• Journal of Radiation Protection and Research
• /
• 제46권4호
• /
• pp.204-212
• /
• 2021

Background: Identification of radioisotopes for plastic scintillation detectors is challenging because their spectra have poor energy resolutions and lack photo peaks. To overcome this weakness, many researchers have conducted radioisotope identification studies using machine learning algorithms; however, the effect of data normalization on radioisotope identification has not been addressed yet. Furthermore, studies on machine learning-based radioisotope identifiers for plastic scintillation detectors are limited. Materials and Methods: In this study, machine learning-based radioisotope identifiers were implemented, and their performances according to data normalization methods were compared. Eight classes of radioisotopes consisting of combinations of ²²Na, ⁶⁰Co, and ¹³⁷Cs, and the background, were defined. The training set was generated by the random sampling technique based on probabilistic density functions acquired by experiments and simulations, and test set was acquired by experiments. Support vector machine (SVM), artificial neural network (ANN), and convolutional neural network (CNN) were implemented as radioisotope identifiers with six data normalization methods, and trained using the generated training set. Results and Discussion: The implemented identifiers were evaluated by test sets acquired by experiments with and without gain shifts to confirm the robustness of the identifiers against the gain shift effect. Among the three machine learning-based radioisotope identifiers, prediction accuracy followed the order SVM > ANN > CNN, while the training time followed the order SVM > ANN > CNN. Conclusion: The prediction accuracy for the combined test sets was highest with the SVM. The CNN exhibited a minimum variation in prediction accuracy for each class, even though it had the lowest prediction accuracy for the combined test sets among three identifiers. The SVM exhibited the highest prediction accuracy for the combined test sets, and its training time was the shortest among three identifiers.

• 한국치위생학회지
• /
• 제23권2호
• /
• pp.105-113
• /
• 2023

Objectives: The purpose of this study is to verify the usefulness and practicality of the program in the daily life of the elderly by performing a three-dimensional tongue muscle exercise for the elderly to identify the dysphagia, swallowing ability, and tongue pressure. Methods: The subjects of the study were 29 elderly people aged 65 or older living in Busan, divided into a oral exercises group and tongue strength training program combined with oral exercises group, and operated 16 times for 8 weeks twice a week, and the pre and post-program evaluation was conducted in the 1st and 8th weeks. For variable selection, 7 general characteristics, 5 oral health-related characteristics, 5 Likert scale for swallowing disorder, repetitive swallowing ability test for swallowing power measurement, and tongue pressure measurement was used. Data analysis was conducted using SPSS window program 25.0 version (IBM), general characteristics and homogeneity tests, oral health-related characteristics and homogeneity tests were chi-square test, swallowing disorder, swallowing ability, and change in tongue pressure were paired t-test, Wilcoxon signed rank test, t-test, Mann-Whitney U test for swallowing disorder and changes in swallowing ability and tongue pressure, and Spearman's correlation for the relationship between swallowing disorder and swallowing ability and tongue pressure. Results: As a result of tongue strength training program combined with oral exercise, both relieve swallowing disorder and improve low eating and tongue pressure than oral exercise, and the difference in improvement effects of both relieve swallowing disorder, swallowing ability, and tongue pressure is higher. Conclusions: Based on the results of this study, it is believed that simple and practical oral muscle function reinforcement products and practical use are needed, and institutional devices to seek oral health promotion programs for the elderly are needed.

• 운동영양학회지
• /
• 제16권1호
• /
• pp.27-33
• /
• 2012

This study was conducted to investigate the effect of a 24-week combined exercise training program in older women with hypertension. Women with hypertension who were 70 years and older were randomized into two groups: combined exercise group (CE; n = 15) and a control group (n = 15). The CE group performed a combined exercise training program four times per week for 24 weeks and the control group did not. Five factors, including body composition (percent body fat and skeletal muscle mass), health-related physical fitness, adipocytokines (interleukin-6 [IL-6] and tumor necrosis factor-alpha [TNF-α]), kidney risk factors (glomerular filtration rate [GFR] and cystatin C), and systolic and diastolic blood pressure were measured before and after the program. The findings showed that total muscle mass, health-related physical fitness factors, and GFR increased significantly in the CE group compared to those in the control. Additionally, systolic and diastolic blood pressure and IL-6, TNF-α, and cystatin C levels in the CE group decreased significantly after the intervention. In contrast, total muscle mass decreased significantly and blood pressure remained unchanged in the control group. These results suggest that CE training may positively impact circulating levels of adipocytokines and cystatin C and improve physical fitness levels in elderly women with hypertension. Therefore, CE training helps to prevent renal disease and improve health-related physical fitness, eventually leading to a better quality of life.

