• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.22 no.2
• /
• pp.1-8
• /
• 2014

This paper introduces a new framework of predicting the arrival time of an aircraft by incorporating the probabilistic information of what type of trajectory pattern will be applied by human air traffic controllers. The proposed method is based on identifying the major patterns of vectored trajectories and finding the statistical relationship of those patterns with various traffic complexity factors. The proposed method is applied to the traffic scenarios in real operations to demonstrate its performances.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.183-193
• /
• 2024

Recurrent Neural Network technology that learns past patterns and predicts future patterns using technology for recognizing and classifying objects is being applied to various industries, economies, and languages. And research for practical use is making a lot of progress. However, research on the application of Recurrent Neural Networks for evaluating and predicting the safety of mechanical structures is insufficient. Accurate detection of external load applied to the outside is required to evaluate the safety of mechanical structures. Learning of Recurrent Neural Networks for this requires a large amount of load data. This study applied the Gated Recurrent Unit technique to examine the possibility of load learning and investigated the possibility of applying a stacked Auto Encoder as a way to secure load data. In addition, the usefulness of learning mechanical loads was analyzed with the Gated Recurrent Unit technique, and the basic setting of related functions and parameters was proposed to secure accuracy in the recognition and prediction of loads.

• Journal of Satellite, Information and Communications
• /
• v.11 no.1
• /
• pp.55-57
• /
• 2016

In this paper, we present an algorithm to determine the abnormal behavior through a CCTV-based behavioral recognition and a pattern of hand using ConvexHull. In the existing way that using CCTV for crime prevention, facial recognition is mainly used. Facial recognition is the way that compares the faces that are seen on the screen and faces of criminals for determining how dangerous targets are, however, this way is hard to predict future criminal behavior. Therefore, to predict more various situations, abnormal behaviours are determined with targets' incline of arms, legs and bodys and patterns of hand movements. it can forecast crimes when an acting has been getting within common normality out, comparing whose acting patterns with the crime patterns.

• The Journal of Information Systems
• /
• v.27 no.3
• /
• pp.123-140
• /
• 2018

Purpose The purpose of this study is to explore the optimal trading frequency which is useful for stock price prediction by using deep learning for charting image data. We also want to identify the appropriate time for accurate forecasting of stock price when performing pattern analysis. Design/methodology/approach In order to find the optimal trading frequency patterns and forecast timings, this study is performed as follows. First, stock price data is collected using OpenAPI provided by Daishin Securities, and candle chart images are created by data frequency and forecasting time. Second, the patterns are generated by the charting images and the learning is performed using the CNN. Finally, we find the optimal trading frequency patterns and forecasting timings. Findings According to the experiment results, this study confirmed that when the 10 minute frequency data is judged to be a decline pattern at previous 1 tick, the accuracy of predicting the market frequency pattern at which the market decreasing is 76%, which is determined by the optimal frequency pattern. In addition, we confirmed that forecasting of the sales frequency pattern at previous 1 tick shows higher accuracy than previous 2 tick and 3 tick.

• International Journal of Computer Science & Network Security
• /
• v.21 no.5
• /
• pp.23-30
• /
• 2021

In recent years, hazardous flash flooding has caused deaths and damage to infrastructure in Saudi Arabia. In this paper, our aim is to assess patterns and trends in climate means and extremes affecting flash flood hazards and water resources in Saudi Arabia for the purpose to improve risk assessment for forecast capacity. We would like to examine temperature, precipitation climatology and trend magnitudes at surface stations in Saudi Arabia. Based on the assessment climate patterns maps and trends are accurately used to identify synoptic situations and tele-connections associated with flash flood risk. We also study local and regional changes in hydro-meteorological extremes over recent decades through new applications of statistical methods to weather station data and remote sensing based precipitation products; and develop remote sensing based high-resolution precipitation products that can aid to develop flash flood guidance system for the flood-prone areas. A dataset of extreme events has been developed using the multi-decadal station data, the statistical analysis has been performed to identify tele-connection indices, pressure and sea surface temperature patterns most predictive to heavy rainfall. It has been combined with time trends in extreme value occurrence to improve the potential for predicting and rapidly detecting storms. A methodology and algorithms has been developed for providing a well-calibrated precipitation product that can be used in the early warning systems for elevated risk of floods.

• International Journal of Advanced Culture Technology
• /
• v.12 no.3
• /
• pp.434-440
• /
• 2024

SIZE KOREA updates body measurement data every five years, providing essential information for the fashion industry. This anthropometric data is widely used to diagnose consumer body shapes and develop optimal clothing sizes. Artificial intelligence, particularly machine learning, excels in predicting such body shape classifications. This study seeks to enhance the suitability of clothing design by applying the new analytical methodology of machine learning techniques to better capture and classify the unique body shapes of Korean women. In this study, machine learning techniques such as K-means clustering, Silhouette analysis, and Decision Tree analysis were used to classify the lower body shapes of Korean women in their twenties and identify standard body shapes useful for slacks design. The results showed that the lower body of the age group could be classified into three categories: 'small stature' (the majority), 'tall with an average lower body volume,' and 'medium height with a fuller lower body' (the smallest share). The three-cluster approach is validated through Silhouette analysis, which minimizes misclassification. Decision Tree analysis then further defines the criteria for these clusters, highlighting waist height and hip depth as the most significant factors, achieving a classification accuracy of 90.6%. While this study is not directly related to Robotic Process Automation, its detailed analysis of body shapes for slacks patterns can aid RPA in clothing production. Future research should continue integrating machine learning in human body and fashion design studies.

