Refining breast cancer biomarker discovery and drug targeting through an advanced data-driven approach.

Breast cancer remains a major public health challenge worldwide. The identification of accurate biomarkers is critical for the early detection and effective treatment of breast cancer. This study utilizes an integrative machine learning approach to analyze breast cancer gene expression data for superior biomarker and drug target discovery. Gene expression datasets, obtained from the GEO database, were merged post-preprocessing. From the merged dataset, differential expression analysis between breast cancer and normal samples revealed 164 differentially expressed genes. Meanwhile, a separate gene expression dataset revealed 350 differentially expressed genes. Additionally, the BGWO_SA_Ens algorithm, integrating binary grey wolf optimization and simulated annealing with an ensemble classifier, was employed on gene expression datasets to identify predictive genes including TOP2A, AKR1C3, EZH2, MMP1, EDNRB, S100B, and SPP1. From over 10,000 genes, BGWO_SA_Ens identified 1404 in the merged dataset (F1 score: 0.981, PR-AUC: 0.998, ROC-AUC: 0.995) and 1710 in the GSE45827 dataset (F1 score: 0.965, PR-AUC: 0.986, ROC-AUC: 0.972). The intersection of DEGs and BGWO_SA_Ens selected genes revealed 35 superior genes that were consistently significant across methods. Enrichment analyses uncovered the involvement of these superior genes in key pathways such as AMPK, Adipocytokine, and PPAR signaling. Protein-protein interaction network analysis highlighted subnetworks and central nodes. Finally, a drug-gene interaction investigation revealed connections between superior genes and anticancer drugs. Collectively, the machine learning workflow identified a robust gene signature for breast cancer, illuminated their biological roles, interactions and therapeutic associations, and underscored the potential of computational approaches in biomarker discovery and precision oncology.

Genetic justification of COVID-19 patient outcomes using DERGA, a novel data ensemble refinement greedy algorithm.

Complement inhibition has shown promise in various disorders, including COVID-19. A prediction tool including complement genetic variants is vital. This study aims to identify crucial complement-related variants and determine an optimal pattern for accurate disease outcome prediction. Genetic data from 204 COVID-19 patients hospitalized between April 2020 and April 2021 at three referral centres were analysed using an artificial intelligence-based algorithm to predict disease outcome (ICU vs. non-ICU admission). A recently introduced alpha-index identified the 30 most predictive genetic variants. DERGA algorithm, which employs multiple classification algorithms, determined the optimal pattern of these key variants, resulting in 97% accuracy for predicting disease outcome. Individual variations ranged from 40 to 161 variants per patient, with 977 total variants detected. This study demonstrates the utility of alpha-index in ranking a substantial number of genetic variants. This approach enables the implementation of well-established classification algorithms that effectively determine the relevance of genetic variants in predicting outcomes with high accuracy.

Should Transport Ventilators Be Used in Times of Crisis? The Use of Emergency Authorized Nonconventional Ventilators Is Associated With Mortality Among Patients With COVID-19 Acute Respiratory Distress Syndrome.

OBJECTIVES: Nonconventional ventilators (NCVs), defined here as transport ventilators and certain noninvasive positive pressure devices, were used extensively as crisis-time ventilators for intubated patients with COVID-19. We assessed whether there was an association between the use of NCV and higher mortality, independent of other factors. DESIGN: This is a multicenter retrospective observational study. SETTING: The sample was recruited from a single healthcare system in New York. The recruitment period spanned from March 1, 2020, to April 30, 2020. PATIENTS: The sample includes patients who were intubated for COVID-19 acute respiratory distress syndrome (ARDS). INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The primary outcome was 28-day in-hospital mortality. Multivariable logistic regression was used to derive the odds of mortality among patients managed exclusively with NCV throughout their ventilation period compared with the remainder of the sample while adjusting for other factors. A secondary analysis was also done, in which the mortality of a subset of the sample exclusively ventilated with NCV was compared with that of a propensity score-matched subset of the control group. Exclusive use of NCV was associated with a higher 28-day in-hospital mortality while adjusting for confounders in the regression analysis (odds ratio, 1.41; 95% CI [1.07-1.86]). In the propensity score matching analysis, the mortality of patients exclusively ventilated with NCV was 68.9%, and that of the control was 60.7% ( p = 0.02). CONCLUSIONS: Use of NCV was associated with increased mortality among patients with COVID-19 ARDS. More lives may be saved during future ventilator shortages if more full-feature ICU ventilators, rather than NCVs, are reserved in national and local stockpiles.

Hybrid WT-CNN-GRU-based model for the estimation of reservoir water quality variables considering spatio-temporal features.

