Search

Tackling traffic signal control through multi-agent reinforcement learning is a widely-employed approach. However, current state-of-the-art models have drawbacks: intersections optimize their own local rewards and cause traffic to waste time and fuel with a start-stop mode at each intersection. They also lack information sharing among intersections and their specialized policy hinders the ability to adapt to new traffic scenarios. To overcome these limitations, This work presents a centralized collaborative graph network (CCGN) with the core objective of a signal-free corridor once the traffic flows have waited at the entry intersection of the traffic intersection network on either side, the subsequent intersection gives the open signal as the traffic flows arrive. CCGN combines local policy networks (LPN) and global policy networks, where LPN employed at each intersection predicts actions based on Transformer and Graph Convolutional Network (GCN). In contrast, GPN is based on GCN and Q-network that receives the LPN states, traffic flow and road information to manage intersections to provide a signal-free corridor. We developed the Deep Graph Convolution Q-Network (DGCQ) by combining Deep Q-Network (DQN) and GCN to achieve a signal-free corridor. DGCQ leverages GCN's intersection collaboration and DQN's information aggregation for traffic control decisions Proposed CCGN model is trained on the robust synthetic traffic network and evaluated on the real-world traffic networks that outperform the other state-of-the-art models. [ABSTRACT FROM AUTHOR]

Recently, biometric technology has been extensively embedded in mobile devices to enhance security of mobile devices. With rise of financial technology (FinTech) that employs mobile applications as well as devices as promotional platforms, biometrics has a significant role in strengthening the detection of this privacy application. This manuscript offers the design of salp swarm optimization with auto-encoder based biometric authentication (SSOAE-BMA) model for the recognition of abnormal activities in the Fintech banking applications based on wireless communication. The major aim of the SSOAE-BMA model lies in the proper authentication of persons via biometric matching process. Initially, the presented SSOAE-BMA model makes use of stacked ResNet-50 model for deriving feature vectors. Next, the SSOAE-BMA model utilizes AE for biometric verification and the performance of the AE model is adjusted using the Social Spider Optimization (SSO) Algorithm which in turn enhances the recognition outcomes. To demonstrate the improved performance of SSOAE-BMA model, a series of simulations were carried out. The experimental outcomes signified the enhancements of the SSOAE-BMA model over existing models. [ABSTRACT FROM AUTHOR]

• The 5G technology assisted smart home security framework is developed with key exchange, authentication, and privacy management processes. • A novel Sailfish-based distributed IP mobility management (SbDMM) protocol is implemented for enhancing the security level of smart home systems. • The main aim of implementing the optimization based routing mechanism is to secure data between the SH network and MN. Generally, cellular networks are divided into discrete geographic zones where a secure routing protocol is important. In this study, Sailfish-based Distributed IP Mobility Management (SbDMM) architecture for security protocol in a smart home using 5G is suggested. Smart homes first gathered data via IoT devices which are then communicated with the use of a Home Gateway (HGW). Mobile Nodes (MN) and Corresponding Nodes (CN) process data communication (CN). In addition, the acquired data are encrypted and secured using the session key. Additionally, use an authenticated key and a cipher key to secure the routing optimization. As a result, the fitness of sailfish is updated in a protocol path that is optimized for securing data from attackers. The designed framework is then implemented in Python and the obtained results are compared to those of other methodologies in terms of execution time, confidentiality rate, efficiency, delay, and task completion. [Display omitted] [ABSTRACT FROM AUTHOR]