• Title/Summary/Keyword: learning rule

Search Result 651, Processing Time 0.029 seconds

Fault Severity Diagnosis of Ball Bearing by Support Vector Machine (서포트 벡터 머신을 이용한 볼 베어링의 결함 정도 진단)

  • Kim, Yang-Seok;Lee, Do-Hwan;Kim, Dae-Woong
    • Transactions of the Korean Society of Mechanical Engineers B
    • /
    • v.37 no.6
    • /
    • pp.551-558
    • /
    • 2013
  • A support vector machine (SVM) is a very powerful classification algorithm when a set of training data, each marked as belonging to one of several categories, is given. Therefore, SVM techniques have been used as one of the diagnostic tools in machine learning as well as in pattern recognition. In this paper, we present the results of classifying ball bearing fault types and severities using SVM with an optimized feature set based on the minimum distance rule. A feature set as an input for SVM includes twelve time-domain and nine frequency-domain features that are extracted from the measured vibration signals and their decomposed details and approximations with discrete wavelet transform. The vibration signals were obtained from a test rig to simulate various bearing fault conditions.

Automatic Recognition of the Front/Back Sides and Stalk States for Mushrooms(Lentinus Edodes L.) (버섯 전후면과 꼭지부 상태의 자동 인식)

  • Hwang, H.;Lee, C.H.
    • Journal of Biosystems Engineering
    • /
    • v.19 no.2
    • /
    • pp.124-137
    • /
    • 1994
  • Visual features of a mushroom(Lentinus Edodes, L.) are critical in grading and sorting as most agricultural products are. Because of its complex and various visual features, grading and sorting of mushrooms have been done manually by the human expert. To realize the automatic handling and grading of mushrooms in real time, the computer vision system should be utilized and the efficient and robust processing of the camera captured visual information be provided. Since visual features of a mushroom are distributed over the front and back sides, recognizing sides and states of the stalk including the stalk orientation from the captured image is a prime process in the automatic task processing. In this paper, the efficient and robust recognition process identifying the front and back side and the state of the stalk was developed and its performance was compared with other recognition trials. First, recognition was tried based on the rule set up with some experimental heuristics using the quantitative features such as geometry and texture extracted from the segmented mushroom image. And the neural net based learning recognition was done without extracting quantitative features. For network inputs the segmented binary image obtained from the combined type automatic thresholding was tested first. And then the gray valued raw camera image was directly utilized. The state of the stalk seriously affects the measured size of the mushroom cap. When its effect is serious, the stalk should be excluded in mushroom cap sizing. In this paper, the stalk removal process followed by the boundary regeneration of the cap image was also presented. The neural net based gray valued raw image processing showed the successful results for our recognition task. The developed technology through this research may open the new way of the quality inspection and sorting especially for the agricultural products whose visual features are fuzzy and not uniquely defined.

  • PDF

The impact of Rene Descartes′s Mind-Body Theory on Medicin (데카르트의 심신론이 의학에 미친 영향)

  • 반덕진
    • Health Policy and Management
    • /
    • v.10 no.1
    • /
    • pp.31-56
    • /
    • 2000
  • A purpose of this study is to study on Rene Descartes's mind-body theory in medical aspect. Though Rene Descartes was not so much a doctor as a philosopher, he had health and medical science at heart. When he came into the world in 1596, he was in poor health. Therefore, he suffered from his bad health. Descartes's ideas absolutely colored Western thought for three hundred years, especially, his mind-body theory, mechanistic life-view, and reductionism had important effect on medical study and science of public health. As a rule, we know that his mind-body theory was applicable to mind-body dualism, and his mind-body dualism was connected with biomedical model of medicine. But by this study, his mind-body theory was not only mind-body dualism but also mind-body monoism. And he asserted mind-body interaction too. In other words, he advocated mind-body dualism in scientific aspect, but he knew mind-body monoism from his experence. He confessed this fact to Princess Elizabeth of Bohemia, he wrote mind-body interaction in $\boxDr$Discours de la methode$\boxUl$, $\boxDr$Meditationes de prima philosophia$\boxUl$, and $\boxDr$Traite des passions de 1'ame$\boxUl$ etc. However, only mind-body dualism of his mind-body theories was written in our medical text book, morever mental realm was excluded from the persuit of learning Descartes advocated a mechanistic world-view and mechanistic life-view, he regarded human body as a machine part. And a paticent corresponds to a troubled machine, a doctor deserves a repairman. But this point of view made holistic understanding of man impossible. Descartes divide the whole into basic building blocks, we named the approach Reductionism. Reductionism led to ontological concept in medical science, bacteriology established 'specific cause-specific disease-specific therapy'. We examined medical influence of Descartes's thought, we need to draw out a philosophic basis of medical science and science of public health by a close study of his records.

