KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 7 of 7

Some of the metrics are blocked by your
consent settings
A COMPARATIVE APPROACH TO SVM KERNEL FUNCTIONS VIA ACCURATE EVALUATING ALGORITHMS
(2023-08-01)
Nurhidayat, Irfan
;
Pimpunchat, Busayamas
The Accurate Evaluation Algorithm in R Programming is used to assess the feasibility of classification using the SVM Radial Basis Function (RBF) kernel method. This algorithm encompasses some statistical tools. Among the various scenarios for improving dataset accuracy, employing the accurate evaluating algorithm before classifying with the SVM RBF kernel method is crucial. The current objective is to achieve an enhanced accuracy of up to 83% by leveraging this algorithm. The significance of this research lies in the development of an accurate evaluation algorithm for data analysis and its application using the SVM RBF kernel method. This contribution provides a solution for players in the digital insurance business within the data processing industry. The novelty lies in the accurate evaluating algorithm, which is thoroughly explained alongside simulation graphs for sum insured data. The accuracy comparisons based on the root-mean-square error (RMSE) and density are extensively investigated. The results conclude that employing this algorithm leads to more accurate data analysis (83% accuracy).
Some of the metrics are blocked by your
consent settings
Comparisons of SVM Kernels for Insurance Data Clustering
(2022-08-01)
Nurhidayat, Irfan
;
Pimpunchat, Busayamas
;
Noeiaghdam, Samad
;
Fernández-Gámiz, Unai
This paper will study insurance data clustering using Support Vector Machine (SVM) approaches. It investigates the optimum condition employing the three most popular kernels of SVM, i.e., linear, polynomial, and radial basis kernel. To explore sum insured datasets, kernel comparisons for Root Mean Square Error (RMSE) and density analysis have been provided. It employs these kernels to classify based on sum insured datasets. The objective of this research is to demonstrate to industrial researchers that data grouping may be accomplished in an organized, error-free, and efficient manner utilizing R programming and the SVM approach. In this study, we check the insurance data for the sum insured with statistical methods in the form of Model Performance Evaluation (MPE), Receiver Operating Characteristics (ROC), Area Under Curve (AUC), partial AUC (pAUC), smoothing, confidence intervals, and thresholds. Then, sum insured data are followed up to classify using SVM kernels. This paper finds new ideas for evaluating insurance data using the SVM approach with multiple kernels. This novel research emphasizes the statistical analysis methods for insurance data and uses the SVM method for more accurate data classification. Finally, it informs that this research is a pure finding, and there has never been any research on this subject. This research was conducted using the sum insured data as a sample from the Office of the Insurance Commission (OIC) in Thailand as an independent insurance institution providing actual data.
Some of the metrics are blocked by your
consent settings
Comparison of Performance of 1D5P with 2 Input and 1 Input Model in Forecasting of Power Output for Photovoltaic Systems
(2018-07-02)
Dawan, Promphak
;
Kittisontirak, Songkiate
;
Sriprapha, Kobsak
;
Muanglua, Rangson
;
Titiroongruang, Wisut
This paper presents the comparison on forecasting performance of power output for photovoltaic system type 1D \pmb{5}\mathbf{P}, which used 1 input parameter being solar irradiance and 2 input parameters consisting of solar irradiance and the temperature model. The result shows that the forecasting of power output for photovoltaic system type 1D5P, which used 1 input parameter, provided root-mean-square deviation (RMSE) at 0.04 and for 2 input parameters provided RMSE at 0.05.
Some of the metrics are blocked by your
consent settings
The analysis of dynamic O/D adjustment for bicycle traffic demand estimation with aimsun simulation model: A case study of nakhon sawan municipality in Thailand
(2018-01-01)
Chalermwongphan, Karn
;
Upala, Prapatpong
Aim: This research aimed to present the process of estimating bicycle traffic demand in order to design bike routes that meet the daily transportation needs of the people in Nakhon Sawan Municipality. Methods: The primary and secondary traffic data were collected to develop a virtual traffic simulation model with the use of the AIMSUN simulation software. The model validation method was carried out to adjust the origin and destination survey data (O/D matrix) by running dynamic O/D adjustment. The 99 replication scenarios were statistically examined and assessed using the goodness-of-fit test. The 9 measures, which were examined, included: 1) Root Mean Square Error (RMSE), 2) Root Mean Square Percentage Error (RMSPE%), 3) Mean Absolute Deviation (MAD), 4) Mean Bias Error (MBE), 5) Mean Percentage Error (MPE%), 6) Mean Absolute Percentage Error (MAPE%), 7) Coefficient of Determination (R2), 8) GEH Statistic (GEH), and 9) Thiel’s U Statistic (Theil’s U). Results: The resulting statistical values were used to determine the acceptable ranges according to the acceptable indicators of each factor. Conclusion: It was found that there were only 8 scenarios that met the evaluation criteria. The selection and ranking process was consequently carried out using the multi-factor scoring method, which could eliminate errors that might arise from applying only one goodness-offit test measure.