• Korean Journal of Radiology
• /
• 제22권3호
• /
• pp.415-424
• /
• 2021

Objective: To determine whether noncontrast computed tomography (NCCT) models based on multivariable, radiomics features, and machine learning (ML) algorithms could further improve the discrimination of early hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (sICH). Materials and Methods: We retrospectively reviewed 261 patients with sICH who underwent initial NCCT within 6 hours of ictus and follow-up CT within 24 hours after initial NCCT, between April 2011 and March 2019. The clinical characteristics, imaging signs and radiomics features extracted from the initial NCCT images were used to construct models to discriminate early HE. A clinical-radiologic model was constructed using a multivariate logistic regression (LR) analysis. Radiomics models, a radiomics-radiologic model, and a combined model were constructed in the training cohort (n = 182) and independently verified in the validation cohort (n = 79). Receiver operating characteristic analysis and the area under the curve (AUC) were used to evaluate the discriminative power. Results: The AUC of the clinical-radiologic model for discriminating early HE was 0.766. The AUCs of the radiomics model for discriminating early HE built using the LR algorithm in the training and validation cohorts were 0.926 and 0.850, respectively. The AUCs of the radiomics-radiologic model in the training and validation cohorts were 0.946 and 0.867, respectively. The AUCs of the combined model in the training and validation cohorts were 0.960 and 0.867, respectively. Conclusion: NCCT models based on multivariable, radiomics features and ML algorithm could improve the discrimination of early HE. The combined model was the best recommended model to identify sICH patients at risk of early HE.

• Physical Therapy Rehabilitation Science
• /
• 제4권2호
• /
• pp.73-78
• /
• 2015

Objective: This study focused on subacute stroke patients who were asked to kick a ball while walking on a treadmill. The aim of the study was to determine the effect of a body weight-supported treadmill training (BWSTT) combined with ball-kicking on muscle strength, balance, and gait. Design: Single blind, randomized controlled trial. Methods: Twenty stroke patients who volunteered to participate in this study were randomly assigned to either the BWSTT combined with ball-kicking (BWSTT-BK; 10 participants) group or the BWSTT group (10 participants). Participants in the BWSTTBK group performed treadmill walking combined with simultaneous ball-kicking for 30 minutes daily for 5 weeks. Participants from the BWSTT group performed only treadmill walking. The muscular strength, balance, and gait ability were measured before and after the 5-week training. To assess for muscular strength, a digital muscle tester was used to measure hip flexor, knee extensor, and dorsiflexor strength. To assess for balance, the Berg Balance Scale (BBS) and Timed Up and Go Test (TUG) was used. To assess for gait, the 10 meter walk test (10MWT) and Functional Gait Assessment (FGA) was used. Results: The BWSTT-BK group showed significantly improved muscular strength, balance, and gait according to BBS, TUG, 10MWT, FGA, and digital muscle testing scores compared to the BWSTT group (p<0.05). In addition, within-group comparison showed significant improvement in all variables (p<0.05). Conclusions: These findings suggest that BWSTT-BK results in more favourable outcomes for stroke patients. Therefore, BWSTT-BK may be useful for the recovery of gait ability of stroke patients.

• 대한정형도수물리치료학회지
• /
• 제25권2호
• /
• pp.73-81
• /
• 2019

Background: Patellofemoral pain is one of the common diseases of the musculoskeletal system. Many previous studies have recommended the application of exercise therapy to patellofemoral pain patients for treatment. The purpose of this study was to investigate effect of coordinative locomotor training (CLT) and sling exercise combined program on knee pain and functional movement in patellofemoral pain patient. Methods: In this study, single-subject design (A-B-A') was conducted for 6 weeks. A repeted-measure analysis was conducted to assess results of the anterior knee pain scale (AKPS), Clarke's test (CT), eccentric step down test (ESDT). During the intervention (B), the CLT and sling exercise combined program was conducted three times a week for 4 weeks. Results: From baseline period A to intervention period B, the AKPS, CT, ESDT were improved from 61 to 48 (27%), from 8.33 to 3 (64%), from 7.67 to 3,58 (53%). From baseline period A to baseline period A', the AKPS, CT, ESDT were improved from 70.67 to 48 (47%), from 0.67 to 3 (92%), from 1.33 to 3,58 (83%). Conclusion: Based on the results of this study, we recommend the application of CLT and sling exercise combined program to improve the pain and functional movement in patellofemoral pain patients.

