【文章頁數(shù)】：104 頁

【學位級別】：博士

【文章目錄】：
Abstract
1. INTRODUCTION
    1.1. Motivation: Multi-criteria Recommendation Technique
    1.2. Structure of the Thesis
    1.3. Main Contributions
2. BACKGROUND
    2.1. Collaborative Recommendation system (CF):
    2.2. Content Recommendation System(CB):
    2.3. Knowledge-Based Recommendation System:
    2.4. Demographic Recommender Systems
    2.5. Hybrid Based Recommendation System:
        2.5.1. Weighted
        2.5.2. Switching
        2.5.3. Mixed
        2.5.4. Feature Combination
        2.5.5. Cascade
        2.5.6. Feature Augmentation
        2.5.7. Meta-level
    2.6. Multi-Criteria Recommender Systems:
        2.6.1. Neighborhood-Based Methods
        2.6.2. Ensemble-Based Methods
    2.7. Decision Support System
    2.8. Recommendation System
    2.9. Decision Support Systems in Healthcare
3. DATA MINING AND DATA FILTERING APPROACHES
    3.1. Data Preprocessing
        3.1.1. Similarity Measures
        3.1.2. Sampling
        3.1.3. Reducing Dimensionality
        3.1.4. Denoising
    3.2. Classification
        3.2.1. Nearest Neighbors
        3.2.2. Decision Trees
        3.2.3. Bayesian Classifiers
        3.2.4. Artificial Neural Networks
        3.2.5. Support Vector Machines
    3.3. Dataset Features Description
    3.4. Model Design
        3.4.1. Extracting Features:
        3.4.2. Data Mining & Service Layer:
        3.4.3. Recommendation (Application Layer):
4. RECOMMENDATION SYSTEM WITH PREDICTION OF DISEASES USING FEATUREEXTRACTION
    4.1. System Overview:
    4.2. Analysis
    4.3. Evaluation metrics
    4.4. Discussion
5. MULTI-CRITERIA RECOMMENDATION SYSTEM
    5.1. Multi-criteria decision view
        5.1.1. Multi-Attributes Decision Making
        5.1.2. Multi-Criteria Recommender Systems
        5.1.3. Tool
        5.1.4. Validation & Evaluation Metrics
    5.2. Algorithms Used
        5.2.1. Multi-Label K-Nearest Neighbors algorithm(MLKNN)
        5.2.2. Instance-Based Logistic Regression (IBLR):
        5.2.3. Slope One:
        5.2.4. RAndom k-labELsets(RAKEL):
        5.2.5. Item-Based Collaborative Filtering (IBCF):
        5.2.6. User Based Collaborative Filtering (UBCF):
        5.2.7. Perceptron with Margins (PM):
6. RISK FACTOR PREDICTION USING ARTIFICIAL INTELLIGENCE
    6.1. Methodology
        6.1.1. Cohort and Feature Selection
        6.1.2. Data source:
        6.1.3. Proposed Algorithm
        6.1.4. Variable Importance:
        6.1.5. Prediction Accuracy & Validation of Results:
    6.2. Discussion
    6.3. Limitation
7. CONCLUSION AND FUTURE WORK
LIST OF ABBRIVIATIONS
REFERENCES
PUBLISHED RESEARCH PAPERS
Acknowledgments
作者簡歷



本文編號：3778489