• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.59-66
• /
• 2016

This paper presents an empirical evaluation on dimensionality reduction strategies by which dissimilarity-based classifications (DBC) can be implemented efficiently. In DBC, classification is not based on feature measurements of individual objects (a set of attributes), but rather on a suitable dissimilarity measure among the individual objects (pair-wise object comparisons). One problem of DBC is the high dimensionality of the dissimilarity space when a lots of objects are treated. To address this issue, two kinds of solutions have been proposed in the literature: prototype selection (PS)-based methods and dimension reduction (DR)-based methods. In this paper, instead of utilizing the PS-based or DR-based methods, a way of performing DBC in Eigen spaces (ES) is considered and empirically compared. In ES-based DBC, classifications are performed as follows: first, a set of principal eigenvectors is extracted from the training data set using a principal component analysis; second, an Eigen space is expanded using a subset of the extracted and selected Eigen vectors; third, after measuring distances among the projected objects in the Eigen space using $l_p$-norms as the dissimilarity, classification is performed. The experimental results, which are obtained using the nearest neighbor rule with artificial and real-life benchmark data sets, demonstrate that when the dimensionality of the Eigen spaces has been selected appropriately, compared to the PS-based and DR-based methods, the performance of the ES-based DBC can be improved in terms of the classification accuracy.

• Korean Journal of Remote Sensing
• /
• v.23 no.2
• /
• pp.113-117
• /
• 2007

In this paper, we propose a new method for determining automatically the size of the matching window using histogram of the gradient in order to improve the performance of stereo matching using one-meter resolution satellite imagery. For each pixel, we generate Flatness Index Image by calculating the mean value of the vertical or horizontal intensity gradients of the 4-neighbors of every pixel in the entire image. The edge pixel has high flatness index value, while the non-edge pixel has low flatness index value. By using the histogram of the Flatness Index Image, we find a flatness threshold value to determine whether a pixel is edge pixel or non-edge pixel. If a pixel has higher flatness index value than the flatness threshold value, we classify the pixel into edge pixel, otherwise we classify the pixel into non-edge pixel. If the ratio of the number of non-edge pixels in initial matching window is low, then we consider the pixel to be in homogeneous region and enlarge the size of the matching window We repeat this process until the size of matching window reaches to a maximum size. In the experiment, we used IKONOS satellite stereo imagery and obtained more improved matching results than the matching method using fixed matching window size.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.03a
• /
• pp.671-679
• /
• 2008

The effect of Pre-cooled Turbojet Engine installation and nozzle exhaust jet on Hypersonic Turbojet EXperimental aircraft(HYTEX aircraft) were investigated by three-dimensional numerical analyses to obtain aerodynamic characteristics of the aircraft during its in-flight condition. First, simulations of wind tunnel experiment using small scale model of the aircraft with and without the rectangular duct reproducing engine was performed at M=5.1 condition in order to validate the calculation code. Here, good agreements with experimental data were obtained regarding centerline wall pressures on the aircraft and aerodynamic coefficients of forces and moments acting on the aircraft. Next, full scale integrated analysis of the aircraft and the engine were conducted for flight Mach numbers of M=5.0, 4.0, 3.5, 3.0, and 2.0. Increasing the angle of attack $\alpha$ of the aircraft in M=5.0 flight increased the mass flow rate of the air captured at the intake due to pre-compression effect of the nose shockwave, also increasing the thrust obtained at the engine plug nozzle. Sufficient thrust for acceleration were obtained at $\alpha=3$ and 5 degrees. Increase of flight Mach number at $\alpha=0$ degrees resulted in decrease of mass flow rate captured at the engine intake, and thus decrease in thrust at the nozzle. The thrust was sufficient for acceleration at M=3.5 and lower cases. Lift force on the aircraft was increased by the integration of engine on the aircraft for all varying angles of attack or flight Mach numbers. However, the slope of lift increase when increasing flight Mach number showed decrease as flight Mach number reach to M=5.0, due to the separation shockwave at the upper surface of the aircraft. Pitch moment of the aircraft was not affected by the installation of the engines for all angles of attack at M=5.0 condition. In low Mach number cases at $\alpha=0$ degrees, installation of the engines increased the pitch moment compared to no engine configuration. Installation of the engines increased the frictional drag on the aircraft, and its percentage to the total drag ranged between 30-50% for varying angle of attack in M=5.0 flight.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.4
• /
• pp.475-481
• /
• 2018

