Comprehensive Model Research Articles

Enhancing control in spatial atomic layer deposition: insights into precursor diffusion, geometric parameters, and CVD mitigation strategies

In recent years, spatial atomic layer deposition (SALD) has gained significant attention for its remarkable capability to accelerate ALD growth by several orders of magnitude compared to conventional ALD, all while operating at atmospheric pressure. Nevertheless, the persistent challenge of inadvertent contributions from chemical vapor deposition (CVD) in SALD processes continues to impede control over film homogeneity, and properties. This research underscores the often-overlooked influence of diffusion coefficients and important geometric parameters on the close-proximity SALD growth patterns. We introduce comprehensive physical models complemented by finite element method simulations for fluid dynamics to elucidate SALD growth kinetics across diverse scenarios. Our experimental findings, in alignment with theoretical models, reveal distinctive growth rate trends in ZnO and SnO2 films as a function of the deposition gap. These trends are ascribed to precursor diffusion effects within the SALD system. Notably, a reduced deposition gap proves advantageous for both diffusive and low-volatility bulky precursors, minimizing CVD contributions while enhancing precursor chemisorption kinetics. However, in cases involving highly diffusive precursors, a deposition gap of less than 100 μm becomes imperative, posing technical challenges for large-scale applications. This can be ameliorated by strategically adjusting the separation distance between reactive gas outlets to mitigate CVD contributions, which in turn leads to a longer deposition time. Furthermore, we discuss the consequential impact on material properties and propose a strategy to optimize the injection head to control the ALD/CVD growth mode.

Cross-jurisdictional disaster preparedness: A Nigeria-USA data-analytical approach

Disasters pose significant challenges globally, demanding effective preparedness strategies to mitigate their impact. This study proposes a novel approach to disaster preparedness through cross-jurisdictional collaboration between Nigeria and the United States, leveraging data analytics for enhanced readiness. Nigeria, with its vulnerability to various disasters, and the United States, known for its advanced disaster management systems, offer a unique opportunity for mutual learning and collaboration. This research aims to bridge the gap in disaster preparedness between these two countries by employing a data-driven analytical framework. Through the collection, analysis, and comparison of disaster-related data from both nations, this approach seeks to identify commonalities, differences, and best practices in disaster preparedness strategies. By leveraging the strengths of both countries, such as Nigeria's community resilience and the USA's technological advancements, this approach aims to develop comprehensive disaster preparedness models tailored to the specific needs and contexts of each jurisdiction. Key components of this approach include data collection from various sources, including historical disaster records, socio-economic indicators, infrastructure data, and community resilience metrics. Advanced analytical techniques, such as machine learning algorithms and spatial analysis, will be employed to identify patterns, assess vulnerabilities, and predict potential disaster scenarios. The findings will inform the development of targeted preparedness strategies, including early warning systems, evacuation plans, resource allocation, and capacity building initiatives. Furthermore, this research emphasizes the importance of multi-stakeholder collaboration and knowledge exchange in disaster preparedness. By involving government agencies, non-governmental organizations, academic institutions, and local communities from both Nigeria and the USA, this approach aims to foster a holistic and inclusive preparedness framework. Ultimately, this study seeks to contribute to the global discourse on disaster risk reduction by demonstrating the effectiveness of cross-jurisdictional collaboration and data-driven approaches in enhancing disaster preparedness. By leveraging the strengths and experiences of Nigeria and the USA, this research aims to develop scalable and adaptable models that can be applied in diverse contexts to build resilience and mitigate the impact of disasters.

Submolecular-scale control of phototautomerization.

Optically activated reactions initiate biological processes such as photosynthesis or vision, but can also control polymerization, catalysis or energy conversion. Methods relying on the manipulation of light at macroscopic and mesoscopic scales are used to control on-surface photochemistry, but do not offer atomic-scale control. Here we take advantage of the confinement of the electromagnetic field at the apex of a scanning tunnelling microscope tip to drive the phototautomerization of a free-base phthalocyanine with submolecular precision. We can control the reaction rate and the relative tautomer population through a change in the laser excitation wavelength or through the tip position. Atomically resolved tip-enhanced photoluminescence spectroscopy and hyperspectral mapping unravel an excited-state mediated process, which is quantitatively supported by a comprehensive theoretical model combining ab initio calculations with a parametric open-quantum-system approach. Our experimental strategy may allow insights in other photochemical reactions and proof useful to control complex on-surface reactions.

