Updating

Cyber-attack detection and information security in Industry 4.0

A main driver for smart city development is Industry 4.0, in which ICT helps connect physical systems to the cyber-world, thereby enabling supply chain market more efficient, agile, and customer-focused. However, cyber-security risks become a key concern due to open systems with IP addresses, creating more avenues for cyber-attacks.

Information and communication technology (ICT) is expected to play an increasingly pivotal role in deepening economic integration and community building across the Association of Southeast Asian Nations (ASEAN), transitioning towards a digitally-enabled economy that is secure, sustainable, and transformative. This project considers the development of connected smart cities for a smart ASEAN society in general and in Vietnam in particular.

The project aims to provide tools to enhance cyber-security in Industry 4.0, contributing to the enhancement of information reliability for smart society. In particular, it will develop (i) an innovative method to detect cyber-security threats in Industry 4.0 using advanced deep learning technology, (ii) an unprecedented framework to protect massive Industry 4.0 data from cyber-attacks using blockchain technology, and (iii) novel security solutions at the physical interface of information transmission using physical-layer security technology.

Agricultural IoT based on Edge Computing

This project aims to build an agricultural IoT framework based on edge computing, with a focus on solving existing challenges for agricultural IoT systems for both academic and practical aspects at the network edge.

Research findings on improving edge computing performance, system security, and advanced intelligent computing will be applied and tested on farms across the participating countries. As an outcome, the exchange of experiences and data sharing among research institutions, as well as the collected data, will serve as a foundation for continuing to develop a common and effective model/framework for countries to apply to agricultural IoT applications in practice.

Vision-based crack detection with crack propagation modeling

In this work, the propagation of cracks on some materials, such as concrete, is analyzed, the best-fit model of which is employed for vision-based crack detection. Some research questions are being investigated:

• 1. What is the correlation between simulated crack propagation and real-world crack? Here, we measure the fitting errors between best-fit regression models of simulated cracks and the skeleton of crack images from some reputable image datasets.
• 2. How can we leverage the information obtained from simulations to enhance the performance of crack detection models? Some approaches are being conducted: i) employing the propagation similarity as a feature to develop post-processing classifiers, ii) generating GAN-based quality training samples using crack models and background pixels from other reputable crack image datasets.

Machine learning based beacon placement optimization for indoor robots localization

Indoor localization systems usually consist of transceiver with fixed positions, which are called beacons. These beacons act as landmarks for localizing objects that need to be positioned. One can easily see that the positions of beacons have a great impact on the performance of the localization system. The problem of beacon placement optimization is to optimize the positions of beacons in order to maximize the performance of the localization system.

The goal is to build a framework for beacon placement optimization for localization systems based on machine learning. The expected outcome is a procedure to place beacons optimally and apply it to construct and design real-world localization systems. Applying artificial intelligence for beacon placement is at its early stage and has not been fully investigated.

System identification: from blind to informed paradigm

Telecommunication: Aeronautical mobile and a ground station interactions

Our project consists firstly to implement, analyze and test the IF-77 model in order to highlight its weaknesses under various specific configurations (low altitude, high relief). In addition, the obtained simulation results should be also compared to the results provided by the American aeronautical agency.

In a second step, we should suggest some solutions to address the weaknesses of the classical model. We should pay a particular attention to the consistency of the modified model and various existing ITU recommendations (P.525 and P.526 for instance).

Finally, the theoretical propagation models must allow a realistic estimation for our two major concerns: the distance of coordination for the interaction between radars and civilian aircrafts, the data rate between UAV and a ground stations.

LANTERN: Low-latency and private edge computing in random-access networks

In this project, we investigate how low-latency and private edge computing protocols can be developed in wireless random-access networks. Relying on tools from information theory and coding theory, we will tackle the two following challenging objectives: i) to establish a foundation for privacy and reliability in latency-critical, multi-client and multi-server edge computing in random-access networks; and ii) to devise resilient coding schemes together with energy-efficient and scalable wireless random-access protocols to achieve low latency and preserve privacy in distributed edge computing. The results of this project will help to pave the way to the full realization of the IoT in the near future.

Other information

Contact: Dr. Dinh Tran Hiep