• 제목/요약/키워드: Condition Classification

검색결과 902건 처리시간 0.023초

텍스트 문서 분류에서 범주간 유사도와 계층적 분류 방법의 성과 관계 연구 (A Study on the Relationship between Class Similarity and the Performance of Hierarchical Classification Method in a Text Document Classification Problem)

  • 장수정;민대기
    • 한국전자거래학회지
    • /
    • 제25권3호
    • /
    • pp.77-93
    • /
    • 2020
  • 비정형 텍스트 문서를 다중 범주로 분류하는 문제에 있어서, 계층적 분류 방법이 비계층적 분류 방법에 비하여 분류 성능이 우수한 것으로 알려져 있다. 기존 문헌과 다르게 본 연구에서는 사전에 범주들의 계층 구조가 정의된 상황에서 계층적 분류 방법과 비계층적 분류 방법의 성능을 비교하였다. 수자원 분야 기후변화 적응기술과 관련한 논문 분류 데이터와 20NewsGroup 오픈 데이터를 대상으로 계층적/비계층적 분류 방법의 성능을 비교하였다. 본 연구결과 기존 문헌과 다르게 계층적 분류 방법이 비계층적 분류 방법에 비하여 언제나 성능이 우수한 것은 아님을 확인하였다. 계층 구조의 상위/하위 수준에서의 상대적 유사도에 따라서 계층적/비계층적 분류 방법의 성능에 차이가 있음을 확인하였다. 즉, 상위 수준의 유사도가 하위 수준보다 상대적으로 낮은 경우 상위 수준에서의 오분류 감소로 계층적 분류 방법의 성능이 개선됨을 확인하였다.

조건 술어 분석을 이용한 능동규칙의 조건부 처리 시스템 (A Condition Processing System of Active Rules Using Analyzing Condition Predicates)

  • 이기욱;김태식
    • 정보처리학회논문지D
    • /
    • 제9D권1호
    • /
    • pp.21-30
    • /
    • 2002
  • 능동 데이터베이스 시스템은 특정한 상태를 탐지하는 능동규칙을 도입한다. 조건부 평가는 사건이 발생할 때마다 수행되기 때문에 조건부를 처리하는 방법에 따라 시스템의 성능에 중요한 영향을 미친다. 본 논문에서는 차이트리 구조, 분류트리, 그리고 집계함수 테이블을 생성하는 전처리 기능을 갖는 조건부 처리 시스템을 제안한다. 전처리는 능동규칙을 미리 파악할 수 있는 능동 데이터베이스의 특징 때문에 도입될 수 있다. 본 논문에서는 선택연산, 조인연산, 그리고 집계함수를 효율적으로 처리할 수 있는 차이트리를 제안하고 조건부의 처리 성능을 높인다. 그리고 조인연산을 효과적으로 처리하는 분류트리와 높은 처리비용을 요구하는 집계함수를 처리하는 집계함수 테이블을 제안한다. 본 논문의 조건부 처리 시스템은 전처리 기능에서 만들어진 조건부 처리 구조 때문에 조건 비교의 횟수를 감소시켜 능동규칙에서 조건부 처리의 성능 향상을 기대할 수 있다.

뿌리산업 제조현장 체계분석 및 데이터 기반 설비보전 환경구축 (Equipment Maintenance Environment Based on Field-Data of Root Industry by Manufacturing-Field Analysis)

  • 김동훈;송준엽
    • 한국정밀공학회지
    • /
    • 제34권1호
    • /
    • pp.19-22
    • /
    • 2017
  • This paper describes the efficient equipment maintenance that can offer the exact time for repair and change of component in root industry. A conventional method offered the fixed time for repair and change of component because the method is based on early guarantee specification of the component. However the operating condition of manufacturing field is often under worse condition than early guarantee condition for high productivity. So, most components can't use until early guarantee time due to the operation of various different condition. Therefore we suggest the useful method for efficient equipment-maintenance by manufacturing-field analysis and feedback database. For this, the classification of root industry and related equipment is performed and then the detail classification of the process and component for equipment maintenance. And the monitoring module is also designed to gather data for feedback process and the environment is basically implemented for aging and reliability test.

