• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• Journal of Acupuncture Research
• /
• v.41 no.2
• /
• pp.75-86
• /
• 2024

A review of randomized controlled trials (RCTs) using electroacupuncture (EA) to treat patients with foot drop was performed to analyze the effectiveness of EA for this condition. Relevant studies (n = 183) from 7 databases (Cochrane Library, Excerpta Medica Database, PubMed, China National Knowledge Infrastructure, Korean Studies Information Service System, Research Information Sharing Service, and Oriental Medicine Advanced Searching Integrated System) were selected based on the inclusion and exclusion criteria, and 12 RCTs met the selection criteria. In all 12 studies, EA showed significantly positive changes. In most indicators, positive changes were observed in the EA group compared with that in the control group. Significant increases were confirmed in muscle strength-related indicators such as the Fugl-Meyer motor scale, surface electromyography, active range of motion, and gait-related indicators such as the Tinetti score, maximum walking speed, and Berg balance scale. No notable adverse events were reported. EA is suggested as an effective treatment for post-stroke foot drop; however, more RCTs are required.

• The Journal of Internal Korean Medicine
• /
• v.45 no.1
• /
• pp.75-86
• /
• 2024

Spinal cord infarction is one of the rare strokes with no clear signs of serious nerve damage or after-effects. This study reports on the effectiveness of a combined treatment of Korean medicine and acupuncture on bilateral paraplegia, dysuria, and constipation in a patient with sudden-onset spinal cord infarction. An 84-year-old male patient was diagnosed with spinal cord infarction in August 2022. After diagnosis by whole spine MRI, he received treatment for two months at another hospital, but the improvement was insignificant. He then received Korean medicine treatment, and during this period, his lower extremity manual muscle test grade improved from 3 to 4 and his modified Rivermead mobility index score increased by 13 points, compared with hospitalization. Dysuria improved with acupuncture, and constipation improved with herbal medicine treatment. A combination of herbal medicine and acupuncture can be used to treat paraplegia, dysuria, and constipation caused by spinal cord infarction.

• Journal of Korean Academy of Rural Health Nursing
• /
• v.19 no.1
• /
• pp.66-74
• /
• 2024

Purpose: This study evaluates the effectiveness of providing frailty prevention services by living support workers through a case of community resource connection centered on living support workers to revitalize frailty prevention programs for vulnerable elderly people. Methods: This is a research study using secondary data from a neighborhood health-sharing project among the integrated health promotion projects of one public health center in Daegu Metropolitan City. To assess frailty effects pre-assessments were conducted in August, and post-assessments were conducted in November. Frailty was measured using a 20-item frailty instrument used in home healthcare projects. Data were analyzed using the chi-square, independent t-test, and paired t-test. Results: Preliminary measurements showed that older elderly had higher frailty scores than younger elderly. However, among the elderly aged 75 or older the total frailty score decreased statistically significantly from 5.97 points to 5.30 points (t=3.03, p=.003). Conclusion: The older elderly showed greater effect of frailty prevention than the younger elderly.

• Journal of the Korean Applied Science and Technology
• /
• v.40 no.6
• /
• pp.1413-1424
• /
• 2023

Virtual reality (VR) simulation in nursing education, especially in the teaching of VR simulations just prior to clinical practice, has the potential to enhance the effectiveness of clinical practice and better prepare nursing students for patient care. The aim of this study was to evaluate the effect of a preclinical VR simulation education program on the development of critical thinking, self-efficacy, problem-solving ability, and perceived clinical competency among undergraduate nursing students. The study was conducted between May and June 2021 using a pretest-posttest design with a control group. A total of 42 nursing students were recruited through convenience sampling from two separate classes. The intervention group participated in VR simulation education, while the control group engaged in lecture-based education, before beginning clinical practice. Assessments were conducted before preclinical education and after completing clinical practice using structured questionnaires. The data was analyzed using chi-square tests, independent t-tests, and ANCOVA. The findings indicated that the intervention group had a significantly higher score in perceived clinical competency compared to the control group (F = 5.25, p = 0.029) after controlling for pretest scores. However, there were no statistically significant differences in critical thinking, self-efficacy, or problem-solving abilities between the two groups. These findings suggest that preclinical VR simulation education is partially effective in preparing nursing students for their clinical practice, underscoring the need for a balanced educational approach that integrates VR with clinical practice to develop a full spectrum of nursing skills and knowledge.

• Nuclear Engineering and Technology
• /
• v.55 no.12
• /
• pp.4685-4694
• /
• 2023

The ability to calculate the material density sensitivity coefficients of power with respect to the material density has broad application prospects for accelerating Monte Carlo-Thermal Hydraulics iterations. The second-order material density sensitivity coefficients for the general Monte Carlo score have been derived based on the differential operator sampling method in this paper, and the calculation of the sensitivity coefficients of cell power scores with respect to the material density has been realized in continuous-energy Monte Carlo code RMC. Based on the power-density sensitivity coefficients, the sensitivity coefficients of power scores to some other physical quantities, such as power-boron concentration coefficients and power-temperature coefficients considering only the thermal expansion, were subsequently calculated. The effectiveness of the proposed method is demonstrated in the power-density coefficients problems of the pressurized water reactor (PWR) moderator and the heat pipe reactor (HPR) reflectors. The calculations were carried out using RMC and the ENDF/B-VII.1 neutron nuclear data. It is shown that the calculated sensitivity coefficients can be used to predict the power scores accurately over a wide range of boron concentration of the PWR moderator and a wide range of temperature of HPR reflectors.

