Explore the vast range of titles available.

Previous studies have shown that deep learning is very effective in detecting known attacks. However, when facing unknown attacks, models such as Deep Neural Networks (DNN) combined with Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN) combined with LSTM, and so on are built by simple stacking, which has the problems of feature loss, low efficiency, and low accuracy. Therefore, this paper proposes an autonomous detection model for Distributed Denial of Service attacks, Multi-Scale Convolutional Neural Network-Bidirectional Gated Recurrent Units-Single Headed Attention (MSCNN-BiGRU-SHA), which is based on a Multi-strategy Integrated Zebra Optimization Algorithm (MI-ZOA). The model undergoes training and testing with the CICDDoS2019 dataset, and its performance is evaluated on a new GINKS2023 dataset. The hyperparameters for Conv_filter and GRU_unit are optimized using the Multi-strategy Integrated Zebra Optimization Algorithm (MI-ZOA). The experimental results show that the test accuracy of the MSCNN-BiGRU-SHA model based on the MI-ZOA proposed in this paper is as high as 0.9971 in the CICDDoS2019 dataset. The evaluation accuracy of the new dataset GINKS2023 created in this paper is 0.9386. Compared to the MSCNN-BiGRU-SHA model based on the Zebra Optimization Algorithm (ZOA), the detection accuracy on the GINKS2023 dataset has improved by 5.81%, precision has increased by 1.35%, the recall has improved by 9%, and the F1 score has increased by 5.55%. Compared to the MSCNN-BiGRU-SHA models developed using Grid Search, Random Search, and Bayesian Optimization, the MSCNN-BiGRU-SHA model optimized with the MI-ZOA exhibits better performance in terms of accuracy, precision, recall, and F1 score.

The Internet of Things (IoT) permeates various sectors, including healthcare, smart cities, and agriculture, alongside critical infrastructure management. However, its susceptibility to malware due to limited processing power and security protocols poses significant challenges. Traditional antimalware solutions fall short in combating evolving threats. To address this, the research work developed a feature selection-based classification model. At first stage, a preprocessing stage enhances dataset quality through data smoothing and consistency improvement. Feature selection via the Zebra Optimization Algorithm (ZOA) reduces dimensionality, while a classification phase integrates the Graph Attention Network (GAN), specifically the Dual-channel GAN (DGAN). DGAN incorporates Node Attention Networks and Semantic Attention Networks to capture intricate IoT device interactions and detect anomalous behaviors like botnet activity. The model's accuracy is further boosted by leveraging both structural and semantic data with the Sooty Tern Optimization Algorithm (STOA) for hyperparameter tuning. The proposed STOA-DGAN model achieves an impressive 99.87% accuracy in botnet activity classification, showcasing robustness and reliability compared to existing approaches.

This study introduces a novel approach for analyzing photovoltaic (PV) systems that employ block lookup tables for speedy and efficient simulation. It introduces an innovative method for tracking the Global Maximum Power Point (GMPP) by utilizing Zebra Optimization Algorithm (ZOA). The suggested method was carefully evaluated under difficult Partial Shading Conditions (PSCs) and Dynamic Shading Conditions (DSCs) to determine its global and local search capability. ZOA’s performance was examined in four scenarios and compared to four existing MPPT algorithms: Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), Flower Pollination Algorithm (FPA), and Whale Optimization Algorithm (WOA). ZOA surpassed its competitors with an average tracking time of 0.875 s and a tracking efficiency of 99.95% in PSCs. In comparison, ZOA increased tracking efficiency by up to 2%, increased resilience under varied circumstances, and produced a faster convergence speed—approaching the maximum Power Point 10–15% faster than the other algorithms. Furthermore, ZOA significantly decreased operating point variations. The algorithm’s overall performance was tested using an experimental setup with a DSPACE board and a PV emulator. These findings demonstrate that ZOA is a highly efficient and dependable MPPT solution for PV systems, especially in severe PSCs.

The output of photovoltaic (PV) power generation systems remains uncertain primarily due to the uncontrollable nature of weather conditions, which may introduce disturbances to the power grid upon integrating PV systems. Accurate short-term PV power forecasting is an essential approach for ensuring the stability of the power system. The paper proposes a short-term PV power forecasting model based on improved zebra optimization algorithm (IZOA)-stochastic configuration network (SCN). First, the historical PV data are divided into three weather patterns, effectively reducing the uncertainty of PV power. Second, a prediction model based on SCN is developed. To enhance the forecasting model’s accuracy even further, the IZOA is introduced to optimize the key parameters of the SCN. Finally, IZOA-SCN is employed for short-term PV power through various weather patterns. Experiment results show that the proposed method significantly improves the prediction accuracy in contrast to other comparison models.

