False Data Injection Attacks (FDIAs) present a significant threat to smart grids by manipulating measurement data, which may lead control centers to make incorrect operational decisions. Accurate and efficient detection of FDIAs is critical for ensuring reliable grid operation. Existing deep learning approaches often fail to capture both short-term local features and long-term dependencies in power grid data, and they typically show weak correlations with past and future time series information, reducing the trustworthiness of detection results. Similarly, conventional Intrusion Detection Systems (IDS) struggle to detect advanced FDIAs due to their reliance on predefined signatures and rule-based mechanisms. To overcome these limitations, we propose IG-APSO-DNN, a two-stage deep learning model for detecting FDIAs in smart grids. The first stage employs Information Gain (IG) and Adaptive Particle Swarm Optimization (APSO) for feature selection, reducing data dimensionality and improving model efficiency. The second stage uses a Deep Neural Network (DNN) to effectively capture both spatial and temporal patterns in smart grid measurements. The proposed model is evaluated on the Industrial Control System (ICS) Cyber Attack Power System Dataset, which simulates various FDIA scenarios. Results demonstrate that IG-APSO-DNN significantly outperforms traditional methods, improving key performance metrics including detection accuracy, precision, recall, and F-measure, while ensuring reliable operation of the smart grid. This study presents a robust anomaly-based IDS framework and highlights future directions, such as real-world validation, adaptive learning, exploration of novel optimization algorithms, and addressing scalability and real-time processing challenges.

this paper presents that mobile communication networks are essential for connecting with a significant portion of the world's population. Users' calls, SMS, and mobile data security are heavily reliant on how well Authenticated Key Exchange (AKE) protocols work. By streamlining two crucial procedures, authentication and key establishment, these protocols facilitate secure communication. While key setup creates secure cryptographic keys that guarantee the confidentiality and integrity of the data transmitted, authentication verifies the identities of the communicating parties. An authentication scheme based on Chebyshev chaotic maps, which have a dynamic and complex structure and are highly unpredictable due to their sensitivity to initial circumstances, is proposed in this article. This extra security measure increases the protocol's resistance to replay and man-in-the-middle attacks, among others. The Tamarin Prover, a strong formal verification tool for cryptographic protocols, is used to confirm the security of the proposed protocol. The improved 5G-AKA protocols' security features, such as secrecy authentication and resistance to known attack vectors, can be fully evaluated and replicated using Tamarin Prover. In 5G communications, our results show that using Chebyshev chaotic maps enhances the protocol and offers strong security against potential attacks.

Parallel power loads anomalies are processed by a fast-density peak clustering technique that capitalizes on the hybrid strengths of Canopy and K-means algorithms all within Apache Mahout’s distributed machine-learning environment. The study taps into Apache Hadoop’s robust tools for data storage and processing, including HDFS and MapReduce, to effectively manage and analyze big data challenges. The preprocessing phase utilizes Canopy clustering to expedite the initial partitioning of data points, which are subsequently refined by K-means to enhance clustering performance. Experimental results confirm that incorporating the Canopy as an initial step markedly reduces the computational effort to process the vast quantity of parallel power load abnormalities. The Canopy clustering approach, enabled by distributed machine learning through Apache Mahout, is utilized as a preprocessing step within the K-means clustering technique. The hybrid algorithm was implemented to minimise the length of time needed to address the massive scale of the detected parallel power load abnormalities. Data vectors are generated based on the time needed, sequential and parallel candidate feature data are obtained, and the data rate is combined. After classifying the time set using the canopy with the K-means algorithm and the vector representation weighted by factors, the clustering impact is assessed using purity, precision, recall, and F value. The results showed that using canopy as a preprocessing step cut the time it proceeds to deal with the significant number of power load abnormalities found in parallel using a fast density peak dataset and the time it proceeds for the k-means algorithm to run. Additionally, tests demonstrate that combining canopy and the K-means algorithm to analyze data performs consistently and dependably on the Hadoop platform and has a clustering result that offers a scalable and effective solution for power system monitoring.

In the Beyond-5G (B5G) and sixth generation (6G), several advanced techniques are based on high-frequency millimeter-wave wireless communications. This paper proposes the design of a novel B5G and 6G wireless radio access network (RAN) architecture. This architecture aims to be a key enabling factor for significantly increasing network capacity, promoting the deployment of new services, and integrating with the evolution of the previous cellular wireless access network architecture. Furthermore, the proposed architecture is adaptable to the various characteristics of high-frequency millimeter-wave communication. It leverages on the allocation of each layer resources of the different networks for more efficient deployment.

In autonomous driving, environment perception is an important step in understanding the driving scene. Objects in images captured through a vehicle camera can be detected and classified using semantic segmentation and depth estimation methods. Both these tasks are closely related to each other and this association helps in building a multi-task neural network where a single network is used to generate both views from a given monocular image. This approach gives the flexibility to include multiple related tasks in a single network. It helps reduce multiple independent networks and improve the performance of all related tasks. The main aim of our research presented in this paper is to build a multi-task deep learning network for simultaneous semantic segmentation and depth estimation from monocular images. Two decoder-focused U-N et-based multi-task networks that use a pre-trained Resnet-50 and DenseNet-121 which shared encoder and task-specific decoder networks with Attention Mechanisms are considered. We also employed multi-task optimization strategies such as equal weighting and dynamic weight averaging during the training of the models. The corresponding models' performance is evaluated using mean IoU for semantic segmentation and Root Mean Square Error for depth estimation. From our experiments, we found that the performance of these multi-task networks is on par with the corresponding single-task networks.

Early and accurate detection of brain tumors is very important to save the patient's life. Brain tumors are generally diagnosed manually by a radiologist by analyzing the patient”s brain MRI scans which is a time-consuming process. This led to our study of this research area for finding out a solution to automate the diagnosis to increase its speed and accuracy. In this study, we investigate the use of Residual Network deep learning architecture to diagnose and segment brain tumors. We proposed a two-step method involving a tumor detection stage, using ResNet50 architecture, and a tumor area segmentation stage using ResU-Net architecture. We adopt transfer learning on pre-trained models to help get the best performance out of the approach, as well as data augmentation to lessen the effect of data population imbalance and hyperparameter optimization to get the best set of training parameter values. Using a publicly available dataset as a testbed we show that our approach achieves 84.3 % performance outperforming the state-of-the-art using U-Net by 2% using the Dice Coefficient metric.

Automatic car damage detection and assessment are very useful in alleviating the burden of manual inspection associated with car insurance claims. This will help filter out any frivolous claims that can take up time and money to process. This problem falls into the image classification category and there has been significant progress in this field using deep learning. However, deep learning models require a large number of images for training and oftentimes this is hampered because of the lack of datasets of suitable images. This research investigates data augmentation techniques using Generative Adversarial Networks to increase the size and improve the class balance of a dataset used for training deep learning models for car damage detection and classification. We compare the performance of such an approach with one that uses a conventional data augmentation technique and with another that does not use any data augmentation. Our experiment shows that this approach has a significant improvement compared to another that does not use data augmentation and has a slight improvement compared to one that uses conventional data augmentation.