• Journal of Korea Water Resources Association
• /
• v.46 no.8
• /
• pp.857-871
• /
• 2013

The interest in rainfall observation and forecasting using remote sensing method like RADAR (Radio Detection and Ranging) and satellite image is increased according to increased damage by rapid weather change like regional torrential rain and flash flood. In this study, the basin runoff was calculated using adaptive neuro-fuzzy technique, one of the data driven model and MAPLE (McGill Algorithm for Precipitation Nowcasting by Lagrangian Extrapolation) forecasted precipitation data as one of the input variables. The flood estimation method using neuro-fuzzy technique and RADAR forecasted precipitation data was evaluated. Six rainfall events occurred at flood season in 2010 and 2011 in Chungju Reservoir basin were used for the input data. The flood estimation results according to the rainfall data used as training, checking and testing data in the model setup process were compared. The 15 models were composed of combination of the input variables and the results according to change of clustering methods were compared and analysed. From this study was that using the relatively larger clustering radius and the biggest flood ever happened for training data showed the better flood estimation. The model using MAPLE forecasted precipitation data showed relatively better result at inflow estimation Chungju Reservoir.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.21 no.4
• /
• pp.437-448
• /
• 2015

In this paper, smartphone based measuring device was developed by integration of several sonsors such as moving, temperature, pulsation, respiration and hearing and sever/client programs was developed for the data acquisition and communication between smartphone and server computer. Then, the concept of CSI(combined safety index) was proposed for the comprehensive diagnositcs of workers status. For the validation of the proposed concept, the real data was acquired by boarding at training ship of korea maritime and ocean university. The acquired data was analyzed with the stochastical method of regressionn, then the meaningful result was driven that could explain the relation between the risky situation and the measured chronical data.

• Tribology and Lubricants
• /
• v.22 no.4
• /
• pp.190-195
• /
• 2006

A simple and effective analysis method is presented for gaining a complete transient temperatures on the internal and external surfaces of a 40 mm gun tube subjected to a series of rapid firings. Two series of temperature data for both Hs and As were measured by using two rapid response k-type surface thermocouples near the firing origin and the muzzle. With other available temperature data, patterns of temperature variations of the gun tube as a function of time variable were driven through complete evaluations of the data. It is found that overall temperature gradients which increase exponentially toward saturation temperature, actually consist of a series of linear temperature gradients corresponding to the firing sequences. Under the similar firing sequences, patterns of temperature variations fur both the surface temperatures near the chamber and those near the muzzle were found to have linear temperature gradients with different values and the same response frequencies, i.e. they had peaks and lows in temperatures at the same time. The resultant complete temperature data can be used as the fundamental bases for analysis of thermoelastic properties of the materials such as thermal strain and stress, and f3r the prediction of cannon tube life-time through calculation of wear rate.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.11
• /
• pp.101-105
• /
• 2012

Various social problems through violating personal information and privacy are growing with the rapid spread of smartphones. For this reason, variety of researches and technology developments to protect personal information being made. The smartphone, contains almost all of the personal information, can cause data spill at any time. Collecting or analyzing evidence is not an easy job with forensic analyzing tool. Android forensics research has been focused on techniques to collect and analyze data from non-volatile memory but research for volatile data is very slight. Android log is the non-volatile data that can be collected by volatile storage. It is enough to use as a material to track the usage of the Android phone because all of the recent driven records from system to application are stored. In this paper, we propose a method to respond to determining the existence of personal information leakage by filtering logs without forensic analysis tools.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.7
• /
• pp.303-310
• /
• 2019

In the current mobile environment that is indispensable to our everyday lives, various forms of new business models are created including personalized services such as Google's "Google NOW" and Apple's "Siri". These services would not have been possible without technologies on the effective integration of various services and models. The requirements for effective integration of services include, 1) the efficient data sharing among multiple services, 2) the data-driven asynchronous execution of services, and 3) the simple extensible interaction method for the services. In this paper, we propose a mobile service architecture that utilizes the blackboard architecture to satisfy the aforementioned requirements to enable effective integration of various services, sharing and management of data between services, and asynchronous execution of services.

