Intelligent Terrestrial and Non-Terrestrial Vehicular Networks with Green AI and Red AI Perspectives.

In this paper, we aim to envision 6G convergent terrestrial and non-terrestrial infrastructure of virtual emotion and epidemic prevention with two differential perspectives: Green AI and Red AI, where Green AI focuses on efficiency and reduction, and Red AI additionally pursues accuracy. By fitting with each perspective, we introduce promising key applications using smart devices, autonomous UAVs, mobile robots and subsequently suggest critical future research directions and opportunities toward new frontiers in intelligent terrestrial and non-terrestrial vehicular networks.

Anomaly Detection in Industrial IoT Using Distributional Reinforcement Learning and Generative Adversarial Networks.

Anomaly detection is one of the biggest issues of security in the Industrial Internet of Things (IIoT) due to the increase in cyber attack dangers for distributed devices and critical infrastructure networks. To face these challenges, the Intrusion Detection System (IDS) is suggested as a robust mechanism to protect and monitor malicious activities in IIoT networks. In this work, we suggest a new mechanism to improve the efficiency and robustness of the IDS system using Distributional Reinforcement Learning (DRL) and the Generative Adversarial Network (GAN). We aim to develop realistic and equilibrated distribution for a given feature set using artificial data in order to overcome the issue of data imbalance. We show how the GAN can efficiently assist the distributional RL-based-IDS in enhancing the detection of minority attacks. To assess the taxonomy of our approach, we verified the effectiveness of our algorithm by using the Distributed Smart Space Orchestration System (DS2OS) dataset. The performance of the normal DRL and DRL-GAN models in binary and multiclass classifications was evaluated based on anomaly detection datasets. The proposed models outperformed the normal DRL in the standard metrics of accuracy, precision, recall, and F1 score. We demonstrated that the GAN introduced in the training process of DRL with the aim of improving the detection of a specific class of data achieves the best results.

CCS_WHMS: A Congestion Control Scheme for Wearable Health Management System.

Wearable computing is becoming a more and more attracting field in the last years thanks to the miniaturisation of electronic devices. Wearable healthcare monitoring systems (WHMS) as an important client of wearable computing technology has gained a lot. Indeed, the wearable sensors and their surrounding healthcare applications bring a lot of benefits to patients, elderly people and medical staff, so facilitating their daily life quality. But from a research point of view, there is still work to accomplish in order to overcome the gap between hardware and software parts. In this paper, we target the problem of congestion control when all these healthcare sensed data have to reach the destination in a reliable manner that avoids repetitive transmission which wastes precious energy or leads to loss of important information in emergency cases, too. We propose a congestion control scheme CCS_WHMS that ensures efficient and fair data delivery while used in the body wearable system part or in the multi-hop inter bodies wearable ones to get the destination. As the congestion detection paradigm is very important in the control process, we do experimental tests to compare between state of the art congestion detection methods, using MICAz motes, in order to choose the appropriate one for our scheme.