• Steel and Composite Structures
• /
• v.36 no.3
• /
• pp.261-272
• /
• 2020

A novel precast concrete-encased steel composite beam, which can be abbreviated as PCES beam, is introduced in this paper. In order to investigate the shear behavior of this PCES beam, a test of eight full-scale PCES beam specimens was carried out, in which the specimens were subjected to positive bending moment or negative bending moment, respectively. The factors which affected the shear behavior, such as the shear span-to-depth aspect ratio and the existence of concrete flange, were taken into account. During the test, the load-deflection curves of the test specimens were recorded, while the crack propagation patterns together with the failure patterns were observed as well. From the test results, it could be concluded that the tested PCES beams could all exhibit ductile shear behavior, and the innovative shear connectors between the precast concrete and cast-in-place concrete, namely the precast concrete transverse diaphragms, were verified to be effective. Then, based on the shear deformation compatibility, a theoretical model for predicting the shear capacity of the proposed PCES beams was put forward and verified to be valid with the good agreement of the shear capacities calculated using the proposed method and those from the experiments. Finally, in order to facilitate the preliminary design in practical applications, a simplified calculation method for predicting the shear capacity of the proposed PCES beams was also put forward and validated using available test results.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.91-98
• /
• 2023

With the increasing flood damage by frequently localized heavy rains, flood prediction research are being conducted to prevent flooding damage in advance. In this paper, we present a machine-learning scheme for developing a flooding depth and location prediction model using real-time rainfall data. This scheme proposes a dataset configuration method using the data as input, which can robustly configure various rainfall distribution patterns and train the model with less memory. These data are composed of two: valid total data and valid local. The one data that has a significant effect on flooding predicted the flooding location well but tended to have different values for predicting specific rainfall patterns. The other data that means the flood area partially affects flooding refers to valid local data. The valid local data was well learned for the fixed point method, but the flooding location was not accurately indicated for the arbitrary point method. Through this study, it is expected that a lot of damage can be prevented by predicting the depth and location of flooding in a real-time manner.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.6
• /
• pp.59-72
• /
• 2012

Since a protein displays its specific functions when disorder region of protein sequence transits to order region with provoking a biological reaction, the separation of disorder region and order region from the sequence data is urgently necessary for predicting three dimensional structure and characteristics of the protein. To classify the disorder and order region efficiently, this paper proposes a classification/prediction method using sequence data while acquiring a non-biased result on a specific characteristics of protein and improving the classification speed. The emerging patterns based EPs-TFP methods utilizes only the essential emerging pattern in which the redundant emerging patterns are removed. This classification method finds the sequence patterns of disorder region, such sequence patterns are frequently shown in disorder region but relatively not frequently in the order region. We expand P-tree and T-tree conceptualized TFP method into a classification/prediction method in order to improve the performance of the proposed algorithm. We used Disprot 4.9 and CASP 7 data to evaluate EPs-TFP technique, the results of order/disorder classification show sensitivity 73.6, specificity 69.51 and accuracy 74.2.

• Journal of Ecology and Environment
• /
• v.47 no.1
• /
• pp.1-13
• /
• 2023

Background: The positive effects of Arctic plants on the soil environment and plant-species co-occurrence patterns are known to be particularly important in physically harsh environments. Although three dominant plants (Cassiope tetragona, Dryas octopetala, and Silene acaulis) are abundant in the Arctic ecosystem at Ny-Ålesund, Svalbard, few studies have examined their occurrence patterns with other species and their buffering effect on soil-temperature and soil-moisture fluctuation. To quantify the plant-species co-occurrence patterns and their positive effects on soil environments, I surveyed the vegetation cover, analyzed the soil-chemical properties (total carbon, total nitrogen, pH, and soil organic matter) from 101 open plots, and measured the daily soil-temperature and soil-moisture content under three dominant plant patches and bare soil. Results: The Cassiope tetragona and Dryas octopetala communities increased the soil-temperature stability; however, the three dominant plant communities did not significantly affect the soil-moisture stability. Non-metric multidimensional scaling separated the sampling sites into three groups based on the different vegetation compositions. The three dominant plants occurred randomly with other species; however, the vegetation composition of two positive co-occurring species pairs (Oxyria digyna-Cerastium acrticum and Luzula confusa-Salix polaris) was examined. The plant species richness did not significantly differ in the three plant communities. Conclusions: The three plant communities showed distinctive vegetation compositions; however, the three dominant plants were randomly and widely distributed throughout the study sites. Although the facilitative effects of the three Arctic plants on increases in the soil-moisture fluctuation and richness were not quantified, this research enables a deeper understanding of plant co-occurrence patterns in Arctic ecosystems and thereby contributes to predicting the shift in vegetation composition and coexistence in response to climate warming. This research highlights the need to better understand plant-plant interactions within tundra communities.