• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.139-140
• /
• 2018

본 논문에서는 지도 기계 학습 알고리즘 중 하나인 Naive Bayesian (NB) 알고리즘의 데이터 분류 정확도를 향상시키기 위하여 데이터 속성에 Weight를 부여하는 새로운 기법을 제안하였다. 기존에 Decision Tree(DT) 알고리즘의 깊이를 이용하여 Weigth를 부여하는 방법이 제안되었으나, DT를 구축하는데 오버헤드가 크기 때문에 데이터의 실시간 분석이나 자원 제한적인 환경에서의 적용은 어렵다는 단점이 있다. 이를 해결하기 위하여 본 논문에서는 최소한의 데이터를 사용하여 신속하게 DT를 구축하는 Very Fast Decision Tree (VFDT) 알고리즘 기반의 Weight 부여 기법을 제안함으로써 적은 오버헤드로 NB의 정확도를 향상시킨다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.11
• /
• pp.1536-1544
• /
• 1995

We propose a design scheme of a binary decision tree and apply it to the tire tread pattern recognition problem. In this scheme, a binary decision tree is constructed by using fuzzy C-means( FCM ) algorithm. All the available features are used while clustering. At each node, the best feature or feature subset among these available features is selected based on proposed similarity measure. The decision tree can be used for the classification of unknown patterns. The proposed design scheme is applied to the tire tread pattern recognition problem. The design procedure including feature extraction is described. Experimental results are given to show the usefulness of this scheme.

• International Journal of Contents
• /
• v.17 no.4
• /
• pp.79-90
• /
• 2021

With the deepening of population aging, pension has become an urgent problem in most countries. Community smart pension can effectively resolve the problem of traditional pension, as well as meet the personalized and multi-level needs of the elderly. To predict the pension intention of the elderly in the community more accurately, this paper uses the decision tree classification method to classify the pension data. After missing value processing, normalization, discretization and data specification, the discretized sample data set is obtained. Then, by comparing the information gain and information gain rate of sample data features, the feature ranking is determined, and the C4.5 decision tree model is established. The model performs well in accuracy, precision, recall, AUC and other indicators under the condition of 10-fold cross-validation, and the precision was 89.5%, which can provide the certain basis for government decision-making.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.1274-1277
• /
• 2011

단백질 1차 서열로부터 DISORDER와 ORDER지역을 예측하기 위해서 이 논문에서는 EP-tree에 기반한 출현패턴 발견 알고리즘을 제안하였다. EP-tree 알고리즘을 적용함으로서 기존의 단백질 특징 추출을 통한 방법과 달리 서열 자체에서 발견되는 출현패턴만을 이용하여 분류 모델을 생성하므로 기존의 신경망이나 SVM 보다 분류모델 생성 및 예측 속도가 빠르다. 또한 Disprot 4.9과 CASP7 테스트 데이터로 DISORDER/ORDER 지역을 예측한 결과, 73.4%의 높은 정확성을 보였다.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.33 no.2
• /
• pp.1-16
• /
• 2008

The purpose of this paper is to propose a new binary classification method for predicting corporate failure based on genetic algorithm, and to validate its prediction power through empirical analysis. Establishing virtual companies representing bankrupt companies and non-bankrupt ones respectively, the proposed method measures the similarity between the virtual companies and the subject for prediction, and classifies the subject into either bankrupt or non-bankrupt one. The values of the classification variables of the virtual companies and the weights of the variables are determined by the proper model to maximize the hit ratio of training data set using genetic algorithm. In order to test the validity of the proposed method, we compare its prediction accuracy with ones of other existing methods such as multi-discriminant analysis, logistic regression, decision tree, and artificial neural network, and it is shown that the binary classification method we propose in this paper can serve as a premising alternative to the existing methods for bankruptcy prediction.

