• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.31-40
• /
• 2024

In the realm of domestic online fashion platform industry the manual registration of product information by individual business owners leads to inconvenience and reliability issues, especially when dealing with simultaneous registrations of numerous product groups. Moreover, bias is significantly heightened due to the low quality of product images and an imbalance in data quantity. Therefore, this study proposes a ResNet50 model aimed at minimizing data bias through oversampling techniques and conducting multiple classifications for 13 fashion categories. Transfer learning is employed to optimize resource utilization and reduce prolonged learning times. The results indicate improved discrimination of up to 33.4% for data augmentation in classes with insufficient data compared to the basic convolution neural network (CNN) model. The reliability of all outcomes is underscored by precision and affirmed by the recall curve. This study is suggested to advance the development of the domestic online fashion platform industry to a higher echelon.

• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.529-542
• /
• 2000

Recent years, the use of multimedia information is rapidly increasing, and the video media is the most rising one than any others, and this field Integrates all the media into a single data stream. Though the availability of digital video is raised largely, it is very difficult for users to make the effective video access, due to its length and unstructured video format. Thus, the minimal interaction of users and the explicit definition of video structure is a key requirement in the lately developing image and video management systems. This paper defines the terms and hierarchical video structure, and presents the system, which construct the clustering-based video hierarchy, which facilitate users by browsing the summary and do a random access to the video content. Instead of using a single feature and domain-specific thresholds, we use multiple features that have complementary relationship for each other and clustering-based methods that use normalization so as to interact with users minimally. The stage of shot boundary detection extracts multiple features, performs the adaptive filtering process for each features to enhance the performance by eliminating the false factors, and does k-means clustering with two classes. The shot list of a result after the proposed procedure is represented as the video hierarchy by the intelligent unsupervised clustering technique. We experimented the static and the dynamic movie videos that represent characteristics of various video types. In the result of shot boundary detection, we had almost more than 95% good performance, and had also rood result in the video hierarchy.

• The Journal of Korean Medicine Ophthalmology and Otolaryngology and Dermatology
• /
• v.25 no.1
• /
• pp.84-103
• /
• 2012

Objectives : The middle school students'life style were studied with focus on Body Mass Index(BMI). Information was collected during 1st June 2009 to 10th July from 397 students(both male and female) by the subjective survey centered on personal characteristic, understanding about health in general, everyday activities, eating habits, preference in food, understanding about diet and obesity, and thoughts about fitness and diet. Methods : Students were selected from six classes by convenience sampling, then the final analysis was performed on 397 self-administered questionnaires, excepting 5 questionnaires, which have insincere answers. The data collection was carried out by SPSS(V.14.0 English Version), and the data was verified by $x^2$-test, ANOVA, multiple regression analysis. Results and Conclusion : The survey subjects were in the following distribution of body weights - underweight: 63.6%, normal weight: 29.5% and 6.9% were overweight. There was significantly different between BMI and mothers' occupation and satisfaction with school life(p<0.05). As for the analysis(multiple regression analysis) on understanding about health, the factors that affect BMI are self recognition of figure and efforts to reduce weight. In terms of efforts for one's own health, 78.2% of under weight and 82.3% of normal weight were taking active initiatives. But 85.2% of the overweight students were not giving any efforts. As for the free time activities, more than half answered, 'playing with computers'(48.4 - 66.7%, 1.57 hours on average). As for TV, on average, 2.03 hours were spent in overall. And it turned out that the overweight students spent more time watching TV by 46.49 minutes(0.77 hours) on average(p<0.05). 7.4 hours was the average sleeping time. As for the eating habit,'quantity of meal, snack, meal between meals, fat reduction, and supplementary food'were shown to be related to the BMI(p<0.05). The instant food, meat and sweet food were shown to be also related to the BMI. In terms of knowledge about overweight and diet, only 8 students(2% of the total) answered all 10 questions correct. On average, 7-8 questions were correctly answered(53.9 %). When the scores were analyzed against the BMI by classifying the scores to high, middle and low categories, it showed a relationship by different weight group(p<0.02), and the overweight students had higher score by 0.82 compared to the underweight students. When thoughts and attitude on fitness and diet were analyzed in relationship to the BMI, the result was only - "I try to eat fruits more often"(fruits)(p<0.00).

