• Title/Summary/Keyword: 비정형적 문제

Search Result 178, Processing Time 0.037 seconds

A Hybrid Oversampling Technique for Imbalanced Structured Data based on SMOTE and Adapted CycleGAN (불균형 정형 데이터를 위한 SMOTE와 변형 CycleGAN 기반 하이브리드 오버샘플링 기법)

  • Jung-Dam Noh;Byounggu Choi
    • Information Systems Review
    • /
    • v.24 no.4
    • /
    • pp.97-118
    • /
    • 2022
  • As generative adversarial network (GAN) based oversampling techniques have achieved impressive results in class imbalance of unstructured dataset such as image, many studies have begun to apply it to solving the problem of imbalance in structured dataset. However, these studies have failed to reflect the characteristics of structured data due to changing the data structure into an unstructured data format. In order to overcome the limitation, this study adapted CycleGAN to reflect the characteristics of structured data, and proposed hybridization of synthetic minority oversampling technique (SMOTE) and the adapted CycleGAN. In particular, this study tried to overcome the limitations of existing studies by using a one-dimensional convolutional neural network unlike previous studies that used two-dimensional convolutional neural network. Oversampling based on the method proposed have been experimented using various datasets and compared the performance of the method with existing oversampling methods such as SMOTE and adaptive synthetic sampling (ADASYN). The results indicated the proposed hybrid oversampling method showed superior performance compared to the existing methods when data have more dimensions or higher degree of imbalance. This study implied that the classification performance of oversampling structured data can be improved using the proposed hybrid oversampling method that considers the characteristic of structured data.

Design of Streaming based Unstructured-Data Collecting Framework in IoT Environment (IoT 환경에서 스트리밍 기반의 비정형 데이터 수집 프레임워크 설계)

  • Lee, Hoo-Young;Park, Koo-Rack;Kim, Dong-Hyun
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2017.01a
    • /
    • pp.57-58
    • /
    • 2017
  • 사물인터넷 환경의 다양한 기기에서는 매초마다 시스템 로그 데이터, 온도, 습도, 조도 및 위치 정보 등과 같은 데이터를 지속적으로 생성한다. 이렇게 생성된 데이터는 기기 안에서 대부분 소멸되거나 수집된다 하더라도 시스템 개선의 일부 목적으로 활용하는데 그칠 뿐이다. 본 논문에서는 각각의 사물인터넷 기기에서 발생하는 비정형 데이터를 스트리밍 방식을 통해 수집 서버로 전송하고 이를 유연한 스키마 구조를 가지는 NoSQL 데이터베이스에 적재하는 프레임워크 설계를 제안한다. 이렇게 수많은 장비로부터 수집된 로그 및 센싱 데이터는 빅데이터 분석을 통해 산업의 현장에서 생산성 향상을 위해 사용할 수 있으며 공공의 목적으로 도심지의 교통문제 해소와 재난 및 재해 예측에 활용될 수 있다.

  • PDF

Management for Cervical Instability (경추 불안정성의 관리)

  • Kim, Young-Min;Kim, Ho-Bong
    • The Journal of Korean Academy of Orthopedic Manual Physical Therapy
    • /
    • v.11 no.1
    • /
    • pp.74-91
    • /
    • 2005
  • 척추의 기본적인 생체 역학적 기능은 신체 부분간의 운동을 허용하고 척수와 신경근을 보호하는 것으로서 이러한 기능을 수행하기 위해서는 척추의 역학적 안정성이 필수적이다. 척추의 안정체계는 수동적 근 골격계, 능동적 근 골격계, 그리고 신경계의 세 가지 하부체계로 나누어지며 이들 하부체계는 각각 독립적으로 안정성에 관여하고 있다. 경추의 불안정성의 문제는 비정상적으로 증가된 추간관절의 운동에 의해 염증성의 신경을 압박 또는 신장하거나 또는 통증수용기가 많이 분포하는 인대, 관절낭, 섬유륜과 종판에 비정상적인 변형을 일으키는 것을 말한다. 안정성의 장애는 근육의 기능적 측면에서 국소적 안정체계와 포괄적 안정체계의 문제로 구분할 수 있다. 불안정한 경추 환자의 임상적 양상은 일반적으로 머리가 앞으로 나오고 전방 전위된 자세로 견갑대와 승모근 상부의 과활동성을 나타낸다. 또한 능동운동은 감소되지 않으나 수동운동에서 분절의 회전운동과 병진운동의 증가와 종말감의 변화가 있다. 경추의 불안정성을 관리하기 위한 실험적 연구로 전반적인 근육 훈련, 고유수용기 훈련, 그리고 도수치료의 세 가지 주된 접근법이 있고 실제적인 접근법으로는 고유수용성 재활프로그램, 칼텐본-에반스 접근법, 그리고, 슬링운동법 등이 있다. 각 방법들은 임상에서 나름대로의 이점이 있으며 환자의 상태에 따라 이들 방법을 단독으로 또는 병행해서 적용할 수 있을 것이다. 그러나 경추에서 이러한 방법들의 효과를 입증하는 증거는 부족하여 앞으로 이러한 방법에 대한 임상적 경험보다는 그 효과를 입증할 수 있는 연구가 필요하다고 본다.

  • PDF

A Study of improving reliability on prediction model by analyzing method Big data (빅데이터 분석방법을 이용한 예측모형의 신뢰도 향상에 관한 연구)

  • Song, Min-Gu;Kim, Sun-Bae
    • Journal of Digital Convergence
    • /
    • v.11 no.6
    • /
    • pp.103-112
    • /
    • 2013
  • Traditional method of establishing prediction model is usually using formal data stored in Data Base. However, nowadays advent of "smart" era brought by ground-breaking development of communication system makes informal data to dominate overall data, such 80% in total. Therefore, conventional method using formal data as establishing predicting model would be untrustworthy means in present. In other words, it is indispensible to make prediction model credible including informal data(SNS, image, video) and semi-formal data(log data). In this study, we increase credibility of predicting model adapting Bigdata method and comparing reliability of conventional measurement to real-data.

