• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.12-15
• /
• 2020

Data access characteristics can directly affect the efficiency of the system execution. This research is to design an accurate predictor by using historical memory access information, where highly accessible data can be migrated from low-speed storage (SSD/HHD) to high-speed memory (Memory/CPU Cache) in advance, thereby reducing data access latency and further improving overall performance. For this goal, we design a locally weighted linear regression prefetch scheme to cope with irregular access patterns in large graph processing applications for a DARM-PCM hybrid memory structure. By analyzing the testing result, the appropriate structural parameters can be selected, which greatly improves the cache prefetching performance, resulting in overall performance improvement.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.24 no.4
• /
• pp.44-52
• /
• 2016

The departure flow management is the planning tool to optimize the schedule of the departure aircraft and allows them to join smoothly into the overhead traffic flow. To that end, the arrival time prediction to the merge point for the cruising aircraft is necessary to determined. This paper proposes a trajectory prediction model for the cruising aircraft based on the machine learning approach. The proposed method includes the trajectory vectored from the procedural route and is applied to the historical data to evaluate the prediction performances.

• Journal of the Korean Statistical Society
• /
• v.27 no.1
• /
• pp.91-100
• /
• 1998

A method of estimating probability density using regression tools is presented here. It is based on equal-length binning and locally weighted approximate likelihood for bin counts. The method is particularly useful for densities with bounded supports, where it automatically corrects edge effects without using boundary kernels.

• Geomechanics and Engineering
• /
• v.34 no.5
• /
• pp.507-527
• /
• 2023

Accurately estimation of the geo-mechanical parameters in Artificial Ground Freezing (AGF) is a most important scientific topic in soil improvement and geotechnical engineering. In order for this, one way is using classical and conventional constitutive models based on different theories like critical state theory, Hooke's law, and so on, which are time-consuming, costly, and troublous. The others are the application of artificial intelligence (AI) techniques to predict considered parameters and behaviors accurately. This study presents a comprehensive data-mining-based model for predicting the Young's Modulus of frozen sand under the triaxial test. For this aim, several single and hybrid models were considered including additive regression, bagging, M5-Rules, M5P, random forests (RF), support vector regression (SVR), locally weighted linear (LWL), gaussian process regression (GPR), and multi-layered perceptron neural network (MLP). In the present study, cell pressure, strain rate, temperature, time, and strain were considered as the input variables, where the Young's Modulus was recognized as target. The results showed that all selected single and hybrid predicting models have acceptable agreement with measured experimental results. Especially, hybrid Additive Regression-Gaussian Process Regression and Bagging-Gaussian Process Regression have the best accuracy based on Model performance assessment criteria.

• Computers and Concrete
• /
• v.21 no.4
• /
• pp.407-417
• /
• 2018

Concrete which is a composite material is one of the most important construction materials. Compressive strength is a commonly used parameter for the assessment of concrete quality. Accurate prediction of concrete compressive strength is an important issue. In this study, we utilized an experimental procedure for the assessment of concrete quality. Firstly, the concrete mix was prepared according to C 20 type concrete, and slump of fresh concrete was about 20 cm. After the placement of fresh concrete to formworks, compaction was achieved using a vibrating screed. After 28 day period, a total of 100 core samples having 75 mm diameter were extracted. On the core samples pulse velocity determination tests and compressive strength tests were performed. Besides, Windsor probe penetration tests and Schmidt hammer tests were also performed. After setting up the data set, twelve artificial intelligence (AI) models compared for predicting the concrete compressive strength. These models can be divided into three categories (i) Functions (i.e., Linear Regression, Simple Linear Regression, Multilayer Perceptron, Support Vector Regression), (ii) Lazy-Learning Algorithms (i.e., IBk Linear NN Search, KStar, Locally Weighted Learning) (iii) Tree-Based Learning Algorithms (i.e., Decision Stump, Model Trees Regression, Random Forest, Random Tree, Reduced Error Pruning Tree). Four evaluation processes, four validation implements (i.e., 10-fold cross validation, 5-fold cross validation, 10% split sample validation & 20% split sample validation) are used to examine the performance of predictive models. This study shows that machine learning regression techniques are promising tools for predicting compressive strength of concrete.

