Transactions on Emerging Telecommunications Technologies最新文献

Segmentation is a crucial step to divide an image into background and foreground sections and uses different colors to identify the target portion. Different thresholding-based segmentations have been developed in the current research analysis; however, the problems are difficult to solve and take a long time. To overcome these existing limitations, a novel Masi entropy-based multi-level thresholding with an effective optimization algorithm is introduced for image segmentation. The input images are collected from the open-source dataset, namely the Berkeley Segmentation Dataset 500 (BSDS500) and the Cityscapes dataset. To remove noise and enhance image quality, use the Quantized Haar Wavelet Assisted Histogram Equalization (QuaWHe) technique in the pre-processing stage. After noise removal, image segmentation was performed by the 2D practical Masi entropy histogram function (2D-MentH) with the Reinforcement Learning-assisted fire-fly-oriented multiverse optimizer (RL-FF-MVO) algorithm. The RL-FF-MVO mechanism helps to select the optimal set of threshold values from the values obtained using the 2D-MentH mechanism. By integrating reinforcement learning, the optimization process's convergence speed and accuracy are greatly increased while computing overhead is decreased. The proposed model has obtained Peak Signal Noise Ratio (PSNR) and Structural Similarity Index (SSIM) values of 30.587 and 0.9995 at threshold level 10. At threshold level 10, the proposed model has obtained Mean Square Error (MSE) and Feature Similarity Index (FSIM) values of 0.8531 and 0.96 248. For the Probabilistic Rand Index (PRI), the proposed model obtains a value of 0.72003, and for Variation of Information (VOI), it achieves 4.0298 at threshold level 10. The proposed approach outperforms existing methods regarding segmentation quality and computational efficiency, making it suitable for applications requiring high-accuracy image analysis, such as autonomous systems and medical imaging.

VANETs are essential for communication and coordination between autonomous vehicles, particularly in emergency scenarios where quick decisions are necessary. The proposed Deep Learning-based Control Approach for Autonomous Vehicles (DL-CA-AV) introduces a hybrid DL control framework that integrates Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) with an attention-driven decision-fusion mechanism for real-time maneuver control in VANET-enabled environments. The CNN module extracts spatial features from sensor and VANET communication data, while the LSTM network models temporal dependencies to predict dynamic vehicular states across time. These learned spatiotemporal representations are then passed to a reinforcement learning (RL) layer, where the actor–critic mechanism evaluates potential maneuvers and selects optimal control actions based on collision probability and situational awareness. The proposed approach encourages vehicles to autonomously choose the best emergency response (lane change, deceleration, or cooperative braking) while preserving stability and minimizing secondary risks. This study demonstrates the capability of DL-based VANET architectures to enable real-time autonomous driving control in hazardous environments, facilitating safer and more dependable intelligent mobility. The proposed framework achieves a collision probability of 29%, a latency below 225 ms, a detection accuracy above 85%, and a packet delivery ratio above 88%.

Vehicular networks are essential to the advancement of intelligent transportation systems by enabling continuous data exchange between vehicles and infrastructure to support safe mobility. However, the distributed and dynamic nature of these networks creates opportunities for adversarial threats. Existing attack-detection models primarily rely on centralized architectures, which often suffer from high latency, privacy risks, and limited robustness against advanced attacks. To address these challenges, this study proposes the LIFT-SFD model. This lightweight federated learning framework integrates Smooth Federated Dropout (SFD) with trust-weighted mask-aware aggregation for secure and resource-aware training in vehicular ad hoc networks (VANET). Each vehicle trains a masked submodel, while smooth dropout regularization ensures stable convergence and reduced communication overhead. Then, an integrated assault monitoring module detects and reduces malicious behavior by assigning anomaly scores at the vehicle level, adjusting trust weights during RSU-level aggregation, and gradually filtering out malicious participants. The simulation of the models is performed using the VeReMi dataset, demonstrating high detection accuracy of 99.98% at round 5. It acts as a stable and trustworthy global model for future vehicular networks.

