• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.436-454
• /
• 2016

This research presents the battery discharge rate models for the energy consumption of mobile phone batteries based on machine learning by taking into account three usage patterns of the phone: the standby state, video playing, and web browsing. We present the experimental design methodology for collecting data, preprocessing, model construction, and parameter selections. The data is collected based on the HTC One X hardware platform. We considered various setting factors, such as Bluetooth, brightness, 3G, GPS, Wi-Fi, and Sync. The battery levels for each possible state vector were measured, and then we constructed the battery prediction model using different regression functions based on the collected data. The accuracy of the constructed models using the multi-layer perceptron (MLP) and the support vector machine (SVM) were compared using varying kernel functions. Various parameters for MLP and SVM were considered. The measurement of prediction efficiency was done by the mean absolute error (MAE) and the root mean squared error (RMSE). The experiments showed that the MLP with linear regression performs well overall, while the SVM with the polynomial kernel function based on the linear regression gives a low MAE and RMSE. As a result, we were able to demonstrate how to apply the derived model to predict the remaining battery charge.

• Communications for Statistical Applications and Methods
• /
• v.16 no.1
• /
• pp.127-135
• /
• 2009

It is necessary to forecast the amount of the maximum electricity demand for stabilizing the flow of electricity. The time series data was collected from the Korea Energy Research between January 2000 and December 2006. The data showed that they had a strong linear trend and seasonal change. Winters seasonal model, ARMA model were used to examine it. Root mean squared prediction error and mean absolute percentage prediction error were a criteria to select the best model. In addition, a nonstationary generalized extreme value distribution with explanatory variables was fitted to forecast the maximum electricity.

• ETRI Journal
• /
• v.25 no.2
• /
• pp.109-120
• /
• 2003

Though the airborne laser scanning (ALS) technique is becoming more popular in many applications, horizontal accuracy of points scanned by the ALS is not yet satisfactory when compared with the accuracy achieved for vertical positions. One of the major reasons is the drift that occurs in the inertial measurement unit (IMU) during the scanning. This paper presents an algorithm that adjusts for the error that is introduced mainly by the drift of the IMU that renders systematic differences between strips on the same area. For this, we set up an observation equation for strip-wise adjustments and completed it with tie point and control point coordinates derived from the scanned strips and information from aerial photos. To effectively capture the tie points, we developed a set of procedures that constructs a digital surface model (DSM) with breaklines and then performed feature-based matching on strips resulting in a set of reliable tie points. Solving the observation equations by the least squares method produced a set of affine transformation equations with 6 parameters that we used to transform the strips for adjusting the horizontal error. Experimental results after evaluation of the accuracy showed a root mean squared error (RMSE) of the adjusted strip points of 0.27 m, which is significant considering the RMSE before adjustment was 0.77 m.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.1205-1215
• /
• 2017

In this paper, we aim to estimate two scale-parameters of exponentiated Pareto distribution (EPD) based on lower record values. Record values arise naturally in many real life applications involving data relating to weather, sport, economics and life testing studies. We calculate the Bayesian estimators for the two parameters of EPD based on lower record values. The Bayes estimators of two parameters for the EPD with lower record values under the squared error loss (SEL), linex loss (LL) and entropy loss (EL) functions are provided. Lindley's approximate method is used to compute these estimators. We compare the Bayesian estimators in the sense of the bias and root mean squared estimates (RMSE).

• Journal of the Korea Institute of Military Science and Technology
• /
• v.15 no.2
• /
• pp.155-160
• /
• 2012

In this paper, a strip modeling method is developed for the acquisition of target positions in remote area and validated using the imagery of SPOT satellite. This method utilizes the parameters given in header files and constructs a camera model without ground control points. In most cases, the root mean squared error of check points is less than pixel size with one ground control point. The model error of reference image is evaluated using ground control points and used to remove the model error of target images acquired along the same satellite orbit, which enables one to calculate target positions in remote area where no ground control points are available.

