Nowadays, internet security is a critical concern; the One of the most difficult study issues in network security is "intrusion detection". Fight against external threats. Intrusion detection is a novel method of securing computers and data networks that are already in use. To boost the efficacy of intrusion detection systems, machine learning and deep learning are widely deployed. While work on intrusion detection systems is already underway, based on data mining and machine learning is effective, it requires to detect intrusions by training static batch classifiers regardless considering the time-varying features of a regular data stream. Real-world problems, on the other hand, rarely fit into models that have such constraints. Furthermor

The rapid development of Internet of Things (IoT) devices and their increasing numbers have caused a tremendous increase in network traffic and a wider range of cyber-attacks. This growing trend has complicated the detection process for traditional intrusion detection systems and heightened the challenges faced by these devices, such as imbalanced and large training data. This study presents a cohesive methodology of a series of intelligent techniques to prepare clean and balanced data for training the first (core) layer of a robust hierarchical intrusion detection system. The methodology was built by cleaning and compressing the data using an Autoencoder and preparing a strong latent space for balancing using a hybrid method that combines

The Internet of Things (IoT) has significantly transformed modern systems through extensive connectivity but has also concurrently introduced considerable cybersecurity risks. Traditional rule-based methods are becoming increasingly insufficient in the face of evolving cyber threats.  This study proposes an enhanced methodology utilizing a hybrid machine-learning framework for IoT cyber-attack detection. The framework integrates a Grey Wolf Optimizer (GWO) for optimal feature selection, a customized synthetic minority oversampling technique (SMOTE) for data balancing, and a systematic approach to hyperparameter tuning of ensemble algorithms: Random Forest (RF), XGBoost, and CatBoost. Evaluations on the RT-IoT2022 dataset demonstrat

In recent years, there has been expanding development in the vehicular part and the number of vehicles moving on the roads in all the sections of the country. Arabic vehicle number plate identification based on image processing is a dynamic area of this work; this technique is used for security purposes such as tracking of stolen cars and access control to restricted areas. The License Plate Recognition System (LPRS) exploits a digital camera to capture vehicle plate numbers is used as input to the proposed recognition system. Basically, the proposed system consists of three phases, vehicle license plate localization, character segmentation, and character recognition, the License Plate (LP) detection is presented using canny edge detection

Finding communities of connected individuals in complex networks is challenging, yet crucial for understanding different real-world societies and their interactions. Recently attention has turned to discover the dynamics of such communities. However, detecting accurate community structures that evolve over time adds additional challenges. Almost all the state-of-the-art algorithms are designed based on seemingly the same principle while treating the problem as a coupled optimization model to simultaneously identify community structures and their evolution over time. Unlike all these studies, the current work aims to individually consider this three measures, i.e. intra-community score, inter-community score, and evolution of community over

Modern machine-learning applications require GPUs, and modern platforms can leverage numerous GPUs on one or more machines to increase performance. Contemporary deep-learning models are too huge for CPU or GPU training. Training these models with many GPUs without performance degradation is necessary to train them rapidly and maximize GPU consumption. Thus, training deep convolutional neural networks (DCNN) with multiple GPUs has become necessary for improving training. Therefore, we presented a parallel design and development of an efficient model for enhancing face mask CNN performance and improving resource efficiency. This DCNN model is a parallel training system over multiple GPUs, a multi-core CPU, and a multi-process GPU platform wit

In order to scrutinize the impact of the decoration of Sc upon the sensing performance of an XN nanotube (X = Al or Ga, and XNNT) in detecting sarin (SN), the density functionals M06-2X, τ-HCTHhyb, and B3LYP were utilized. The interaction of the pristine XNNT with SN was a physical adsorption with the sensing response (SR) of approximately 5.4. Decoration of the Sc metal into the surface of the AlN and GaN led to an increase in the adsorption energy of SN from −3.4 to −18.9, and −3.8 to −20.1 kcal/mol, respectively. Also, there was a significant increase in the corresponding SR to 38.0 and 100.5, the sensitivity of metal decorated XNNT (metal@XNNT) is increased. So, we found that Sc-decorating more increases the sensitivity of GaNN