Electrically tunable plasmonic metasurface as a matrix of nanoantennas

Abstract We report the fabrication and characterization of a plasmonic metasurface comprising electrically-contacted sub-wavelength gold dipole nanoantennas, conformally coated by a thin hafnia film, an indium tin oxide layer and a backside mirror, forming metal–oxide–semiconductor (MOS) capacitors, for use as an electrically-tunable reflectarray or metasurface. By voltage biasing the nanoantennas through metallic connectors and leveraging the carrier refraction effect in the MOS capacitors, our measurements demonstrate phase control in reflection over a range of about 30°, with a constant magnitude of reflection coefficient of 0.5, and the absence of secondary lobes. Comprehensive electromagnetic and quantum carrier models of the structure are developed and are in excellent agreement with the measurements. The metasurface holds promise for use as an optical phased array.

Optimizing irrigation schedules of greenhouse tomato based on a comprehensive evaluation model

In the context of climate change, water availability has emerged as a pressing concern in agriculture, indicating the urgency to enhance irrigation management. Nevertheless, accurately quantifying irrigation schedules in diverse climates and soil textures remains a complex challenge. Here, a three-year irrigation experiment (2020–2022) of greenhouse tomato was conducted at three typical locations (Yulin, Yangling and Hanzhong) in northwest China. The irrigation schedules were determined by the cumulative evaporation (CE) measured from a 20 cm pan. A total nine treatments were set by combining three irrigation frequencies (IF) with three single doses (ID). Twenty indices related to tomato growth, photosynthesis, yield and water use, fruit quality, and environmental benefit were evaluated comprehensively by using TOPSIS (technique for order preference by similarity to ideal solution) and GRA (grey relational analysis) methods of combining weights based on game theory. The results showed that the indicator with highest weight was yield, followed by crop water productivity and vitamin C. The optimal ranges of irrigation frequency (irrigation dose) were determined as follows: 10.00–11.08 mm (0.81–0.90 CE) in Yulin, 13.12–15.68 mm (0.77–0.89 CE) in Yangling, and 11.44–16.40 mm (0.67–0.77 CE) in Hanzhong, respectively. This study introduces a method applied to prioritize the key indicators for irrigation scheduling, providing a reference for optimizing irrigation practices in greenhouse tomato production and improving water management in agriculture.

Multi-index comprehensive evaluation model for assessing risk to trainees in an emergency rescue training base for building collapse

Rescues from building collapse accidents present a significant challenge for China’s emergency rescue system. However, there are also many risk factors in a training scenario, which have been summarized in this study. A hierarchical indicator system for personnel safety was established, including 12 first-level indicators and 23s-level indicators. Then, an improved Grey-DEMATEL-ISM-MICMAC evaluation model was constructed to evaluate the level of risk. Influencing factor scores were determined according to the responses from the questionnaire survey. The influencing degree, influenced degree, centrality, and causality were identified, and the importance, relevance, and clustering of the various factors were obtained after making quantitative calculations. The results showed that the order of priority for solving the essential issues was safety education (A2), operating standards and proficiency (A10), equipment inspection (A4), equipment warehousing maintenance and records (A21). The solving of safety education was identified to be the most essential priority. The priority control order of direct causes was Scientific design and construction (A5), Potential fixed hazards in the facility (A12), Physical fitness of personnel (A1), Weather influences (A18), and Initiation efficiency of emergency plans (A20), and direct control measures for these five factors could achieve a relatively significant effect.

Geographic information system-based multi-criteria decision-making analysis for investment assessment of wind-photovoltaic-shared energy storage power stations: a case study of Shanxi Province.

As the center of the development of power industry, wind-photovoltaic (PV)-shared energy storage project is the key tool for achieving energy transformation. This research seeks to construct a feasible model for investment appraisal of wind-PV-shared energy storage power stations by combining geographic information system (GIS) and multi-criteria decision-making (MCDM) method. Firstly, a comprehensive criteria system is established from the perspectives of orography, economy, resources, climate, and society, and the evaluation data is described using probabilistic linguistic term sets (PLTSs). Then, to avoid the weight deviation produced by the single weighting approach, a comprehensive weighting model including the best-worst method (BWM) and entropy weight method is provided to calculate the weights of criteria. Next, expert weights are calculated based on trust analysis. Finally, alternatives are ranked by the improved gained and lost dominance score (GLDS) method. To verify the validity of the model, an empirical investigation is carried out in Shanxi Province. The results show that the economy is the primary factor influencing the investment decision. Among all the projects approved by the government, alternative F4 located in Yanzhuang Town, Yuanping City is the best investment object. Furthermore, to illustrate the stability of the result, triple sensitivity analysis and comparative analysis are conducted in Shanxi Province. This study expands the application scope of GIS and MCDM method by first providing support for government and investors to identify optimal investment targets.