Instantaneous interaction and autonomous modes of transport are facilitated by Vehicular Ad Hoc Networks (VANETs), which play a crucial role in the development of smart cities. However, the flexible and autonomous architecture of VANETs poses significant security risks, including susceptibility to cyberattacks, privacy breaches, and information manipulation. These challenges are exacerbated by high node mobility and the large volume of heterogeneous data exchanged in modern urban environments. This study proposes a novel security framework that leverages transfer learning-based threat detection and mitigation techniques to address these issues. By utilizing pre-trained machine learning models fine-tuned with VANET-specific datasets, the approach reduces training time and computational costs while enabling efficient detection of anomalies and attacks. The objectives are to enhance network security, safeguard data integrity, and minimize latency in threat detection processes. Research findings indicate that the proposed framework outperforms traditional machine learning models in terms of scalability, resilience, and the ability to detect malicious activities. By providing a secure communication infrastructure for VANETs, this research contributes to the development of reliable and efficient smart city systems.

This investigation delineates a dual-domain computational paradigm integrating machine learning (ML)-based parametrization of gaseous optical properties with ensemble-driven anomaly detection in Vehicular Ad Hoc Networks (VANETs), aimed at accelerating predictive fidelity in climate-cyber-physical simulations. The study formulates a Random Forest (RF) surrogate model to approximate nonlinear radiative transfer coefficients and simultaneously classify spatiotemporally correlated anomalies induced by cyber-physical perturbations within VANET topologies. A synthetically constructed dataset comprising 500 multi-dimensional vehicular communication profiles encoding instantaneous velocity vectors, geospatial coordinates, signal-to-noise ratios, inter-vehicular latency, and communication fidelity metrics was employed for rigorous model training and validation. The surrogate framework achieved a coefficient of determination ($$) of 0.963, Mean Squared Error (MSE) of $$, and Mean Absolute Error (MAE) of 0.028, reflecting sub-3% deviation from empirically derived ground truth in both anomaly classification and optical property approximation. Notably, latency analysis indicated a 35% reduction relative to conventional rule-based intrusion detection paradigms, underscoring the potential of ensemble-based surrogate learning for real-time, computationally efficient detection of VANET anomalies under high-dimensional, stochastic environments. Prospective enhancements include hybridization with temporal convolution networks and federated learning strategies to enable edge-resident deployment while preserving high-resolution optical and cyber-physical predictive accuracy. This study substantively demonstrates the feasibility of co-optimized surrogate modeling frameworks for synergistic acceleration of climate simulation fidelity and cyber-physical system resilience.

Vehicular Ad Hoc Networks (VANETs), a crucial part of Intelligent Transportation Systems, provide real-time vehicle-RSU communication. VANETs are subject to DDoS assaults, which may undermine safety-critical systems due to their dynamic and dispersed nature. VANET DDoS detection solutions frequently use centralized designs that need raw data aggregation (DA), which causes scalability, communication cost, and privacy difficulties. Additionally, traditional models fail to adapt to vehicular surroundings' varied and frequently changing traffic patterns. Federated Anomaly Detection with Personalized Autoencoders (FAD-PAE) is proposed to address these issues. Vehicles and roadside equipment train lightweight Autoencoders (AE) locally to simulate regular traffic behavior, exchanging just model updates via federated learning. Personalized fine-tuning at each node adapts to local traffic changes, while safe and strong aggregation protects against compromised clients. The VANET-based cooperative and privacy-preserving DDoS detection approach reduces false alarms and communication costs. Experimental results show superior detection accuracy (ACC), reaction speed, and flexibility compared to centralized techniques.

The rapid expansion of IoT ecosystems has intensified challenges in securely managing large volumes of sensitive data generated by devices operating under constraints of limited computation, energy, and bandwidth. Conventional key management and authentication mechanisms struggle with scalability and efficiency, increasing susceptibility to emerging security threats. To address these limitations, this study proposes a lightweight, post-quantum secure key management framework that integrates lattice-based encryption with Ciphertext-Policy Attribute-Based Encryption (CP-ABE). The model incorporates SHA-512–based authentication to ensure device integrity and employs Elastic Search with MapReduce for scalable data compression and handling. End-to-end confidentiality is maintained through secure encryption, dynamic re-encryption, and fine-grained cloud-based access control. MATLAB simulations validate system performance, demonstrating improved encryption and decryption times of 145 and 160 ms, surpassing traditional CP-ABE and RSA approaches. Key generation and update times are reduced to 120 and 95 ms, enabling dynamic policy management. Authentication accuracy reaches 98.7% precision and 97.9% recall, ensuring reliable device verification, while Elastic Search and MapReduce achieve 250 MB/s throughput and reduce network load by 35% via data-locality scheduling. Re-encryption overhead remains low at 130 ms, with minimal resource usage (20% CPU, 25 MB memory), supporting constrained devices. Scalability tests show only modest latency growth up to 200 nodes. The proposed lattice-based CP-ABE framework offers a secure, efficient, and scalable solution for next-generation IoT environments. Future work will extend applicability to larger networks and integrate AI-driven adaptive security for enhanced resilience.