• The Journal of Korea Robotics Society
• /
• v.8 no.1
• /
• pp.20-28
• /
• 2013

Large workspace and strong grasping force are required when a robot manipulates big and/or heavy objects. In that situation, bimanual manipulation is more useful than unimanual manipulation. However, the control of both hands to manipulate an object requires a more complex model compared to unimanual manipulation. Learning by human demonstration is a useful technique for a robot to learn a model. In this paper, we propose an imitation learning method of bimanual object manipulation by human demonstrations. For robust imitation of bimanual object manipulation, movement trajectories of two hands are encoded as a movement trajectory of the object and a force trajectory to grasp the object. The movement trajectory of the object is modeled by using the framework of dynamic movement primitives, which represent demonstrated movements with a set of goal-directed dynamic equations. The force trajectory to grasp an object is also modeled as a dynamic equation with an adjustable force term. These equations have an adjustable force term, where locally weighted regression and multiple linear regression methods are employed, to imitate complex non-linear movements of human demonstrations. In order to show the effectiveness our proposed method, a movement skill of pick-and-place in simulation environment is shown.

• Journal of Medicine and Life Science
• /
• v.20 no.3
• /
• pp.107-114
• /
• 2023

Epidemiological control of coronavirus disease 2019 (COVID-19) is needed to estimate the infection period of confirmed cases and identify potential cases. The present study, targeting confirmed cases for which the time of COVID-19 symptom onset was disclosed, aimed to investigate the relationship between intervals (day) from symptom onset to testing the cycle threshold (CT) values of real-time reverse transcription-polymerase chain reaction. Of the COVID-19 confirmed cases, those for which the date of suspected symptom onset in the epidemiological investigation was specifically disclosed were included in this study. Interval was defined as the number of days from symptom onset (as disclosed by the patient) to specimen collection for testing. A locally weighted regression smoothing (LOWESS) curve was applied, with intervals as explanatory variables and CT values (CTR for RdRp gene and CTE for E gene) as outcome variables. After finding its non-linear relationship, a polynomial regression model was applied to estimate the 95% confidence interval values of CTR and CTE by interval. The application of LOWESS in 331 patients identified a U-shaped curve relationship between the CTR and CTE values according to the number of interval days, and both CTR and CTE satisfied the quadratic model for interval days. Active application of these results to epidemiological investigations would minimize the chance of failing to identify individuals who are in contact with COVID-19 confirmed cases, thereby reducing the potential transmission of the virus to local communities.

• Journal of Korea Water Resources Association
• /
• v.43 no.12
• /
• pp.1083-1091
• /
• 2010

Distributed hydrologic models typically require spatial estimates of precipitation interpolated from sparsely located observational points to the specific grid points. However, widely used estimation schemes fail to describe the realistic variability of daily precipitation field. We compare and contrast the performance of statistical methods for the spatial estimation of precipitation in two hydrologically different basins, and propose a two-step process for effective daily precipitation estimation. The methods assessed are: (1) Inverse Distance Weighted Average (IDW); (2) Multiple Linear Regression (MLR); (3) Climatological MLR; and (4) Locally Weighted Polynomial Regression (LWP). In the suggested simple two-step estimation process, precipitation occurrence is first generated via a logistic regression model before applying IDW scheme (one of the local scheme) to estimate the amount of precipitation separately on wet days. As the results, the suggested method shows the better performance of daily rainfall interpolation which has spatial differences compared with conventional methods. And this technique can be used for streamflow forecasting and downscaling of atmospheric circulation model effectively.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.5 no.3
• /
• pp.76-85
• /
• 2024

The purpose of this study is to propose a new method of analysis focusing on interconnections between species rather than traditional biodiversity analysis, which represents ecosystems in terms of species and individual counts such as species diversity and species richness. This new approach aims to enhance our understanding of ecosystem networks. Utilizing data from the 4th National Natural Environment Survey (2014-2018), the following eight taxonomic groups were targeted for our study: herbaceous plants, woody plants, butterflies, Passeriformes birds, mammals, reptiles & amphibians, freshwater fishes, and benthonic macroinvertebrates. A co-occurrence frequency analysis was conducted using nationwide data collected over five years. As a result, in all eight taxonomic groups, the degree value represented by a linear regression trend line showed a slope of 0.8 and the weighted degree value showed an exponential nonlinear curve trend line with a coefficient of determination (R²) exceeding 0.95. The average value of the clustering coefficient was also around 0.8, reminiscent of well-known social phenomena. Creating a combination set from the species list grouped by temporal information such as survey date and spatial information such as coordinates or grids is an easy approach to discern species distributed regionally and locally. Particularly, grouping by species or taxonomic groups to produce data such as co-occurrence frequency between survey points could allow us to discover spatial similarities based on species present. This analysis could overcome limitations of species data. Since there are no restrictions on time or space, data collected over a short period in a small area and long-term national-scale data can be analyzed through appropriate grouping. The co-occurrence frequency analysis enables us to measure how many species are associated with a single species and the frequency of associations among each species, which will greatly help us understand ecosystems that seem too complex to comprehend. Such connectivity data and graphs generated by the co-occurrence frequency analysis of species are expected to provide a wealth of information and insights not only to researchers, but also to those who observe, manage, and live within ecosystems.