In the context of global economic integration, corporate bankruptcy risk poses a significant threat to economic stability, making accurate bankruptcy prediction critically important. As a binary classification problem, traditional statistical approaches struggle to handle nonlinear features, resulting in limited predictive accuracy. While machine learning-based intelligent models have improved prediction performance, the effectiveness of Kernel Extreme Learning Machine (KELM) heavily depends on the selection of the penalty parameter (C) and kernel parameter (γ). However, conventional optimization methods often suffer from low efficiency and a tendency to fall into local optima. The Zebra Optimization Algorithm (ZOA), a newly developed swarm intelligence algorithm, also faces limitations such as rapid loss of population diversity and weak local exploitation capabilities. To address these issues, this paper proposes an Enhanced Archive-based Zebra Optimization Algorithm (EAZOA). By incorporating a Levy mutation strategy guided by elite individuals, a dynamic elite archive mechanism, and a hybrid boundary handling technique, the proposed algorithm significantly improves optimization performance. EAZOA is then employed to optimize the parameters of KELM, resulting in the EAZOA-KELM bankruptcy prediction model. Experimental results on the CEC2020 and CEC2022 benchmark suites demonstrate that EAZOA outperforms several state-of-the-art algorithms in terms of convergence accuracy, stability, and scalability. Moreover, experiments on the Wieslaw financial dataset show that EAZOA-KELM achieves superior performance across multiple evaluation metrics, including accuracy, precision, recall, and F1-score. These results validate the model’s effectiveness in corporate bankruptcy prediction and highlight its potential as a powerful tool for financial risk early warning.

Renewable energy systems are becoming more and more popular and used these days as a result of environmental, technical, and economic concerns. The reliable and optimal economic size of the system is the primary issue with the renewable energy-based power supply system for rural electrification. A new Zebra optimization algorithm (ZOA) is used for the optimal design and to perform the techno-economic performance analysis of the renewable energy-based off-grid power supply system with the stochastic load profile of Ethiopian rural communities. The components of the power supply system are modeled, the objective function is formulated, and optimization and techno-economic analysis are performed to get the minimum total annual cost of the hybrid system with the consideration of loss of power supply probability (LPSP), stochastic load profile and solar module optimal tilt angle. Three off-grid power supply systems, such as PV-BAT, PV-WT-BAT, and WT-BAT, are proposed to evaluate the optimal configuration for the study site at various LPSP. The study’s findings showed that the photovoltaic-battery (PV-BAT) system, with an optimal size of 3483.161 kW of PV, 3668 units of storage batteries (11,444.160 kWh), and 2082 kW of converter at 0.044030% LPSP, is the best configuration for electrifying the rural communities of the study site with the minimum annual total cost of 621,736.056 USD and 0.227063 $/kWh COE. It results in a 3.3% annual total cost reduction and a 1.3% unmet load (kWh/year) improvement as compared to the PV-WT-BAT system. The performance of the proposed ZOA in obtaining the optimal size of the renewable energy-based power supply system for rural communities is evaluated by comparing it with the previous studies, gray wolf optimization (GWO) and HOMER Pro software, and it was found that the proposed algorithm is best at finding the optimal size of the power supply system at the minimum annual cost. The standard deviation for ZOA and GWO, respectively, in determining the optimal configuration value for 25 runs is 14.295 and 36.360 for the PV-BAT configuration, indicating that ZOA is more reliable than GWO in determining the optimal size. Furthermore, ZOA yields a 16.76% reduction in the total net present cost when compared to the HOMER software results.

This study is an attempt to improve the recently introduced American Zebra Optimization Algorithm (AZOA), which is inspired by the leadership dynamics and scavenging behaviour of American zebras in nature. Although AZOA demonstrates strong exploration capability, it suffers from certain limitations, such as weak exploitation ability and a tendency to become trapped in local optima when dealing with complex optimization problems. To alleviate these challenges, a novel strategy called Enhanced Opposition-Based Learning (EOBL) is suggested and integrated with the AZOA framework. The EOBL mechanism extends the traditional opposition-based learning by incorporating a degree of controlled randomness, aiming to achieve a better balance between exploration and exploitation during the search process. Consequently, an improved algorithm termed the Enhanced Opposition-Based American Zebra Optimization Algorithm (EOBAZOA) is proposed to enhance the performance of the standard AZOA. The effectiveness of EOBAZOA has been validated through extensive experimentation on both classical benchmark functions from CEC2005 and recent test suites from CEC2022, in addition to a set of real-world engineering design problems. Furthermore, rigorous statistical analysis, such as the t-test has been conducted to assess the robustness and reliability of the results. The experimental findings confirm that the proposed EOBAZOA approach achieves superior performance than other cutting-edge optimization algorithms in both benchmark and real-world engineering problem scenarios.