Evaluating ICT Competencies of Higher Education Faculty:A Comprehensive Quantitative Model after the Pandemic

This study aimed to enhance the Information and Communication Technology (ICT) skills of faculty members in a higher education institution. The faculty’s limited proficiency in ICT impeded the integration of technology instruments across different topics. A training program was devised, executed, and assessed to tackle these problems within six months. Online courses were developed for participants under the training’s criteria. Quantitative data collection involved administering a pre-test and post-test, which were subsequently analyzed using descriptive statistics. The assessed competencies encompassed the utilization of computers in instructional activities and the development and implementation of educational initiatives. The findings indicated that 75% of the faculty did not typically include technology in their instructional methods, whereas 41% recognized the potential of technology to enhance and innovate teaching practices. Only 66.67% of the participants possessed knowledge of fundamental components of computers, while the same percentage was aware of basic peripherals. Additionally, 58.33% of the participants demonstrated proficiency in installing computer programs. The program sought to enhance the educational quality and showed positive modifications in formulating strategies for integrating ICTs into the curriculum. The results showcased the efficacy of the training program in improving teaching skills in the field of information and communication technologies (ICTs), enhancing the teaching methods of faculty members, and providing the opportunity to deliver courses either fully online or in a blended format.

Model Multi Objektif untuk Pemilihan Supplier Industri CPO pada Jaringan Rantai Pasokan Ramah Lingkungan dengan Ketidakpastian Pasokan

This study proposes a mathematical model for the problem of selecting suppliers for the palm oil industry by considering the green factor. Stochastic parameters are also considered to deal with uncertain parameters in green supply chain networks. The objective of this model is to select suppliers considering the total costs and total greenhouse gas emissions. This paper aims to present a more comprehensive model based on real-world conditions for the supplier selection problem of green supply chain in the palm oil industries under uncertainty. Besides economic issues, environmental issues are also considered from several aspects such as selecting environmentally friendly suppliers and purchasing from them and considering the environmental impact of the finished product. The results show that increasing one of the indicators such as the number of products and market demand leads to an increase in the value of the total objective function, which is caused by an increase in problem size. On the other hand, the cost function increases when most supplier selection is environmentally friendly suppliers. Meanwhile, the function of the objective level of greenhouse gas emissions increases when the selection of suppliers is most suppliers with high greenhouse gas emissions, but the objective function of costs decreases

Analysis of the Effect of the Comprehensive Nursing Model on Patients with Moyamoya Disease Undergoing Intracranial and Extracranial Revascularization Surgery

Objective: To explore the effect of a comprehensive nursing model on patients with Moyamoya disease who underwent intracranial and extracranial revascularization surgery. Methods: 110 cases were divided into control and observation groups with 55 cases each. The control group received routine perioperative care, and the observation group received perioperative care along with comprehensive nursing care. The two groups’ disease cognition levels, anxiety, symptoms, daily living ability scores, and postoperative complication rates were compared. Results: The anxiety score and total postoperative complications of the observation group upon discharge were lower than that of the control group, and the disease cognition level and daily living ability upon discharge were higher than that of the control group (P < 0.05). Conclusion: Applying the comprehensive nursing model in conjunction with perioperative care for patients undergoing surgery can effectively improve their anxiety, strengthen activities of daily living, and reduce the risk of postoperative complications.

