• Journal of Preventive Medicine and Public Health
• /
• v.56 no.4
• /
• pp.338-347
• /
• 2023

Objectives: Young children's feeding characteristics can play an important role in eating habits and health during later childhood. This study was conducted to examine the associations of feeding characteristics with dietary patterns and obesity in children. Methods: This study utilized data from the Korea National Health and Nutrition Examination Survey conducted between 2013 and 2017. In total, 802 toddlers were included, with information on their demographic characteristics, feeding practices and duration, and 24-hour recall obtained from their parents. Feeding characteristics were categorized into feeding type, duration of total breastfeeding, duration of total formula feeding, duration of exclusive breastfeeding, and age when starting formula feeding. Dietary patterns were identified based on factor loadings for the food groups for 3 major factors, with "vegetables & traditional," "fish & carbohydrates," and "sweet & fat" patterns. Overweight/obesity was defined as ≥85th percentile in body mass index based on the 2017 Korean National Growth charts for children and adolescents. Multiple regression analysis was conducted to examine associations between feeding characteristics and dietary patterns. The association between dietary patterns and obesity was analyzed using multivariable logistic regression analysis. Results: The early introduction of formula feeding was inversely associated with the "vegetables & traditional" pattern (β=-0.18; 95% confidence interval [CI], -0.34 to -0.02). A higher "vegetables & traditional" intake was associated with a lower risk of obesity (odds ratio, 0.48; 95% CI, 0.24 to 0.95). Conclusions: Feeding characteristics are associated with dietary patterns in later childhood, and dietary patterns were shown to have a potential protective association against obesity.

• 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.

• Advances in nano research
• /
• v.16 no.6
• /
• pp.531-548
• /
• 2024

The study focuses on using remote sensing to gather data about the Earth's surface, particularly in urban environments, using satellites and aircraft-mounted sensors. It aims to develop a classification framework for road targets using multi-spectral imagery. By integrating Convolutional Neural Networks (CNNs) with XGBoost, the study seeks to enhance the accuracy and efficiency of road target identification, aiding urban infrastructure management and transportation planning. A novel aspect of the research is the incorporation of quantum sensors, which improve the resolution and sensitivity of the data. The model achieved high predictive accuracy with an MSE of 0.025, R-squared of 0.85, RMSE of 0.158, and MAE of 0.12. The CNN model showed excellent performance in road detection with 92% accuracy, 88% precision, 90% recall, and an f1-score of 89%. These results demonstrate the model's robustness and applicability in real-world urban planning scenarios, further enhanced by data augmentation and early stopping techniques.

• 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.

• ETRI Journal
• /
• v.46 no.4
• /
• pp.671-682
• /
• 2024

Violence can be committed anywhere, even in crowded places. It is hence necessary to monitor human activities for public safety. Surveillance cameras can monitor surrounding activities but require human assistance to continuously monitor every incident. Automatic violence detection is needed for early warning and fast response. However, such automation is still challenging because of low video resolution and blind spots. This paper uses ResNet50v2 and the gated recurrent unit (GRU) algorithm to detect violence in the Movies, Hockey, and Crowd video datasets. Spatial features were extracted from each frame sequence of the video using a pretrained model from ResNet50V2, which was then classified using the optimal trained model on the GRU architecture. The experimental results were then compared with wavelet feature extraction methods and classification models, such as the convolutional neural network and long short-term memory. The results show that the proposed combination of ResNet50V2 and GRU is robust and delivers the best performance in terms of accuracy, recall, precision, and F1-score. The use of ResNet50V2 for feature extraction can improve model performance.

• 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.