• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.999-1008
• /
• 2023

Early prediction of chronic diseases such as diabetes is an important issue, and improving the accuracy of diabetes prediction is especially important. Various machine learning and deep learning-based methodologies are being introduced for diabetes prediction, but these technologies require large amounts of data for better performance than other methodologies, and the learning cost is high due to complex data models. In this study, we aim to verify the claim that DNN using the pima dataset and k-fold cross-validation reduces the efficiency of diabetes diagnosis models. Machine learning classification methods such as decision trees, SVM, random forests, logistic regression, KNN, and various ensemble techniques were used to determine which algorithm produces the best prediction results. After training and testing all classification models, the proposed system provided the best results on XGBoost classifier with ADASYN method, with accuracy of 81%, F1 coefficient of 0.81, and AUC of 0.84. Additionally, a domain adaptation method was implemented to demonstrate the versatility of the proposed system. An explainable AI approach using the LIME and SHAP frameworks was implemented to understand how the model predicts the final outcome.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1964-1965
• /
• 2011

본 연구에서는 패턴분류를 위해 기존의 방사형 기저 함수 신경회로망(Radial Basis Funtion Neural Network)과 다항식 신경회로망(Polynomial Neural Network)을 결합한 다중 출력 방사형 기저 함수다항식 신경회로망 (Multi Output Radial Basis Funtion Polynomial Neural Network)의 분류기를 제안한다. 제안된 모델은 PNN을 기본 구조로 하여 1층에 기존의 다항식 노드 대신 다중 출력 형태의 RBFNN을 적용 한다. RBFNN의 은닉층에는 기존의 활성함수가 아닌 fuzzy 클러스터링을 사용하여 입력 데이터의 특성을 고려한 적합도를 사용하였다. PNN은 입력변수의 수와 다항식 차수가 모델의 성능을 결정함으로 최적화가 필요하며 본 논문에서는 Differential Evolution(DE)을 사용하여 모델의 구조 및 파라미터를 최적화시켜 모델의 성능을 향상시켰다. 패턴분류기로써의 제안된 모델을 평가하기 위해 pima 데이터를 이용하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.462-465
• /
• 2004

수치적인 데이터를 분류하기 위한 대표적인 방법은 퍼지 규칙을 사용하는 것이다. 하지만, 이러한 방법은 퍼지 소속 함수를 어떻게 정의하느냐에 따라 퍼지 분류의 성능이 크게 영향을 받는다는 문제점과 퍼지 규칙을 쉽게 이해하기 위해 가능한 퍼지 규칙의 수를 적게 유지해야한다는 문제점이 있다. 본 논문에서는 효과적이며 이해하기 쉬운 퍼지 규칙을 생성하기 위해 기울기 강하법을 기반으로 하는 소속 함수 학습 방법을 제안한다. 에러율을 감소하기 위해 Penalty 연산과 Reward 연산을 통해 소속 함수가 반복적으로 조절된다. 새로운 소속 함수는 Coverage 연산에 의해 생성된다. 또한 이해하기 쉬운 퍼지 규칙을 최적화하기 위해 학습된 소속 함수를 퍼지 결정 트리에 적용한다. 본 논문에서 제안한 알고리즘의 타당성을 확인하기 위해 벤치 마크 데이터인 Iris, Wisconsin Breast Cancer, Pima. Bupa 데이터를 이용하여 실험 결과를 보인다. 실험 결과를 통해 제안한 알고리즘이 기존의 C4.5와 FID 3.1 알고리즘보다 더 효과적이거나 비슷한 성능을 보임을 알 수 있다.

• Communications for Statistical Applications and Methods
• /
• v.27 no.3
• /
• pp.285-299
• /
• 2020

In many cases, we are interested in identifying independence between variables. For continuous random variables, correlation coefficients are often used to describe the relationship between variables; however, correlation does not imply independence. For finite discrete random variables, we can use the Pearson chi-square test to find independency. For the mixed type of continuous and discrete random variables, we do not have a general type of independent test. In this study, we develop a independence test of a continuous random variable and a discrete random variable without assuming a specific distribution using kernel density estimation. We provide some statistical criteria to test independence under some special settings and apply the proposed independence test to Pima Indian diabetes data. Through simulations, we calculate false positive rates and true positive rates to compare the proposed test and Kolmogorov-Smirnov test.

• Biomedical Science Letters
• /
• v.15 no.1
• /
• pp.101-103
• /
• 2009

The hepatocyte nuclear factor-$4{\alpha}$ (HNF-$4{\alpha}$), transcription factor involved in the regulation of serum lipid and glucose levels, has recently been reported to be associated with type 2 diabetes. Therefore, we investigated the genotype for the rs1884614 of HNF-$4{\alpha}$ gene in Korean population and compared genotype of patients with control group. 100 patients (Male 63, Female 37), who previously underwent type 2 diabetes (T2DM) and 100 controls (Male 36, Female 64) participated in this study. According to our present study there was no association between rs1884614 polymorphism in HNF-$4{\alpha}$ gene and T2DM in Koreans although other reports showed that HNF-$4{\alpha}$ polymorphisms might be associated with the pathogenesis of T2DM in Pima Indians et al. We assume that this finding should contribute to understanding of type 2 diabetes in Korean population in detail at genetic level.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.1
• /
• pp.47-53
• /
• 2019

The idea of ensemble learning is to train multiple models, each with the objective to predict or classify a set of results. Most of the errors from a model's learning are from three main factors: variance, noise, and bias. By using ensemble methods, we're able to increase the stability of the final model and reduce the errors mentioned previously. By combining many models, we're able to reduce the variance, even when they are individually not great. In this paper we propose an ensemble model and applied it to classification problem. In iris, Pima indian diabeit and semiconductor fault detection problem, proposed model classifies well compared to traditional single classifier that is logistic regression, SVM and random forest.