Addressing the challenges of energy imbalance and the difficulty in optimizing cluster head selection in clustering protocols for wireless sensor networks (WSNs), this paper proposes a clustering protocol based on an improved zebra optimization algorithm (IZOACP). The method systematically solves the NP-hard problem of cluster head selection by integrating the zebra optimization algorithm (ZOA), Gaussian mutation strategy, and opposition-based learning mechanism, while optimizing the clustering process based on four key metrics: node residual energy, network density, intra-cluster distance, and communication delay. To further enhance data transmission efficiency, a dynamic adaptive inter-cluster routing mechanism is designed, which achieves path dynamic balancing based on node distance, residual energy, and load status. Experimental results demonstrate that, compared to the LEACH, DMaOWOA, and ARSH-FATI-CHS protocols, IZOACP significantly outperforms the comparison schemes in key metrics such as network lifespan (improved by 97.56%), throughput (improved by 93.88%), and transmission delay (reduced by 10.12%). These results validate its superiority in energy consumption control, topology stability, and large-scale monitoring scenarios, providing an efficient and reliable clustering optimization framework for WSN information monitoring systems.

The rapid growth of integrating electrical vehicles (EVs) into the distribution network has introduced complexities and power flow inefficiencies. To address these challenges, optimal renewable energy resources (RERs) integration along with applied demand-side management (DSM) contribute to managing load profiles and generation thus reducing costs. This should be smartly attained through selecting efficient optimization techniques to improve power quality, voltage profile, and reliability. This paper aims to investigate the effect of integrating EVs and applying peak load shifting (PLS) as a DSM strategy with the optimal allocation of distributed energy resources, specifically wind and photovoltaic (PV) systems, as distributed generators (DGs) on distribution networks. Taking into consideration the stochastic behavior of RERs, EVs demand elasticity of charging and discharging scenarios and load variance. The main objective of this work focuses on power loss reduction and implementing PLS to flatten the load profile and form a new loadability to reduce costs. The study is demonstrated on a typical IEEE 69-bus system, considering the load, EVs, and RERs profiles during weekdays in winter and summer seasons. The study examines the optimal size and location of combining two DGs (wind and PV), in addition to incorporating bidirectional plug-in hybrid electric vehicles into the system. The study utilizes the Zebra optimization algorithm (ZOA), in comparison with the Whale optimization algorithm (WOA), Grey wolf optimization algorithm (GWO), and Genetic algorithm (GA). The latter is employed only as a reference for comparison. For each season, the simulation is divided into two parts, each part consists of four cases. Part (1) is simulated assuming constant power integration for the RERs while part (2) considers their stochastic behavior. Also, optimal charging strategies for EVs are examined for cost-effectiveness during high penetration levels for the IEEE 123-bus system. The results demonstrated the effectiveness of the proposed algorithm in reducing power loss. Moreover, shifting peak hours flattens the load profile, thereby reducing costs and power loss across the distribution network. Furthermore, the performance of the ZOA dominates the WOA, GWO, and GA.

With the increasing popularity of Android smartphones, malware targeting the Android platform is showing explosive growth. Currently, mainstream detection methods use static analysis methods to extract features of the software and apply machine learning algorithms for detection. However, static analysis methods can be less effective when faced with Android malware that employs sophisticated obfuscation techniques such as altering code structure. In order to effectively detect Android malware and improve the detection accuracy, this paper proposes a dynamic detection model for Android malware based on the combination of an Improved Zebra Optimization Algorithm (IZOA) and Light Gradient Boosting Machine (LightGBM) model, called IZOA-LightGBM. By introducing elite opposition-based learning and firefly perturbation strategies, IZOA enhances the convergence speed and search capability of the traditional zebra optimization algorithm. Then, the IZOA is employed to optimize the LightGBM model hyperparameters for the dynamic detection of Android malware multi-classification. The results from experiments indicate that the overall accuracy of the proposed IZOA-LightGBM model on the CICMalDroid-2020, CCCS-CIC-AndMal-2020, and CIC-AAGM-2017 datasets is 99.75%, 98.86%, and 97.95%, respectively, which are higher than the other comparative models.