• 대한정형도수물리치료학회지
• /
• 제28권3호
• /
• pp.61-68
• /
• 2022

Background: This study aimed to investigate the effects of noninvasive electrical stimulation combined with trunk stabilization exercise on balance and fall risk in patients with stroke. Methods: Twenty-two patients with stroke were enrolled in the study and randomly divided into experimental and control groups, each with 11 patients. noninvasive electrical stimulation combined with trunk stabilization training was applied to the experimental group, and sham noninvasive electrical stimulation combined with trunk stabilization training, to the control group. Both groups were treated for 6 weeks, five times a week for 30 min each time; the balance and fall risk of patients with stroke were measured before and after treatment, and the changes in the two groups were compared and analyzed. Results: The experimental group's left and right weight-bearing indices (affect and non-affect sides) and the front and rear weight-bearing indices, were significantly improved (p<.05, p<.001). when the changes in balance ability between groups were compared before and after treatment. The total fall efficacy score in the experimental group was substantially lower than that in the control group when the changes in fall efficacy score were compared between groups following treatment (p<.001). Conclusion: The improvement in balance and fall risk in patients with stroke can be attributed to using noninvasive electrical stimulation in combination with trunk stabilization training. This clinically helpful treatment method for patients with stroke warrants further promotion and implementation in the clinic.

• Korean Journal of Radiology
• /
• 제23권9호
• /
• pp.921-930
• /
• 2022

Objective: To identify epidermal growth factor receptor (EGFR) mutations in lung adenocarcinoma based on ¹⁸F-fluorodeoxyglucose (FDG) PET/CT radiomics and clinical features and to distinguish EGFR exon 19 deletion (19 del) and exon 21 L858R missense (21 L858R) mutations using FDG PET/CT radiomics. Materials and Methods: We retrospectively analyzed 179 patients with lung adenocarcinoma. They were randomly assigned to training (n = 125) and testing (n = 54) cohorts in a 7:3 ratio. A total of 2632 radiomics features were extracted from the tumor region of interest from the PET (1316) and CT (1316) images. Six PET/CT radiomics features that remained after the feature selection step were used to calculate the radiomics model score (rad-score). Subsequently, a combined clinical and radiomics model was constructed based on sex, smoking history, tumor diameter, and rad-score. The performance of the combined model in identifying EGFR mutations was assessed using a receiver operating characteristic (ROC) curve. Furthermore, in a subsample of 99 patients, a PET/CT radiomics model for distinguishing 19 del and 21 L858R EGFR mutational subtypes was established, and its performance was evaluated. Results: The area under the ROC curve (AUROC) and accuracy of the combined clinical and PET/CT radiomics models were 0.882 and 81.6%, respectively, in the training cohort and 0.837 and 74.1%, respectively, in the testing cohort. The AUROC and accuracy of the radiomics model for distinguishing between 19 del and 21 L858R EGFR mutational subtypes were 0.708 and 66.7%, respectively, in the training cohort and 0.652 and 56.7%, respectively, in the testing cohort. Conclusion: The combined clinical and PET/CT radiomics model could identify the EGFR mutational status in lung adenocarcinoma with moderate accuracy. However, distinguishing between EGFR 19 del and 21 L858R mutational subtypes was more challenging using PET/CT radiomics.

• 한국항해학회지
• /
• 제22권1호
• /
• pp.91-106
• /
• 1998

Traditionally, in the education for the trainees of marine officier, the emphasis is laid on the practical training on board to prepare them for the future position on board and to fit them for the shipboard life. Though the education has been carried out in various ways according to each country's social tradition, culture and educational system, in these days it is done normally by the combined way of school education and training on board to get the competence for the marine officer. Thus the shipboard training course is compulsively required to the candidates for certification as merchant marine officers by the IMO STCW convention 1978 and also it is believed that the education for the dacet officers is to be completed through the shipboard training. In spite of the various earlier studies to improve the training education system, there are few studies for the matters and problems form the standing point of cadet.

• Journal of information and communication convergence engineering
• /
• 제11권4호
• /
• pp.268-273
• /
• 2013

In this paper, we propose a document classification model using Web documents as a part of the training corpus in order to resolve the imbalance of the training corpus size per category. For the purpose of retrieving the Web documents closely related to each category, the proposed document classification model calculates the matching score between word features and each category, and generates a Web search query by combining the higher-ranked word features and the category title. Then, the proposed document classification model sends each combined query to the open application programming interface of the Web search engine, and receives the snippet results retrieved from the Web search engine. Finally, the proposed document classification model adds these snippet results as Web documents to the training corpus. Experimental results show that the method that considers the balance of the training corpus size per category exhibits better performance in some categories with small training sets.