• The KIPS Transactions:PartD
• /
• v.14D no.6
• /
• pp.585-596
• /
• 2007

XML data generally consists of a hierarchical tree-structure which is reflected in mechanisms to store and retrieve XML data. Therefore, when storing XML data in the database, the hierarchical relationships among the XML elements are taken into consideration during the restructuring and storing of the XML data. Also, in order to support the search queries from the user, a mechanism is needed to compute the hierarchical relationship between the element structures specified by the query. The structural join operation is one solution to this problem, and is an efficient computation method for hierarchical relationships in an in database based on the node numbering scheme. However, in order to process a tree structured XML query which contains a complex nested hierarchical relationship it still needs to carry out multiple structural joins and results in another problem of having a high query execution cost. Therefore, in this paper we provide a preprocessing mechanism for effectively reducing the cost of multiple nested structural joins by applying the concept of equivalence classes and suggest a query path reduction algorithm to shorten the path query which consists of a regular expression. The mechanism is especially devised to reduce path queries containing branch nodes. The experimental results show that the proposed algorithm can reduce the time requited for processing the path queries to 1/3 of the original execution time.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.1
• /
• pp.59-65
• /
• 2008

In this paper, a new adaptive resource allocation scheme is proposed in orthogonal frequency-division multiple access(OFDMA) systems with rate proportionality constraints. The problem of maximizing the overall system capacity with constraints on bit error rate, total transmission power and rate-proportionality for user requiring different classes of service is formulated. Since the optimal solution to the constrained fairness problem is extremely complex to obtain, a low-complexity suboptimal algorithm that separates subchannel allocation and power allocation is proposed. Firstly, the number of subchannels to be assigned to each user is determined based on the users' average signal-to-noise ratio and rate-proportion. Subchannels are subsequently distributed according to the modified max-min criterion. Lastly, based on the subchannel allocation, the optimal power allocation by solving the Language dual problem is proposed. Additionally, in order to reduce the computational complexity, iterative rate proportionality tracking algorithm is proposed for maximizing the capacity together with maintaining the rate proportionality constraint.

• Education of Primary School Mathematics
• /
• v.11 no.1
• /
• pp.39-57
• /
• 2008

The purpose of this study is to affirm what influences the lessons applied by reorganizing the ratio-graph unit of level 6-A on the basis on Realistic Mathematics Education(RME) give on mathematical scholastic achievements and mathematical preferences.In order to achieve the purpose of this study, the experimental study was exerted by making two classes of 6 grades in J elementary school located in Gumi city, Gyeongbuk province as subjects. In this study, test of degree of the mathematics learning ability of student, multiple-choice test and descriptive test of the learning dispositions of student were exerted and the results were t-test officially. The results and the conclusions of this study were as follows: First, the results acquired by officially t-test the levels of the mathematics learning ability of student of the group taught by lessons according to the teaching materials reorganized on the basis of RME and the group taught by lessons according to the 7th curriculum show a meaningful difference(p=.007). This means that the lessons according to the teaching materials reorganized on the basis of RME showed meaningful influences on the improvement of degree of the mathematics learning ability of student. Second, the results acquired by officially t-test the learning dispositions of student multiple-choice test of the group taught by lessons according to the teaching materials reorganized on the basis of RME and the group taught by lessons according to the 7th curriculum show a meaningful difference. Especially in the factors of 'mathematical will'(p=.017) and 'mathematical value'(p=.029) were meaningful differences. Also in the descriptive test of the learning dispositions of student, the experimental class showed that it had the potential possibility to have more positive attitudes meaningfully in comparison with the compared class. This means that the lessons according to the teaching materials reorganized on the basis of RME showed meaningful influences on the learning dispositions of student.

