• Title, Summary, Keyword: C4.5 Algorithm

Search Result 288, Processing Time 0.041 seconds

Research of Decision Tree Based Blob Occlusion Solution Method Using Time Series Featur (시계열 특징을 이용한 의사결정트리 기반 블랍 겹침 해결 방법 연구)

  • Kang, Min-Koo
    • 한국정보기술학회논문지
    • /
    • v.15 no.12
    • /
    • pp.9-15
    • /
    • 2017
  • Object tracking, which is the core technology of intelligent video surveillance system, is a technique to observe spatial and temporal changes of objects in video sequence. Correct object detection is indispensable in object detection stage. However, in the object detection stage, blob occlusion problem, in which many foreground blobs are combined and detected as one blob, often occurs. In this paper, we propose a decision tree based blob occlusion solution algorithm using time series feature of blob. After extracting the time series feature of blob based on two consecutive image frames, it learns by C4.5 algorithm and creates decision tree that can classify occlusion state of blob. extracts the correct center point of the blob for the blobs classified in the occlusion state, thereby contributing to the improvement of the performance of the object tracking technique.

Effective Diagnostic Method Of Breast Cancer Data Using Decision Tree (Decision Tree를 이용한 효과적인 유방암 진단)

  • Jung, Yong-Gyu;Lee, Seung-Ho;Sung, Ho-Joong
    • The Journal of The Institute of Internet, Broadcasting and Communication
    • /
    • v.10 no.5
    • /
    • pp.57-62
    • /
    • 2010
  • Recently, decision tree techniques have been studied in terms of quick searching and extracting of massive data in medical fields. Although many different techniques have been developed such as CART, C4.5 and CHAID which are belong to a pie in Clermont decision tree classification algorithm, those methods can jeopardize remained data by the binary method during procedures. In brief, C4.5 method composes a decision tree by entropy levels. In contrast, CART method does by entropy matrix in categorical or continuous data. Therefore, we compared C4.5 and CART methods which were belong to a same pie using breast cancer data to evaluate their performance respectively. To convince data accuracy, we performed cross-validation of results in this paper.

Efficient Fuzzy Rule Generation Using Fuzzy Decision Tree (퍼지 결정 트리를 이용한 효율적인 퍼지 규칙 생성)

  • 민창우;김명원;김수광
    • Journal of the Korean Institute of Telematics and Electronics C
    • /
    • v.35C no.10
    • /
    • pp.59-68
    • /
    • 1998
  • The goal of data mining is to develop the automatic and intelligent tools and technologies that can find useful knowledge from databases. To meet this goal, we propose an efficient data mining algorithm based on the fuzzy decision tree. The proposed method combines comprehensibility of decision tree such as ID3 and C4.5 and representation power of fuzzy set theory. So, it can generate simple and comprehensive rules describing data. The proposed algorithm consists of two stages: the first stage generates the fuzzy membership functions using histogram analysis, and the second stage constructs a fuzzy decision tree using the fuzzy membership functions. From the testing of the proposed algorithm on the IRIS data and the Wisconsin Breast Cancer data, we found that the proposed method can generate a set of fuzzy rules from data efficiently.

  • PDF

A Combat Effectiveness Evaluation Algorithm Considering Technical and Human Factors in C4I System (NCW 환경에서 C4I 체계 전투력 상승효과 평가 알고리즘 : 기술 및 인적 요소 고려)