Management of Elderly Patients with Spinal Disease: Interventional Nonsurgical Treatment (고령 척추 질환자의 치료: 중재적 비수술 치료)

  • Park, Soo-An
    • Journal of the Korean Orthopaedic Association
    • /
    • v.54 no.1
    • /
    • pp.9-17
    • /
    • 2019
  • Owing to the upward shift in age structure, there is an increasing number of spinal diseases specific to elderly patients. Elderly spinal patients typically have a poor general condition with several medical comorbidities, low bone mineral density, more extensive and severe degeneration, and less effective treatment outcomes than young patients. This is why spinal physicians need to establish interventional nonsurgical treatment modalities for elderly patients with spinal disease. The objective of this study was to define the spinal disorders problematic to elderly patients and discuss the nonsurgical treatments for each subject.

A Study on Students' Responses to Non-routine Problems Using Numerals or Figures (숫자 또는 도형을 사용하여 제시된 비정형적인 문제에서 학생들의 반응에 대한 연구)

  • Hwang, Sun-Wook;Shim, Sang-Kil
    • The Mathematical Education
    • /
    • v.49 no.1
    • /
    • pp.39-51
    • /
    • 2010
  • The purpose of this article is to study students' responses to non-routine problems which are presented by using solely numerals or symbolic figures. Such figures have no mathematical meaning but just symbolical meaning. Most students understand geometric figures more concrete objects than numerals because geometric figures such as circles and squares can be visualized by the manipulatives in real life. And since students need not consider (unvisible) any operational structure of numerals when they deal with (visible) figures, problems proposed using figures are considered relatively easier to them than those proposed using numerals. Under this assumption, we analyze students' problem solving processes of numeral problems and figural problems, and then find out when students' difficulties arise in the problem solving process and how they response when they feel difficulties. From this experiment, we will suggest several comments which would be considered in the development and application of both numerical and figural problems.

Vibration Control Performance Evaluation of Smart TMD for a Tilted Diagrid Tall Building (경사진 다이어그리드 비정형 초고층 건물에 대한 스마트 TMD의 제진성능평가)

  • Kim, Hyun-Su;Kang, Joo-Won
    • Journal of Korean Association for Spatial Structures
    • /
    • v.11 no.4
    • /
    • pp.79-88
    • /
    • 2011
  • Recently, complex-shaped tall buildings represented by 3T(Twisted, Tapered, Tilted) are planed largely. A diagrid structural system is one of the most widely used structural system for complex-shaped tall buildings because of its structural efficiency and formativeness. Plans for tilted tall buildings are largely presented because of beauty of a sculpture and many of buildings use diagrid structural systems. Lateral displacements of tilted tall buildings are induced by not only lateral loads but also self weight. Therefore, reduction of lateral responses of tilted tall buildings is as important as typical tall buildings. In this study, a smart TMD is introduced to reduce seismic responses of tilted diagrid tall buildings and its control performance is evaluated. MR damper is employed for the smart TMD and ground-hook controller is used as a control algorithm for the smart TMD. 100-story tall building is used as an example structure. Control performances of uncontrolled case, controlled case with TMD and controlled case with smart TMD are compared and investigated. Numerical simulation has shown that smart TMD presented good control performance for displacement response but acceleration response was not controlled well.

A Study on Analyzing and Solving Problems Related with Equation of High School Mathematics (고등학교 수학의 방정식에 관련된 문제의 분석 및 해결에 관한 연구)

  • Lyou, Ik-Seung;Han, In-Ki
    • Communications of Mathematical Education
    • /
    • v.24 no.3
    • /
    • pp.793-806
    • /
    • 2010
  • In this paper we study meaning and methods of analyzing problems related with equation of high school mathematics. By analyzing problem we can get two types of informations. Based on these informations we suggest some problem solving methods. Especially we try to extract second type information using analysis through synthesis. This second type information can help us to find new non-routine problem solving method.

Customer Behavior Prediction of Binary Classification Model Using Unstructured Information and Convolution Neural Network: The Case of Online Storefront (비정형 정보와 CNN 기법을 활용한 이진 분류 모델의 고객 행태 예측: 전자상거래 사례를 중심으로)

  • Kim, Seungsoo;Kim, Jongwoo
    • Journal of Intelligence and Information Systems
    • /
    • v.24 no.2
    • /
    • pp.221-241
    • /
    • 2018
  • Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

Interface Technique for Optimization of Free-form Structural System (구조 최적화를 위한 비정형 구조시스템의 인터페이스 기법)

  • Na, Yoo-Mi;Lee, Jae-Hong;Kang, Joo-Won
    • Journal of Korean Association for Spatial Structures
    • /
    • v.12 no.1
    • /
    • pp.43-50
    • /
    • 2012
  • Recently, due to the advanced computer technology, momental architectures have been designed and built using features that are very sophisticated. People's interest in free-form structural system has increased steadily not only nationwide, but also worldwide. However, there were many difficulties in the materialization of free-form structural system owing to the lack of technique and research. To solve this problem, this study performs the interface between the 3D modeling program and the optimization program. In the 3D modeling program, it is possible to automatic mesh generation and immediately to information extraction. It performs the shape optimization. Consequently, this research designs the example model and performs optimization in order to verify the developed interface module.