Wolf Research Articles

Using green hydrogen as the supplementary fuel for a scheme of power/fresh water production: An application of AI for optimal energy management and emission reduction

The primary objective of the current research is to speed up the shift towards a carbon-neutral economy and reduce our reliance on fossil fuels by developing a novel, highly efficient, environmentally friendly, and economically feasible multi-generation system based on solar-biomass hybridization. The essential element of this concept involves the introduction of green hydrogen into the combustion chamber, aiming to enhance the quality of the incineration products and facilitate the implementation of a waste-to-power Rankine cycle. The practicality of the suggested model is compared with a system that does not incorporate hydrogen injection. As a part of artificial intelligence, a neural network model integrated with the grey wolf optimizer is applied to ascertain the most optimal energy conversion/management condition with reduced computational time. The results show that the injection of additional hydrogen exhibits superior performance compared to the base system from all facets. The optimization achieves higher exergy efficiency and drinkable water production of 8.7 % and 27.9 kg/s while reducing the total cost and emission index of 13.7 $/h and 410.7 kg/GWh. The results indicate that the combustion chamber and steam generator are the poorest parts in terms of exergy under ideal conditions. Potential future directions of this work are to explore alternate techniques for generating hydrogen and perform regional evaluations to comprehend the accessibility and fluctuation of biomass and solar resources in various geographical areas.

Optimized PI-PDF active structural acoustic control of smart FG GPL-reinforced closed-cell metallic foam sandwich plate

This study investigates Active Structural Acoustic Control (ASAC) applied to sandwich plates featuring Functionally Grade (FG) porous Graphene-Platelet-Reinforced Piezoelectric (GPLRP) materials. These plates incorporate a core layer with internal pores and GPLs dispersed in a metal matrix, along with piezoelectric sensors and actuators. Using a spatial state-space formulation based on linear 3D piezoelasticity theory, a semi-analytical solution is derived for the vibroacoustic response of these sandwich plates. The mechanical properties of the porous core are modeled using a closed-cell metal foam. The effects of various parameters, including porosity distributions, porosity coefficient, weight fractions of nanofiller, and geometric parameters on the radiation efficiency and radiated sound power have been investigated. Then, the validation of the proposed model is examined by comparing the natural frequencies calculated in the present study to those from the literature. This comparison allows us to assess the accuracy and reliability of our model against established findings. Radiated sound power reduction from mechanically excited structures is achieved by employing a dual-stage Proportional Integral–Proportional Derivative with Filter (PI-PDF) controller, optimized using Grey Wolf Optimization (GWO). Finally, several numerical simulations are conducted to validate the effectiveness and accuracy of the proposed active control strategy.

Speed Control of Sensorless Induction motor based on Grey Wolf Optimizer Fractional Order Controller using MRAS based Speed Estimation

Speed Control of Sensorless Induction motor based on Grey Wolf Optimizer Fractional Order Controller using MRAS based Speed Estimation

Adaptive grey wolf optimizer based on transfer function inertia weight of second-order high-pass filter

This paper proposes an Adaptive Grey Wolf Optimizer based on Transfer function Inertia Weight of Second-order High-pass Filter (SAGWO), aiming to overcome the limitations of Grey Wolf Optimizer (GWO) in terms of convergence speed and solution accuracy. SAGWO enhances the algorithm's dynamic adaptability and greatly speeds up convergence by incorporating the transfer function of the second-order high-pass filter into the modifications of inertia and leader wolves' weight. Furthermore, SAGWO incorporates an adaptive random search component, which significantly enhances the search range and the ability to explore globally. The performance of SAGWO is assessed and compared against three prominent Swarm Intelligence Algorithms (ALO, WOA, and EHO), along with GWO and GWO optimized by PSO. This evaluation is conducted through trials on the CEC2017 standard test set. The experimental results indicate that SAGWO outperforms in terms of both convergence speed and solution correctness. Moreover, SAGWO is utilized to address practical engineering problems such as pressure vessel design and robot gripper design, showcasing its remarkable effectiveness once more. This research enhances the theoretical development of Swarm Intelligence Algorithms and demonstrates the significant utility of SAGWO in practical applications, establishing it as a powerful instrument for scientific investigation and engineering optimization.

Viruses of free-roaming and hunting dogs in Uganda show elevated prevalence, richness and abundance across a gradient of contact with wildlife.