• MALSORI
• /
• no.66
• /
• pp.61-72
• /
• 2008

This paper proposes a method to improve pathological and normal voice classification performance by combining multiple features such as auditory-based and higher-order features. Their performances are measured by Gaussian mixture models (GMMs) and linear discriminant analysis (LDA). The combination of multiple features proposed by the frame-based LDA method is shown to be an effective method for pathological and normal voice classification, with a 87.0% classification rate. This is a noticeable improvement of 17.72% compared to the MFCC-based GMM algorithm in terms of error reduction.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.26 no.4
• /
• pp.333-340
• /
• 2008

This paper shows that the use of prior probabilities of the involved classes improve the accuracy of classification in case of poor separability between classes. Three cases of experiments are designed with two LiDAR datasets while considering three different classes (building, tree, and flat grass area). Moreover, random sampling method with human interpretation is used to achieve the approximate prior probabilities in this research. Based on the experimental results, Bayesian classification with the appropriate prior probability makes the improved classification results comparing with the case of non-prior probability when the ratio of prior probability of one class to that of the other is significantly different to 1.0.

• Journal of Food Hygiene and Safety
• /
• v.34 no.2
• /
• pp.212-218
• /
• 2019

The process of establishing domestic standards on hazardous substances in food safety regulations requires harmonization with standards from the Codex Alimentarius Commission (CAC). For this purpose, food classification by the CAC (Codex Classification of Foods and Animal Feeds) also needs to be clearly understood. Therefore, this paper aimed to introduce the Codex Classification on cereal grains, nuts/seeds and herbs/spices because revisions of the Codex were completed in 2017 for cereal grains and in 2018 for nuts/seeds and herbs/spices. The revised Codex Classification on those foods is briefly summarized as follows. Cereal grains in the domestic food classification by the Ministry of Food and Drug Safety, Korea (MFDS) corresponds to the Codex Group 020 cereal grains with six subgroups. The MFDS's nuts and seeds classification corresponds to three groups in the Codex, namely, Group 022 (tree nuts with no subgroups), Group 023 (oilseeds and oilfruits with 5 subgroups), and Group 024 (seeds for beverages and sweets with no subgroups). The food commodities of herbs and spices are included in two Codex groups, Group 027 (with 3 subgroups) and Group 028 (with 9 subgroups). The number of Codex commodity codes assigned to food commodities was 27 for Group 020, 32 for Group 022, 46 for Group 023, 4 for Group 024, 127 for Group 027 and 138 for Group 028. In between the Codex Classification and the MFDS's classification, some differences are shown. For example, the MFDS did not create a subgroup under groups of cereal grains and herbs. The MFDS classified peanuts into the nut group, though a separate group for oilseeds is present, while the Codex classified peanuts into the oilseed and oilfruit group. In addition, there is also a separate group of "plants, others" present in the MFDS's classification. Therefore, care is needed in using the Codex Classification.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.796-799
• /
• 1996

광섬유는 코어(Core), 클레드(Clad), 그리고 1,2차 코팅(Coating)으로 구성되어 있다. 본 연구에서는 광섬유의 코팅에 생기는 결함의 유무 및 종류와 크기를 분류하는 Vision System을 구현하였다. 전처리 과정으로, CCD Camera를 이용하여 얻은 화상에 대하여 Sobel 연산자로 경계선을 추출하고, 문턱값(Threshold Value)을 적용하여 이진 화상을 만든다. 외경 정보 추출을 위하여, 투영 정보, 수리 형태학(Mathematical Morphology)적 연산을 수행하고, 결함의 종류와 크기를 효율적으로 분류하도록 Tree Classifier를 설계하였다. 실험 결과로서 각 결함 별 오차율, 전체 오차율(Total Error Rate)등을 제시하였다.

• Smart Media Journal
• /
• v.13 no.1
• /
• pp.24-35
• /
• 2024

The combination of Artificial Intelligence and the Internet of Things (AIoT) has gained significant popularity. Deep neural networks (DNNs) have demonstrated remarkable success in various applications. However, deploying complex AI models on embedded boards can pose challenges due to computational limitations and model complexity. This paper presents an AIoT-based system for smart parking lots using edge devices. Our approach involves developing a detection model and a decision tree for occupancy status classification. Specifically, we utilize YOLOv5 for car license plate (LP) detection by verifying the position of the license plate within the parking space.