  • Jung, Whan-Sik;Park, Gun-Woo;Lee, Jae-Yeong;Lee, Sang-Hoon
    • Journal of Intelligence and Information Systems
    • /
    • v.16 no.2
    • /
    • pp.55-72
    • /
    • 2010
  • Recently, the battlefield environment has changed from platform-centric warfare(PCW) which focuses on maneuvering forces into network-centric warfare(NCW) which is based on the connectivity of each asset through the warfare information system as information technology increases. In particular, C4I(Command, Control, Communication, Computer and Intelligence) system can be an important factor in achieving NCW. It is generally used to provide direction across distributed forces and status feedback from thoseforces. It can provide the important information, more quickly and in the correct format to the friendly units. And it can achieve the information superiority through SA(Situational Awareness). Most of the advanced countries have been developed and already applied these systems in military operations. Therefore, ROK forces also have been developing C4I systems such as KJCCS(Korea Joint Command Control System). And, ours are increasing the budgets in the establishment of warfare information systems. However, it is difficult to evaluate the C4I effectiveness properly by deficiency of methods. We need to develop a new combat effectiveness evaluation method that is suitable for NCW. Existing evaluation methods lay disproportionate emphasis on technical factors with leaving something to be desired in human factors. Therefore, it is necessary to consider technical and human factors to evaluate combat effectiveness. In this study, we proposed a new Combat Effectiveness evaluation algorithm called E-TechMan(A Combat Effectiveness Evaluation Algorithm Considering Technical and Human Factors in C4I System). This algorithm uses the rule of Newton's second law($F=(m{\Delta}{\upsilon})/{\Delta}t{\Rightarrow}\frac{V{\upsilon}I}{T}{\times}C$). Five factors considered in combat effectiveness evaluation are network power(M), movement velocity(v), information accuracy(I), command and control time(T) and collaboration level(C). Previous researches did not consider the value of the node and arc in evaluating the network power after the C4I system has been established. In addition, collaboration level which could be a major factor in combat effectiveness was not considered. E-TechMan algorithm is applied to JFOS-K(Joint Fire Operating System-Korea) system that can connect KJCCS of Korea armed forces with JADOCS(Joint Automated Deep Operations Coordination System) of U.S. armed forces and achieve sensor to shooter system in real time in JCS(Joint Chiefs of Staff) level. We compared the result of evaluation of Combat Effectiveness by E-TechMan with those by other algorithms(e.g., C2 Theory, Newton's second Law). We can evaluate combat effectiveness more effectively and substantially by E-TechMan algorithm. This study is meaningful because we improved the description level of reality in calculation of combat effectiveness in C4I system. Part 2 will describe the changes of war paradigm and the previous combat effectiveness evaluation methods such as C2 theory while Part 3 will explain E-TechMan algorithm specifically. Part 4 will present the application to JFOS-K and analyze the result with other algorithms. Part 5 is the conclusions provided in the final part.

RLP : An Efficient HSR Traffic Reduction Algorithm

  • Nsaif, Saad Allawi;Jun, Je Hyun;Shin, Sang Heon;Rhee, Jong Myung
    • Journal of Satellite, Information and Communications
    • /
    • v.7 no.3
    • /
    • pp.47-53
    • /
    • 2012
  • In this paper, we present an algorithm called redundant logical paths (RLP) for efficient HSR traffic reduction. It creates redundant logical paths between each HSR node and all the other nodes. Eventually, a logical full-meshed network or paths will be established among all HSR node types, except the Quadbox type, which is used only for interconnection. The logical full-meshed network will be used instead of using the standard HSR protocol that depends on the concepts of the duplication and forwarding of the received frame until it reaches the destination node. The RLP algorithm results in significantly less frame traffic because there is no random forwarding as in the standard HSR protocol. For the sample network in this paper simulation results showed a 61.5-80% reduction in network frame traffic compared to the standard HSR. Our algorithm will avoid latency issues in the network and even network congestion, thus improving network efficiency.

Comparisons of Collection 5 and 6 Aqua MODIS07_L2 air and Dew Temperature Products with Ground-Based Observation Dataset (Collection 5와 Collection 6 Aqua MODIS07_L2 기온과 이슬점온도 산출물간의 비교 및 지상 관측 자료와의 비교)

  • Jang, Keunchang;Kang, Sinkyu;Hong, Suk Young
    • Korean Journal of Remote Sensing
    • /
    • v.30 no.5
    • /
    • pp.571-586
    • /
    • 2014
  • Moderate Resolution Imaging Spectroradiometer (MODIS) provides air temperature (Tair) and dew point temperature (Tdew) profiles at a spatial resolution of 5 km. New Collection 6 (C006) MODIS07_L2 atmospheric profile product has been produced since 2012. The Collection 6 algorithm has several modifications from the previous Collection 5 (C005) algorithm. This study evaluated reliabilities of two alternative datasets of surface-level Tair and Tdew derived from C005 and C006 Aqua MODIS07_L2 (MYD07_L2) products using ground measured temperatures from 77 National Weather Stations (NWS). Saturated and actual vapor pressures were calculated using MYD07_L2 Tair and Tdew. The C006 Tair showed lower mean error (ME, -0.76 K) and root mean square error (RMSE, 3.34 K) than the C005 Tair (ME = -1.89 K, RMSE = 4.06 K). In contrasts, ME and RMSE of C006 Tdew were higher than those (ME = -0.39 K, RMSE = 5.65 K) of C005 product. Application of ambient lapse rate for Tair showed appreciable improvements of estimation accuracy for both of C005 and C006, though this modification slightly increased errors in C006 Tdew. The C006 products provided better estimation of vapor pressure datasets than the C005-derived vapor pressure. Our results indicate that, except for Tdew, C006 MYD07_L2 product showed better reliability for the region of South Korea than the C005 products.