• The Korean Journal of Applied Statistics
• /
• v.28 no.1
• /
• pp.75-82
• /
• 2015

We discuss confidence intervals for sensitive binomial attributes obtained by a direct question method and indirect question method. The Randomized Response Technique(RRT) by Warner (1965) is an indirect question method that uses a randomization device to reduce the response burden of respondents. We used the mean coverage probability (MCP), root mean squared error (RMSE), and mean expected width (MEW) to compare the confidence intervals by the two methods. The numerical comparisons indicated found that the MEW of RRT is too large and the RRT is so conservative that the MCP exceeds a nominal level(${\alpha}$); therefore, it is necessary to complement these problem in order to increase the utility of the indirect question method.

• Journal of Korea Water Resources Association
• /
• v.55 no.11
• /
• pp.855-863
• /
• 2022

In this study, the Artificial Neural Network (ANN) was used to mapping air temperature in Seoul. MODerate resolution Imaging Spectroradiomter (MODIS) data was used as auxiliary data for mapping. For the ANN network topology optimizing, scatterplots and statistical analysis were conducted, and input-data was classified and combined that highly correlated data which surface temperature, Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), time (satellite observation time, Day of year), location (latitude, hardness), and data quality (cloudness). When machine learning was conducted only with data with a high correlation with air temperature, the average values of correlation coefficient (r) and Root Mean Squared Error (RMSE) were 0.967 and 2.708℃. In addition, the performance improved as other data were added, and when all data were utilized the average values of r and RMSE were 0.9840 and 1.883℃, which showed the best performance. In the Seoul air temperature map by the ANN model, the air temperature was appropriately calculated for each pixels topographic characteristics, and it will be possible to analyze the air temperature distribution in city-level and national-level by expanding research areas and diversifying satellite data.

• Journal of Navigation and Port Research
• /
• v.47 no.6
• /
• pp.376-385
• /
• 2023

Fishing boat capsizing accidents account for more than half of all capsize accidents. These can occur for a variety of reasons, including inexperienced operation, bad weather, and poor maintenance. Due to the size and influence of the industry, technological complexity, and regional diversity, fishing ships are relatively under-researched compared to commercial ships. This study aimed to predict the rolling motion time series of fishing boats using an image-based deep learning model. Image-based deep learning can achieve high performance by learning various patterns in a time series. Three image-based deep learning models were used for this purpose: Xception, ResNet50, and CRNN. Xception and ResNet50 are composed of 177 and 184 layers, respectively, while CRNN is composed of 22 relatively thin layers. The experimental results showed that the Xception deep learning model recorded the lowest Symmetric mean absolute percentage error(sMAPE) of 0.04291 and Root Mean Squared Error(RMSE) of 0.0198. ResNet50 and CRNN recorded an RMSE of 0.0217 and 0.022, respectively. This confirms that the models with relatively deeper layers had higher accuracy.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.1870-1875
• /
• 2006

This study was carried out to investigate the applicability of SAC-SMA model with parameters which were derived from analytical relationships proposed by Koren etc. (2000), with various data of soil properties in a basin. The studied basin is Yongdam dam basin and the daily runoff with 2003-year hydrological data was simulated. Simulated runoff results were compared with those measured at three check points(Chuchun, Donhyang and Yongdam) and analyzed through the statistical techniques such as VE(Volume Error), RMSE(Root Mean Squared Error) and CORR(Correlation). As a result of analyses, the good agreement was obtained between simulated and measured results.

• Journal of Environmental Science International
• /
• v.21 no.6
• /
• pp.695-704
• /
• 2012

The application of disinfection models on the plasma process was investigated. Nine empirical models were used to find an optimum model. The variation of parameters in model according to the operating conditions (first voltage, second voltage, air flow rate, pH) were investigated in order to explain the disinfection model. In this experiment, the DBD (dielectric barrier discharge) plasma reactor was used to inactivate Ralstonia Solanacearum which cause wilt in tomato plantation. Optimum disinfection models were chosen among the nine models by the application of statistical SSE (sum of squared error), RMSE (root mean sum of squared error), $r^2$ values on the experimental data using the GInaFiT software in Microsoft Excel. The optimum model was shown as Weibull+talil model followed by Log-linear+ Shoulder+Tail model. Two models were applied to the experimental data according to the variation of the operating conditions. In Weibull+talil model, Log10($N_o$), Log10($N_{res}$), ${\delta}$ and p values were examined. And in Log-linear+Shoulder+Tail model, the Log10($N_o$), Log10($N_{res}$), $k_{max}$, Sl values were calculated and examined.