• KIEAE Journal
• /
• v.9 no.2
• /
• pp.91-98
• /
• 2009

The purpose of this study is analyzing the prescriptions of American codes for straw bale structures and proposing the legislation direction of Korean building code. The process of this study is as follows: (1) To set up the legislation direction of straw bale code of Korea, this study investigated the current state and features of straw bale houses in Korea, and looked into the worldwide status of straw bale codes and permitting. (2) To provide basic data for the legislation of Korean straw bale code or guideline, this study analyzed American codes for straw bale structures like the Tucson/Pima County Arizona Building Code Appendix Chapter 72 - Straw-Bale Structures, California State Guidelines for Straw-Bale Structures, New Mexico Standards for Non-load Bearing Baled Straw Construction, Oregon State Residential Code Appendix M - Straw-Bale Structures and so on. The analysis items are the scope of rule application, material specifications, requirements for straw bale walls/foundations and construction requirements. (3) On the base of analysis of American straw bale codes, this study proposed the legislation process and direction of Korean straw bale code and guideline.

• Biomedical Science Letters
• /
• v.15 no.4
• /
• pp.301-307
• /
• 2009

Whole-body insulin resistance results largely from impaired insulin-stimulated glucose disposal in skeletal muscle. Our previous studies using differential display and quantitative real-time RT-PCR have shown that a novel cDNA band (DD23) had a higher level of expression in insulin resistant skeletal muscle and it was correlated with whole-body insulin action, independent of age, sex, and percent body fat. In this study, we cloned and characterized DD23. The DD23 sequence is part of the 3'UTR region of the RNA binding motif, single stranded interacting protein (RBMS3). We have cloned the full length cDNA for RBMS3 and identified two splice variants. These variants named DD23-L and DD23-S have 15 and 14 exons respectively and differ from RBMS3 in the 3'UTR significantly. Northern blot analyses showed that an ~8.8 kb mRNA transcript of DD23 was predominantly expressed in skeletal muscle and to a lesser extent in placenta, but not in heart, brain, lung, liver, or kidney, unlike RBMS3. Elevated expression levels of these novel alternatively spliced variants of RBMS3 in skeletal muscle may play a role in whole body insulin resistance.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.19-30
• /
• 2021

Diabetes Mellitus (DM) is one of common chronic diseases leading to severe health complications that may cause death. The disease influences individuals, community, and the government due to the continuous monitoring, lifelong commitment, and the cost of treatment. The World Health Organization (WHO) considers Saudi Arabia as one of the top 10 countries in diabetes prevalence across the world. Since most of the medical services are provided by the government, the cost of the treatment in terms of hospitals and clinical visits and lab tests represents a real burden due to the large scale of the disease. The ability to predict the diabetic status of a patient without the laboratory tests by performing screening based on some personal features can lessen the health and economic burden caused by diabetes alone. The goal of this paper is to investigate the prediction of diabetic and prediabetic patients by considering factors other than the laboratory tests, as required by physicians in general. With the data obtained from local hospitals, medical records were processed to obtain a dataset that classified patients into three classes: diabetic, prediabetic, and non-diabetic. After applying three machine learning algorithms, we established good performance for accuracy, precision, and recall of the models on the dataset. Further analysis was performed on the data to identify important non-laboratory variables related to the patients for diabetes classification. The importance of five variables (gender, physical activity level, hypertension, BMI, and age) from the person's basic health data were investigated to find their contribution to the state of a patient being diabetic, prediabetic or normal. Our analysis presented great agreement with the risk factors of diabetes and prediabetes stated by the American Diabetes Association (ADA) and other health institutions worldwide. We conclude that by performing class-specific analysis of the disease, important factors specific to Saudi population can be identified, whose management can result in controlling the disease. We also provide some recommendations learnt from this research.

• Smart Media Journal
• /
• v.12 no.8
• /
• pp.26-36
• /
• 2023

The purpose of this study is to propose ways to revitalize the local economy by analyzing the index changes and tourism big data before and after the opining of the KTX on the Gangneung Line in Gangneung City, where the population continues to decline. For This, the main current status of Gangneung-si and internal operation record data(DTG) of Gangneung-si were analyzed. After that, changes in the movement behavior of public transportation users before and after the opening of the KTX Gangneung Line were compared. As a result, it was possible to observe changes in tourist transportation preferences, demographic shifts, alterations in small-scale business sectors and in the travel patterns of tourists within the city of Gangneung. In particular, changes in the small business sector have shown an increase in general restaurants, leisure food establishments(cafes, etc.), and accommodation facilities following the opening of the KTX Gangneung Line. All three sectors have experienced growth concentrated in the vicinity of Gangneung Station, indicating the influence of Gangneung Station, which opened in the central part of Gangneung city, following the inauguration of the KTX Gangneung Line.