Some of the metrics are blocked by your
consent settings
A simplified model for the estimation of energy production of PV Module
(2017-10-19)
Bupi, Aekkawat
;
Kittisontirak, Songkiate
;
Sriprapha, Kobsak
;
Siriwongrungsan, Wilailak
;
Titiroongruang, Wisut
This paper describes the objective of the model to produce electricity from solar cell applications MATLAB / SIMULINK Compared with the data of electricity from photovoltaic power systems in Cambodia. Using models 1D5P (equivalent circuit analysis of one of the diodes, solar cells based on 5 parameters are the main factors in the equation that represents the equivalent circuit). 2 parameters are used to simulate the solar irradiance and module temperature from the retention of a calculation to determine the solar farm to generate electricity. And compared with the actual electricity. By comparing the results of the simulation with high accuracy. And display of the RMSE range of 0.01 to 0.18 and with an average of RMSE is 0.09.
Some of the metrics are blocked by your
consent settings
Comparison of PV module power output measurements
(2017-10-19)
Bupi, Aekkawat
;
Kittisontirak, Songkiate
;
Sriprapha, Kobsak
;
Suriyaammaranon, Chabar
;
Titiroongruang, Wisut
This paper describes the objective of the model to produce electricity from solar program. MATLAB / SIMULINK Compared with actual production data from electricity plants. This information is taken from the program PVSYST (crawlers electricity from real factories). The models created from an analysis of the equivalent circuit model of a diode, solar cell, with 5 parameters are the main factors used in the calculations were called 1 D5 P. The comparison takes into account the impact on solar irradiance and module temperature. The result of the comparison. The model has high accuracy and is close to the actual data to generate electricity.
Some of the metrics are blocked by your
consent settings
Estimation of solar radiation based on air temperature and application with the DSSAT v4.5 peanut and rice simulation models in Thailand
(2013-10-15)
Phakamas, Nittaya
;
Jintrawet, Attachai
;
Patanothai, Aran
;
Sringam, Prakan
;
Hoogenboom, Gerrit
Estimation of solar radiation (SRAD) from daily air temperature by the modified Bristow-Campbell (B-C) model requires three empirical coefficients that are area specific. Previous estimates of these coefficients for Thailand were based on limited data without any evaluation. Accurate estimation of solar radiation has become more important with the wider application of environmental models. The objective of this study was to calibrate and evaluate the coefficients for Thailand with a broader range of data. Meteorological data from 2008 to 2011 were obtained from eight weather stations, three in the North (Chiang Mai, Chiang Rai and Nakhon Sawan), two in the Northeast (Khon Kaen and Ubon Ratchathani), one in the Central (Lop Buri) and two in the South (Chumporn and Surat Thani). Data for 2010 for all locations except Chiang Rai were used for calibration of the coefficients and the remaining data were used as independent data sets for evaluation. The coefficient of determination (R2), root mean square error (RMSE) and normalized root mean square error (RMSEn) were used as indicators of the agreement between the observed and the calculated SRAD. The results showed that the calibration was acceptable (R2=0.56, RMSE=3.07MJm-2d-1 and RMSEn=17.5%). The derived values are a=0.63, b=1.89 and c=1.54. These new coefficients performed well during evaluation with the 13 independent data sets from the eight locations for all four regions, with the R2, RMSE and RMSEn values in the range of 0.39-0.70, 2.42-3.79MJm-2d-1 and 14.0-21.7%, respectively. In addition, simulations using estimated SRAD from the derived values provided high R2 values for peanut and rice yield and total dry matter. These new coefficient values can be used to estimate solar radiation from air temperature data for all locations in Thailand and similar environments in Southeast Asia. © 2013 Elsevier B.V.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results