• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.196-202
• /
• 2024

Currently, the second most devastating form of cancer in people, particularly in women, is Breast Cancer (BC). In the healthcare industry, Machine Learning (ML) is commonly employed in fatal disease prediction. Due to breast cancer's favorable prognosis at an early stage, a model is created to utilize the Dataset on Wisconsin Diagnostic Breast Cancer (WDBC). Conversely, this model's overarching axiom is to compare the effectiveness of five well-known ML classifiers, including Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), and Naive Bayes (NB) with the conventional method. To counterbalance the effect with conventional methods, the overarching tactic we utilized was hyperparameter tuning utilizing the grid search method, which improved accuracy, secondary precision, third recall, and finally the F1 score. In this study hyperparameter tuning model, the rate of accuracy increased from 94.15% to 98.83% whereas the accuracy of the conventional method increased from 93.56% to 97.08%. According to this investigation, KNN outperformed all other classifiers in terms of accuracy, achieving a score of 98.83%. In conclusion, our study shows that KNN works well with the hyper-tuning method. These analyses show that this study prediction approach is useful in prognosticating women with breast cancer with a viable performance and more accurate findings when compared to the conventional approach.

• Journal of The Korean Society of Clinical Toxicology
• /
• v.14 no.2
• /
• pp.115-121
• /
• 2016

Purpose: Because carbon monoxide (CO)-intoxicated patients with an alert mental status and only mild cognitive dysfunction may be inadequately assessed by traditional bedside neurologic examination in the emergency department (ED), they may not receive appropriate treatment. Methods: We retrospectively investigated the incidence and features of cognitive dysfunction using the Korean version of the Mini-Mental State Examination (MMSE-K) in ED patients with CO poisoning with alert mental status. We conducted a retrospective review of 43 consecutive mild CO poisoned patients with a Glasgow Coma Scale score of 15 based on documentation by the treating emergency physician in the ED between July 2014 and August 2015. Results: Cognitive dysfunction, defined as a score of less than 24 in the MMSE-K, was diagnosed in six patients (14%) in the ED. In the MMSE-K, orientation to time, memory recall, and concentration/calculation showed greater impairments. The mean age was significantly older in the cognitive dysfunction group than the non-cognitive dysfunction group (45.3 yrs vs. 66.5 yrs, p<0.001). Among the initial symptoms, experience of a transient change in mental status before ED arrival was significantly more common in the cognitive dysfunction group (32.4% vs. 100%, p=0.003). Conclusion: Patients with CO poisoning and an alert mental status may experience cognitive dysfunction as assessed using the MMSE-K during the early stages of evaluation in the ED. In the MMSE-K, orientation to time, memory recall, and concentration/calculation showed the greatest impairment.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.2
• /
• pp.671-676
• /
• 2014

Objective: The objective of this study was to establish a program model for use in wide-spread cervical cancer screening. :Methods: Cervical cancer screening was conducted in Zhongshan city in Guangdong province, China through a coordinated network of multiple institutes and hospitals. A total of 43,567 women, 35 to 59 years of age, were screened during regular gynecological examinations using the liquid-based ThinPrep cytology test (TCT). Patients who tested positive were recalled for further treatment. Results: The TCT-positive rate was 3.17%, and 63.4% of these patients returned for follow-up. Pathology results were positive for 30.5% of the recalled women. Women who were younger than 50 years of age, urban dwelling, low-income, had a history of cervical disease, began having sex before 20 years of age, or had sex during menstruation, were at elevated risk for a positive TCT test. The recall rate was lower in women older than 50 years of age, urban dwelling, poorly educated, and who began having sex early. Ahigher recall rate was found in women 35 years of age and younger, urban dwelling, women who first had sex after 24 years of age, and women who had sex during menstruation. The positive pathology rate was higher in urban women 50 years of age and younger and women who tested positive for human papillomavirus. Conclusion: An effective model for large-scale cervical cancer screening was successfully established. These results suggest that improvements are needed in basic education regarding cervical cancer screening for young and poorly educated women. Improved outreach for follow-up is also necessary to effectively control cervical cancer.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.91-98
• /
• 2021