• Korean Circulation Journal
• /
• v.53 no.11
• /
• pp.775-786
• /
• 2023

Background and Objectives: Tricuspid valve (TV) repair techniques other than annuloplasty remain challenging and frequently end in tricuspid valve replacement (TVR) in complicated cases. However, the results of TVR are suboptimal compared with TV repair. This study aimed to evaluate the clinical effectiveness of TV edge-to-edge repair (E2E) compared to TVR for severe tricuspid regurgitation (TR). Methods: We retrospectively reviewed 230 patients with severe TR who underwent E2E (n=139) or TVR (n=91) from 2001 to 2020. Clinical and echocardiographic results were analyzed using inverse probability of treatment weighting analysis and propensity score matching. Results: The two groups showed no significant differences in early mortality and morbidities. During the mean follow-up of 106.2±68.8 months, late severe TR and TV reoperation rates were not significantly different between groups. E2E group, however, showed better outcomes in overall survival (p=0.023), freedom from significant tricuspid stenosis (TS) (trans-tricuspid pressure gradient ≥5 mmHg, p=0.021), and freedom from TV-related events (p<0.001). Matched analysis showed consistent results. Conclusions: E2E for severe TR presented more favorable clinical outcomes than TVR. Our study supports that E2E might be a valuable option in severe TR surgery, avoiding TVR.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.290-297
• /
• 2024

We investigate the efficacy of ensemble learning methods, specifically the soft voting technique, for enhancing heart disease prediction accuracy. Our study uniquely combines Logistic Regression, SVM with RBF Kernel, and Random Forest models in a soft voting ensemble to improve predictive performance. We demonstrate that this approach outperforms individual models in diagnosing heart disease. Our research contributes to the field by applying a well-curated dataset with normalization and optimization techniques, conducting a comprehensive comparative analysis of different machine learning models, and showcasing the superior performance of the soft voting ensemble in medical diagnosis. This multifaceted approach allows us to provide a thorough evaluation of the soft voting ensemble's effectiveness in the context of heart disease prediction. We evaluate our models based on accuracy, precision, recall, F1 score, and Area Under the ROC Curve (AUC). Our results indicate that the soft voting ensemble technique achieves higher accuracy and robustness in heart disease prediction compared to individual classifiers. This study advances the application of machine learning in medical diagnostics, offering a novel approach to improve heart disease prediction. Our findings have significant implications for early detection and management of heart disease, potentially contributing to better patient outcomes and more efficient healthcare resource allocation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2333-2345
• /
• 2024

Facial wrinkles are widely used to evaluate skin condition or aging for various fields such as skin diagnosis, plastic surgery consultations, and cosmetic recommendations. In order to effectively process facial wrinkles in facial image analysis, accurate wrinkle segmentation is required to identify wrinkled regions. Existing deep learning-based methods have difficulty segmenting fine wrinkles due to insufficient wrinkle data and the imbalance between wrinkle and non-wrinkle data. Therefore, in this paper, we propose a new facial wrinkle segmentation method based on a UNet++ model. Specifically, we construct a new facial wrinkle dataset by manually annotating fine wrinkles across the entire face. We then extract only the skin region from the facial image using a facial landmark point extractor. Lastly, we train the UNet++ model using both dice loss and focal loss to alleviate the class imbalance problem. To validate the effectiveness of the proposed method, we conduct comprehensive experiments using our facial wrinkle dataset. The experimental results showed that the proposed method was superior to the latest wrinkle segmentation method by 9.77%p and 10.04%p in IoU and F1 score, respectively.

• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.754-755
• /
• 2024

This paper presents a comparative study of five deep learning models-ResNet50, DenseNet121, Vision Transformer (ViT), Swin Transformer (SwinT), and CoatNet-on the task of multi-label classification of fundus images for ocular diseases. The models were trained on the Ocular Disease Recognition (ODIR) dataset and validated on the Retinal Fundus Multi-disease Image Dataset (RFMiD), with a focus on five disease classes: diabetic retinopathy, glaucoma, cataract, age-related macular degeneration, and myopia. The performance was evaluated using the area under the receiver operating characteristic curve (AUC-ROC) score for each class. CoatNet achieved the best AUC-ROC scores for diabetic retinopathy, glaucoma, cataract, and myopia, while ViT outperformed CoatNet for age-related macular degeneration. Overall, CoatNet exhibited the highest average performance across all classes, highlighting the effectiveness of hybrid architectures in medical image classification. These findings suggest that CoatNet may be a promising model for multi-label classification of fundus images in cross-dataset scenarios.