• Journal of agricultural medicine and community health
• /
• v.37 no.4
• /
• pp.246-257
• /
• 2012

Objectives: To compare the self-rated health in chronic disease patients with depression, chronic disease patients, and depression patients, and to observe the related factors to the self-rated health of people age 65 and older. Methods: The subjects were 2,549 elderly people, over 65 years old in Busan Metropolitan City who participated in 2009 community health survey. Association between self-rated health and general characteristics, life style and disease status were observed. Depressive symptoms were measured using the Centre for Epidemiologic Studies Depression Scale (CES-D). Analysis of complex sample was done with SAS (ver. 9.2), using ${\chi}^2$-test and multiple logistic regression. Results: Among total 2,549, there were 740 normal people (29.8%), 50 people with depression (1.8%), 1,495 people with other chronic diseases (58.2%), and 264 people with the comobidity of depression and other chronic diseases (10.1%). Good self-related health accounted for 20.3% for the whole, 33.4% for normal, 16.7% for chronic disease, 16.1% for depression, and 3.2% for chronic diseases with depression. Disease, gender, education, income, alcohol drinking, regular exercise and regular walking were independent factors associated with the good self-related health. Conclusions: It is suggested that when the chronic disease control program for the elderly is developed, depression care should be considered along with the program. This program should be given priority to the women and the vulnerable classes and should also be related to the regular walking.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.1
• /
• pp.109-132
• /
• 2019

The purpose of this study is to examine and propose to improve the features of a simple keyword search box and faceted navigations of KOLIS-NET operated by the National Library of Korea. A record group of '2011-2020 (776)' under 'Publication date' facet, out of 3,702 records retrieved from a search of '김훈', were examined. Major findings are as follows: (1) Five facets including 'Format', 'Publication date', 'Subject', 'Language' and 'Country' are used to limit search results only in the first step, and multiple facets cannot be simultaneously used; (2) With 'Publication date' facet formed in the span of ten years, a separate publication year cannot be identified; (3) 'Subject' facet based on KDC limits the results only in broad subject classes without sub-facets; (4) Under 'Format' facet, a special format such as large print texts cannot be identified; (5) Without 'Author' facet, authors cannot be identified; and (6) 'Publication date missing', 'Language missing', and 'Miscellaneous subject' record groups cannot be clicked and displayed, a navigation to-and-fro between a brief list and bibliographic records is not smooth, etc. Therefore an application of multiple facets in all stages of limiting the search result, a construction of sub-facets for 'Publication date' and 'Subject' facets, an accurate description and coding of 'General Material Designation', etc. are suggested to improve KOLIS-NET's faceted navigation.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.182-189
• /
• 2021

A study was conducted to identify the general characteristics of some dental hygiene students and to identify the factors affecting the achievement goal orientation and academic achievement according to the teaching method selection for increase the academic achievement of the subject in the special education environment caused by the COVID-19. In the second semester of 2020, a survey was conducted on 122 students of G University's dental hygiene department located in Gwangju, and the general characteristics and achievement goal orientation were surveyed. Academic achievement has used the midterm and final exam scores and the collected data were analyzed using Kruskal-Wallis test, Mann-Whitney U test, Pearson's correlation test, Multiple Linear Regrission. According to the general characteristics, there was a significant difference in subject understanding, subject interest, and subject satisfaction, and learning satisfaction showed a strong correlation with the completion goal tendency. There was a significant difference in academic achievement according to the class choice, and the factor that influenced the academic achievement was the case that the teaching method was chosen face-to-face. Therefore, in order to improve learners' academic achievement, it is necessary to increase the proportion of face-to-face classes and to establish an effective lesson plan that can increase the degree of subject understanding, subject interest, and subject satisfaction.