Today's information and communication technology is rapidly developing, the security of IT infrastructure is becoming more important, and at the same time, cyber attacks of various forms are becoming more advanced and sophisticated like intelligent persistent attacks (Advanced Persistent Threat). Early defense or prediction of increasingly sophisticated cyber attacks is extremely important, and in many cases, the analysis of network-based intrusion detection systems (NIDS) related data alone cannot prevent rapidly changing cyber attacks. Therefore, we are currently using data generated by intrusion detection systems to protect against cyber attacks described above through Host-based Intrusion Detection System (HIDS) data analysis. In this paper, we conducted a comparative study on machine learning algorithms using LID-DS (Leipzig Intrusion Detection-Data Set) host-based intrusion detection data including thread information, metadata, and buffer data missing from previously used data sets. The algorithms used were Decision Tree, Naive Bayes, MLP (Multi-Layer Perceptron), Logistic Regression, LSTM (Long Short-Term Memory model), and RNN (Recurrent Neural Network). Accuracy, accuracy, recall, F1-Score indicators and error rates were measured for evaluation. As a result, the LSTM algorithm had the highest accuracy.

• Journal of the Korea Society for Simulation
• /
• v.32 no.4
• /
• pp.19-26
• /
• 2023

The increase in the dropout rate of college students nationwide has a serious negative impact on universities and society as well as individual students. In order to proactive identify students at risk of dropout, this study built a decision tree, random forest, logistic regression, and deep learning-based dropout prediction model using academic data that can be easily obtained from each university's academic management system. Their performances were subsequently analyzed and compared. The analysis revealed that while the logistic regression-based prediction model exhibited the highest recall rate, its f-1 value and ROC-AUC (Receiver Operating Characteristic - Area Under the Curve) value were comparatively lower. On the other hand, the random forest-based prediction model demonstrated superior performance across all other metrics except recall value. In addition, in order to assess model performance over distinct prediction periods, we divided these periods into short-term (within one semester), medium-term (within two semesters), and long-term (within three semesters). The results underscored that the long-term prediction yielded the highest predictive efficacy. Through this study, each university is expected to be able to identify students who are expected to be dropped out early, reduce the dropout rate through intensive management, and further contribute to the stabilization of university finances.

• Journal of the East Asian Society of Dietary Life
• /
• v.13 no.6
• /
• pp.577-585
• /
• 2003

The purpose of this study was to investigate eating behavior, nutritional status and health conditions of college students attempting a weight control. The subjects are 88 students of the Daegu area. Their weight, height, triceps, and mid-arm circumference were measured and their dietary intake and eating behavior were obtained by using questionnaires. The 24-hour recall was obtained from the subjects. The results are summarized as follows: The average height, weight and BMI of the attempt and no-attempt male and female students were 171.2cm, 70.7kg and 24.1; 170.4cm, 79.9kg and 27.5; 159.3cm, 60.9kg and 24.0; 157.7cm 60.1kg and 24.2, respectively. Energy intake of the attempt and no-attempt male and female group was 63.9%, 61.8%, 76.2% and 83.9% of RDA respectively. Protein intake of each group was 97.5%, 83.9%, 60.1% and 67.3% of RDA respectively. The following items registered a negative correlation weight and carbohydrate, weight and Na intake, weight and vitamin C intake, PIBW and Na intake, TSF and fiber intake, TSF and Na intake, TSF and vitamin C intake, MAMC and Na intake, and MAMC and vitamin C intake. A relative magnitude of factors affecting weight control was analyzed by Stepwise multiple regression analysis. Overall results about relative influence of independent variables to the dependent variable(weight control) indicated that the BMI (p<0.01) was the most significantly correlated with weight control in all subjects. The results of this study suggest that the extensive nutrition education in the weight control program should be emphasized to prevent obesity early.

• Journal of Korea Multimedia Society
• /
• v.12 no.7
• /
• pp.1032-1042
• /
• 2009

This research is for early extraction and utilization of semantic information from the tags in tagged Web image retrieval. Generally, users attach a tag to a Web image with little thought of the order, up to over 100 ones. In this paper, we suggest a method of selecting prior tags based on their importance when tagged images are uploaded, and using them in image retrieval. Ideas came from the recognition of the important tags which give a better description of the image as the tags sharing more semantic information with other tags of the same image. This method includes calculation of relation scores between tags based on WordNet and multilevel search of tagged images with the scores. For evaluation, we compared the suggested method and other retrieval methods searching images with simple matching of tags to a given keyword. As the results, we found the superiority of our method in precision and recall rate.

