Transactions on Emerging Telecommunications Technologies最新文献

In smart cities, AI-driven traffic flow prediction and anomaly detection play a crucial role in optimizing urban mobility and reducing congestion. Traditional traffic management systems (TMS) often struggle with real-time adaptability, leading to inefficiencies in traffic prediction and failure to detect anomalies accurately. To address these limitations, we propose the Traffic Flow Prediction using Multi-Agent Approach (TFP-MAA) framework, which leverages multiple intelligent agents to analyze real-time traffic data, predict congestion patterns, and detect anomalies with high precision. The framework integrates deep learning models with a decentralized multi-agent system to enhance prediction accuracy and response efficiency. The proposed method enables adaptive decision-making for traffic authorities by providing real-time congestion forecasts and identifying unusual traffic patterns, such as accidents or roadblocks. This enhances proactive traffic management and reduces delays. Experimental results demonstrate that TFP-MAA significantly outperforms existing models in terms of accuracy (94.7%), response time (96.2%), and anomaly detection efficiency (95.9%). The findings suggest that integrating multi-agent AI systems into smart city infrastructure can lead to improved traffic flow (97.5%), reduced congestion (28.6%), and enhanced road safety.

As a key technology in ocean exploration, underwater wireless sensor networks (UWSNs) are persistently constrained by challenges stemming from limited node energy, namely short network lifespan and low transmission efficiency. Existing routing protocols often fall into local optima due to their inability to effectively balance global exploration and local exploitation. To address these issues, this study proposes a hybrid optimization routing protocol, HFFO-ACRP (hybrid fruit fly optimization-ant colony routing protocol). Its core innovation lies in a synergistic division of labor: the fruit fly optimization algorithm (FOA) performs a global search to generate initial routes by integrating path length, node density, and residual energy. Subsequently, the ant colony optimization (ACO) algorithm conducts local optimization to refine these paths, considering data priority and node energy efficiency. Finally, a unique bidirectional feedback mechanism enables the two algorithms to mutually enhance their search breadth and precision, collectively improving the accuracy and efficiency of route selection. Experimental results demonstrate that, compared to representative protocols, the proposed protocol extends the network lifespan by 9.69%, 16.21%, and 18.68%, respectively, and significantly increases the residual network energy in the later stages of operation. This hybrid strategy provides an efficient and robust routing solution for resolving the critical energy consumption and longevity bottlenecks in UWSNs.

Vehicular ad-hoc networks (VANETs) are critical to intelligent transportation systems yet inherently vulnerable to security threats, including data falsification, message tampering, and denial-of-service attacks. Traditional centralized security mechanisms exhibit limitations in scalability, trustworthiness, and resilience against single points of failure. To address these challenges, this study proposes a blockchain-enabled decentralized framework integrating machine learning for anomaly detection in VANETs. The proposed model employs a multi-layer blockchain architecture to establish transparent and immutable trust among participating nodes, with smart contracts automating security policies, intrusion response, and vehicle reputation management. Machine learning algorithms are incorporated to analyze spatiotemporal traffic patterns, detect abnormal behaviors such as malicious message injection and position spoofing, and differentiate legitimate nodes from intruders. Furthermore, simulation results demonstrate that the proposed framework achieves dual optimization objectives: (1) consensus efficiency improvements reducing verification latency by ≥ 40% through Practical Byzantine Fault Tolerance enhancements; and (2) detection accuracy enhancements reaching 94.2% precision in identifying sophisticated attacks—while maintaining efficient scalability for large-scale VANET environments. This research highlights the synergy of blockchain and machine learning in building a secure, decentralized, and intelligent vehicular network infrastructure, contributing to the safe deployment of next-generation intelligent transportation systems.

Cyberattack detection systems are critical in protecting the Internet of Things (IoT) network from attacks. Cyber-attack detection is critical in fog-based IoT systems to protect against a wide range of threats, such as illegal access, data breaches, and service disruptions. Present cyber-attack detection models have limitations, such as a high false alarm rate (FAR) and limited detection accuracy. Therefore, it is essential to create reliable cyberattack detection systems that can raise the accuracy of detection and lower the rate of false alarms. This paper presents a deep learning (DL)-based classifier model with an effective feature extraction mechanism for detecting cyber-attacks in a fog-based IoT system. Before initiating the process, data augmentation has been done to balance the dataset. Initially, the input data are collected from the public source dataset; the collected data are passed into the pre-processing stage to rescale the data properly, which is performed by Z-Score normalization. The optimal set of features from the pre-processed data is extracted by a meta-heuristic technique, namely the Hybrid white shark sea lion optimization algorithm (Hy-WS²LO). After selecting optimal features, the data is fed into a classifier model to detect cyber-attacks in a fog-based IoT environment. An effective Residual attention-based dilated pyramidal depth-wise separable convolution (ResA-D²PySepCo) is used for identifying cyber-attacks in fog-based IoT networks. The proposed model can obtain an accuracy of 98.87% and 99.74% for ToN IoT and CICIDS 2018 datasets.

