• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• Progress in Medical Physics
• /
• v.34 no.3
• /
• pp.23-32
• /
• 2023

Purpose: In radiomics analysis, to evaluate features, and predict genetic characteristics and survival time, the pixel values of lesions depicted in computed tomography (CT) and magnetic resonance imaging (MRI) images are used. CT and MRI offer three-dimensional images, thus producing three-dimensional features (Features_3d) as output. However, in reports, the superiority between Features_3d and two-dimensional features (Features_2d) is distinct. In this study, we aimed to investigate whether a difference exists in the prediction accuracy of radiomics analysis of lung cancer using Features_2d and Features_3d. Methods: A total of 38 cases of large cell carcinoma (LCC) and 40 cases of squamous cell carcinoma (SCC) were selected for this study. Two- and three-dimensional lesion segmentations were performed. A total of 774 features were obtained. Using least absolute shrinkage and selection operator regression, seven Features_2d and six Features_3d were obtained. Results: Linear discriminant analysis revealed that the sensitivities of Features_2d and Features_3d to LCC were 86.8% and 89.5%, respectively. The coefficients of determination through multiple regression analysis and the areas under the receiver operating characteristic curve (AUC) were 0.68 and 0.70 and 0.93 and 0.94, respectively. The P-value of the estimated AUC was 0.87. Conclusions: No difference was found in the prediction accuracy for LCC and SCC between Features_2d and Features_3d.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.9
• /
• pp.535-547
• /
• 2014

We investigate BER (Bit Error Ratio) performance according to the gain of spatial and frequency diversities in uplink SC-FDMA of SIMO (Single Input Multiple Output) systems. The main results of the analysis in this paper are as follows. First, we prove that performance of integrated system for considering spatial and frequency diversity combining in parallel is equivalent with the performance of sequential system for performing diversity combining in sequence. By signal modeling, it is demonstrated that the performances of both systems are the same when the frequency diversity combining technique of the sequential system is equal to diversity combining technique of the integrated system, and spatial diversity combining technique of the sequential system is performed as MRC in advance of frequency diversity combining. Secondly, it is found that effect on the BER performance is different according to the gain of spatial and frequency diversities, respectively. The frequency diversity gain increases by increasing the number of subcarrier. It might affect the performance improvement of high SNR(Signal to Noise Ratio) while it maintains gap between performances of ZF(Zero Forcing) and MMSE(Minimum Mean Square Error) in frequency diversity combining schemes. Also, spatial diversity gain increases as the number of receiving antennas increases. It means that it can reduce performance gap between ZF and MMSE in frequency diversity combining schemes by increasing the number of receiving antennas. In addition, it might affect the performance improvement of the whole SNR. Finally, through the analysis of performance according to the spatial diversity gain, the performance of ZF in frequency diversity combining is equal to the MMSE if the number of receiving antennas is 6 or more.

• Journal of Chest Surgery
• /
• v.31 no.3
• /
• pp.233-241
• /
• 1998

To define the risk factors affecting the early major morbidity and mortality after multiple- valve operations, the preoperative, intraoperative and postoperative informations were retrospectively collected on 124 consecutive patients undergoing a multiple-valve operation between October 1985 and July 1996 at the department of Thoracic and Cardiovascular Surgery of Pusan Paik Hospital. The study population consists of 53 men and 71 women whose mean age was 37.9$\pm$11.5(mean$\pm$SD) years. Using the New York Heart Association(NYHA) classification, 41 patients(33.1%) were in functional class II, 60(48.4%) in class III, and 20(16.1%) in class IV preoperatively. Seven patients(5.6%) had undergone previous cardiac operations. Atrial fibrillations were present in 76 patients(61.3%), a history of cerebral embolism in 5(4.0%), and left atrial thrombus in 13(10.5%). The overall early mortality rate and postoperative morbidity was 8.1% and 21.8% respectively. Among the 124 cases of multiple-valve operation, there were 57(46.0%) of combined mitral valve replacement(MVR) and aortic valve replacement(AVR), 48(38.7%) of combined MVR and tricuspid annuloplasty(TVA), 12(9.7%) of combined MVR, AVR and TVA, 3(2.4%) of combined MVR and aortic valvuloplasty, 2(1.6%) of combined MVR and tricuspid valve replacement, and others. The patients were classified according to the postoperative outcomes; Group A(27 cases) included the patients who had early death or major morbidity such as low cardiac output syndrome, mediastinitis, cardiac rupture, ventricular arrhythmia, sepsis, and others; Group B(97 cases) included the patients who had the good postoperative outcomes. The patients were also classified into group of early death and survivor. In comparison of group A and group B, there were significant differences in aortic cross-clamping time(ACT, group A:153.4$\pm$42.4 minutes, group B:134.0$\pm$43.7 minutes, p=0.042), total bypass time(TBT, group A:187.4$\pm$65.5 minutes, group B:158.1$\pm$50.6 minutes, p=0.038), and NYHA functional class(I:33.3%, II:9.7%, III:20%, IV:50%, p=0.004). In comparison of early death(n=10) and survivor(n=114), there were significant differences in age(early death:45.2$\pm$8.7 years, survivor:37.2$\pm$11.6 years, p=0.036), sex(female:12.7%, male:1.9%, p=0.043), ACT(early death:167.1$\pm$38.4 minutes, survivor:135.7$\pm$43.7 minutes, p=0.030), and NYHA functional class(I:0%, II:4.9%, III:1.7%, IV:35%, p=0.001). In conclusion, the early major morbidity and mortality were influenced by the preoperative clinical status and therefore the earlier surgical intervention should be recommended whenever possible. Also, improved methods of myocardial protection and operative techniques may reduce the risk in patients with multiple-valve operation.