Deep-learning-based system-scale diagnosis of a nuclear power plant with multiple infrared cameras

  • Ik Jae Jin;Do Yeong Lim;In Cheol Bang
    • Nuclear Engineering and Technology
    • /
    • 제55권2호
    • /
    • pp.493-505
    • /
    • 2023
  • Comprehensive condition monitoring of large industry systems such as nuclear power plants (NPPs) is essential for safety and maintenance. In this study, we developed novel system-scale diagnostic technology based on deep-learning and IR thermography that can efficiently and cost-effectively classify system conditions using compact Raspberry Pi and IR sensors. This diagnostic technology can identify the presence of an abnormality or accident in whole system, and when an accident occurs, the type of accident and the location of the abnormality can be identified in real-time. For technology development, the experiment for the thermal image measurement and performance validation of major components at each accident condition of NPPs was conducted using a thermal-hydraulic integral effect test facility with compact infrared sensor modules. These thermal images were used for training of deep-learning model, convolutional neural networks (CNN), which is effective for image processing. As a result, a proposed novel diagnostic was developed that can perform diagnosis of components, whole system and accident classification using thermal images. The optimal model was derived based on the modern CNN model and performed prompt and accurate condition monitoring of component and whole system diagnosis, and accident classification. This diagnostic technology is expected to be applied to comprehensive condition monitoring of nuclear power plants for safety.

SVM을 이용한 음성 사상체질 분류 알고리즘 (Voice Classification Algorithm for Sasang Constitution Using Support Vector Machine)

  • 강재환;도준형;김종열
    • 사상체질의학회지
    • /
    • 제22권1호
    • /
    • pp.17-25
    • /
    • 2010
  • 1. Objectives: Voice diagnosis has been used to classify individuals into the Sasang constitution in SCM(Sasang Constitution Medicine) and to recognize his/her health condition in TKM(Traditional Korean Medicine). In this paper, we purposed a new speech classification algorithm for Sasang constitution. 2. Methods: This algorithm is based on the SVM(Support Vector Machine) technique, which is a classification method to classify two distinct groups by finding voluntary nonlinear boundary in vector space. It showed high performance in classification with a few numbers of trained data set. We designed for this algorithm using 3 SVM classifiers to classify into 4 groups, which are composed of 3 constitutional groups and additional indecision group. 3. Results: For the optimal performance, we found that 32.2% of the voice data were classified into three constitutional groups and 79.8% out of them were grouped correctly. 4. Conclusions: This new classification method including indecision group appears efficient compared to the standard classification algorithm which classifies only into 3 constitutional groups. We find that more thorough investigation on the voice features is required to improve the classification efficiency into Sasang constitution.

야지 자율주행을 위한 환경에 강인한 지형분류 기법 (Robust Terrain Classification Against Environmental Variation for Autonomous Off-road Navigation)

  • 성기열;유준
    • 한국군사과학기술학회지
    • /
    • 제13권5호
    • /
    • pp.894-902
    • /
    • 2010
  • This paper presents a vision-based robust off-road terrain classification method against environmental variation. As a supervised classification algorithm, we applied a neural network classifier using wavelet features extracted from wavelet transform of an image. In order to get over an effect of overall image feature variation, we adopted environment sensors and gathered the training parameters database according to environmental conditions. The robust terrain classification algorithm against environmental variation was implemented by choosing an optimal parameter using environmental information. The proposed algorithm was embedded on a processor board under the VxWorks real-time operating system. The processor board is containing four 1GHz 7448 PowerPC CPUs. In order to implement an optimal software architecture on which a distributed parallel processing is possible, we measured and analyzed the data delivery time between the CPUs. And the performance of the present algorithm was verified, comparing classification results using the real off-road images acquired under various environmental conditions in conformity with applied classifiers and features. Experiments show the robustness of the classification results on any environmental condition.

