首页--工业技术论文--自动化技术、计算机技术论文--自动化基础理论论文--人工智能理论论文--自动推理、机器学习论文

亚洲烹饪配料分类方法的比较研究

摘要第4-5页
Abstract第5-6页
Abbreviations第12-13页
CHAPTER 1:INTRODUCTION第13-18页
    1.1 Background第13-14页
    1.2 Motivation第14-15页
    1.3 Contribution第15-16页
    1.4 Problem definition and research objectives第16页
    1.5 Structure of the thesis第16-18页
CHAPTER 2:LITERATURE REVIEW第18-35页
    2.1 Overview第18页
    2.2 Food and culture第18-19页
    2.3 Food and Social life第19-21页
    2.4 Food and Price第21页
    2.5 The contribution of food in tourism's field第21-23页
    2.6 Food Engineering第23-24页
    2.7 Consumer behavior model with respect to food第24-25页
    2.8 Criterion of food preference第25-26页
    2.9 Mathematical model of food's flavors第26-34页
        2.9.1 Graph theory and fundamental concepts第26-32页
            2.9.1.1 Types of graphs第28-29页
            2.9.1.2 Classes of graphs第29-30页
            2.9.1.3 Bipartite graphs第30-31页
            2.9.1.4 Ingredient-flavor network第31-32页
        2.9.2 Cuisines classification problem第32-34页
    2.10 Conclusion第34-35页
CHAPTER 3:METHODOLOGIES第35-64页
    3.1. Overview第35页
    3.2 Logistic Regression第35-45页
        3.2.1 Generative model第37-38页
        3.2.2 Two class Discrimination第38-42页
        3.2.3 Binary logistic regression第42-44页
        3.2.4 Multinomial logistic regression第44-45页
    3.3 Support Vector Machine第45-57页
        3.3.1 Linear Discriminants第47-48页
        3.3.2 Margin function第48-50页
        3.3.3 Soft-SVM and Norm Regularization第50-51页
        3.3.4 Overlapping class distributions第51-52页
        3.3.5 Multiclass SVMs第52-57页
            3.3.5.1 One versus all SVM第52-53页
            3.3.5.2 One Vs one support vector machines第53-54页
            3.3.5.3 K-class support vector machines第54-57页
                3.3.5.3.1 Polynomial kernel第55-56页
                3.3.5.3.2 Normalized polynomial kernel第56页
                3.3.5.3.3 Pearson VII universal kernel (PUK)第56页
                3.3.5.3.4 The Radial Basis Function Kernel (RBF)第56-57页
    3.4 Artificial Neural Network第57-62页
        3.4.1 Multi-Layer Perceptron第60-62页
        3.4.2 Neural network used for classifying Problem第62页
    3.5 Conclusion第62-64页
CHAPTER 4:RESULTS AND DISCUSSION第64-83页
    4.1 Overview第64页
    4.2 Data collection and formatting第64-66页
    4.3 Model testing第66-68页
        4.3.1 Training and Test Set第66-67页
        4.3.2 Test and Validation Set第67-68页
    4.4 Accuracy第68-69页
    4.5 Roc Curve第69-71页
    4.6 Recall第71页
    4.7 Precision第71-72页
    4.8 Confusion Matrix第72-73页
    4.9 Evaluation Numeric Prediction第73-74页
    4.10 Means squared error第74页
    4.11 Means absolute error第74-75页
    4.12 Experimental results第75-83页
        4.12.1 Computation steps of each algorithm第75-77页
            4.12.1.1 Support Vector Machine Implementation第75-76页
            4.12.1.2 Neuronal network Implementation第76-77页
            4.12.1.3 Logistic regression第77页
        4.12.2 Discussion第77-83页
CHAPTER 5:CONCLUSION AND FUTURE WORK第83-85页
    5.1 Conclusion第83-84页
    5.2 Future work第84-85页
References第85-92页
Publication第92-93页
Acknowledgements第93-94页
Dedication第94页

论文共94页,点击 下载论文
上一篇:基于路线的SMOTE改进算法L-SMOTE
下一篇:基于深度学习的语音唤醒研究及其应用