• Spatial Information Research
• /
• v.23 no.3
• /
• pp.11-21
• /
• 2015

While the number of total population in Seoul has been on the constant decline for the last few years, the number of household has increased due to the rising tendency of the smaller households. In 2010, the small households in the metropolitan areas accounted for 44% of the entire households, and Statistics Korea has reported that one person household, which will take up more than 30% of the whole household, will have been the most common type of household by 2020. This reason of rise will be differently shown according to age like the preferred housing type or surrounding environments, this research is suggest to research hypothesis that distinction of age leads to the spatial distribution of one person household. Therefore, this research is to exercise a multiple regression analysis targeting on the facilities, which become the spatial distribution factor of one person household, with the independent variable gained from the concluded area calculated with the area ratio of the spatial unit followed by the service area analysis based on network. The spatial unit is the census output of Seoul, and based on this the interaction between the number of one person household according to age and the factors of its distribution. Also, the spatial regions - downtown, northeast, southeast, northwest, southwest - are designed as dummy variables and the results of each region are found out. As a result, the spatial regions occupied according to age are found to be varied - people in their 20s prefer housings near the college, 30s lease or the monthly rental housings, 40s the monthly rental housings, and over 60s the housing with the floor area of less than $40m^2$. Likewise, one person household has different types of housing environments preferred according to age, and thus a housing policy concerning this will have to be suggested.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.9C
• /
• pp.895-904
• /
• 2007

This paper proposes a robust sub-optimal smart antenna in Code Division Multiple Access (CDMA) basestation. It makes use of the property of the Least Mean Square (LMS) algorithm and the Conjugate Gradient Method (CGM) algorithm for beamforming processes. The weight update takes place at symbol level which follows the PN correlators of receiver module under the assumption that the post correlation desired signal power is far larger than the power of each of the interfering signals. The proposed algorithm is simple and has as low computational load as five times of the number of antenna elements(O(5N)) as a whole per each snapshot. The output Signal to Interference plus Noise Ratio (SINR) of the proposed smart antenna system when the weight vector reaches the steady state has been examined. It has been observed in computer simulations that proposed beamforming algorithm improves the SINR significantly compared to the single antenna case. The convergence property of the weight vector has also been investigated to show that the proposed hybrid algorithm performs better than CGM and LMS during the initial stage of the weight update iteration. The Bit Error Rate (BER) characteristics of the proposed array has also been shown as the processor input Signal to Noise Ratio (SNR) varies.

• Journal of Biomedical Engineering Research
• /
• v.33 no.1
• /
• pp.39-46
• /
• 2012

Electrical impedance tomography(EIT) can produce functional images with conductivity distributions associated with physiological events such as cardiac and respiratory cycles. EIT has been proposed as a clinical imaging tool for the detection of stroke and breast cancer, pulmonary function monitoring, cardiac imaging and other clinical applications. However EIT still suffers from technical challenges such as the electrode interface, hardware limitations, lack of animal or human trials, and interpretation of conductivity variations in reconstructed images. We improved the KHU Mark2 EIT system by introducing an EIT electrode interface consisting of nano-web fabric electrodes and by adding a synchronized biosignal measurement system for gated conductivity imaging. ECG and respiration signals are collected to analyze the relationship between the changes in conductivity images and cardiac activity or respiration. The biosignal measurement system provides a trigger to the EIT system to commence imaging and the EIT system produces an output trigger. This EIT acquisition time trigger signal will also allow us to operate the EIT system synchronously with other clinical devices. This type of biosignal gated conductivity imaging enables capture of fast cardiac events and may also improve images and the signal-to-noise ratio (SNR) by using signal averaging methods at the same point in cardiac or respiration cycles. As an example we monitored the beat by beat cardiac-related change of conductivity in the EIT images obtained at a common state over multiple respiration cycles. We showed that the gated conductivity imaging method reveals cardiac perfusion changes in the heart region of the EIT images on a canine animal model. These changes appear to have the expected timing relationship to the ECG and ventilator settings that were used to control respiration. As EIT is radiation free and displays high timing resolution its ability to reveal perfusion changes may be of use in intensive care units for continuous monitoring of cardiopulmonary function.

