1. Introduction
An evolving concept called data-driven intelligence is a model for a new viewpoint on gathering vision from a vast pool of data. Data-driven techniques put robust importance on the large dataset to solve a specific problem. There are more than 370 Million Internet users worldwide. The Number of unique mobile users is almost 5 Billion, with the total number of mobile connections exceeding 8 Billion. This indicates that wireless communication is a prevalent field. Wireless networks can show random interactions between algorithms from multiple protocol layers, interactions between multiple devices, and hardware-specific effects. Different wireless technologies including mobile cellular, fixed line, WiFi, and others are widely used for diverse communication purposes. It is estimated that the majority of users access the Internet via a mobile device. Internet traffic is dominated by multimedia content, and its proportion is ever increasing. This increases the Quality of Service/Quality of Experience requirements. Optimizing multiple, often conflicting goals according to different application requirements is of fundamental importance in the context. With the spreading of the Internet and broadening of its capacity, data is available in abundance. Moreover, more wireless data can be collected from wireless testbeds facilities. Many fields benefit from data to optimize decisions. A lot of datasets, related to the performance and security of different wireless networks i.e., wireless sensors networks and the Internet of things are publicly available. There has been a growing trend to benefit from data-driven techniques like machine learning to improve decision making, management, performance, and security issues in wireless networks.

2. Topics of Interest:

The scope of the handbook includes but is not limited to the following topics:

• Background
o An introduction to Data-Driven techniques applied to wireless communication systems
o A taxonomy of problems in wireless communication candidate for Data-Driven solution
• Data-Driven Techniques, Performance and Design Issues in Wireless Networks
o Data-Driven techniques for lower layer issues (including but not limited to: spectrum management, modulation, radio resource allocation, medium access techniques, etc.)
o Data-Driven techniques for upper and cross-layer issues (including but not limited to: QoS, routing, admission and flow control, etc.)
o Performance issues pertinent to the integration of heterogeneous wireless technologies and IoT
• Data-Driven Techniques and Security Issues in Wireless
o Data-Driven techniques for intrusion detection (including but not limited to Denial of Service, eavesdropping, etc.)
o Data-Driven techniques for traffic analysis
o Security issues pertinent to the integration of heterogeneous wireless technologies and IoT
• Case Studies
o Data-Driven solution for QoS in heterogeneous wireless networks: A case study
o Data-Driven solution for security in heterogeneous wireless networks: A case study
o Data-Driven Solution for 5G/6G Networks: A case study
• Advanced Topics in Data-Driven Intelligence for Wireless Networks
o The Role of SDN/NFV in enabling Data-Driven Design for Wireless Communication
o The Role and Applications of Blockchain in enabling Data-Driven Design for Wireless Communication
o The potential of advanced machine learning techniques (deep learning/federated learning) in enabling Data-Driven Design for Wireless Communication
o Data-Driven Wireless Communication in the Era of IoT: Forecasts, Challenges, and Solutions
• A comprehensive account of programming languages, tools, techniques, and good practices