Domestic dogs (Canis lupus familiaris) live with humans, frequently contact other animals and may serve as intermediary hosts for the transmission of viruses. Free-roaming dogs, which account for over 70% of the world's domestic dog population, may pose a particularly high risk in this regard. We conducted an epidemiological study of dog viromes in three locations in Uganda, representing low, medium and high rates of contact with wildlife, ranging from dogs owned specifically for traditional hunting in a biodiversity and disease 'hotspot' to pets in an affluent suburb. We quantified rates of contact between dogs and wildlife through owner interviews and conducted canine veterinary health assessments. We then applied broad-spectrum viral metagenomics to blood plasma samples, from which we identified 46 viruses, 44 of which were previously undescribed, in three viral families, Sedoreoviridae, Parvoviridae and Anelloviridae. All 46 viruses (100 %) occurred in the high-contact population of dogs compared to 63 % and 39 % in the medium- and low-contact populations, respectively. Viral prevalence ranged from 2.1 % to 92.0 % among viruses and was highest, on average, in the high-contact population (22.3 %), followed by the medium-contact (12.3 %) and low-contact (4.8 %) populations. Viral richness (number of viruses per dog) ranged from 0 to 27 and was markedly higher, on average, in the high-contact population (10.2) than in the medium-contact (5.7) or low-contact (2.3) populations. Viral richness was strongly positively correlated with the number of times per year that a dog was fed wildlife and negatively correlated with the body condition score, body temperature and packed cell volume. Viral abundance (cumulative normalized metagenomic read density) varied 124-fold among dogs and was, on average, 4.1-fold higher and 2.4-fold higher in the high-contact population of dogs than in the low-contact or medium-contact populations, respectively. Viral abundance was also strongly positively correlated with the number of times per year that a dog was fed wildlife, negatively correlated with packed cell volume and positively correlated with white blood cell count. These trends were driven by nine viruses in the family Anelloviridae, genus Thetatorquevirus, and by one novel virus in the family Sedoreoviridae, genus Orbivirus. The genus Orbivirus contains zoonotic viruses and viruses that dogs can acquire through ingestion of infected meat. Overall, our findings show that viral prevalence, richness and abundance increased across a gradient of contact between dogs and wildlife and that the health status of the dog modified viral infection. Other ecological, geographic and social factors may also have contributed to these trends. Our finding of a novel orbivirus in dogs with high wildlife contact supports the idea that free-roaming dogs may serve as intermediary hosts for viruses of medical importance to humans and other animals.

Multi-Objective Optimization of Short-Inverted Transport Scheduling Strategy Based on Road–Railway Intermodal Transport

This study focuses on the ‘short-inverted transportation’ scenario of intermodal transport. It proposes a vehicle unloading reservation mechanism to optimize the point-of-demand scheduling system for the inefficiency of transport due to the complexity and uncertainty of the scheduling strategy. This paper establishes a scheduling strategy optimization model to minimize the cost of short backhaul and obtain the shortest delivery time window and designs a hybrid NSGWO algorithm suitable for multi-objective optimization to solve the problem. The algorithm incorporates the Non-dominated Sorting Genetic Algorithm II (NSGA-II) algorithm based on the Grey Wolf Optimizer (GWO) algorithm, compensating for a single algorithm’s premature convergence. The experiment selects a logistics carrier’s actual road–rail intermodal short-inverted data and compares and verifies the above data. The results show that the scheduling scheme obtained by this algorithm can save 41.01% of the transport cost and shorten the total delivery time by 46.94% compared with the original scheme, which can effectively protect the enterprise’s economic benefits while achieving timely delivery. At the same time, the optimized scheduling plan resulted in a lower number of transport vehicles, which positively impacted the sustainability of green logistics.

Exploring multi-pollution variability in the urban environment: geospatial AI-driven modeling of air and noise

