{%hackmd @ninoagus/rkG8Y3Mfp %}

# 1st Semester (Spring 2024) Course Plan

| Course | Instructor | Schedule | Credit |
|:------------------------------------------------------------------------------------------------------------------------------ |:--------------- |:-------- |:------:|
| [Multimedia Wireless Networks](https://hackmd.io/@ninoagus/ryns2BNh6#1-Multimedia-Wireless-Networks) | Cheng, Ray-Guan | T1,T2,T3 | 3 |
| [Artificial Intelligence and Deep Learning](https://hackmd.io/@ninoagus/ryns2BNh6#2-Artificial-Intelligence-and-Deep-Learning) | Yungho Leu | M6,M7,M8 | 3 |
| [Soft Computing](#3-Soft-Computing) | Loke Kar Seng | M2,M3,M4 | 3 |
| [Computer Algorithms](https://hackmd.io/@ninoagus/ryns2BNh6#4-Computer-Algorithms) | Chen, Wei-Mei | W6,W7,W8 | 3 |
| [Cybersecurity and AI-based Analytics](https://hackmd.io/@ninoagus/ryns2BNh6#5-Cybersecurity-and-AI-based-Analytics) | - | W2,W3,W4 | 3 |
| **Total Credit** | | | **15** |

This draft outlines the courses carefully selected to provide invaluable support and enhancement to my ongoing research in RAN energy-saving strategies. Your comments and input on the chosen courses are highly valued and appreciated.

## 1. Multimedia Wireless Networks

:::info
Instructor: Cheng, Ray-Guan
Code: ET5907701
Schedule: T1,T2,T3
:::

### 1.1 Objective

1. Multimedia Applications
2. QoS Fundamentals
3. QoS Mechanisms
4. Selected Standards This course will give an overview of the multimedia application.

The fundamentals of Quality of Service (QoS)is then introduced. Some commonly used QoS Mechanisms will be given. Finally, we will use some popular wireless standards as examples to illustrate the usage of the QoS mechanisms.

### 1.2 Relation to Research

1. Exploring the unique challenges of multimedia traffic in wireless networks provides valuable context for devising energy-saving strategies.
2. Studying multimedia transmission protocols and traffic management techniques informs the design of energy-efficient RAN architectures.

## 2. Artificial Intelligence and Deep Learning

:::info
Instructor: Yungho Leu
Code: MI5126701
Schedule: M6,M7,M8
:::

### 2.1 Course Objective
Artificial Intelligence includes Machine Learning, Deep Learning, and Reinforcement Learning. It is the most crucial computer technology today. With the advance of many deep neural network models, the abundance of big datasets, and massive computing power, AI is now unprecedentedly changing our ways of living. This course will focus on learning the structures and applications of many deep neural network models. We will cover both theories and practices of different deep neural network models. By constructing and training a deep neural network model with tools like TensorFlow and Keras for many examples of big datasets, a student will learn cutting-edge AI technology, which is very useful in his or her research and jobs.

### 2.2 Relation to Research
1. Deep Learning techniques, including deep neural network models, offer potential for optimizing RAN operations.
2. Application of deep neural networks can lead to more efficient resource allocation and reduced energy consumption in RANs.
3. Hands-on experience with deep learning tools prepares students for research aimed at enhancing RAN energy efficiency.

## 3. Soft Computing

:::info
Instructor: Loke Kar Seng
Code: IM5109701
Schedule: M2,M3,M4
:::

### 3.1 Course Objective
This course is suitable for students with some programming background who is interested to understand and implement algorithms and application using reinforcement learning, swarm, evolutionary and nature-inspired computing and optimization. To understand the theory and algorithms of topics under soft computing such as swarm and evolutionary computing. To be able to critically evaluate the use of them in an application. To be able to apply them in any suitable application

### 3.2 Relation to Research

- Soft computing techniques such as neural networks and fuzzy logic offer flexible solutions for optimizing complex systems like RANs.
- Adaptive algorithms can dynamically adjust RAN configurations to minimize energy consumption.

## 4. Computer Algorithms

:::info
Instructor: Chen, Wei-Mei
Code: ET5003701
Schedule: W6,W7,W8
:::

### 4.1 Course Objective
1. Algorithmic problems: *Sorting and searching,* and *Graph algorithms*
2. Algorithm analysis: * Time and space complexity, * Asymptotic analysis, * Worst case and average case analysis, and * Lower bounds,
3. Algorithm design: * Divide-and-conquer method, * Greedy approach, * Dynamic programming, and * Use of advanced data structures

### 4.2 Relation to Research

1. Understanding sorting and searching algorithms can aid in optimizing data retrieval processes within RANs, potentially reducing energy consumption by streamlining data access.
2. Graph algorithms can be applied to model and optimize network topologies, leading to more energy-efficient routing and resource allocation within RANs.
3. Algorithm analysis provides insights into the computational complexity of energy-saving algorithms, guiding the selection and optimization of algorithms for RAN deployment.
4. Algorithm design methodologies such as dynamic programming and greedy approaches offer systematic strategies for developing efficient RAN management algorithms, considering energy constraints and performance requirements.
5. Mastery of advanced data structures facilitates the implementation of optimized data storage and manipulation techniques within RANs, contributing to energy efficiency improvements.

## 5. Cybersecurity and AI-based Analytics

:::info
Instructor: -
Code: EE5515701
Schedule: W2,W3,W4
:::

### 5.1 Course Objective
This course focuses on the application of artificial intelligence in the field of information security, providing students with an in-depth understanding of the importance of AI in topics such as security attacks and defenses. The course content is divided into three parts:

1. Malware-related Issues:
- Discussion on dynamic and static analysis techniques, as well as the use of neural networks (such as RNNs, CNNs) to detect and classify malware.
2. Red Team Exercises Simulating Intrusion Attacks:
- Introduction to red team exercises simulating intrusion attacks, involving monitoring system behavior and developing intrusion detection systems.
3. Typical Deep Learning Embedding Algorithms and Attention Mechanisms:
- Exploration of typical deep learning embedding algorithms and attention mechanisms used for defending against malicious threats and developing information security tools.

Through this course, students will gain a deeper understanding of research topics such as information security defense, detection, and identification, along with the ability to implement neural network models in information security-related research tasks.

### 5.2 Relation to Research
1. "Cybersecurity and AI-based Analytics" enhances RAN energy-saving efforts.
2. It equips researchers with advanced threat detection techniques.
3. Deep learning algorithms improve anomaly detection capabilities for Energy-saving optimizations facilitated within RAN architectures.
4. Overall, the course directly contributes to efficient and secure RAN operations