• Journal of Distribution Science
• /
• v.12 no.4
• /
• pp.23-30
• /
• 2014

Purpose - The purpose of this study is to analyze the efficiency of retail businesses by dividing domestic retailers into discount stores, super supermarkets (SSMs), and department stores. It suggests retail-business investment strategies by using data environment analysis (DEA) to analyze how input elements such as store area, parking lot area, number of employees, and sales management expenses for the convenience of customers positively affect business performance measurements such as sales and visiting customers per day. Research Design, Data, and Methodology - The DEA model calculates a ratio of the weighted mean of various inputs to the weighted mean of various outputs and measures the efficiency of a specific decision making unit (DMU). The study included 19 companies (five discount store DMUs, ten SSM DMUs, and four department store DMUs). Because the business elements and sizes of retail store DMUs used in this analysis are different, average per-store input and output variables were used. Data were collected from "The Yearbook of Retail Industry in Korea (2012)." DEA analysis was used to determine differences in efficiency among discount stores, SSMs, and department stores in terms of the business elements of each retail business. It was also used to determine what business elements were excessively invested in by comparing and analyzing efficiency by business elements using SPSS software's ANOVA (Analysis of Variance). Results - The CCR and BCC efficiency analysis found that the efficiency of discount stores is low. We believe that the saturation state of discount stores is a major factor. The ANOVA analysis confirms the VRS hypothesis with a statistically significant difference among the three groups, based on an analysis confidence interval of 95%. CRS and SE were not found to be significantly different among the three groups. As for the post hoc test, which concretely shows differences by group, the Scheffe's multiple comparison analysis test found the average differences between group 1 (discount stores) and group 2 (SSM) to be statistically significant. Conclusions - The DEA efficiency analysis implies that investment in input elements, including store area, parking lot area, and sales management expenses, were excessive in the case of discount stores, while SSMs need to invest more in promotion activities such as gifts, events, and coupons for customer management. Department stores have found that small companies invest excessively in input elements. Department stores need to invest in differentiated shopping mall complexes. This study was limited in acquiring statistical data; various input variables which might have shown more secure customer management and promotional expenses could not be applied. As the study was limited in various aspects of the efficiency analyses because financial analyses of the companies and of causal relationships, including satisfaction and loyalty of visiting customers, were not done, these aspects will be examined in the next study.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.19-26
• /
• 2013

This paper deals with the performance comparison of blind adaptive equalization algorithm, the MMA and S-MMA, that is used for compensation of the amplitude and phase distortion simultaneously which occurs in the time dispersive channel. The present CMA algorithm is possible to compensates the amplitude only, but not in phase, so it needs to the another additional circuit for compensating the phase. In order to overcoming the abovemensioned shorthand, the improved cost function is applied to the MMA algorithm. In MMA algorithm, the error is consists of the dispersion constant only, but in S-MMA, the error is consists of the dispersion constant considering the output of decision device (sliced symbol) in order to updating the tap coefficients. By using the two kind error signal, the adaptive equalization algorithm has different performance. In this paper, we compare to the adaptive equalization algorithm performance by using the recovered constellation, residual isi, MD (Maximum Distortion) and SER as a index when the transmitting signal is 16 and 64-QAM and then passing through the same communication channel. As a result of simulation, the S-MMA can improving the Roburstness in SER performance compared to the MMA in the high order QAM signal.

• Journal of The Korean Association of Information Education
• /
• v.21 no.1
• /
• pp.41-55
• /
• 2017

The physical computing education, as the emerging field, is a form of education that helps learners to develop the attitude of scientific inquiry by developing meaningful and creative output through the integration of hardware and software elements. Based on the literature, the authors of the study used science experience, school support and learning flow as the variables that predict the outcome variable which is the attitude of scientific inquiry. The authors collected data from 64 fourth and sixth graders who studied physical computing at an institution for the gifted and talented in Korea and then analyzed them using descriptive statistics, correlation, multiple regression and simple mediation analysis methods. As a result, science experience and learning flow significantly predicted the attitude of scientific inquiry. In addition, learning flow mediated the relationship between science experience and the attitude of scientific inquiry, and the relationship between school support and the attitude of scientific inquiry. Based on these results, the authors propose that to promote the attitude of scientific inquiry in physical computing education, strategies must be implemented for improving science experience, school support and learning flow in instructional design.