ABSTRACT This study addresses the critical need for comprehensive multi-pollution modeling in urban environments by employing Geospatial Artificial Intelligence (GeoAI) techniques. Specifically, it aims to elucidate the variability of air and noise pollution levels in Tehran, Iran, and develop precise multi-pollution susceptibility maps. A spatial database was compiled, encompassing annual average data (2019–2022) of the Air Quality Index (AQI) and Equivalent Continuous Sound Level (Leq), along with 19 influential factors related to both pollutants. The study utilized the CatBoost machine learning algorithm, enhanced with Grey Wolf Optimizer (GWO) and Harris Hawks Optimization (HHO) algorithms, to model and predict pollution patterns. Key quantitative achievements include a remarkable 15% reduction in Root Mean Square Error (RMSE) for air pollution and a 12% reduction in noise pollution when using the CatBoost-HHO configuration compared to the standalone CatBoost algorithm. Validation of the multi-pollution maps utilizing the Area Under the Curve (AUC) analysis showed high accuracy, with the CatBoost-HHO achieving AUC values of 0.943 for air pollution and 0.936 for noise pollution, outperforming CatBoost-GWO and standalone CatBoost models. These results underscore the efficacy of our approach in accurately identifying and mapping multi-pollution hotspots, contributing valuable insights for urban environmental management and public health preservation.

Grain condition inspection: one improved grey wolf algorithm for nodes deployment optimization combining with path planning of multi-inspection robots

Grain condition inspection: one improved grey wolf algorithm for nodes deployment optimization combining with path planning of multi-inspection robots

Detecting diabetes in an ensemble model using a unique PSO-GWO hybrid approach to hyperparameter optimization

Diabetes is a chronic medical condition that disrupts the body's normal blood sugar levels. It is essential to detect this disease at an early stage in order to prevent organ and tissue injury. This study focuses on diagnosing diabetes by leveraging ensemble learning methods, which involve combining various machine learning techniques. The goal is to create an ensemble learning model that achieves the best classification performance by employing different classifiers and combining techniques. The study explores boosting, bagging, voting, and stacking ensemble learning methods, while also introducing an approach called PSO-GWO (Particle Swarm Optimization and Grey Wolf Optimization) hybrid method for optimizing the model's hyperparameters. The model consisting of combining various classifiers in the stacking ensemble learning method provided the highest classification performance in diagnosing diabetes. The 5-fold cross-validation method is used in the study. Within the scope of the study, the highest accuracy with (98.10%) is obtained with the random forest classifier. The results of the study are presented in comparison with other studies in the literature. These findings contribute to the field of diabetes diagnosis and highlight the potential for developing more accurate and reliable diagnostic systems in the future.

Mechanics and microstructure analysis of geopolymer utilizing ilmenite tailing and metakaolin powder as alkali-activated materials

Geopolymers derived from bulk solid waste are considered ideal substitutes for cement-based materials in developing environmentally friendly construction materials. The utilization of solid waste tailings powder as a precursor for alkali activation of geopolymer can enhance the mechanical characteristics of geopolymer. This study conducted extensive experimental studies on the compressive strength, flexural strength, SEM microstructure, thermogravimetric curve, and variable influence of alkali-activated ilmenite tailings (IT) geopolymer mortar, using the liquid-solid ratio and the number of tailings as variables. An analysis was conducted on the mortar's mechanical characteristics, microstructure, and machine-learning properties. Furthermore, the impact of different atomic ratios on the structure and characteristics of geopolymer mortars was also examined. The test results revealed that the metakaolin-iron titanium tailings geopolymer, when doped with 10% ilmenite tailings, exhibited a compressive strength of 72.30MPa at 14 days. Similarly, the flexural strength of the geopolymer reached 4.76MPa at 14 days when doped with 30% ilmenite tailings. XRD analysis showed that Magnesiohornblende particles Mg-F-A-S-H and C-A-S-H gel had positive and negative correlations, respectively, with the tailings doping level. TG results indicated that the specimens exhibit enhanced thermal stability following treatment with tailings. SEM analysis revealed that combining ilmenite tailings with metakaolin formed Me-(F)-A-S-H gels. The examination of surface porosity, pore shape, and unreacted material determined that adding ilmenite tailings increased the Si/Al and Fe/Si ratios, enhancing the transformation of the lamellar structure to the three-dimensional disordered gel mesh structure. Additionally, the tailings contributed a significant amount of Ca, elevating the Ca/Na ratio (0.1−0.6) and triggering calcium precipitation within a Ca/Si range of 0.03−0.2. This increase in calcium led to a decrease in the sample's strength as the curing time was extended. Based on prior research and the application of the Gray Wolf optimization algorithm in extreme learning, a clear negative correlation was identified between the liquid-solid ratio and strength. Furthermore, increasing the Si/Al ratio enhanced the geopolymer's strength, while an extended curing time negatively correlated with strength. The impact of tailings mixing was deemed insignificant when the tailings amount did not exceed 20%. Geopolymers may derive significant environmental and industrial benefits from the improvement of their mechanical properties, thermal stability, and optimization using machine learning.