  • PDF

A Study on the Student Surveys for CAAD(Computer Aided Architectural Design) (건축 CAD 과목에 대한 학생 설문평가에 관한 연구)

  • Nam, Yun-Cheol
    • Journal of The Korean Digital Architecture Interior Association
    • /
    • v.12 no.4
    • /
    • pp.117-124
    • /
    • 2012
  • The importance of the digital architecture is increasing more ever. Currently, CAD and 3D programs are used as design fields, but the BIM (building information modeling) is gradually interested. BIM is mandatory on the project more than 50 billion won ordered by the government since 2012, it will be expanded to a total of government orders by 2016. University needs to evaluate teaching methods and computer-aided design environments such as CAD and BIM. In this paper, we surveyed computer-aided design environments and teaching methods for 73 students at the J University of Department of architectural engineering. Main results are as follows: 1. Hardlock is uncomfortable but necessary program for the computer management. 2. The desk placement considering the behavior of the design students results in higher satisfaction. 3. Because a CAD subject was a difficult course content and progress is fast, students thought it is difficult to follow. Especially, first-year students answered it is difficult to learn program and understand the structure of the building at the same time. 4. First-year students want to learn CAD more. Second-, third-, fourth-year students want to learn Photoshop more. Supplement for these classes is required. 5. Students answered that a teaching method of a CAD subject would be good to their own practice after the professor demonstrates for students. The senior's assistance is also a high effective way in the class. 6. During class, students' activities such surfing the web and Kakao Talk on a smartphone disrupt the class, there is a need to regulate by a rule such as disconnect computers from a network and against using smartphone. Although the Internet with the popularization of smartphones confers a benefit on modern life, it causes damage to us. This is a hard part for a salaried workers as well as students studying equally. The self management is required and a professor needs to control and restraint in a university classroom. The professor's continuing interest to students can increase the effectiveness of learning.

A Study on Wavelet Neural Network Based Generalized Predictive Control for Path Tracking of Mobile Robots (이동 로봇의 경로 추종을 위한 웨이블릿 신경 회로망 기반 일반형 예측 제어에 관한 연구)

  • Song, Yong-Tae;Oh, Joon-Seop;Park, Jin-Bae;Choi, Yoon-Ho
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.15 no.4
    • /
    • pp.457-466
    • /
    • 2005
  • In this paper, we propose a wavelet neural network(WNN) based predictive control method for path tracking of mobile robots with multi-input and multi-output. In our control method, we use a WNN as a state predictor which combines the capability of artificial neural networks in learning processes and the capability of wavelet decomposition. A WNN predictor is tuned to minimize errors between the WNN outputs and the states of mobile robot using the gradient descent rule. And control signals, linear velocity and angular velocity, are calculated to minimize the predefined cost function using errors between the reference states and the predicted states. Through a computer simulation for the tracking performance according to varied track, we demonstrate the efficiency and the feasibility of our predictive control system.

Performance Improvement of Nearest-neighbor Classification Learning through Prototype Selections (프로토타입 선택을 이용한 최근접 분류 학습의 성능 개선)

  • Hwang, Doo-Sung
    • Journal of the Institute of Electronics Engineers of Korea CI
    • /
    • v.49 no.2
    • /
    • pp.53-60
    • /
    • 2012
  • Nearest-neighbor classification predicts the class of an input data with the most frequent class among the near training data of the input data. Even though nearest-neighbor classification doesn't have a training stage, all of the training data are necessary in a predictive stage and the generalization performance depends on the quality of training data. Therefore, as the training data size increase, a nearest-neighbor classification requires the large amount of memory and the large computation time in prediction. In this paper, we propose a prototype selection algorithm that predicts the class of test data with the new set of prototypes which are near-boundary training data. Based on Tomek links and distance metric, the proposed algorithm selects boundary data and decides whether the selected data is added to the set of prototypes by considering classes and distance relationships. In the experiments, the number of prototypes is much smaller than the size of original training data and we takes advantages of storage reduction and fast prediction in a nearest-neighbor classification.

Driver Assistance System By the Image Based Behavior Pattern Recognition (영상기반 행동패턴 인식에 의한 운전자 보조시스템)

  • Kim, Sangwon;Kim, Jungkyu
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.51 no.12
    • /
    • pp.123-129
    • /
    • 2014
  • In accordance with the development of various convergence devices, cameras are being used in many types of the systems such as security system, driver assistance device and so on, and a lot of people are exposed to these system. Therefore the system should be able to recognize the human behavior and support some useful functions with the information that is obtained from detected human behavior. In this paper we use a machine learning approach based on 2D image and propose the human behavior pattern recognition methods. The proposed methods can provide valuable information to support some useful function to user based on the recognized human behavior. First proposed one is "phone call behavior" recognition. If a camera of the black box, which is focused on driver in a car, recognize phone call pose, it can give a warning to driver for safe driving. The second one is "looking ahead" recognition for driving safety where we propose the decision rule and method to decide whether the driver is looking ahead or not. This paper also shows usefulness of proposed recognition methods with some experiment results in real time.

