A hyperjerk system pertains to a dynamical system regulated by an ordinary differential equation of $n$ th order, where $n \geq 4$ . The main contribution of this work is the finding of a new autonomous hyperjerk system with a half line equilibrium. The mathematical framework of the proposed hyperjerk system contains eight terms with an absolute function nonlinearity. The essential dynamic characteristics of the model are explored, encompassing analysis of equilibrium points and their stability, depiction of the phase trajectories, illustration of bifurcation patterns, and visualization of Lyapunov exponent graphs. Our finding shows that the new 4D hyperjerk system exhibits special behavior like multistability, period doubling reversals and antimonotonocity. The proposed hyperjerk system has been implemented with an electronic circuit using MultiSim 14.0. Moreover, the FPGA implementation of the proposed hyperjerk system is performed by applying two numerical methods: Forward Euler and Trapezoidal. Experimental attractors are given from an oscilloscope by using the Zybo Z7-20 FPGA development board, which are in good agreement with the MATLAB and MultiSim 14.0 simulations. Finally, based on the chaotic dynamical behavior of the proposed chaotic hyperjerk system, a new image encryption approach is proposed. The experimental outcomes of the presented encryption algorithm prove its efficiency and security.

Manufacturing processes need optimization. Three-dimensional (3D) printing is not an exception. Consequently, 3D printing process parameters must be accurately calibrated to fabricate objects with desired properties irrespective of their field of application. One of the desired properties of a 3D printed object is its tensile strength. Without predictive models, optimizing the 3D printing process for achieving the desired tensile strength can be a tedious and expensive exercise. This study compares the effectiveness of the following five predictive models (i.e., machine learning algorithms) used to estimate the tensile strength of 3D printed objects: (1) linear regression, (2) random forest regression, (3) AdaBoost regression, (4) gradient boosting regression, and (5) XGBoost regression. First, all the machine learning models are tuned for optimal hyperparameters, which control the learning process of the algorithms. Then, the results from each machine learning model are compared using several statistical metrics such as 𝑅², mean squared error (MSE), mean absolute error (MAE), maximum error, and median error. The XGBoost regression model is the most effective among the tested algorithms. It is observed that the five tested algorithms can be ranked as XG boost > gradient boost > AdaBoost > random forest > linear regression.

Phishing is one of the biggest crimes in the world and involves the theft of the user’s sensitive data. Usually, phishing websites target individuals’ websites, organizations, sites for cloud storage, and government websites. Most users, while surfing the internet, are unaware of phishing attacks. Many existing phishing approaches have failed in providing a useful way to the issues facing e-mails attacks. Currently, hardware-based phishing approaches are used to face software attacks. Due to the rise in these kinds of problems, the proposed work focused on a three-stage phishing series attack for precisely detecting the problems in a content-based manner as a phishing attack mechanism. There were three input values—uniform resource locators and traffic and web content based on features of a phishing attack and non-attack of phishing website technique features. To implement the proposed phishing attack mechanism, a dataset is collected from recent phishing cases. It was found that real phishing cases give a higher accuracy on both zero-day phishing attacks and in phishing attack detection. Three different classifiers were used to determine classification accuracy in detecting phishing, resulting in a classification accuracy of 95.18%, 85.45%, and 78.89%, for NN, SVM, and RF, respectively. The results suggest that a machine learning approach is best for detecting phishing.

The rapid proliferation of smart devices in Internet of Things (IoT) networks has amplified the security challenges associated with device communications. To address these challenges in 5G-enabled IoT networks, this paper proposes a multi-level blockchain security architecture that simplifies implementation while bolstering network security. The architecture leverages an adaptive clustering approach based on Evolutionary Adaptive Swarm Intelligent Sparrow Search (EASISS) for efficient organization of heterogeneous IoT networks. Cluster heads (CH) are selected to manage local authentication and permissions, reducing overhead and latency by minimizing communication distances between CHs and IoT devices. To implement network changes such as node addition, relocation, and deletion, the Network Efficient Whale Optimization (NEWO) algorithm is employed. A localized private blockchain structure facilitates communication between CHs and base stations, providing an authentication mechanism that enhances security and trustworthiness. Simulation results demonstrate the effectiveness of the proposed clustering algorithm compared to existing methodologies. Overall, the lightweight blockchain approach presented in this study strikes a superior balance between network latency and throughput when compared to conventional global blockchain systems. Further analysis of system under test (SUT) behavior was accomplished by running many benchmark rounds at varying transaction sending speeds. Maximum, median, and lowest transaction delays and throughput were measured by generating 1000 transactions for each benchmark. Transactions per second (TPS) rates varied between 20 and 500. Maximum delay rose when throughput reached 100 TPS, while minimum latency maintained a value below 1 s.

Chronic kidney disease (CKD) is a gradual decline in renal function that can lead to kidney damage or failure. As the disease progresses, it becomes harder to diagnose. Using routine doctor consultation data to evaluate various stages of CKD could aid in early detection and prompt intervention. To this end, researchers propose a strategy for categorizing CKD using an optimization technique inspired by the learning process. Artificial intelligence has the potential to make many things in the world seem possible, even causing surprise with its capabilities. Some doctors are looking forward to advancements in technology that can scan a patient’s body and analyse their diseases. In this regard, advanced machine learning algorithms have been developed to detect the presence of kidney disease. This research presents a novel deep learning model, which combines a fuzzy deep neural network, for the recognition and prediction of kidney disease. The results show that the proposed model has an accuracy of 99.23%, which is better than existing methods. Furthermore, the accuracy of detecting chronic disease can be confirmed without doctor involvement as future work. Compared to existing information mining classifications, the proposed approach shows improved accuracy in classification, precision, F-measure, and sensitivity metrics.

One of the most complex areas of image processing is image classification, which is heavily relied upon in clinical care and educational activities. However, conventional models have reached their limits in effectiveness and require extensive time and effort to extract and choose classification variables. In addition, the large volume of medical image data being produced makes manual procedures ineffective and prone to errors. Deep learning has shown promise for many classification problems. In this study, a deep learning-based classification model is developed to decrease misclassifications and handle large amounts of data. The Adaptive Guided Bilateral Filter is used to filter images, and texture and edge attributes are gathered using the Spectral Gabor Wavelet Transform. The Black Widow Optimization method is used to choose the best features, which are then input into the Red Deer Optimization-enhanced Gated Deep Reinforcement Learning network model for classification. The brain tumor MRI dataset was used to test the model on the MATLAB platform, and the results showed an accuracy of 98.8%.