Due to great advances in wireless communication, the connected Internet of vehicles (CIoVs) has become prevalent. Naturally, internal connections among active vehicles are an indispensable factor in traffic forecasting. Although many related research studies have been conducted in the past few years, they mainly designed and/or developed single forecasting models for traffic forecasting. Such models may show ideal performance in some scenarios but lack satisfactory robustness to dynamic scenario changes. To address this challenge, a graph neural network-driven traffic forecasting model for CIoVs is proposed in this work, which is denoted as Gra-TF. In this paper, we regard the dynamics of traffic data as a temporal evolution scenario. With the assistance of ensemble learning, three typical graph-level prediction methods are employed to construct an integrated and enhanced forecasting model. This design utilizes several methods to minimize uncertainty in CIoVs. Finally, we use a real-world dataset to build an experimental scenario for further assessment. Numerical results indicate that the proposed Gra-TF improves the prediction accuracy by 30% to 40% compared with several baseline methods. 

Graph Neural Network-Driven Traffic Forecasting for the Connected Internet of Vehicles

An essential consideration in cyber-physical systems (CPS) is the ability to support secure communication services, such as points of interest (POI) microservices. Existing approaches to support secure POI microservices generally rely on anonymity and/or differential privacy technologies. There are, however, a number of known limitations with such approaches. Hence, this work presents a deep-federated-learning-based framework for securing POI microservices in CPS. In order to enhance data security, the system architecture is designed to isolate the cloud center from accessing user data on edge nodes, and an interactive training mechanism is introduced between the cloud center and edge nodes. Specifically, edge nodes pre-train reliable deep-learning-based models for users, and the cloud server coordinates parameter updating via federated learning. The connected and isolated structure between cloud center and edges facilitates deep federated learning. Finally, we implement and evaluate the performance of our proposed approach using two real-world POI-related datasets. The results show that our proposed approach achieves optimal scheduling performance and demonstrates its practical utility.

Deep Federated Learning Enhanced Secure POI Microservices for Cyber-Physical Systems

Nowadays, online spamming has already been a remarkable threat to contents security of Internet of Things. Due to constant technical progress, online spamming activities have been more and more concealed. This brings much fuzziness to spammer detection scenarios, yielding the issue of fuzzy detection of spammers. Although existing detection techniques for spammers utilized idea of deep learning, they still ignore to release power of label spaces. As real nature about a user may be usually fuzzy, but the label annotated for a user is always certain. To remedy such gap, this article proposes a label smoothing-based fuzzy detection method for spammers (Fuz-Spam). First of all, deep representation is still utilized to deeply fuse features, which acts as the foundation of neural computing. On this basis, generative adversarial learning is introduced to transform previous label spaces into distributed forms. In addition, two groups of experiments are carried out on two real-world datasets for evaluation. The results demonstrate that the Fuz-Spam improves identification efficiency about 10% to 20% than previous ones, and that the Fuz-Spam is endowed with proper stability. 

Fuz-Spam: Label Smoothing-Based Fuzzy Detection of Spammers in Internet of Things

With the growing importance of green wireless communications, point-of-interest (POI) scheduling in the mobile social network (MSN) environment has become important in addressing the high demand for innovative scheduling solutions. To enhance feature expressions for the complicated structures in MSNs, this article explores a deep information, fusion-based POI scheduling system of the MSN environment via the implementation of an edge-cloud deep hybrid sensing (PS-MSN) framework. Cloud sensing modules utilize the explicit contextual real-time information for each user, while edge sensing modules detect the real-time implicit linkages among users. Based on these two types of modules, a deep representation scheme is embedded into the hybrid sensing framework to improve its feature expression abilities. As a result, this type of framework is able to integrate multisource information so that more fine-grained feature spaces are built. In this work, two groups of experiments are conducted on a real-world dataset to evaluate the efficiency, as well as stability, of the designed PS-MSN. Using three benchmark methods to make comparisons, the excellent overall performance of PS-MSN is properly verified. 

/pdf/deep-information-fusion-driven-poi-scheduling-for-mobile-1egvy9sr.pdf

Deep Information Fusion-Driven POI Scheduling for Mobile Social Networks

In ear of smart cities, intelligent medical image recognition technique has become a promising way to solve remote patient diagnosis in IoMT. Although deep learning-based recognition approaches have received great development during the past decade, explainability always acts as a main obstacle to promote recognition approaches to higher levels. Because it is always hard to clearly grasp internal principles of deep learning models. In contrast, the conventional machine learning (CML)-based methods are well explainable, as they give relatively certain meanings to parameters. Motivated by the above view, this paper combines deep learning with the CML, and proposes a hybrid intelligence-driven medical image recognition framework in IoMT. On the one hand, the convolution neural network is utilized to extract deep and abstract features for initial images. On the other hand, the CML-based techniques are employed to reduce dimensions for extracted features and construct a strong classifier that output recognition results. A real dataset about pathologic myopia is selected to establish simulative scenario, in order to assess the proposed recognition framework. Results reveal that the proposal that improves recognition accuracy about two to three percent. 

Yang Xiao

Papers

A data-driven intelligent planning model for UAVs routing networks in mobile Internet of Things