Object detection has gradually developed into a popular research area because of the rife use of Remote Sensing Images (RSIs) in military and civil domains. However, complex backgrounds and problems with small items are the two biggest obstacles in object detection. Deep learning techniques have a significant advantage for object detection over conventional methods that rely on manually derived characteristics, and they have a lot of attention. Due to the wide range of objects and complex visual backgrounds in RSIs, current deep-learning algorithms in the area of RSI object detection leave much to be desired. For this case, algorithms need to be specifically optimized. In this paper, a novel optimization-driven Enhanced Faster Region Convolutional Neural Network (FRCNN) is proposed for object detection. This approach has five modules, namely pre-processing, data augmentation, segmentation, feature extraction, and object detection. The detection process is performed using Enhanced FRCNN and it is trained by the proposed Gazelle White Shark Optimization Algorithm (GWSOA). Extensive experiments in high-resolution RSI data sets have exposed the efficacy of the proposed approach. The novel approach achieved better accuracy of 97.31%, Mean Average Precision (MAP) of 97.85%, precision of 97.76%, recall of 96.16%, F-score of 95.78%, and error rate of 2.69.

The rapid emergence of Internet of Things (IoT) applications such as smart cities, intelligent transportation, healthcare, logistics, and wearable systems has increased the demand for scalable and low-latency computing infrastructure. Despite the widespread adoption of traditional cloud computing platforms to handle these applications, offloading all tasks to centralized cloud data centers results in significant latency, high energy consumption, and increased operational costs. Many of these applications are delay-sensitive and computationally intensive, requiring immediate decision-making and localized processing. To address these limitations, we propose a prioritized constraint-aware task offloading mechanism (PCATOM) that efficiently schedules and offloads tasks by considering task-level and resource-level constraints in a fog-cloud computing environment. PCATOM leverages the Deep Deterministic Policy Gradient (DDPG) algorithm, a policy gradient reinforcement learning method designed to balance exploration and exploitation while dynamically learning optimal offloading strategies. The framework reduces overall latency, energy consumption, and execution cost by making intelligent decisions about where and how to offload tasks. PCATOM was implemented using the SimPy simulation framework and evaluated using a combination of statistical workloads and real-world parallel computing traces from NASA and HPC2N. Experimental results show that PCATOM consistently outperforms baseline models such as DQN and A2C, achieving up to 32.5% lower latency, 28.7% lower energy consumption, and 18.4% higher throughput. These results demonstrate the effectiveness and scalability of PCATOM in dynamic and diverse fog-cloud environments.

The terahertz (THz) range is perfect for high-throughput applications like enhanced sensing, ultra-fast wireless backhauls, and real-time virtual and augmented reality because of its availability of unoccupied spectrum, which permits unparalleled bandwidths. The novel THz designs and components are being propelled by recent developments in nanomaterials, photonic devices, and intelligent surfaces. Additionally, the integration of THz waves with sensing and security capabilities opens up new paradigms in secure communication, healthcare applications, and intelligent settings. To achieve reliable and extensible THz communication systems, this article delves into the necessary technologies, propagation properties, and future study paths. Photonic crystals (PhC) have recently gained popularity for use in cutting-edge electromagnetic fields because of their remarkable controllability over the transmission of electromagnetic waves. The use of PhC ideas along with old and new antenna designs offers a way to create antennas that are very directional, slim, and adjustable. This article proposes a new design that combines the Kagome lattice PhC structure with a modified patch antenna that uses a Gingham sequence. The air holes in the Kagome lattice are optimized to enhance antenna characteristics like return loss (RL), gain, voltage standing wave ratio (VSWR), directivity, and so on. The proposed Kagome lattice PhC antenna works at THz frequency; hence, it is suitable for medical applications like cancer detection, and so on.