Machine learning is making strides towards autonomous mobile communications

We gladly took the opportunity to talk with Gongliang Liu (Harbin Institute of Technology, Weihai, China), one of the general chairs of MLICOM 2017, 2nd EAI International Conference on Machine Learning and Intelligent Communications. MLICOM 2017 will take place in Weihai, China on August 5-6, 2017. We talked machine learning, future of mobile communications, and how the two can work together for better QoS.

What is the central topic of MLICOM 2017 and why is it important? What is this event’s vision?

The central topic of MLICOM 2017 is the up-to-date research in machine learning and its applications in communications systems. Along with the fast developing of mobile communications technologies, the amount of required high-quality wireless services is increasing exponentially. According to the prediction of Cisco VNI Mobile Forecast 2016, Global mobile data traffic will increase nearly eightfold between 2015 and 2020, and mobile network connection speeds will increase more than threefold by 2020. Hence, there are still big gaps between the future requirements and current communications technologies, even using 4G/5G. How to integrate the limited wireless resources with some intelligent algorithms/schemes and boost potential benefits are the interests of the conference.

As an emerging discipline, machine learning is a subfield of computer science that evolved from the study of pattern recognition and computational learning theory in artificial intelligence and explores the study and construction of algorithms that can learn from and make predictions on complicated scenarios. In communication systems, the previous/current radio situations and communication paradigms should be well considered to obtain a high quality of service (QoS), such us available spectrum, limited energy, antenna configurations, and heterogeneous properties. Machine learning algorithms facilitate complicated scenarios analysis and prediction, and thus to make optimal actions in OSI seven layers.

What have been the recent developments in machine learning and intelligent communications?

Recently, the research hot-spots in communication area have been extended from traditional human-to-human communication systems to human-to-machine and machine-to-machine systems. With the advent of the Internet, people have become increasingly interconnected at an unprecedented scale. However, due to the proliferation of short-range networks and the prevalence of devices connected to these networks, a seamless interconnection between devices is gradually being created. Next-generation communication systems are expected to learn the diverse and colorful characteristics of both the users’ ambiance as well as human behavior, in order to autonomously determine the optimal system configurations. These smart mobile terminals have to rely on sophisticated learning and decision-making. Machine learning, as one of the most powerful artificial intelligence tools, constitutes a promising solution.

What does the future of this research domain look like? What topics can we expect to see covered at this year’s MLICOM?

In our view, the combination of machine learning and intelligent communication is a well-reasoned and promising area. The integrating of machine learning algorithms into communication systems will improve the QoS and make the systems smart, intelligent, and efficient. The topics of interest for the conference include, but are not limited to:

  • Intelligent cloud-support communications
  • Intelligent spectrum (or resource block) allocation schemes
  • Intelligent energy-aware/green communications
  • Intelligent software defined flexible radios
  • Intelligent cooperative networks
  • Intelligent antennas design and dynamic configuration.
  • Intelligent Massive MIMO communication systems
  • Intelligent positioning and navigation systems
  • Intelligent cooperative/distributed coding
  • Intelligent wireless communications
  • Intelligent wireless sensor networks
  • Intelligent underwater sensor networks
  • Intelligent satellite communications
  • Machine learning algorithm & cognitive radio networks
  • Machine learning and information processing in wireless sensor networks
  • Data mining in heterogeneous networks
  • Machine learning for multimedia
  • Machine learning for IoT
  • Decentralized learning for wireless communication systems

What are your expectations for MLICOM 2017?

We hope to attract the attention for the research in applying machine learning algorithms to intelligent communication systems and greatly improve the QoS and adaptation of the systems. Meanwhile, we expect to enrich the theory of machine learning itself.

MLICOM 2017 is still accepting papers, workshops, and special sessions! Learn more here.