Brain tumor classification is essential for clinical diagnosis and treatment planning. Deep learning models have shown great promise in this task, but they are often challenged by the complex and diverse nature of brain tumors. To address this challenge, we propose a novel deep residual and region-based convolutional neural network (CNN) architecture, called Res-BRNet, for brain tumor classification using magnetic resonance imaging (MRI) scans. Res-BRNet employs a systematic combination of regional and boundary-based operations within modified spatial and residual blocks. The spatial blocks extract homogeneity, heterogeneity, and boundary-related features of brain tumors, while the residual blocks significantly capture local and global texture variations. We evaluated the performance of Res-BRNet on a challenging dataset collected from Kaggle repositories, Br35H, and figshare, containing various tumor categories, including meningioma, glioma, pituitary, and healthy images. Res-BRNet outperformed standard CNN models, achieving excellent accuracy (98.22%), sensitivity (0.9811), F1-score (0.9841), and precision (0.9822). Our results suggest that Res-BRNet is a promising tool for brain tumor classification, with the potential to improve the accuracy and efficiency of clinical diagnosis and treatment planning.

Recommendation services become a critical and hot research topic for researchers. A recommendation agent that automatically suggests products to users according to their tastes or preferences instead of wandering in a huge corpus for a product. Social data such as Reviews play an important role in the recommendation of products. Improvement was achieved by neural network methods for capturing user and product information from a short text. However, such approaches do not fairly and efficiently incorporate users’ preferences and product characteristics. We are proposing the novel Hybrid Neural Collaborative Filtering (HNCF) model that combines deep learning capabilities and deep interaction modelling for recommender systems with a rating matrix. To overcome the cold start problem, we use the new overall rating by aggregating the multivariate rating MR (votes, likes, stars and sentiment scores of reviews) from different external data sources because different sites have different rating scores about the same product. The propose novel model consists of four major modules HUAPA-DCF+NSC+MR (Hierarchical User Attention and Hierarchical Product Attention, Deep Collaborative Filtering, Neural Sentiment Classifier, and multivariant rating) to solve the addressed problems. Initially, the HUAPA module is based on BiLSTM’s hierarchical user attention (HUA) and hierarchical product attention (HPA) to embed the user preferences and product characteristics respectively. Further, these are combined nonlinear representations and fed as input to the interaction module. Secondly, the deep collaborative filtering module is implemented to find the explicit interaction between user and product. Thirdly, NSC module will extract the user’s semantic about products by incorporating the user’s preferences and product characteristics. Finally, the module uses explicit information (multivariant rating) to the maximum extent for final classification. Experimental results demonstration that our novel model is outperforming than state-of-the-art at IMDb, Yelp2013 and Yelp2014 datasets for the true recommendation of top-n products using HNCF (HUAPA+DCF+NSC+MR) to increase the accuracy, confidence, and trust on recommendation services.

The advent of 6G networks and the rapid expansion of IoT ecosystems, particularly in energy hub (EH) networks, present significant challenges in ensuring secure and reliable communication. Among these, Distributed Denial-of-Service (DDoS) attacks pose a critical threat to the stability of IoT-enabled infrastructures. This study addresses these challenges by systematically evaluating a range of machine learning models and hybrid ensemble techniques tailored for DDoS detection in IoT-driven 6G EH networks. The performance of Random Forest (RF), Gradient Boosting (GB), Support Vector Machines (SVM), Decision Trees (DT), and K-Nearest Neighbors (KNN), as well as hybrid combinations like RF + KNN, GB + KNN, and GB + DT, was rigorously assessed across three benchmark datasets (CICDDOS2019, KDD-CUP, and UNSW-NB) with varying training data sizes (80% and 60%). Among these, RF + KNN emerged as the most effective, achieving the highest accuracy (99.44%) and F1-score (66.62%) on CICDDOS2019 while maintaining robust performance on UNSW-NB. GB + DT demonstrated superior precision (70.95%) on KDD-CUP, while GB + KNN achieved the highest recall (66.67%) on CICDDOS2019, highlighting its capability to minimize false negatives. The findings emphasize the influence of dataset characteristics and training sizes on model performance. CICDDOS2019 consistently produced the highest accuracy due to its well-defined class separability, while KDD-CUP exhibited greater variability and UNSW-NB provided stable yet moderate precision and recall. Smaller training data sizes generally led to performance degradation in F1-score and recall, although occasional accuracy improvements suggested potential overfitting with larger datasets. This research underscores the importance of tailoring hybrid ensemble models to the specific properties of datasets and attack types, offering a scalable, real-time framework for intrusion detection. By enhancing the security and resilience of IoT-driven 6G EH networks, this study provides practical solutions to mitigate the evolving threats posed by DDoS attacks.

Ensuring the best quality of smart multimedia services becomes an essential goal for modern enterprises so there is always a need for effective IP mobility smart management schemes in order to fulfill the following two main functions: (I) interconnecting the moving terminals around the extended indoor smart services. In addition, (II) providing session continuity for instant data transfer in real-time and multimedia applications with negligible latency, efficient bandwidth utilization, and improved reliability. In this context, it found out that the Generalized Multi-Protocol Label Switching (GMPLS) over LTE-A network that offers many advanced services for large numbers of users with higher bandwidths, better spectrum efficiency, and lower latency. In GMPLS, there is an elimination of the routing searches and choice of routing protocols on every core LTE-A router also it provides the architecture simplicity and increases the scalability. A comparative assessment of three types of IPv6 mobility management schemes over the LTE-A provided by using various types of multimedia. By using OPNET Simulator 17.5, In accordance with these schemes, it was proven that the IPv6-GMPLS scheme is the best choice for the system's operation, in comparison to the IPv6-MPLS and Mobile IPv6 for all multimedia offerings and on the overall network performance.