Hybrid coati–grey wolf optimization with application to tuning linear quadratic regulator controller of active suspension systems

Vehicle suspension systems have become increasingly crucial for both driving safety and comfort. Active suspension systems can dynamically adjust suspension characteristics in real-time by introducing force into the system. Designing a controller for the real-time adjustment of the control force in active suspension systems is essential to meet challenging control objectives, including body acceleration, suspension deflection, and tire deflection. This article proposes a hybrid optimization approach named Coati–Grey Wolf Optimization (COAGWO), which combines the strengths of the coati optimization algorithm and grey wolf optimization to tune the gains of linear quadratic control applied to vehicle suspension systems. The COAGWO algorithm incorporates a unique strategy inspired by the Coati Optimization Algorithm, allowing wolves to climb trees. This enhancement significantly improves the wolves’ ability to explore the global search space and reduces the likelihood of being trapped in local optima. Initially, we conduct extensive experiments using a suite of challenging optimization problems from the CEC2019 benchmark to evaluate the effectiveness of the COAGWO algorithm. The effectiveness of COAGWO is compared against several state-of-the-art algorithms, including grey wolf, coati, aquila-grey wolf, whale, reptile search, tunicate swarm, and seagull optimization algorithms. The experimental results demonstrate that COAGWO consistently outperforms these algorithms in terms of solution quality and convergence speed. For the optimal weight selection problem of linear quadratic control applied to the control of vehicle suspension systems, the excellent performance of the proposed method is illustrated through comparative simulation studies under various road disturbance conditions. The results indicate that the COAGWO algorithm achieves a more efficient active suspension system compared to competitor algorithms by reducing the overall acceleration of the driver’s body, thereby enhancing ride comfort.

Grey wolf‐based heuristic methods for accurate parameter extraction to optimize the performance of PV modules

AbstractParameterprediction for PV solar cells plays a crucial role in controlling andoptimizing the performance of PV modules. In this study, the parameter prediction of a four‐diode PV model wascarried out using the Improved Grey Wolf Optimization (IGWO) algorithm, whichbuilds upon the Grey Wolf Optimization (GWO) algorithm. The parameters requiredfor the four‐diode PV model were optimized based on a predefined objectivefunction. Subsequently, the obtained data were compared with the data from RTCFrance Solar Cell to validate the accuracy and reliability of the optimizationresults. The evaluation of the optimization results revealed that the SumSquare Error (SSE) values for PSOGWO, AGWOCS, GWOCS, and GWO were 3.96E‐05, while the MSE value for IGWO was 3.6309E‐05. These findings clearly demonstratethat the proposed IGWO algorithm outperforms the other algorithms used in thestudy, based on the minimized SSE values. This study emphasizes the importanceof parameter prediction in optimizing PV performance, and it contributes to thefield by introducing the novel IGWO algorithm for the four‐diode PV model. Thealgorithm's superior performance, as demonstrated through extensive testing andcomparison with existing algorithms, validates its efficacy in accuratelypredicting the parameters for the PV solar cell model.

Harvest of transboundary grey wolves from Yellowstone National Park is largely additive

Abstract Large carnivores are globally threatened due to habitat fragmentation and loss, prey depletion and human exploitation. Human exploitation includes both legal and illegal hunting and trapping. Protected areas can create refugia from hunting and trapping; however, hunting can still threaten wide‐ranging large carnivores when they leave these areas. Large carnivore reintroductions to protected areas are often motivated to restore ecological processes, including wolf reintroduction to Yellowstone National Park (YNP). Determining if harvest is compensatory or additive is essential for informed conservation strategies, as it influences the overall impact on wolf populations and their ecosystems. If harvest was compensatory, then increasing harvest pressure outside YNP should not decrease overall survival for transboundary wolves. Alternatively, if increasing harvest was additive, then increasing harvest pressure outside YNP should decrease overall survival for transboundary wolves. We tested the effects of variable harvest pressure following delisting on the survival of YNP grey wolves (Canis lupus) from 1995 to 2022. We defined three harvest levels: no harvest, harvest with limited quotas and unlimited harvest. We used Cox‐proportional hazards models and cumulative incidence functions to estimate survival rates, factors affecting survival and cause‐specific mortality between these three harvest periods to test predictions of the additive mortality hypothesis. Most harvested wolves that primarily lived in YNP were killed adjacent to the park border. Cox‐proportional hazards models revealed that mortality was highest during years of unlimited harvest during winter outside YNP. Cause‐specific mortality analyses showed that natural mortality from other wolves and harvest were the two leading causes of death, but that harvest mortality had additive effects on wolf mortality. Wolf survival decreased with increased harvest mortality, while natural mortality remained relatively unchanged. Synthesis and applications. High rates of additive harvest mortality of wolves could negatively impact wolf survival in YNP. Harvest mortality of transboundary wolves is additive possibly due to source‐sink dynamics of uneven spatial susceptibility of wolves to harvest mortality across protected area borders, as well as effects of harvest on complex social dynamics of wolves in YNP. Transboundary management of large carnivores is challenging, yet cooperation between agencies is vital for wolf management in and around YNP. Our results support the use of small quota zones surrounding protected areas, that minimize transboundary mortality impacts on large carnivores living primarily inside protected areas.