A comprehensive multiphysics approach to model solutal buoyancy, thermal convection, and electro-vortex flow phenomena for liquid metal batteries

To alleviate the effects of pollution and global warming, the transition to renewable energy sources is taking place at an accelerating rate. The intermittent nature of renewable energy production can be addressed by an energy storage solution that is low-cost, efficient, and based on earth-abundant materials, and a liquid metal battery (LMB) is coming up as one such solution. Liquid metal battery (LMB) performance, especially its discharge voltage, depends on the concentration profile of cathode which in turn is influenced by fluid flow. In this study, we examine three significant phenomena that impact fluid behavior: solutal buoyancy, internally heated convection, and electro-vortex flow (EVF). Though several attempts have been made to model these processes individually or in a combination of two, a model that simulates all three aspects for resultant fluid flow has not been reported. Therefore, this study develops a comprehensive multiphysics model to simulate the positive electrode that is validated with experimental results for Li||Bi cell operating at 450 °C by coupling all of the aforementioned phenomena. While charging with a current density of 1 A/cm2, our model predicts an average velocity of ∼6 mm/s in the cathode solely due to solutal buoyancy. In the case of discharging, both solutal and internal thermal effects lead to an increase in overpotential to as high as ∼200 mV. Moreover, during discharging, the EVF induced a poloidal fluid flow with a maximum velocity of ∼3–5.5 mm/s at 1 A/cm2, reducing mass transport overpotential by ∼10 mV, but it could not disrupt the lighter intermetallic stratification layer on top of the cathode. Additionally, we investigated the charging overpotential phenomenon due to unstable stratification. This all-inclusive model leveraging solutal, thermal, and EVF effects not only offers insights into the fluid motion, concentration gradient, and voltage profile for a lab-scale LMB but can accurately simulate te conditions prevalent in commercial large LMBs, thereby catalysing the path to commercialization of LMBs.

Comprehensive evaluation of intrinsic safety of railway facilities and equipment based on improved cloud model-fuzzy Petri net

In order to achieve the goal of transforming China into a modernized railway powerhouse, a comprehensive evaluation model of intrinsic safety is constructed in this paper by focussing on the intrinsic safety of railway facilities and equipment. Firstly, the index system for evaluating the intrinsic safety of railway facilities and equipment is divided. Secondly, the fuzzy Petri net (FPN) model for intrinsic safety evaluation is constructed according to the fuzzy generative rules, and the similarity calculation method of the cloud model based on shape and distance is applied to derive the initial state value of the FPN model and carry out the calculation of fuzzy reasoning of the intrinsic safety. Finally, the comprehensive evaluation of intrinsic safety is carried out using the example of railroad facilities and equipment at one China Railway Group bureau’s station section. The results indicate that the intrinsic safety level of the station section falls into Class IV intrinsic safety, exhibiting a few vulnerabilities. However, the risk level is low, aligning with the findings of the actual research. Moreover, the evaluation results based on the FPN, the cloud model’s similarity calculation method and the suggested method are compared and analysed with the findings of the actual research. The comparative results demonstrate the accuracy and scientificity of the proposed method, providing a reference for enhancing the intrinsic safety of railway facilities and equipment.

A Multiple Criteria Decision-Making Method Generated by the Space Colonization Algorithm for Automated Pruning Strategies of Trees

The rise of mechanical automation in orchards has sparked research interest in developing robots capable of autonomous tree pruning operations. To achieve accurate pruning outcomes, these robots require robust perception systems that can reconstruct three-dimensional tree characteristics and execute appropriate pruning strategies. Three-dimensional modeling plays a crucial role in enabling accurate pruning outcomes. This paper introduces a specialized tree modeling approach using the space colonization algorithm (SCA) tailored for pruning. The proposed method extends SCA to operate in three-dimensional space, generating comprehensive cherry tree models. The resulting models are exported as normalized point cloud data, serving as the input dataset. Multiple criteria decision analysis is utilized to guide pruning decisions, incorporating various factors such as tree species, tree life cycle stages, and pruning strategies during real-world implementation. The pruning task is transformed into a point cloud neural network segmentation task, identifying the trunks and branches to be pruned. This approach reduces the data acquisition time and labor costs during development. Meanwhile, pruning training in a virtual environment is an application of digital twin technology, which makes it possible to combine the meta-universe with the automated pruning of fruit trees. Experimental results demonstrate superior performance compared to other pruning systems. The overall accuracy is 85%, with mean accuracy and mean Intersection over Union (IoU) values of 0.83 and 0.75. Trunks and branches are successfully segmented with class accuracies of 0.89 and 0.81, respectively, and Intersection over Union (IoU) metrics of 0.79 and 0.72. Compared to using the open-source synthetic tree dataset, this dataset yields 80% of the overall accuracy under the same conditions, which is an improvement of 6%.

