In recent decades, automatic vehicle classification plays a vital role in intelligent transportation systems and visual traffic surveillance systems. Especially in countries that imposed a lockdown (mobility restrictions help reduce the spread of COVID‐19), it becomes important to curtail the movement of vehicles as much as possible. For an effective visual traffic surveillance system, it is essential to detect vehicles from the images and classify the vehicles into different types (e.g., bus, car, and pickup truck). Most of the existing research studies focused only on maximizing the percentage of predictions, which have poor real‐time performance and consume more computing resources. To highlight the problems of classifying imbalanced data, a new technique is proposed in this research article for vehicle type classification. Initially, the data are collected from the Beijing Institute of Technology Vehicle Dataset and the MIOvision Traffic Camera Dataset. In addition, adaptive histogram equalization and the Gaussian mixture model are implemented for enhancing the quality of collected vehicle images and to detect vehicles from the denoised images. Then, the Steerable Pyramid Transform and the Weber Local Descriptor are employed to extract the feature vectors from the detected vehicles. Finally, the extracted features are given as the input to an ensemble deep learning technique for vehicle classification. In the simulation phase, the proposed ensemble deep learning technique obtained 99.13% and 99.28% of classification accuracy on the MIOvision Traffic Camera Dataset and the Beijing Institute of Technology Vehicle Dataset. The obtained results are effective compared to the standard existing benchmark techniques on both datasets.

In response to the growing need for enhanced energy management in smart grids in sustainable smart cities, this study addresses the critical need for grid stability and efficient integration of renewable energy sources, utilizing advanced technologies like 6G IoT, AI, and blockchain. By deploying a suite of machine learning models like decision trees, XGBoost, support vector machines, and optimally tuned artificial neural networks, grid load fluctuations are predicted, especially during peak demand periods, to prevent overloads and ensure consistent power delivery. Additionally, long short-term memory recurrent neural networks analyze weather data to forecast solar energy production accurately, enabling better energy consumption planning. For microgrid management within individual buildings or clusters, deep Q reinforcement learning dynamically manages and optimizes photovoltaic energy usage, enhancing overall efficiency. The integration of a sophisticated visualization dashboard provides real-time updates and facilitates strategic planning by making complex data accessible. Lastly, the use of blockchain technology in verifying energy consumption readings and transactions promotes transparency and trust, which is crucial for the broader adoption of renewable resources. The combined approach not only stabilizes grid operations but also fosters the reliability and sustainability of energy systems, supporting a more robust adoption of renewable energies.

Cloud-based deployments face increasing threats from various types of attacks, necessitating robust anomaly detection frameworks to safeguard against potential security breaches. Existing solutions, such as RSSI, GTM, and APG, though effective to a certain extent, exhibit limitations in terms of precision, accuracy, and scalability. To address these shortcomings, this paper proposes a novel anomaly detection framework that integrates multimodal feature analysis, deep learning models, and QoS-aware sidechains to enhance the prediction accuracy of cloud attacks and optimize blockchain-based cloud installations. By maximizing feature variance across different sample types and leveraging advanced deep learning techniques, the proposed approach significantly outperforms conventional methods in terms of precision, accuracy, recall, and AUC performance. Furthermore, the framework demonstrates superior efficiency in block mining delay, energy consumption, and throughput, making it highly suitable for real-time cloud attack prediction scenarios. The proposed methodology represents a significant advancement in anomaly detection and cloud security, offering a comprehensive solution for addressing challenges in blockchain-based cloud deployments. Thus, the proposed anomaly detection framework employs both Deep Learning and Blockchain technologies. Using Recurrent Neural Networks (RNN) with Convolutional Neural Networks (CNN), the system examines system logs and identifies unusual behavior patterns associated with different attacks. Using Blockchain technology, the framework ensures the transparency and integrity of system logs, and Deep Learning models provide precise and timely anomaly detection. The decision to combine Deep Learning and Blockchain technology is justified by the merits of each technique. The distributed, immutable ledger provided by blockchain technology makes it impossible to tamper with system logs and ensures the accuracy of anomaly detection. While, deep learning models, have exceptional pattern recognition abilities and can adapt to changing attack methods, resulting in high precision, accuracy, recall, and AUC metrics. Analyses of experimental data demonstrate that the proposed framework is effective. The framework achieves impressive performance metrics, such as low delays, 98.5% precision, 99.4% accuracy, 98.3% recall, and 99.2% Area Under the Curve (AUC).

Tomato ( Solanum lycopersicum ) is a globally cultivated horticultural crop, yet its productivity is severely constrained by foliar and insect-vectored diseases that reduce its quality and production. Early and accurate diagnosis of these diseases, along with sustainable biocontrol strategies, is essential for improving crop health and reducing economic losses. This review synthesizes and evaluates the recent progress in lightweight deep learning models and edge AI for tomato disease detection, highlighting their potential for practical deployment in precision agriculture. A comprehensive survey of recent literature was conducted, which covers convolutional neural networks, transformer-based models, optimization techniques including pruning, quantization, and knowledge distillation, and use of explainable AI tools to enhance transparency and trust. In addition, experimental validation was performed by utilizing MobileNetV2 and EfficientNetB0 on a subset of tomato diseases that are most common and prevalent in Tamil Nadu. The test performance of both the models resulted in an overall accuracy of 99.9% and macro-F1 nearly 0.99. Further, a unique framework that combines AI-powered diagnosis with microbial biocontrol recommendations is proposed offering a solution to manage diseases in both eco-friendly and region-specific way. Overall, this work provides a roadmap for combining sustainable methods with AI-driven diagnosis, promoting resilient, scalable, and farmer-friendly agricultural systems.

Detecting attacks in 5G software-defined network (SDN) environments requires a comprehensive approach that leverages traditional security measures, such as firewalls, intrusion prevention systems, and specialized techniques personalized to the unique characteristics of a 5G network. The attack detection in 5G SDN involves Machine learning (ML) and Deep learning (DL) algorithms to analyze large volumes of network data and identify patterns indicative of attacks. The study’s main objective is to develop an efficient DL model to improve the detection performance and respond to security breaches effectively in a 5G SDN environment. The DL model integrates the Particle Swarm Optimizer-Gated Recurrent Unit Layer-Generative Adversarial Network-Intrusion Detection System classifier (PSO-GRUGAN-IDS). The PSO optimizes the network weight of the GAN model to improve the backpropagation while generating the synthetic data (attack data) in the generator model using GRU. The discriminator model uses the PSO-optimized generator model to produce synthetic and real attack data to forecast the attack. Finally, a deep classification (IDS) model is trained using a GRU network with a GAN model-produced attack data and real data to classify whether the SDN traffic is malicious or normal. Moreover, the performance of this model is evaluated using the InSDN dataset and compared with existing DL model-based intrusion detection approaches and the results demonstrate a significantly higher accuracy rate of 98.4%, precision rate of 98%, recall rate of 98.5%, less detection time of 2.464 s, lesser Log loss rate of 1.0 and more metrics instilling confidence in the effectiveness of the proposed method.