Convolutional Neural Networks for Time Series Forecasting

General Information:

Cover Page:

Outline:

General Introduction
1. Background.
2. Problem statement
3. Approach
4. Outline
CHAPTER 1: Time Series Forecasting
1.1 Introduction
1.2 Time Series
1.2.1 Time Series Presentation.
1.2.1.1 Definitions
1.2.1.2 Examples
1.2.2 Time Series Data and Components.
1.2.2.1 Components.
1.2.2.1.1 Trend Component
1.2.2.1.2 Seasonality Component
1.2.2.1.3 Cyclical Component
1.2.2.1.4 Irregular Component
1.2.2.2 Understanding time series
1.2.3 Time Series Types.
1.2.3.1 Univariate Time Series
1.2.3.2 Multivariate Time Series
1.2.4 Stationary Time Series
1.3 Time Series Forecasting
1.3.1 One-step ahead prediction.
1.3.2 Multi-step ahead prediction
1.4 Time Series Forecasting Models
1.4.1 Statistical Models
1.4.2 Machine Learning Models
1.5 Deep Learning Models
1.6 Conclusion
CHAPTER 2: Convolutional Neural Networks (CNN)
2.1 Introduction
2.2 Historical context.
2.2.1 Artificial Intelligence.
2.2.2 Machine Learning
2.2.3 Types of Machine Learning
2.3 Deep Learning and Neural Networks.
2.3.1 Artificial Neurons
2.3.2 Biological Neural Network
2.3.3 Artificial neural networks
2.3.4 Models of Artificial Neural Networks
2.3.5 Gradient Descent.
2.4 Activation Functions
2.4.1 Linear activation functions
2.4.2 Activation Functions (Non-Linearity)
2.4.2.1 Sigmoid
2.4.2.2 Tanh.
2.4.2.3 ReLU
2.4.2.4 SoftMax
2.4.3 Loss Functions
2.5 Convolutional Neural Networks.
2.5.1 Convolution operation
2.5.2 Architecture of CNN
2.5.2.1 Convolution layer.
2.5.2.2 Filter/ Kernel
2.5.2.3 Hyperparameters
2.5.2.4 Pooling layer
2.5.3 Fully Connected Layer.
2.5.4 Real world applications of Convolutional neural network
2.5.5 Advantages and disadvantages of ANNS and CNNs
2.6 Conclusion.
Chapter 3: Convolutional Neural Networks For Time Series Forecasting.
3.1 Introduction
3.2 Proposed time series forecasting method
3.3 Implementation.
3.3.1 Python
3.3.2 Matplotlib
3.3.3 Scikit-learn
3.3.4 Pandas
3.3.5 StatsModels.
3.3.6 Keras
3.3.7 Colaboratory.
3.3.8 Hardware
3.4 Experiments.
3.4.1 Datasets
3.4.2 Implementation details
3.4.3 Evaluation Metrics
3.4.4 Baselines
3.5 Results
3.5.1 Results and comparison.
3.5.1.1 Forecast results using univariate time series
3.5.1.2 Forecast results using multivariate time series.
3.5.2 Performance Comparison
3.5.3 Discussion
3.6 Conclusion
General Conclusion
Bibliography

Download The Thesis:

📥 تحميل الملف

For more
academic sources and references,
including theses and dissertations from Algerian universities,
, visit our main website.