Managing the Energy-Saving of College Students

Gaining a comprehensive understanding of the energy-saving behaviors (ESB) of college students, who represent the backbone of the future society, is imperative for advancing energy conservation initiatives. This paper employs a PLS-SEM model with 2786 valid responses to investigate the determinants of college students' ESB within the comprehensive action determination model (CADM). The results show that (1) the applicability of CADM, including the theory of planned behavior, norm activation model, and ipsative theory of behavior, was confirmed in the context of college students' ESB. (2) The cultivation of energy-saving habits significantly contributes to the promotion of ESB. (3) The availability of energy-saving access has a positive impact on ESB. (4) Media's energy-saving promotional activities positively influence the energy-saving intention. (5) Energy-saving policy incentives exert a positive moderating influence on the transition from energy-saving intentions to ESB. Based on these empirical findings, this paper provides specific and target policy recommendations.

A Comprehensive Evaluation of Shale Oil Reservoir Quality

To enhance the accuracy of the comprehensive evaluation of reservoir quality in shale oil fractured horizontal wells, the Pearson correlation analysis method was employed to study the correlations between geological parameters and their relationship with production. Through principal component analysis, the original factors were linearly combined into principal components with clear and specific physical meanings, aiming to eliminate correlations among factors. Furthermore, Gaussian membership functions were applied to delineate fuzzy levels, and the entropy weight method was used to determine the weights of principal components, establishing a fuzzy comprehensive evaluation model for reservoir quality. Without using principal component analysis, the correlation coefficient between production and evaluation results for the 40 wells in the Cangdong shale oil field was only 0.7609. However, after applying principal component analysis, the correlation coefficient increased to 0.9132. Field application demonstrated that the average prediction accuracy for the cumulative oil production per kilometer of fractured length over 12 months for the 10 applied wells was 91.8%. The proposed comprehensive evaluation method for reservoir quality can guide the assessment of reservoir quality in shale oil horizontal wells.

COBRAs and virality: viral campaign values on consumer behaviour

In the digital marketing era, a viral brand campaign is a potent marketing tool for a brand, enabling it to derive multiple benefits through rapid and widespread information diffusion. Despite the important role of brand viral campaigns, existing studies have minimally explored the effect of viral campaign values on consumer behaviours, especially on a set of consumers’ online brand-related activities (COBRAs). Therefore, this study bridges this gap by proposing a detailed framework to measure the impact of viral campaigns on COBRAs through the aspects of medium, content, and interaction. To investigate this phenomenon, a survey was conducted with 409 respondents from the US, employing partial least-squares structural equation modelling (PLS-SEM). The findings reveal that six values of brand viral campaigns, including ease of browsing, hedonic value, functional value, aesthetic value, social interaction, and self-identity, significantly motivate consumers to actively engage in COBRAs. By examining COBRAs’ motivations in the viral brand campaign context, this study expands the existing literature with a comprehensive model of campaign values. Furthermore, by elucidating the impact of each campaign value on COBRAs, this study offers valuable insights to marketers and suggests effective strategies to engage consumers with brands.

Validity of the flap risk score in predicting nasoseptal flap use after endoscopic transsphenoidal pituitary mass resection

IntroductionThere remains a paucity of literature examining the decision algorithm for use of nasoseptal flap (NSF) after endoscopic endonasal approaches (EEA) to pituitary adenoma resection. In 2018, we published the first ever flap risk score (FRS) to predict the use of NSF. We present here a validity study examining the FRS as applied to our center. MethodsA retrospective review was completed of consecutive patients undergoing EEA from January 2015 to March 2021. The sensitivity, specificity, and predictive value of the FRS were calculated. A multivariate logistic model was used to determine the relative weight imaging characteristics in predicting need for NSF. The relative weighting of the FRS was then re-optimized. ResultsA total of 376 patients underwent EEA for pituitary adenoma resection, with 113 (30.1%) requiring NSF. The FRS had a sensitivity and specificity of 43.4% and 94.7%, respectively. Sphenoid sinus extension increased the odds of needing a NSF equivalent to 19 mm of tumor height, as opposed to 6 mm in the original 2018 cohort. The re-optimized model had sensitivity and specificity of 79.6% and 76.4%, respectively. ConclusionWe present a validity study examining the utility of FRS in predicting the use of NSF after EEA for pituitary adenoma resection. Our results show that while FRS is still predictive of the need for NSF after EEA, it is not as predictive now as it was for its original cohort. Therefore, a more comprehensive model is necessary to more accurately stratify patients’ preoperative risk for NSF.

