• The Korean Journal of Pain
• /
• 제34권1호
• /
• pp.82-93
• /
• 2021

Background: This study used bibliometric analysis of articles published about the topic of regional anesthesia from 1980-2019 with the aim of determining which countries, organizations, and authors were effective, engaged in international cooperation, and had the most cited articles and journals. Methods: All articles published from 1980-2019 included in the Web of Science database and found using the keywords regional anesthesia/anaesthesia, spinal anesthesia/anaesthesia, epidural anesthesia/anaesthesia, neuraxial anesthesia/anaesthesia, combined spinal-epidural, and peripheral nerve block in the title section had bibliometric analysis performed. Correlations between the number of publications from a country with gross domestic product (GDP), gross domestic product (at purchasing power parity) per capita (GDP PPP), and human development index (HDI) values were investigated with the Spearman correlation coefficient. The number of articles that will be published in the future was estimated with linear regression analysis. Results: Literature screening found 11,156 publications. Of these publications, 6,452 were articles. The top 4 countries producing articles were United States of America (n = 1,583), Germany (585), United Kingdom (510), and Turkey (386). There was a significant positive correlation found between the GDP, GDP PPP, and HDI markers for global countries with publication productivity (r = 0.644, P < 0.001; r = 0.623, P < 0.001, r = 0.542, P < 0.001). The most productive organizations were Harvard University and the University of Toronto. Conclusions: This comprehensive study presenting a holistic summary and evaluation of 6,452 articles about this topic may direct anesthesiologists, doctors, academics, and students interested in this topic.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.294-302
• /
• 2022

Detection of fake news is a complex and a challenging task. Generation of fake news is very hard to stop, only steps to control its circulation may help in minimizing its impacts. Humans tend to believe in misleading false information. Researcher started with social media sites to categorize in terms of real or fake news. False information misleads any individual or an organization that may cause of big failure and any financial loss. Automatic system for detection of false information circulating on social media is an emerging area of research. It is gaining attention of both industry and academia since US presidential elections 2016. Fake news has negative and severe effects on individuals and organizations elongating its hostile effects on the society. Prediction of fake news in timely manner is important. This research focuses on detection of fake news spreaders. In this context, overall, 6 models are developed during this research, trained and tested with dataset of PAN 2020. Four approaches N-gram based; user statistics-based models are trained with different values of hyper parameters. Extensive grid search with cross validation is applied in each machine learning model. In N-gram based models, out of numerous machine learning models this research focused on better results yielding algorithms, assessed by deep reading of state-of-the-art related work in the field. For better accuracy, author aimed at developing models using Random Forest, Logistic Regression, SVM, and XGBoost. All four machine learning algorithms were trained with cross validated grid search hyper parameters. Advantages of this research over previous work is user statistics-based model and then ensemble learning model. Which were designed in a way to help classifying Twitter users as fake news spreader or not with highest reliability. User statistical model used 17 features, on the basis of which it categorized a Twitter user as malicious. New dataset based on predictions of machine learning models was constructed. And then Three techniques of simple mean, logistic regression and random forest in combination with ensemble model is applied. Logistic regression combined in ensemble model gave best training and testing results, achieving an accuracy of 72%.

• 대한원격탐사학회지
• /
• 제38권1호
• /
• pp.111-126
• /
• 2022

Land use and land cover (LULC) mapping is an important factor in geospatial analysis. Although highly precise ground-based LULC monitoring is possible, it is time consuming and costly. Conversely, because the synthetic aperture radar (SAR) sensor is an all-weather sensor with high resolution, it could replace field-based LULC monitoring systems with low cost and less time requirement. Thus, LULC is one of the major areas in SAR applications. We developed a LULC model using only KOMPSAT-5 single co-polarized data and digital elevation model (DEM) data. Twelve HH-polarized images and 18 VV-polarized images were collected, and two HH-polarized images and four VV-polarized images were selected for the model testing. To train the LULC model, we applied the conditional generative adversarial network (cGAN) method. We used U-Net combined with the residual unit (ResUNet) model to generate the cGAN method. When analyzing the training history at 1732 epochs, the ResUNet model showed a maximum overall accuracy (OA) of 93.89 and a Kappa coefficient of 0.91. The model exhibited high performance in the test datasets with an OA greater than 90. The model accurately distinguished water body areas and showed lower accuracy in wetlands than in the other LULC types. The effect of the DEM on the accuracy of LULC was analyzed. When assessing the accuracy with respect to the incidence angle, owing to the radar shadow caused by the side-looking system of the SAR sensor, the OA tended to decrease as the incidence angle increased. This study is the first to use only KOMPSAT-5 single co-polarized data and deep learning methods to demonstrate the possibility of high-performance LULC monitoring. This study contributes to Earth surface monitoring and the development of deep learning approaches using the KOMPSAT-5 data.