An evaluation of potential inbreeding depression in wild Mexican wolves

AbstractEstimates of the influence of inbreeding on the fitness of wild animals can guide genetic conservation in rare species. Conservation genetics is important in Mexican wolves (Canis lupus baileyi) because the current population descended from 7 founders and mean inbreeding is relatively high. As an endangered subspecies, Mexican wolves are actively managed using select conflict avoidance measures and by placing captive‐born foster pups into wild litters. We obtained data on inbreeding coefficients of wolf pups and adults based on a pedigree dating to 1957 and data on reproduction for wild wolf packs during 1998–2022. We estimated trends in inbreeding coefficients and the associations between dam, sire, and pup inbreeding coefficients and pup recruitment to age 9 months, and assessed 3 components of recruitment: probability of producing a litter, number of pups produced, and recruitment conditional on successful reproduction. We generated estimates using generalized linear mixed models and bootstrapped estimates of confidence intervals. Mean inbreeding coefficients were high (0.227, SD = 0.047) in the wild population, but we detected no significant evidence of an increase during 2010–2022. Overall, the net associations of dam, sire, and pup inbreeding coefficients with our primary fitness metric, pup recruitment to age 9 months, did not differ from zero. While high inbreeding coefficients are a concern for the long‐term recovery of the subspecies, the stable level of inbreeding, lack of evidence for inbreeding depression, high pup production (5.1 pups/litter, SD = 1.64), and rapid population growth (384% increase from 2010–2022) indicate that inbreeding has not prevented rapid progress towards recovery goals under current management practices.

Where is the wolf? A multi‐method comparison of social values and perceptions in a Swiss park

This article presents our recent experience studying public perceptions, discourses, and social values in Park Beverin, a Regional Nature Park in Switzerland. We applied four social research methods (news media analysis, survey with micro‐narratives, go‐along interviews, and focus groups), and delved into the subject of wolf Canis lupus adapting a triangulation protocol and systematic process from the health sciences. We observed the recurring perceptions of ‘wolf' throughout three of the four methods; however, depictions, values, prominence, and presence varied by method. Social values of the wolf were mostly silent when compared to other topics, and ‘wolf amplification' and ‘wolf fatigue' point to the need to rethink the social aspects in wolf management, conservation, and policy. The findings also show the need for diverse research methods for revealing social values and perceptions on sensitive topics that otherwise the use of one method may be masking or amplifying.

Hybrid deep learning-based identification of microseismic events in TBM tunnelling

For TBM’s safe and efficient tunnelling, the microseismic monitoring technique has been widely applied in rockburst warning. However, useful microseismic events are often mixed with noisy events, which seriously affects warning accuracy. To this end, this study proposes several hybrid deep learning-based microseismic identification approaches in TBM tunnelling, where recurrent neural networks directly treat monitored microseismic events as time series and avoid complex feature pre-extraction, and grey wolf optimization and attention mechanism are embedded to optimize model hyper-parameters and recognize value information. Additionally, the learning curve and early-stopping strategy are also integrated to reduce overfitting and underfitting risks. Results in a real TBM-excavated water conveyance tunnel indicate that the bidirectional long short-term memory network model combined with grey wolf optimization and attention mechanism achieves the greatest identification performance among discussed models and provides an effective support for intelligent identification of microseismic events under TBM tunnelling environments.

