首页--工业技术论文--自动化技术、计算机技术论文--计算技术、计算机技术论文--计算机的应用论文--信息处理(信息加工)论文--模式识别与装置论文

基于模糊粗糙C均值的图像大数据CNN聚类与分类

摘要第5-7页
ABSTRACT第7-8页
List of Abbreviations第14-22页
Chapter 1 Introduction第22-40页
    1.1. Rough Set Theory (RST)第26-27页
    1.2. Fuzzy C-Mean Clustering (FCM)第27-28页
    1.3. Fuzzy Rough C-Mean Clustering (FRCM)第28-30页
    1.4. Rough Set Attributes Reduction (RSAR)第30-31页
    1.5. Convolution Neural Network第31-34页
    1.6. Motivations第34-36页
        1.6.1. Motivation of Fuzzy Rough C-Mean Based Unsupervised CNN Clustering forLarge-Scale Image Data第34-35页
        1.6.2. Motivation of the A Semi-Supervised CNN with Fuzzy Rough C-Mean forImage Classification第35页
        1.6.3. Motivation of Rough-KNN Noise-Filtered Convolutional Neural Network forImage Classification第35-36页
        1.6.4. Motivation of Rough Noise-Filtered Easy Ensemble for Software FaultPrediction第36页
    1.7. Contributions and Organization第36-40页
        1.7.1. Contribution of Fuzzy Rough C-Mean Based Unsupervised CNN Clusteringfor Large-Scale Image Data第36-37页
        1.7.2. Contribution of a Semi-Supervised CNN with Fuzzy Rough C-Mean for ImageClassification第37页
        1.7.3. Contribution of Rough-KNN Noise-Filtered Convolutional Neural Networkfor Image Classification第37-38页
        1.7.4. Contribution of Rough Noise-Filtered Easy Ensemble for Software FaultPrediction第38页
        1.7.5. Organization第38-40页
Chapter 2 Fuzzy Rough C-Mean Based Unsupervised CNN Clustering for Large-ScaleImage Data第40-62页
    2.1. Introduction第40页
    2.2. Fuzzy Rough C-Mean Based Unsupervised CNN Clustering第40-50页
        2.2.1. The Problem of Deep-Learning-Based Clustering第40-42页
        2.2.2. Background of Fuzzy Rough C-Mean (FRCM)第42-43页
        2.2.3. Theoretical description of Proposed Approach第43-50页
            2.2.3.1. FRUCNN Clustering Architecture第43-45页
            2.2.3.2. Joint Clustering and Representation Learning第45-50页
                2.2.3.2.1. Pre-Processing Data for UCNN第46页
                2.2.3.2.2. Cluster Centroid Updating第46-47页
                2.2.3.2.3. Representation Learning第47-50页
    2.3. Experiments第50-59页
        2.3.1. Data Preparation第50-51页
        2.3.2. Performance Measure第51-52页
        2.3.3. Comparison Schemes第52-53页
        2.3.4. Implementation Details第53页
        2.3.5. Experimental Design第53-59页
            2.3.5.1. Computational Time Comparison第56-57页
            2.3.5.2. Performance on Number of Cluster (k)第57-58页
            2.3.5.3. Performance on Number of Epochs第58-59页
    2.4. Threats to Validity第59-60页
    2.5. Chapter Summary第60-62页
Chapter 3 A Semi-Supervised CNN with Fuzzy Rough C-Mean for Image Classification第62-84页
    3.1. Introduction第62页
    3.2. A Semi-Supervised Fuzzy Rough Convolutional Neural Network (SSFRCNN)第62-72页
        3.2.1. Framework of Our Approach第62-63页
        3.2.2. Theoretical description of Proposed Approach第63-67页
        3.2.3. Semi-Supervised Fuzzy Rough Convolution Neural Network (FRCNN)Training第67-69页
        3.2.4. Mathematical Description第69-72页
    3.3. Experiments第72-82页
        3.3.1. Data Preparation第72-73页
        3.3.2. Experimental Setup第73页
        3.3.3. Experiment Result and Analysis第73-79页
        3.3.4. Time Complexity第79-80页
        3.3.5. Convergence Analysis of Semi-Supervised Fuzzy Rough ConvolutionalNeural Network (SSFRCNN)第80-82页
    3.4. Chapter Summary第82-84页
Chapter 4 Rough-KNN Noise-Filtered Convolutional Neural Network for ImageClassification第84-100页
    4.1. Introduction第84页
    4.2. Rough Set Theory Based 2d-Reduction Method第84-89页
        4.2.1. Framework of Our Approach第84-85页
        4.2.2. Theoretical description of Proposed Approach第85-89页
    4.3. Experiments第89-99页
        4.3.1. Data Preparation第89页
        4.3.2. Implementation of Experiment第89-90页
        4.3.3. Experiment Design&Analysis第90-99页
            4.3.3.1. MNIST第90-94页
            4.3.3.2. CIFAR-10第94-96页
            4.3.3.3. YTF (Youtube-Face)第96-99页
    4.4. Chapter Summary第99-100页
Chapter 5 Rough Noise-Filtered Easy Ensemble for Software Fault Prediction第100-124页
    5.1. Introduction第100-101页
    5.2. Rough Noise-Filtered Easy Ensemble for Software Fault Prediction第101-107页
        5.2.1. Framework of Our Approach第101-102页
        5.2.2. Theoretical description of Proposed Approach第102-107页
            5.2.2.1. Information Gain (IG) based Feature Selection第102-103页
                5.2.2.1.1. Information Gain (IG)第102-103页
                5.2.2.1.2. Symmetrical Uncertainty (SU)第103页
            5.2.2.2. Rough- KNN Noise Filter (RK- Filter)第103-106页
            5.2.2.3. Rough-KNN Noise Filtered Easy Ensemble (RKEE)第106-107页
    5.3. Experiments第107-122页
        5.3.1. Data Preparation第108-109页
        5.3.2. Performance Measure第109-110页
        5.3.3. Classification Models第110-111页
        5.3.4. Experimental Design第111-113页
        5.3.5. Result and Analysis第113-122页
            5.3.5.1. Analysis of X-All verses X第116-117页
            5.3.5.2. The effectiveness of Noise-Filter through KNN rule第117-118页
            5.3.5.3. Impact of Rough set theory with Noise-Filter第118-119页
            5.3.5.4. The impact of the combination of feature selection with Rough Noise-FilterEasy Ensemble第119-120页
            5.3.5.5. Relationship between the performance and imbalanced ratio第120-121页
            5.3.5.6. Comparison of different Schemes第121-122页
    5.4. Chapter Summery第122-124页
Chapter 6 Concluding Remarks and Future Work第124-126页
    6.1. Concluding Remarks第124-125页
    6.2. Future work第125-126页
References第126-142页
Acknowledgements第142-144页
Bibliography第144-145页

论文共145页,点击 下载论文
上一篇:女性主义视野下我国高等教育性别平等问题研究
下一篇:乌兰夫民族高等教育办学思想研究