• 대한물리의학회지
• /
• 제17권4호
• /
• pp.75-83
• /
• 2022

PURPOSE: This study was conducted to find out the effects of neurocognitive rehabilitation therapy on the swallowing function and quality of life of stroke patients. METHODS: Thirty patients were selected and randomly allocated into an experimental and a control group. Patients in the experimental group received 15 minutes of neurocognitive rehabilitation treatment combined with 15 minutes of traditional treatment. For the control group, patients received 30 minutes of traditional dysphasia treatment. The experiments were conducted for 30 minutes a day, five times a week, for four weeks. New VFSS and SWAL-QOL were administrated to evaluate the outcomes. RESULTS: Swallowing functions were significantly improved in the experimental group and the control group (p < .05), but there was no statistically significant difference in pre- and post-interventional swallowing between the groups (p > .05). The quality of life was also significantly improved (p < .05) for both groups, but there was a statistically significant difference between the two groups (p > .05). Third, a correlational analysis between swallowing function and quality of life revealed a moderate correlation between New VFSS and SWAL-QOL (p < .05). CONCLUSION: The results of this study suggest that swallowing therapy through neurocognitive rehabilitation treatment program could be helpful for improving swallowing function and quality of life in stroke patients. Although there was no statistically significant changes from traditional rehabilitation therapy, training in recognizing the senses in the oral cavity and external environment through neurocognitive rehabilitation therapy can be applied as one of the treatment options.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.93-103
• /
• 2022

With the wider availability of sensor technology through easily affordable sensor devices, several Structural Health Monitoring (SHM) systems are deployed to monitor vital civil infrastructure. The continuous monitoring provides valuable information about the health of the structure that can help provide a decision support system for retrofits and other structural modifications. However, when the sensors are exposed to harsh environmental conditions, the data measured by the SHM systems tend to be affected by multiple anomalies caused by faulty or broken sensors. Given a deluge of high-dimensional data collected continuously over time, research into using machine learning methods to detect anomalies are a topic of great interest to the SHM community. This paper contributes to this effort by proposing a relatively new time series representation named "Shapelet Transform" in combination with a Random Forest classifier to autonomously identify anomalies in SHM data. The shapelet transform is a unique time series representation based solely on the shape of the time series data. Considering the individual characteristics unique to every anomaly, the application of this transform yields a new shape-based feature representation that can be combined with any standard machine learning algorithm to detect anomalous data with no manual intervention. For the present study, the anomaly detection framework consists of three steps: identifying unique shapes from anomalous data, using these shapes to transform the SHM data into a local-shape space and training machine learning algorithms on this transformed data to identify anomalies. The efficacy of this method is demonstrated by the identification of anomalies in acceleration data from an SHM system installed on a long-span bridge in China. The results show that multiple data anomalies in SHM data can be automatically detected with high accuracy using the proposed method.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.117-127
• /
• 2022

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.

• 대한물리치료과학회지
• /
• 제29권3호
• /
• pp.75-84
• /
• 2022

Background: This study was to investigate the effect of non-invasive transcranial direct current stimulation due to hemiplegic patients due to stroke on temporal and spatial gait ability. Design: Randomized sham controlled trial. Methods: For the study method, 42 patients with hemiplegia due to stroke were randomly assigned to 14 patients each, and the general walking group, tDCS walking group, and tDCS (sham) walking group were subjected to 5 times a week, 30 minutes a day, and 6 weeks. In the temporal gait variables of hemiplegic patients due to stroke, the effect of the gait time, gait cycle, single support, double support, swing phase, stance phase, gait speed, cadence were measured. In spatial variables, one step length and one step length were measured. Results: As a result of the study, the EG group significantly increased in the step time, gait velocity, and cadence of the paralysis side in the comparison of temporal walking variables between groups according to the application of tDCS of walking ability in hemiplegic patients due to stroke patients(p<.05). In the change in spatial walking variables between groups according to the application of tDCS, the step length and stride length of the EG group showed a significant increase. Both the comparison of temporal and spatial symmetry walking variables between groups according to tDCS application was not significant(p>.05) Conclusion: As a result, tDCS has an effective effect on the improvement of the gait ability of stroke patients. In particular, it is an effective method of physical therapy that can improve the cadence and speed of gait, which can be combined with the existing gait training to effectively increase the gait of hemiplegia due to stroke patients.

