-bar assembly. Now, this part is classified as a consumable, and it is imported into Korea from France. Therefore, there is a strong need to domestically develop a torsion bar suitable for Korean conditions and to reduce cost and improve quality. In this study, an antiroll bar is developed, and it is analyzed and tested by using a road histogram measured on Korean railroads. This bar shows satisfactory results in a comparison with the imported bar. It has a novel design featuring a ring cover made of SUS steels to prevent the corrosion of the torsion bar. Its safety is examined through CAE analysis and wear tests. It is found that its design does not result in a significant difference in static and fatigue safety. Two different SUS steels were investigated in terms of their wear resistance, and the best one was adopted.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.689-694
• /
• 2009

In this paper an approach to building fuzzy models for predicting daily and weekly stock prices is presented. Predicting stock prices with traditional time series analysis has proven to be difficult. Fuzzy logic based models have advantage of expressing the input-output relation linguistically, which facilitates the understanding of the system behavior. In building a stock prediction model we bear a burden of selecting most effective indicators for the stock prediction. In this paper information used in traditional candle stick-chart analysis is considered as input variables of our fuzzy models. The fuzzy rules have the premises and the consequents composed of trapezoidal membership functions and nonlinear equations, respectively. DE(Differential Evolution) identifies optimal fuzzy rules through an evolutionary process. The fuzzy models to predict daily and weekly open, high, low, and close prices of KOSPI(KOrea composite Stock Price Index) are built, and their performances are demonstrated.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.33-41
• /
• 2014

In this paper, we implemented a system to measure respiration rate with nonrestraint sensors comfortable for people to do their everyday life. The proposed system consists of a pad covered with a Piezoelectric sensor, a respiration measuring device able to send the signal data after amplifying and filtering the source signals to the viewer, a viewer providing sensor data visualization and implementing the respiration measuring algorithm. The algorithm is based on a breathing cycle with the local peak points extracted from threshold on sensor data. Respiration measurements on 3 subjects were performed by changing moving averages and thresholds. The proposed system showed less than 5% error rate when proper moving averages are N=50~60 and a range of thresholds is 800~1300. The system will contribute to preventing suffocation during sleep for infants and the elderly living alone.