An AI-based Framework to Optimize Mobile Services

Loading...
Thumbnail Image

URL

Journal Title

Journal ISSN

Volume Title

School of Electrical Engineering | Doctoral thesis (article-based) | Defence date: 2023-11-16

Date

2023

Major/Subject

Mcode

Degree programme

Language

en

Pages

148 + app. 124

Series

Aalto University publication series DOCTORAL THESES, 143/2023

Abstract

In current digital networks, novel verticals require diversity and extreme efficiency from network infrastructures. Recent studies have shown the key role of Artificial intelligence (AI) to improve resource management and to reduce operational costs of mobile services and networks. Furthermore, the rapid development of connected Internet of Things devices has created a variety of services. Since the complexity of mobile services has increased, efficient designs for these services are required to satisfy increasing power and processing requirements. Mobile services, however, face numerous challenges, including a shortage of data, inefficient data processing, and a lack of multi-service collaboration mechanisms. These setbacks have delayed the development of commercial applications that rely on mobile networks. Therefore, this thesis presents a framework, based on the "global brain" concept, to orchestrate various mobile services. The framework enhances mobile services for two scenarios: 1) low data rate (e.g., ambient intelligence) and 2) high data rate (e.g., virtual reality (VR) streaming). The distinction between low and high data rates is based upon bandwidth requirement. For low data rate scenarios, this thesis investigates the usefulness of emotion-based data for static (e.g., customer satisfaction) and dynamic (e.g., location-based recommendations) environments. We begin by presenting a practical multimodal emotion recognition system based on audio and video information, which improves emotion recognition accuracy. The results indicate that the integration of emotions is vital for customer satisfaction assessment and recommendation systems. For high data rate scenarios, we address VR streaming due to its high computational cost and latency. Notably, improved viewport (VP) and gaze prediction schemes are critical for enabling smoother VR streaming, as these features are the foundation of the user's experience while wearing the headset. Thus, the global brain proposes novel VP and gaze prediction schemes which produce high prediction accuracy and reduced resource consumption. Finally, this thesis proposes a novel knowledge sharing mechanism that enables mobile services to improve their models by learning from others and incorporating global knowledge, which significantly increases inference accuracy. To prevent sensitive information leakage during knowledge sharing among service providers, we propose a lightweight multi-key homomorphic encryption scheme that allows mobile services to protect their knowledge (i.e., deep neural network weights).

Description

Supervising professor

Sigg, Stephan, Prof., Aalto University, Department of Information and Communications Engineering, Finland

Keywords

artificial intelligence, mobile services, privacy protection, virtual reality, federated learning, internet of things, 5G

Other note

Parts

  • [Publication 1]: Si-Ahmed Naas, and Stephan Sigg. Challenges for AI beyond 5G: Overview, Outlook and Opportunities. Submitted.
  • [Publication 2]: Si-Ahmed Naas, Thaha Mohammed, and Stephan Sigg. A Global Brain fuelled by Local intelligence: Optimizing Mobile Services and Networks with AI. 16th International Conference on Mobility, Sensing and Networking, pp. 23-32, Dec 2020.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202105126706
    DOI: 10.1109/MSN50589.2020.00021 View at publisher
  • [Publication 3]: Si-Ahmed Naas, and Stephan Sigg. Real-time Emotion Recognition for Sales. 16th International Conference on Mobility, Sensing and Networking, pp. 584-591, Dec 2020.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202105126694
    DOI: 10.1109/MSN50589.2020.00096 View at publisher
  • [Publication 4]: Andreas Hitz, Si-Ahmed Naas, and Stephan Sigg. Sharing Geotagged Pictures for an Emotion-based Recommender System. 19th IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops), pp. 68-73, Mar 2021.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202202021678
    DOI: 10.1109/PerComWorkshops51409.2021.9430978 View at publisher
  • [Publication 5]: Xiaolan Jiang, Si-Ahmed Naas, Yi-Han Chiang, Stephan Sigg, and Yusheng Ji. SVP: Sinusoidal Viewport Prediction for 360-Degree Video Streaming. IEEE Access, vol. 8, pp. 164471-164481, Sep 2020.
    DOI: 10.1109/ACCESS.2020.3022062 View at publisher
  • [Publication 6]: Si-Ahmed Naas, Xiaolan Jiang, Stephan Sigg, and Yusheng Ji . Functional Gaze Prediction in Egocentric Video. 18th International Conference on Advances in Mobile Computing and Multimedia, pp. 40–47,Nov 2021.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202103312665
    DOI: 10.1145/3428690.3429174 View at publisher
  • [Publication 7]: Thaha Mohammed, Si-Ahmed Naas, Stephan Sigg, and Mario Di Francesco. Knowledge Sharing in AI Services: A Market-based Approach. IEEE Internet of Things Journal, vol. 10, no. 2, pp. 1320-1331, Jan 2023.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202209215643
    DOI: 10.1109/JIOT.2022.3206585 View at publisher
  • [Publication 8]: Jing Ma, Si-Ahmed Naas, Stephan Sigg, and Xixiang Lyu. Privacy-preserving Federated Learning Based on Multi-key Homomorphic Encryption. International Journal of Intelligent Systems, pp. 5880-5901, Jan 2022.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202304052686
    DOI: 10.1002/int.22818 View at publisher

Citation