• 대한지역사회영양학회지
• /
• 제28권1호
• /
• pp.61-73
• /
• 2023

Objectives: Prophylactic vaccines against high-risk human papillomaviruses (HR-HPVs) hold promise to prevent the development of higher grade cervical intraepithelial neoplasia (CIN 2+) and cervical cancer (CC) that develop due to HR-HPV genotypes that are included in HPV vaccines, but women will continue to develop CIN 2+ and CC due to HR-HPV genotypes that are not included in the quadrivalent HPV vaccine (qHPV) and 9-valent HPV vaccine (9VHPV). Thus, the current vaccines are likely to decrease but not entirely prevent the development of CIN 2+ or CC. The purpose of the study was to determine the prevalence and determinants of CIN 2+ that develop due to HR-HPVs not included in vaccines. Methods: Study population consisted of 1476 women tested for 37 HPVs and known to be negative for qHPVs (6/11/16/18, group A, n = 811) or 9VHPVs (6/11/16/18/31/33/45/52/58, group B, n = 331), but positive for other HR-HPVs. Regression models were used to determine the association between plasma concentrations of micronutrients, socio-demographic, lifestyle factors and risk of CIN 2+ due to HR-HPVs that are not included in vaccines. Results: The prevalence of infections with HPV 31, 33, 35 and 58 that contributed to CIN 2+ differed by race. In group A, African American (AA) women and current smokers were more likely to have CIN 2 (OR = 1.76, P = 0.032 and 1.79, P = 0.016, respectively) while in both groups of A and B, those with higher vitamin B12 were less likely to have similar lesions (OR = 0.62, P = 0.036 and 0.45, P = 0.035, respectively). Conclusions: We identified vitamin B12 status and smoking as independent modifiable factors and ethnicity as a factor that needs attention to reduce the risk of developing CIN 2+ in the post vaccination era. Continuation of tailored screening programs combined with non-vaccine-based approaches are needed to manage the residual risk of developing HPV-related CIN 2+ and CC in vaccinated women.

• 농업과학연구
• /
• 제49권1호
• /
• pp.129-136
• /
• 2022

In this study, we aimed to develop a maturity classification model for tomatoes using hyperspectral imaging in the range of 400 - 1,000 nm. Fifty-seven tomatoes harvested in August and November of 2021 were used as the sample set, and hyperspectral data was extracted from the surfaces of these tomatoes. A combined method of SNV (standard normal variate) and SG (Savitzky-Golay) methods was used for the pre-processing of the hyperspectral data. In addition, the hyperspectral data were analyzed for all maturity stages and considering bandwidths with different FWHM (full width at half maximum) values of 2, 25, and 50 nm. The PCA (principal component analysis) method was used to analyze the principal components related to maturity stages for the tomatoes. As a result, 500 - 550 nm and 650 - 700 nm bands were found to be related to the maturity stages of tomatoes. In addition, PC1 and PC2 explained approximately 97% of the variance at all FWHM conditions and thus were used as input data for classification model training based on the SVM (support vector machine). The SVM models were able to classify tomato maturity into five stages (Green, Turning, Pink, Light red, and Red) with over 95% accuracy regardless of the FWHM condition. Therefore, it was considered that hyperspectral data with 50 nm FWHM and SVM is feasible for use in the classification of tomato maturity into five stages.

• PNF and Movement
• /
• 제21권2호
• /
• pp.151-158
• /
• 2023

Purpose: This study aimed to examine the immediate effects of different breathing training techniques on diaphragm excursion and vital capacity in healthy adults. Specifically, the study focused on comparing respiratory exercise without PNF, bilateral pattern respiratory exercise, and bilateral pattern with spiral pattern respiratory exercise. Methods: Twenty-seven healthy adults in their 20s participated in the study. Diaphragm excursion and vital capacity were evaluated under three different conditions. A one-way repeated ANOVA was used to analyze the differences in diaphragm excursion and vital capacity among the interventions. Results: Statistically significant differences were observed in diaphragm excursion among the interventions, comparing respiratory exercise without PNF, bilateral pattern respiratory exercise, and bilateral pattern with spiral pattern respiratory exercise. Similarly, statistically significant differences were found in vital capacity among the interventions without PNF respiratory exercise, bilateral pattern respiratory exercise, and bilateral pattern with spiral pattern respiratory exercise. Conclusion: The study demonstrated that incorporating the spiral technique in respiratory exercise led to increased diaphragm excursion and lung capacity compared to other interventions. These findings suggest that PNF respiratory exercise combined with the spiral pattern may have clinical implications for the treatment of respiratory diseases. Further research is warranted to explore the long-term effects and clinical application of these approaches.