• Korean Journal of Community Nutrition
• /
• v.10 no.6
• /
• pp.860-868
• /
• 2005

Anemia diagnosed early in pregnancy is associated with increased risks of low birth weight and preform delivery. The purposes of this study were to assess the maternal iron status during pregnancy and to evaluate the relationships between the iron indices of maternal-umbilical cord serum iron and ferritin levels and pregnancy outcomes. Dietary intakes of the pregnant women were estimated by 24 hour-recall (3 times). Serum iron and ferritin levels in maternal blood and umbilical cord were measured at 1st-, 2nd-, 3rd- trimester and delivery, respectively. The mean of maternal se겨m iron levels of the trimester and delivery were $124.27\;{\mu}g/dl,\;97.03\;{\mu}g/dl,\;94.32\;{\mu}g/dl,\;and\;145.53\;{\mu}g/dl$. Those maternal levels were significantly lower than that of umbilical cord blood ($222.59\;{\mu}g/dl$). Serum ferritin levels of maternal trimester and delivery were 22.68 $22.68\;{\mu}g/l,\;11.09\;{\mu}g/l,\;14.18\;{\mu}g/l,\;and\;\;24.54\;{\mu}g/l$, which were significantly lower than those of umbilical cord blood ($184.35\;{\mu}g/l$) (p < 0.0001). This prevalence of anemia of total subjects was $30.3\%$ by WHO criteria (Hb < 11.0 g/dl, Hct < $33\%$). Iron levels of 2nd-trimester was significantly higher in the normal group than in the anemia group. And ferritin levels of 3rd-trimester and delivery was significantly higher in the normal group than in the anemia group. Therefore, we suggest for successful pregnancy outcome and delivery differential iron supplementation programs will be carried out with individual Pregnant women on the basis of pre-Pregnancy nutrition. (Korean J Community Nutrition 10(6) : $860\∼868$, 2005)

• Korean Journal of Community Nutrition
• /
• v.16 no.2
• /
• pp.278-293
• /
• 2011

The purpose of this study was to examine the research trend of nutrition for the recent 12 years from 1996 to 2007 by analyzing 734 articles published in the Korean Journal of Community Nutrition. The majority of the articles (61.4%) were classified as survey types in terms of data collection methods. Most of the subjects used in the articles were adults (28.8%), and the subject whose research has been increased at the highest rate was "patients". The most frequent keywords in the title of articles were "nutrient intake" (231times), "food service" (92times), "dietary habits" (69times), and "obesity" (69times). The keywords that have appeared more frequently with the years were "osteoporosis" (450.0%), "menopause" (350.0%) and "dietary attitudes" (208.3%). As for research interests, "nutrient intake" was dominant in the early stage of research while "disease", "dietary habits", "dietary attitudes" and "nutrition education" have increased in recent years. Some of the most common methods of nutrition assessment were "dietary intake" (41.2%), "anthropometric" (34.0%) and "biochemical test" (14.7%). The most common methods of dietary intake were "24-hours recall" (28.6%) and "dietary habits" (23.3%). The results of this study showed some biases in data collection methods, gender of the subjects, and study areas. Moreover, inconsistent terminologies, questionnaire contents, and measures were used for the researches on dietary behaviors, dietary habits, dietary attitudes, which made it difficult to compare their results for each research. Therefore, standardized research methods and terminologies need to be developed regarding dietary practices.

• Nutrition Research and Practice
• /
• v.8 no.3
• /
• pp.319-326
• /
• 2014

BACKGROUND/OBJECTIVES: The immigrant population has grown considerably in South Korea since the early 1990s due to international marriages. Dietary changes in immigrants are an important issue, because they are related to health and disease patterns. This study was conducted to compare changes in dietary intake between baseline and follow-up periods. SUBJECTS/METHODS: Two hundreds thirty three Vietnamese female married immigrants. Baseline data were collected during 2006-2009, and the follow-up data were collected during 2008 and 2010. Food consumption was assessed using a 1-day 24-hour recall. RESULTS: The amount of the total food consumed (P < 0.001) including that of cereals (P = 0.004), vegetables (P = 0.003), and fruits (P = 0.002) decreased at follow-up compared to that at baseline, whereas consumption of milk and dairy products increased (P = 0.004). Accordingly, the overall energy and nutrient intake decreased at follow-up, including carbohydrates (P = 0.012), protein (P = 0.021), fiber (P = 0.008), iron (P = 0.009), zinc (P = 0.006), and folate (P = 0.002). Among various anthropometric and biochemical variables, mean skeletal muscle mass decreased (P = 0.012), plasma high density lipoprotein-cholesterol increased, (P = 0.020) and high sensitivity C-reactive protein decreased at follow-up (P < 0.001). CONCLUSIONS: A long-term follow-up study is needed to investigate the association between changes in food and nutrient intake and anthropometric and biochemical variables in these Vietnamese female marriage immigrants.