Vehicular Ad-hoc Networks (VANETs) are a cornerstone of Intelligent Transportation Systems (ITS), enabling efficient vehicle-to-vehicle and vehicle-to-infrastructure communication. However, their open and dynamic nature makes them highly susceptible to security threats such as Distributed Denial of Service (DDoS) attacks and the injection of false data by malicious nodes. Existing security mechanisms often fall short in addressing these challenges due to the real-time and mobile characteristics of VANETs. This paper proposes a Hybrid Explainable Artificial Intelligence (XAI) framework integrated with a Swin Vision Transformer for robust intrusion detection in VANET environments. The proposed model leverages the Swin Transformer's hierarchical feature extraction capabilities and the interpretability of XAI to accurately classify network nodes based on behavioral and transmission characteristics. Key features such as packet transmission duration, communication regularity, and node status are analyzed to detect anomalies and differentiate between benign and malicious nodes. The inclusion of explainability allows for transparent decision-making, facilitating trust and understanding in critical automotive applications. Simulation results validate the model's effectiveness in detecting a wide range of attack vectors while maintaining high accuracy and low false-positive rates. This study contributes to the development of adaptive, intelligent, and trustworthy security solutions for next-generation vehicular networks operating in complex urban traffic scenarios.

In the modern era, blockchain technology integrated with the Internet of Things (IoT) has emerged as a powerful segment for secured and translucent smart city applications. Initially, authentication forms the stepping stone for defense in different types of information systems; earlier approaches used in the context of single-side centralization were found faint and uncertain, with the enlarged single-point failure owing to external vulnerabilities. With the incorporation of an advanced authentication scheme, this research proposes the Elliptic Key-modified Rivest Shamir Adleman (EKMRS) scheme to overcome the tackles in existing techniques, thereby improving the security of applications. Moreover, the risks involved in identity fraud can be effectively minimized by blockchain technology that assures that public keys are verified using a decentralized consensus technique and stored securely. This combination not only secures communication channels but also includes a decentralized ledger for identity verification with tamper-proof evidence. The EKMRS utilizes the Elliptic Curve Digital Signature Algorithm that enhances the scalability enlargement and robust solution for a smart city environment, ensuring strong authentication. The experimental results demonstrate the effectiveness of the EKMRS scheme by offering significant improvements in terms of metrics, achieving 0.029 ms for decryption time, an encryption time of 0.39 ms, and an information loss of 0.13 with the students mark sheet dataset over the other recognized approaches.

Recent years have seen tremendous progress in Autonomous Vehicle (AV) technology. Today, certain locations provide various levels of autonomy. Constrained environments, such as airports and golf clubs, may allow fully autonomous driving (AD). Meanwhile, many public roads have started providing Vehicle-to-Everything (V2X) capabilities, enabling AVs with driver intervention (DI). Yet, for future scenarios without DI, low-latency technologies, robust protocols, and secure communication mechanisms will be essential. However, dependence on computer algorithms introduces security concerns. A breach in an AV can result in serious injuries or even death. This issue requires next-generation vehicles to implement robust security solutions to prevent malicious attacks. This study discusses state-of-the-art security technologies, protocols, and organizations relevant to autonomous driving (AD) and autonomous vehicles (AVs). First, the paper explores concepts like V2X, Intrusion Detection Systems (IDS), and collaborative security measures. Then, it will discuss the state-of-the-art security studies from the perspective of misbehavior detection and collective perception. This survey fills a void in the literature (at the time of the writing). It is also a comprehensive V2X security guide on misbehavior detection, collective perception, and related technologies.

The advancement of collaborative autonomous driving relies on robust and efficient data exchange between vehicles and surrounding infrastructure. Vehicle-to-everything (V2X) fusion communication frameworks, built upon vehicular ad hoc networks (VANETs), enable the integration of heterogeneous data sources to enhance environmental perception and decision-making. However, practical implementation faces significant challenges due to communication interruptions inherent in dynamic VANET environments, leading to incomplete cooperative perception and increased safety risks. To address these challenges, this research proposes a V2X fusion communication framework, incorporating communication-interruption-aware cooperative perception, to ensure reliable information exchange for autonomous vehicles operating in collaborative scenarios. The framework leverages historical cooperation information to compensate for missing data caused by communication disruptions. Furthermore, a communication stochastic temporal convolutional networks (STCN) prediction model is introduced to extract critical features under varying network conditions, enhancing predictive accuracy for lost information. The data were collected from an open-source platform, which includes multi-agent sensor data (LiDAR, radar, and camera), global positioning system (GPS), and timestamped V2X messages simulating realistic vehicular traffic and environmental conditions under varying communication qualities. Packet drop rates were emulated to reflect real-world VANET communication inconsistencies. Additionally, knowledge distillation techniques provide targeted supervision to the predictive model, while curriculum learning strategies stabilize the training process under complex VANET scenarios. The results of the experiments prove that the proposed framework enhanced the perception reliability, and collaborative performance, communication reliability, decreased latency, enhanced obstacle detection accuracy, and decreased error results, including MAE (0.11) and MSE (0.12). This VANET communication architecture is a fusion-based framework that provides reliable, efficient, and safe data-driven collaboration within a group of autonomous vehicles.