Difference between Collection 4 and 5 MODIS Aerosol Products and Comparison with Ground based Measurements (Collection 4 와 Collection 5 MODIS 에어러솔 분석 자료의 차이와 지상관측자료와의 비교)

  • Lee, Kwon-Ho;Kim, Young-Joon
    • Korean Journal of Remote Sensing
    • /
    • v.24 no.4
    • /
    • pp.369-379
    • /
    • 2008
  • The aerosol retrieval algorithm for the Moderate Resolution Imaging Spectroradiometer (MODIS) measurements was updated recently. This paper reports on the comparison and validation of two latest versions (Collection 4 and 5, shortly C004 and C005) of the MODIS aerosol product over northeast Asian region. The differences between the aerosol optical thickness (AOT) from the C004 and C005 retrieval algorithms and the correlation with ground based AERONET sunphotometer observations are investigated. Over the study region, spatially averaged annual mean AOT retrieved from C005 algorithm $(AOT_{C005})$ is about 0.035 AOT (5%) less than the C004 counterparts. The linear correlations between MODIS and AERONET AOT also are R=0.89 (slope=0.86) for the C004 and R=0.95 (slope=1.00) for the C005. Moreover, the magnitude of the mean error in $AOT_{C005}$, difference between MODIS AOT and AERONET AOT, is 40% less than that in $AOT_{C004}$.

Ordinal Variable Selection in Decision Trees (의사결정나무에서 순서형 분리변수 선택에 관한 연구)

  • Kim Hyun-Joong
    • The Korean Journal of Applied Statistics
    • /
    • v.19 no.1
    • /
    • pp.149-161
    • /
    • 2006
  • The most important component in decision tree algorithm is the rule for split variable selection. Many earlier algorithms such as CART and C4.5 use greedy search algorithm for variable selection. Recently, many methods were developed to cope with the weakness of greedy search algorithm. Most algorithms have different selection criteria depending on the type of variables: continuous or nominal. However, ordinal type variables are usually treated as continuous ones. This approach did not cause any trouble for the methods using greedy search algorithm. However, it may cause problems for the newer algorithms because they use statistical methods valid for continuous or nominal types only. In this paper, we propose a ordinal variable selection method that uses Cramer-von Mises testing procedure. We performed comparisons among CART, C4.5, QUEST, CRUISE, and the new method. It was shown that the new method has a good variable selection power for ordinal type variables.

Classification Accuracy Improvement for Decision Tree (의사결정트리의 분류 정확도 향상)

  • Rezene, Mehari Marta;Park, Sanghyun
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • /
    • pp.787-790
    • /
    • 2017
  • Data quality is the main issue in the classification problems; generally, the presence of noisy instances in the training dataset will not lead to robust classification performance. Such instances may cause the generated decision tree to suffer from over-fitting and its accuracy may decrease. Decision trees are useful, efficient, and commonly used for solving various real world classification problems in data mining. In this paper, we introduce a preprocessing technique to improve the classification accuracy rates of the C4.5 decision tree algorithm. In the proposed preprocessing method, we applied the naive Bayes classifier to remove the noisy instances from the training dataset. We applied our proposed method to a real e-commerce sales dataset to test the performance of the proposed algorithm against the existing C4.5 decision tree classifier. As the experimental results, the proposed method improved the classification accuracy by 8.5% and 14.32% using training dataset and 10-fold crossvalidation, respectively.

A New Incremental Learning Algorithm with Probabilistic Weights Using Extended Data Expression

  • Yang, Kwangmo;Kolesnikova, Anastasiya;Lee, Won Don
    • Journal of information and communication convergence engineering
    • /
    • v.11 no.4
    • /
    • pp.258-267
    • /
    • 2013
  • New incremental learning algorithm using extended data expression, based on probabilistic compounding, is presented in this paper. Incremental learning algorithm generates an ensemble of weak classifiers and compounds these classifiers to a strong classifier, using a weighted majority voting, to improve classification performance. We introduce new probabilistic weighted majority voting founded on extended data expression. In this case class distribution of the output is used to compound classifiers. UChoo, a decision tree classifier for extended data expression, is used as a base classifier, as it allows obtaining extended output expression that defines class distribution of the output. Extended data expression and UChoo classifier are powerful techniques in classification and rule refinement problem. In this paper extended data expression is applied to obtain probabilistic results with probabilistic majority voting. To show performance advantages, new algorithm is compared with Learn++, an incremental ensemble-based algorithm.