Effectiveness of Technology Use in Indonesian High Schools: Student Engagement, School Capacity, Teacher Performance

The present research investigates the intricate interplay among student engagement, school capacity, teacher performance, and the proficient implementation of technology within secondary institutions in Indonesia. This study employs a quantitative methodology to incorporate these constructs into a comprehensive model by utilizing Structural Equation Modeling with Partial Least Squares. The study surveyed 243 educators using a stratified random sample, which yielded valuable information regarding demographic characteristics, patterns of technology usage, and the intricate interrelationships among the variables identified. The robust validity and reliability of the measurement model validated the efficacy of the chosen indicators. Significant positive correlations were identified through path analysis among student engagement, school capacity, teacher performance, and technology effectiveness. By drawing inspiration from the Integrated Educational Technology Ecosystem theory, this model enhances the theoretical comprehension of technology integration specifically within the domain of secondary schools in Indonesia. In addition, recommendations and practical implications for policymakers, educators, and future research are addressed.

Incidence, prognostic factors, and a nomogram of cervical cancer with lung metastasis: A SEER-based study

AimsThe purpose of this study was to investigate the incidence, survival and prognostic factors of cervical cancer with lung metastasis at the initial diagnosis and to develop a visual nomogram to predict the prognosis of these patients. MethodsWe used the Surveillance, Epidemiology and End Results (SEER) database to screen patients diagnosed with cervical cancer from 2010 to 2015. After strict inclusion and exclusion, the chi-square test was used to evaluate the differences in the clinical characteristics of patients with cervical cancer, and then we used Kaplan–Meier method to perform survival analysis among cervical cancer patients with lung metastasis. Next, univariate and multivariate Cox proportional hazard regression models were used to estimate prognostic factors of these patients and we developed a visualized and novel nomogram to judge the prognosis. Results476 patients with lung metastasis and 12,016 patients without lung metastasis were included in this study. The incidence of lung metastasis was higher in unmarried white cervical cancer patients between the ages of 40 and 60, and grade III cervical squamous cell carcinoma patients were more likely to have lung metastasis. In addition, grade, surgery, radiotherapy, sequence of surgery and radiotherapy and chemotherapy were significantly related to the outcomes of cervical cancer patients with lung metastasis. Furthermore, our nomogram could predict the 3-year and 5-year overall survival (OS) of these patients. Finally, the AUC of 3-year OS and 5-year OS were confirmed to be 0.969 and 0.939 respectively by ROC curves, with good consistency. ConclusionsAge at diagnosis, race, marital status, and characteristics of the tumor can influence the incidence of lung metastasis in cervical cancer patients. Besides, grade, surgery, radiotherapy, sequence of surgery and radiotherapy and chemotherapy may deeply affect the prognosis of cervical cancer patients with lung metastasis. The nomogram built in this study may help clinicians to formulate individualized treatment strategies and encourage the development of more and more comprehensive and accurate predictive models.

Empirical exploration of whale optimisation algorithm for heart disease prediction

Heart Diseases have the highest mortality worldwide, necessitating precise predictive models for early risk assessment. Much existing research has focused on improving model accuracy with single datasets, often neglecting the need for comprehensive evaluation metrics and utilization of different datasets in the same domain (heart disease). This research introduces a heart disease risk prediction approach by harnessing the whale optimization algorithm (WOA) for feature selection and implementing a comprehensive evaluation framework. The study leverages five distinct datasets, including the combined dataset comprising the Cleveland, Long Beach VA, Switzerland, and Hungarian heart disease datasets. The others are the Z-AlizadehSani, Framingham, South African, and Cleveland heart datasets. The WOA-guided feature selection identifies optimal features, subsequently integrated into ten classification models. Comprehensive model evaluation reveals significant improvements across critical performance metrics, including accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve. These enhancements consistently outperform state-of-the-art methods using the same dataset, validating the effectiveness of our methodology. The comprehensive evaluation framework provides a robust assessment of the model’s adaptability, underscoring the WOA’s effectiveness in identifying optimal features in multiple datasets in the same domain.