Flood assessment using machine learning and its implications for coastal spatial planning in Phu Yen Province, Vietnam

ABSTRACT The objective of this study was the development of a new machine learning model using a radial basis function neural network (RBFNN) to build flood susceptibility maps and damage assessment for the Phu Yen province of Vietnam. The built model will be optimized by five algorithms, namely Giant Trevally Optimization (GTO), Golden Jackal Optimization (GJO), Brown-Bear Optimization (BBO), Gray Wolf Optimizer (GWO), and Whale Optimization Algorithm (WOA) to find out the best model to establish the flood susceptibility map. These models were evaluated using the statistical indices such as root mean square error (RMSE), mean absolute error (MAE), receiver operating characteristic (ROC), area under the curve (AUC), and coefficient of determination (COD). The result showed that all five optimization algorithms were successfully improving the performance of the RBFNN model, among them the hybrid model RBFNN–BBO has the highest performance with AUC = 0.998 and R2 = 0.8 and the RBFNN–GTO model has the lowest performance with AUC = 0.755 and R2 = 0.65. The regions identified with a high- and very-high flood susceptibility area (1,075 km2) were concentrated on the plain and along three of the largest rivers in Phu Yen province.

A fused grey wolf and artificial bee colony model for imbalanced data classification problems

A fused grey wolf and artificial bee colony model for imbalanced data classification problems

Bidirectional long-short term memory predictor for material removal rate in computer-controlled optical surfacing

In Computer-Controlled Optical Surfacing technology, the precision of the removal function directly affects the accuracy of computer-aided processing software predictions, which in turn influences subsequent polishing machine processing. A key parameter for constructing the removal function is the material removal rate, which is often challenging to obtain accurately. Currently, the Preston equation is widely used to describe the principles of material removal. However, as a linear equation that omits many factors, it struggles to accurately model the removal function in complex machining scenarios. Therefore, this paper proposes a hybrid neural network model combining Convolutional Neural Networks and Bidirectional Long Short-Term Memory to predict the material removal rate. The model's parameters are optimized using an improved Grey Wolf Optimization algorithm, ultimately establishing a removal function closely consistent with an actual removal function. We first tested our method on the PHM2016 Data Challenge dataset, achieving a mean squared error of 6.19 and an R2 of 0.9949, outperforming other mainstream neural network prediction models developed in recent years. Additionally, we further validated the performance of the neural network using a small grinding head polishing dataset, achieving MSE and R2 values of 1.9035 and 0.99902, respectively. Finally, we applied this method to construct the removal function on an actual small grinding head production line. Compared to the traditional Preston equation-based removal function, the predicted residual surface's PV and RMS errors were reduced from 28.24 % to 35.58 %–4.563 % and 4.86 %, respectively. These validation results demonstrate that the proposed method not only facilitates easier acquisition of the removal function model but also significantly enhances the accuracy of computer-aided processing software predictions, thereby better guiding ultra-precision machining processes.

FSBOA: feature selection using bat optimization algorithm for software fault detection

Feature selection (FS) plays a crucial role in software fault prediction (SFP), aiming to identify a subset of relevant and discriminative features from a large pool of software metrics. It serves as a critical preprocessing step in building accurate fault prediction models, enabling the identification of potential software faults early in the development life cycle and facilitating effective resource allocation for testing and maintenance activities. The study's objective is to determine how well the bat optimization algorithm (BOA) can extract the features that are most important for correctly predicting software flaws, improve the accuracy of fault prediction, reduce the dimensionality of the feature space, and mitigate the risk of overfitting, thereby enabling more effective resource utilization and better allocation of testing efforts. The forecasting models underwent testing and training utilizing a collection of software metrics, with the datasets undergoing evaluation using several different FS algorithms. An assessment was conducted by contrasting the effectiveness of multiple optimization algorithms, including evolutionary methods such as FS employing genetic algorithm (FSGA), FS employing differential evolution (FSDE), and swarm-based techniques such as FS employing ant colony optimization (FSACO), FS employing particle swarm optimization (FSPSO), FS employing firefly algorithm (FSFA), and FS employing binary grey wolf optimization algorithm (FSBGWO) in relation to FS employing bat optimization algorithm (FSBAO). The results obtained from FSBAO approach demonstrate the effectiveness in solving FS optimization problems with at most accuracy of 98.92%. Furthermore, the experimental results have been statistically validated for the greater efficiency of the proposed FSBAO algorithm. This study's findings have crucial implications for developing a software failure prediction models that is more accurate and efficient.