In this study, the safety and effectiveness of ope cutter, developed to prevent frequent accident propeller windingness at sea. First, we calculated the bolt strength of the three types of rope cutting devices used in the experiment and the torsional stresses on the shafting system theoretical equation and the finite element method. As a result, the bolts used in the rope cutter confirmed from the viewpoint of safety life design and fail safe design. Also, safety satisfactory because of the small effect on the shaft system when locking up. Experiments were carried out to cut ropes and fishing nets from the sea using the ships equipped with three types of rope cutters verified to be safe. As a result, ropes of 20 to 50 mm in thickness were generally cut. It was found that the cutting efficiency of a rope cutter attached to shafting decreased when cutting thick ropes.

• Korean Journal of Plant Resources
• /
• v.13 no.2
• /
• pp.111-117
• /
• 2000

In an attempt to select grape bag, which elevates grape quality and make easy maturation period determination, the following research was carried out at Chungbuk Institute of Agricultural Technology, Grape Experiment Station. Light transmittance rate of bag reached to 11-65% with non-woven fabric and non-dripped vinyl bags. Non-dripped vinyl perforation and white painting bag resulted in 50 and 75%, respectively. Berry weights in non-woven fabric and non-dripped vinyl bag were high than that in paper bag. Non-dripped vinyl perforation 50%, white painting bag brought into fruit cracking, shattering, and rotten fruit, making the investigation difficult. Maturation period preceded about 1-4 day with non-woven fabric and non-dripped vinyl compared with that in paper bag. Soluble solids content with non-woven fabric and non-dripped vinyl bags was high and acidity showed a reverse result. Coloring extent was developed rapidly with non-woven fabric and non-dripped vinyl than paper bag. During initial state of coloring, coloring was rapid with Maekban-Stone mixed non-woven fabric and non-dripped vinyl + non-woven fabric bag. This was rapid with non-woven fabric bag as long appropriate maturation period. Abnormal berry rate was 5.4-7.0% with paper and non-woven fabric bags but brought about as much as 16.6-100% with non-dripped vinyl and it's mixed bags. Appearance quality was the best with index 9.0 for non-woven fabric bag. Maekban-Stone mixed non-woven fabric but non-dripped vinyl performance 50% white painting bag was the least, showing index 1.0. The time consumed for maturation determination was reduced to 74-93% with non-woven fabric and non-dripped vinyl bag compared with 17.4h/10a with paper bag.

• Korean Journal of Optics and Photonics
• /
• v.28 no.5
• /
• pp.213-220
• /
• 2017

This paper proposes how to fabricate an educational Mach-Zehnder interferometer that is easy to align and inexpensive, using 3D printers and semiconductor lasers. The interferometer consists of a body $165mm{\times}120mm{\times}57mm$ in size, mirror mounts, a laser holder, beam splitters, and so on. The laser path is adjusted by 4 mirror mounts, each comprised of rubber bands, small metal wires, and a screw. The interference fringe is enlarged by the lens at the final stage. The refractive index of a slide glass was measured by counting the number of moving interference fringes while the slide glass, inserted into one of the two interferometer arms, is rotating. The formula for the refractive index as a function of the optical-path difference and rotation angle was obtained, and used to calculate the refractive index of glass from the interferometer experiment. The use of a rotating glass in one arm of the interferometer nullifies the need for a precision stage, which despite its high cost is often required to observe the moving interference fringe in the classroom. Therefore, the 3D-printed Mach-Zehnder interferometer proposed in this paper can be very useful for education, because of its affordability and performance. It enables students to perform both qualitative and quantitative studies using a 3D-printed interferometer, such as measuring the refractive index of a glass sample, and the wavelength of light.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.5
• /
• pp.574-583
• /
• 2021