Efficient Data Management for Hull Condition Assessment

  • Jaramillo, David;Cabos, Christian;Renard, Philippe
    • International Journal of CAD/CAM
    • /
    • 제6권1호
    • /
    • pp.9-17
    • /
    • 2006
  • Performing inspections for Hull Condition Monitoring and Assessment as stipulated in IACS unified requirements and IMO's Condition Assessment Scheme (CAS) IMO Resolution MEPC.94(46), 2001, Condition Assessment Scheme, IMO Resolution MEPC.111(50), 2003, Amendments to regulation 13G, addition of new regulation 13H involves a huge amount of measurement data to be collected, processed, analysed and maintained. Information to be recorded consists of thickness measurements and visual assessment of coating and cracks. The amount of data and increasing requirements with respect to condition assessment demand efficient computer support. Currently, due to the lack of standardization for this kind of data, the thickness measurements are recorded manually on ship drawings or tables. In this form, handling of the measurements is tedious and error-prone and assessment is difficult. Data reporting and analysis takes a long time, leading to some repairs being performed only at the next docking of the ship or making an additional docking necessary. The recently started ED funded project CAS addresses this topic and develops-as a first step-a data model for Hull Condition Monitoring and Assessment (HCMA) based on XML-technology. The model includes simple geometry representation to facilitate a graphically supported data collection as well as an easy visualisation of the measurement results. In order to ensure compatibility with the current way of working, the content of the data model is strictly confined to the requirements of the measurement process. Appropriate data interfaces to classification software will enable rapid assessment by the classification societies, thus improving the process in terms of time and cost savings. In particular, decision-making can be done while the ship is still in the dock for maintenance.

ICD 연계 한의질병분류를 위한 전제로서의 공통개념어 연구 (Study on Common Conceptual Terms as a Premise for Korean Classification of Disease in Oriental Medicine in Connection with ICD-10)

  • 지규용
    • 동의생리병리학회지
    • /
    • 제22권4호
    • /
    • pp.718-724
    • /
    • 2008
  • In order to classify diseases of oriental medicine in liaison with International Classification of Diseases, there should be intermediation and sharing concepts between the two in addition to proper classification. Classification units were settled for differentiation of diseases or syndromes first. And second, the standard forms of disease classification system were proposed. Third, this classification system was made of serial groupings of syndrome under the traditional disease name. Fourth, the location of disease and the interrelation between different syndromes were depicted with diagram in order to define more clearly. As the results and conclusion, The classification units were composed of 2 categories; topology, organ, meridian, somatic structure, body fluid units for description and various regulatory unit terms of western and traditional medicine for explanation. The mixed classification model of western diseases and traditional syndromes(證) was adopted as a fundamental classification system containing disease by exterior pathogen, systemic internal diseases, psychoneuronal diseases, metabolic diseases, diseases of sense organs, supportive structure diseases, obstetric-gynecology diseases, child diseases, 4-type constitutional diseases. And those were differentiated with generalized, localized, functional, oncogenic, environmental features in detail. The cause, site, condition, dispositions must be expressed in each disease name too. The types of diagnosis using classification system are principal and final diagnosis, principal procedure, main conditions, and these are applied to this Korean classification system equally. For more clarification of differentiation, a plane topological map and three dimensional coordinates were proposed to manifest the location, features and relation of disease itself or each other.

THE CLASSIFICATION SYSTEM OF RIVER HEALTH FOR THE ENVIRONMENTAL WATER QUALITY MANAGEMENT

  • Carolyn G. Palmer;Jang, Suk-Hwan
    • Water Engineering Research
    • /
    • 제3권4호
    • /
    • pp.259-267
    • /
    • 2002
  • South Africa has developed a policy and law that calls and provides for the equitable and sustainable use of water resources. Sustainable resource use is dependent on effective resource protection. Rivers are the most important freshwater resources in the country, and there is a focus on developing and applying methods to quantify what rivers need in terms of flow and water quality. These quantified and descriptive objectives are then related to specified levels of ecological health in a classification system. This paper provides an overview of an integrated and systematic methodology, where, fer each river, and each river reach, the natural condition and the present ecological condition are described, and a level/class of ecosystem health is selected. The class will define long term management goals. This procedure requires each ecosystem component to be quantified, starting with the abiotic template. A modified flow regime is modelled for each ecosystem health class, and the resultant fluvial geomorphology and hydraulic habitats are described. Then the water chemistry is described, and the water quality changes that are likely to occur as a consequence of altered flows are predicted. Finally, the responses to the stress imposed on the biota (fish, invertebrates and vegetation) by modified flow and water quality are predicted. All of the predicted responses are translated into descriptive and/or quantitative management objectives. The paper concludes with the recognition of active method development, and the enormous challenge of applying the methods, implementing the law, and achieving river protection and sustainable resource-use.

  • PDF