Explore the vast range of titles available.

For the purpose of usability feature extraction and prediction, an innovative metaheuristic algorithm is introduced. Generally, the term “usability” is defined by the several researchers with respect to the hierarchical-based software usability model and it has become one of the important methods in terms of software quality. In hierarchically based software, its usability factors, attributes, and its characteristics are combined. The paper presented an algorithm, i.e., modified crow search algorithm (MCSA) mainly for extraction of usability features from hierarchical model with the optimal solution under the search for useful features. MCSA is an extension of original crow search algorithm (CSA), which is a naturally inspired algorithm. The mechanism of this algorithm is based on the process of hiding food and prevents theft and hence introduced this CSA in the field of software engineering practices as an inspiration. The algorithm generates a particular number of selected features/attributes and is applied on software development life cycles models, finding out the best among them. The results of the presented algorithm are compared with the standard binary bat algorithm (BBA), original CSA, and modified whale optimization algorithm (MWOA). The outcomes conclude that the proposed MCSA performs well than the standard BBA and original CSA as the proposed algorithms generate fewer number of feature selection equal to 17 than 18 in BBA, 23 in CSA, and 19 in MWOA.

Healthcare organizations and Health Monitoring Systems generate large volumes of complex data, which offer the opportunity for innovative investigations in medical decision making. In this paper, we propose a beetle swarm optimization and adaptive neuro-fuzzy inference system (BSO-ANFIS) model for heart disease and multi-disease diagnosis. The main components of our analytics pipeline are the modified crow search algorithm, used for feature extraction, and an ANFIS classification model whose parameters are optimized by means of a BSO algorithm. The accuracy achieved in heart disease detection is 99.1 % with 99.37 % precision. In multi-disease classification, the accuracy achieved is 96.08 % with 98.63 % precision. The results from both tasks prove the comparative advantage of the proposed BSO-ANFIS algorithm over the competitor models.

Heating, ventilation and air-conditioning (HVAC) systems constitute the majority of the demands in modern power systems for aggregated buildings. However, HVAC integrated with renewable energy sources (RES) face notable issues, such as uneven demand–supply balance, frequency oscillation and significant drop in system inertia owing to sudden disturbances in nearby generation for a longer period. To overcome these challenges, load frequency control (LFC) is implemented to regulate the frequency, maintain zero steady-state error between the generation and demand, reduce frequency deviations and balance the active power flow with neighboring control areas at a specified value. In view of this, the present paper investigates LFC with a proposed centralized single control strategy for a micro-grid (µG) system consisting of RESs and critical load of a HVAC system. The proposed control strategy includes a newly developed cascaded two-degree-of-freedom (2-DOF) proportional integral (PI) and proportional derivative filter (PDF) controller optimized with a very recent meta-heuristic algorithm—a modified crow search algorithm (mCSA)—after experimenting with the number of performance indices (PICs). The superiority of both the proposed optimization algorithm and the proposed controller is arrived at after comparison with similar other algorithms and similar controllers, respectively. Compared to conventional control schemes, the proposed scheme significantly reduces the frequency deviations, improving by 27.22% from the initial value and reducing the performance index criteria (ƞISE) control error to 0.000057. Furthermore, the demand response (DR) is implemented by an energy storage device (ESD), which validates the suitability of the proposed control strategy for the µG system and helps overcome the challenges associated with variable RESs inputs and load demand. Additionally, the improved robustness of the proposed controller for this application is demonstrated through sensitivity analysis with ±20% μG coefficient variation.

Selective Laser Melting (SLM) is a prevalent technology in additive manufacturing, primarily due to its high design freedom and quality. However, ascertaining the optimal process window remains challenging due to the complex nonlinear relationships among process parameters and the significant resource cost associated with traditional experimental methods. This paper is devoted to addressing aforementioned challenges by integrating numerical simulation with swarm intelligence algorithms. Specifically, a novel swarm intelligence optimizer based on the original Crow Search Algorithm (CSA), named Modified Crow Search Algorithm (MCSA), is proposed in this research. In an effort to overcome the tendency of CSA to easily converge towards local optima, MCSA incorporates four main improvements. The nonlinear perturbation factor and the stochastically adjusted sine-cosine mechanism are employed to strengthen the capability in both local and global search. A random opposition-based learning strategy is utilized to escape local optima. Then, two adaptive parameters are adopted to balance the weights between search methods. The effectiveness of MCSA in search accuracy and convergence speed is rigorously evaluated through testing on twenty-three benchmark functions. Finally, numerical simulation is employed to capture dynamic melt pool behavior, enabling the establishment of keyhole and no-continuity models. The performance of MCSA is further investigated for the Ti6Al4V single-track formation optimization problem in SLM. Experimental results demonstrate that MCSA effectively identifies the optimal process window.