Predicting shipping markets is an important issue. Such predictions form the basis for decisions on investment methods, fleet formation methods, freight rates, etc., which greatly affect the profits and survival of a company. To this end, in this study, we propose a shipping freight rate prediction model for container ships using gated recurrent units (GRUs) and long short-term memory structure. The target of our freight rate prediction is the China Container Freight Index (CCFI), and CCFI data from March 2003 to May 2020 were used for training. The CCFI after June 2020 was first predicted according to each model and then compared and analyzed with the actual CCFI. For the experimental model, a total of six models were designed according to the hyperparameter settings. Additionally, the ARIMA model was included in the experiment for performance comparison with the traditional analysis method. The optimal model was selected based on two evaluation methods. The first evaluation method selects the model with the smallest average value of the root mean square error (RMSE) obtained by repeating each model 10 times. The second method selects the model with the lowest RMSE in all experiments. The experimental results revealed not only the improved accuracy of the deep learning model compared to the traditional time series prediction model, ARIMA, but also the contribution in enhancing the risk management ability of freight fluctuations through deep learning models. On the contrary, in the event of sudden changes in freight owing to the effects of external factors such as the Covid-19 pandemic, the accuracy of the forecasting model reduced. The GRU1 model recorded the lowest RMSE (69.55, 49.35) in both evaluation methods, and it was selected as the optimal model.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.5
• /
• pp.100-112
• /
• 2021

With the advent of big data, traffic prediction has been developed based on historical data analysis methods, but this method deteriorates prediction performance when a traffic incident that has not been observed occurs. This study proposes a method that can compensate for the reduction in traffic prediction accuracy in traffic incidents situations by hybrid approach of machine learning and traffic simulation. The blind spots of the data-driven method are revealed when data patterns that have not been observed in the past are recognized. In this study, we tried to solve the problem by reinforcing historical data using traffic simulation. The proposed method performs machine learning-based traffic prediction and periodically compares the prediction result with real time traffic data to determine whether an incident occurs. When an incident is recognized, prediction is performed using the synthetic traffic data generated through simulation. The method proposed in this study was tested on an actual road section, and as a result of the experiment, it was confirmed that the error in predicting traffic state in incident situations was significantly reduced. The proposed traffic prediction method is expected to become a cornerstone for the advancement of traffic prediction.

• Smart Media Journal
• /
• v.10 no.3
• /
• pp.39-47
• /
• 2021

Enhanced index tracking is a problem of optimizing the objective function to generate returns above the index based on the index tracking that follows the market return. In order to avoid problems such as large transaction costs and illiquidity, we used a method of constructing a portfolio by selecting only some of the stocks included in the index. Commonly used enhanced index tracking methods tried to find the optimal portfolio with only one objective function in all tested periods, but it is almost impossible to find the ultimate strategy that always works well in the volatile financial market. In addition, it is important to improve generalization performance beyond optimizing the objective function for training data due to the nature of the financial market, where statistical characteristics change significantly over time, but existing methods have a limitation in that there is no direct discussion for this. In order to solve these problems, this paper proposes ensemble learning that composes a portfolio by combining several objective functions and a 3-stage portfolio selection algorithm that can select a portfolio by applying criteria other than the objective function to the training data. The proposed method in an experiment using the S&P500 index shows Sharpe ratio that is 27% higher than the index and the existing methods, showing that the 3-stage portfolio selection algorithm and ensemble learning are effective in selecting an enhanced index portfolio.

• Convergence Security Journal
• /
• v.21 no.1
• /
• pp.191-200
• /
• 2021

Artificial intelligence technology is developing in an environment where a lot of data is produced due to the development of computing technology, a cloud environment that can store data, and the spread of personal mobile phones. Among these artificial intelligence technologies, the deep neural network provides excellent performance in image recognition and image classification. There have been many studies on image detection for forest fires and fire prevention using such a deep neural network, but studies on detection of cigarette smoking were insufficient. Meanwhile, military units are establishing surveillance systems for various facilities through CCTV, and it is necessary to detect smoking near ammunition stores or non-smoking areas to prevent fires and explosions. In this paper, by reflecting experimentally optimized numerical values such as activation function and learning rate, we did the detection of smoking pictures and non-smoking pictures in two cases. As experimental data, data was constructed by crawling using pictures of smoking and non-smoking published on the Internet, and a machine learning library was used. As a result of the experiment, when the learning rate is 0.004 and the optimization algorithm Adam is used, it can be seen that the accuracy of 93% and F1-score of 94% are obtained.