• Journal of the Korean Geotechnical Society
• /
• v.25 no.12
• /
• pp.107-118
• /
• 2009

As CPT penetration tends to show a similar behavior to that of pile driving, a number of methods for estimating the toe bearing capacity of piles based on CPT data have been proposed. To evaluate the applicability of the methods in this country, a total of 172 dynamic load tests data on PHC piles and 82 CPT data at a site in the Nakdong River estuary were collected. A specific four-step procedure was adopted for the selection of the reliable data, and statistical techniques were then applied to the analysis of the applicability. The results indicated that among a total of 10 CPT-based methods applied, the best one is the Aoki method (1975), followed by the LCPC (1982), ICP (2005) methods and others.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3330-3344
• /
• 2023

This paper proposes an antenna performance prediction model in the autonomous driving radar manufacturing process. Our research work is based upon a challenge dataset, Driving Radar Manufacturing Process Dataset, and a typical AutoML machine learning workflow engine, Pycaret open-source Python library. Note that the dataset contains the total 70 data-items, out of which 54 used as input features and 16 used as output features, and the dataset is properly built into resolving the multi-output regression problem. During the data regression analysis and preprocessing phase, we identified several input features having similar correlations and so detached some of those input features, which may become a serious cause of the multicollinearity problem that affect the overall model performance. In the training phase, we train each of output-feature regression models by using the AutoML approach. Next, we selected the top 5 models showing the higher performances in the AutoML result reports and applied the ensemble method so as for the selected models' performances to be improved. In performing the experimental performance evaluation of the regression prediction model, we particularly used two metrics, MAE and RMSE, and the results of which were 0.6928 and 1.2065, respectively. Additionally, we carried out a series of experiments to verify the proposed model's performance by comparing with other existing models' performances. In conclusion, we enhance accuracy for safer autonomous vehicles, reduces manufacturing costs through AutoML-Pycaret and machine learning ensembled model, and prevents the production of faulty radar systems, conserving resources. Ultimately, the proposed model holds significant promise not only for antenna performance but also for improving manufacturing quality and advancing radar systems in autonomous vehicles.

• Atmosphere
• /
• v.17 no.2
• /
• pp.125-133
• /
• 2007

Cloud amount calculation algorithm was developed using MTSAT-1R satellite data. The cloud amount is retrieved at 5 km ${\times}$ 5 km over the Korean Peninsula and adjacent sea area. The algorithm consists of three steps that are cloud detection, cloud type classification, and cloud amount calculation. At the first step, dynamic thresholds method was applied for detecting cloud pixels. For using objective thresholds in the algorithm, sensitivity test was performed for TBB and Albedo variation with temporal and spatial change. Detected cloud cover was classified into 3 cloud types (low-level cloud, cirrus or uncertain cloud, and cumulonimbus type high-level cloud) in second step. Finally, cloud amount was calculated by the integration method of the steradian angle of each cloud pixel over $3^{\circ}$ elevation. Calculated cloud amount was compared with measured cloud amount with eye at surface observatory for the validation. Bias, RMSE, and correlation coefficient were 0.4, 1.8, and 0.8, respectively. Validation results indicated that calculated cloud amount was a little higher than measured cloud amount but correlation was considerably high. Since calculated cloud amount has 5km ${\times}$ 5km resolution over Korean Peninsula and adjacent sea area, the satellite-driven cloud amount could show the possibility which overcomes the temporal and spatial limitation of measured cloud amount with eye at surface observatory.

• Journal of the Korea Computer Graphics Society
• /
• v.15 no.1
• /
• pp.7-15
• /
• 2009

In this paper, a novel framework that synthesizes and clones facial expression in parameter spaces is presented. To overcome the difficulties in manipulating face geometry models with high degrees of freedom, many parameterization methods have been introduced. In this paper, a data-driven parameterization method is proposed that represents a variety of expressions with a small set of fundamental independent movements based on the ICA technique. The face deformation due to the parameters is also learned from the data to capture the nonlinearity of facial movements. With this parameterization, one can control the expression of an animated character's face by the parameters. By separating the parameterization and the deformation learning process, we believe that we can adopt this framework for a variety applications including expression synthesis and cloning. The experimental result demonstrates the efficient production of realistic expressions using the proposed method.

• Journal of Korean Society for Quality Management
• /
• v.49 no.3
• /
• pp.421-431
• /
• 2021

Purpose: For improving outgoing quality, this study presents a novel sampling framework based on predictive analytics. Methods: The proposed framework is composed of three steps. The first step is the variable selection. The knowledge-based and data-driven approaches are employed to select important variables. The second step is the model learning. In this step, we consider the supervised classification methods, the anomaly detection methods, and the rule-based methods. The applying model is the third step. This step includes the all processes to be enabled on real-time prediction. Each prediction model classifies a product as a target sample or random sample. Thereafter intensive quality inspections are executed on the specified target samples. Results: The inspection data of three Samsung products (mobile, TV, refrigerator) are used to check functional defects in the product by utilizing the proposed method. The results demonstrate that using target sampling is more effective and efficient than random sampling. Conclusion: The results of this paper show that the proposed method can efficiently detect products that have the possibilities of user's defect in the lot. Additionally our study can guide practitioners on how to easily detect defective products using stratified sampling