An Efficient One Class Classifier Using Gaussian-based Hyper-Rectangle Generation (가우시안 기반 Hyper-Rectangle 생성을 이용한 효율적 단일 분류기)

  • Kim, Do Gyun;Choi, Jin Young;Ko, Jeonghan
    • Journal of Korean Society of Industrial and Systems Engineering
    • /
    • v.41 no.2
    • /
    • pp.56-64
    • /
    • 2018
  • In recent years, imbalanced data is one of the most important and frequent issue for quality control in industrial field. As an example, defect rate has been drastically reduced thanks to highly developed technology and quality management, so that only few defective data can be obtained from production process. Therefore, quality classification should be performed under the condition that one class (defective dataset) is even smaller than the other class (good dataset). However, traditional multi-class classification methods are not appropriate to deal with such an imbalanced dataset, since they classify data from the difference between one class and the others that can hardly be found in imbalanced datasets. Thus, one-class classification that thoroughly learns patterns of target class is more suitable for imbalanced dataset since it only focuses on data in a target class. So far, several one-class classification methods such as one-class support vector machine, neural network and decision tree there have been suggested. One-class support vector machine and neural network can guarantee good classification rate, and decision tree can provide a set of rules that can be clearly interpreted. However, the classifiers obtained from the former two methods consist of complex mathematical functions and cannot be easily understood by users. In case of decision tree, the criterion for rule generation is ambiguous. Therefore, as an alternative, a new one-class classifier using hyper-rectangles was proposed, which performs precise classification compared to other methods and generates rules clearly understood by users as well. In this paper, we suggest an approach for improving the limitations of those previous one-class classification algorithms. Specifically, the suggested approach produces more improved one-class classifier using hyper-rectangles generated by using Gaussian function. The performance of the suggested algorithm is verified by a numerical experiment, which uses several datasets in UCI machine learning repository.

A Simple Stereo Matching Algorithm using PBIL and its Alternative (PBIL을 이용한 소형 스테레오 정합 및 대안 알고리즘)

  • Han Kyu-Phil
    • The KIPS Transactions:PartB
    • /
    • v.12B no.4 s.100
    • /
    • pp.429-436
    • /
    • 2005
  • A simple stereo matching algorithm using population-based incremental learning(PBIL) is proposed in this paper to decrease the general problem of genetic algorithms, such as memory consumption and inefficiency of search. PBIL is a variation of genetic algorithms using stochastic search and competitive teaming based on a probability vector. The structure of PBIL is simpler than that of other genetic algorithm families, such as serial and parallel ones, due to the use of a probability vector. The PBIL strategy is simplified and adapted for stereo matching circumstances. Thus, gene pool, chromosome crossover, and gene mutation we removed, while the evolution rule, that fitter chromosomes should have higher survival probabilities, is preserved. As a result, memory space is decreased, matching rules are simplified and computation cost is reduced. In addition, a scheme controlling the distance of neighbors for disparity smoothness is inserted to obtain a wide-area consistency of disparities, like a result of coarse-to-fine matchers. Because of this scheme, the proposed algorithm can produce a stable disparity map with a small fixed-size window. Finally, an alterative version of the proposed algorithm without using probability vector is also presented for simpler set-ups.

Korean Semantic Role Labeling Using Semantic Frames and Synonym Clusters (의미 프레임과 유의어 클러스터를 이용한 한국어 의미역 인식)

  • Lim, Soojong;Lim, Joon-Ho;Lee, Chung-Hee;Kim, Hyun-Ki
    • Journal of KIISE
    • /
    • v.43 no.7
    • /
    • pp.773-780
    • /
    • 2016
  • Semantic information and features are very important for Semantic Role Labeling(SRL) though many SRL systems based on machine learning mainly adopt lexical and syntactic features. Previous SRL research based on semantic information is very few because using semantic information is very restricted. We proposed the SRL system which adopts semantic information, such as named entity, word sense disambiguation, filtering adjunct role based on sense, synonym cluster, frame extension based on synonym dictionary and joint rule of syntactic-semantic information, and modified verb-specific numbered roles, etc. According to our experimentations, the proposed present method outperforms those of lexical-syntactic based research works by about 3.77 (Korean Propbank) to 8.05 (Exobrain Corpus) F1-scores.