Armour steel is a type of steel that is often used in armoured vehicles, military equipment, and structural components that require a high level of resistance to penetration. Because of its high strength and hardness, cutting armour steel presents various obstacles. To overcome these challenges in armour steel cutting, innovative cutting methods, specialized equipment, and careful process planning are required. The current work discusses an experimental investigation that focuses on input process parameters of wire electrical discharge machining and on multi-objective optimization to obtain the best cutting rate (CR), surface roughness (SR), wire electrode temperature (TE) and material removal rate (MRR) for armour steel. The fractional factorial approach has been used in the investigation, with pulse off time (B), pulse on time (A), spark voltage (D), peak current (C), wire feed (E) as machining parameters and workpiece thickness (F) as a material parameter. The main and interaction impacts of the input parameters on the response parameters have been examined using the main effect plot, interaction plot, and ANOVA analysis, followed by the development of regression modeling. The research revealed that the pulse on time and workpiece thickness have the most significant contributions to CR and SR, with 55.25% and 21.77% contributions for CR and 67.87% and 8.72% contributions for SR, respectively. Toff and spark voltage are the major contributors for TE with 33.58% and 26.30% respectively and Ton is a major contributor with 70.04% for MRR. The ideal input parameters for CR [0.71 (mm/min)], SR [2.46 (microns)], TE [52 (°C)] and MRR [23.85 (mm 3 /min)] have been found to be A2B1C2D1E1F1, A1B2C2D2E1F2, A1B2C1D1E1F2 and A1B2C1D1E2F1 respectively. The modified crow search algorithm (MCSA) has been used in this study for single and multi-objective optimization, and their results contrast with other methods such as Rao-1 and Shuffled Frog Leaping Algorithm (SFLA). According to the conclusions of the present investigation, this study demonstrates that the MCSA technique exceeds the Rao-1 and SFLA techniques in terms of producing globally optimal outcomes for the specific problem under examination.

The proposed framework optimizes Explainable AI parameters, combining Predator crow search optimization to refine the predictive model’s performance. To prevent overfitting and enhance feature selection, an information acquisition-based technique is introduced, improving the model’s robustness and reliability. An enhanced U-Net model employing context-based partitioning is proposed for precise and automatic left ventricular segmentation, facilitating quantitative assessment. The methodology was validated using two datasets: the publicly available ACDC challenge dataset and the imATFIB dataset from internal clinical research, demonstrating significant improvements. The comparative analysis confirms the superiority of the proposed framework over existing cardiovascular disease prediction methods, achieving remarkable results of 99.72% accuracy, 96.47% precision, 98.6% recall, and 94.6% F1 measure. Additionally, qualitative analysis was performed to evaluate the interpretability and clinical relevance of the model’s predictions, ensuring that the outputs align with expert medical insights. This comprehensive approach not only advances the accuracy of CVD predictions but also provides a robust tool for medical professionals, potentially improving patient outcomes through early and precise diagnosis.

Phishing is an attack that deceit online users by means of masquerading as a genuine website to pilfer their classified or personal information. This is one among the recognized cybercrime. Disparate phishing website detection systems were recently developed for the purpose of detecting the phishing websites. However, they fail to attain the desired output and are suffered from countless drawbacks like lower accuracy and higher training time. For trouncing such drawbacks, this paper proposes an effectual Hybrid Deep Learning (HDL)-centric Phishing Detection System (PDS) using the MCS-DNN classifier. At first, pre-processing is done on the input dataset for ameliorating its quality. Subsequently, clustering and feature selection (FS) are performed to lessen the processing time and elevate the accuracy using CoK-means and CM-WOA, respectively. The features which are chosen during FS are fed into the MCS-DNN classifier, which classifies the legitimate websites and phishing websites. Lastly, the K -fold cross-validations (KCV) are employed for effectively predicting the proposed system’s accurateness. The outcomes highlight the robustness and predictive ability of the proposed PDS to distinguish the phishing as well as legitimate sites.