Water quality indicators (WQIs), such as chlorophyll-a (Chl-a) and dissolved oxygen (DO), are crucial for understanding and assessing the health of aquatic ecosystems. Precise prediction of these indicators is fundamental for the efficient administration of rivers, lakes, and reservoirs. This research utilized two unique DL algorithms-namely, convolutional neural network (CNNs) and gated recurrent units (GRUs)-alongside their amalgamation, CNN-GRU, to precisely gauge the concentration of these indicators within a reservoir. Moreover, to optimize the outcomes of the developed hybrid model, we considered the impact of a decomposition technique, specifically the wavelet transform (WT). In addition to these efforts, we created two distinct machine learning (ML) algorithms-namely, random forest (RF) and support vector regression (SVR)-to demonstrate the superior performance of deep learning algorithms over individual ML ones. We initially gathered WQIs from diverse locations and varying depths within the reservoir using an AAQ-RINKO device in the study area to achieve this. It is important to highlight that, despite utilizing diverse data-driven models in water quality estimation, a significant gap persists in the existing literature regarding implementing a comprehensive hybrid algorithm. This algorithm integrates the wavelet transform, convolutional neural network (CNN), and gated recurrent unit (GRU) methodologies to estimate WQIs accurately within a spatiotemporal framework. Subsequently, the effectiveness of the models that were developed was assessed utilizing various statistical metrics, encompassing the correlation coefficient (r), root mean square error (RMSE), mean absolute error (MAE), and Nash-Sutcliffe efficiency (NSE) throughout both the training and testing phases. The findings demonstrated that the WT-CNN-GRU model exhibited better performance in comparison with the other algorithms by 13% (SVR), 13% (RF), 9% (CNN), and 8% (GRU) when R-squared and DO were considered as evaluation indices and WQIs, respectively.

Multi-variable approach to groundwater vulnerability elucidation: A risk-based multi-objective optimization model.

Groundwater vulnerability mapping is essential in environmental management since there is an increase in contamination caused by excessive population growth. However, to our knowledge, there is rare research dedicated to optimizing the groundwater vulnerability models, considering risk conditions, using a robust multi-objective optimization algorithm coupled with a multi-criteria decision-making model (MCDM). This study filled this knowledge gap by developing an innovative hybrid risk-based multi-objective optimization model using three distinguished models. The first model generated two series of scenarios for rate modifications associated with two common contaminations, Nitrate and Sulfate, based on susceptibility index (SI) and DRASTICA models. The second model was a multi-objective optimization framework using non-dominated sorting genetic algorithms- II and III (NSGA-II and NSGA-III), considering uncertainties in the input rates by the conditional value-at-risk (CVaR) technique. Finally, the third model was a well-known MCDM model, the COmplex PRoportional ASsessment (COPRAS), which identified the best compromise solution among Pareto-optimal solutions for weights of the contaminations. Regarding the Sulfate's results, although the optimized DRASTICA model led to the same correlation as the initial model, 0.7, the optimized SI model increased the correlation to 0.8 compared to the initial model as 0.58. For the Nitrate, both the optimized SI and the optimized DRASTICA models raised the correlation to 0.6 and 0.7 compared to the initial model with a correlation value of 0.36, respectively. Hence, the best and the lowest correlation among the optimized models were between SI and Sulfate concentration and SI and Nitrate concentration, respectively.

Multi-objective optimization of hydrant flushing in a water distribution system using a fast hybrid technique.

As a critical element in preserving the health of urban populations, water distribution systems (WDSs) must be ready to implement emergency plans when catastrophic events such as contamination events occur. A risk-based simulation-optimization framework (EPANET-NSGA-III) combined with a decision support model (GMCR) is proposed in this study to determine optimal locations for contaminant flushing hydrants under an array of potentially hazardous scenarios. Risk-based analysis using Conditional Value-at-Risk (CVaR)-based objectives can address uncertainties regarding the mode of WDS contamination, thereby providing a robust plan to minimize the associated risks at a 95% confidence level. Conflict modeling by GMCR achieved an optimal compromise solution within the Pareto front by identifying a final stable consensus among the decision-makers involved. A novel hybrid contamination event grouping-parallel water quality simulation technique was incorporated into the integrated model to reduce model runtime, the main deterrent in optimization-based methods. The nearly 80% reduction in model runtime made the proposed model a viable solution for online simulation-optimization problems. The framework's capacity to address real-world problems was evaluated for the WDS operating in Lamerd, a city in Fars Province, Iran. Results showed that the proposed framework was capable of highlighting a single flushing strategy, which not only optimally reduced risks associated with contamination events, but provided acceptable coverage against such threats, flushing 35-61.3% of input contamination mass on average, and reducing average time-to-return to normal conditions by 14.4-60.2%, while employing less than half of the initial potential hydrants.

Genetic prediction of ICU hospitalization and mortality in COVID-19 patients using artificial neural networks.

There is an unmet need of models for early prediction of morbidity and mortality of Coronavirus disease-19 (COVID-19). We aimed to a) identify complement-related genetic variants associated with the clinical outcomes of ICU hospitalization and death, b) develop an artificial neural network (ANN) predicting these outcomes and c) validate whether complement-related variants are associated with an impaired complement phenotype. We prospectively recruited consecutive adult patients of Caucasian origin, hospitalized due to COVID-19. Through targeted next-generation sequencing, we identified variants in complement factor H/CFH, CFB, CFH-related, CFD, CD55, C3, C5, CFI, CD46, thrombomodulin/THBD, and A Disintegrin and Metalloproteinase with Thrombospondin motifs (ADAMTS13). Among 381 variants in 133 patients, we identified 5 critical variants associated with severe COVID-19: rs2547438 (C3), rs2250656 (C3), rs1042580 (THBD), rs800292 (CFH) and rs414628 (CFHR1). Using age, gender and presence or absence of each variant, we developed an ANN predicting morbidity and mortality in 89.47% of the examined population. Furthermore, THBD and C3a levels were significantly increased in severe COVID-19 patients and those harbouring relevant variants. Thus, we reveal for the first time an ANN accurately predicting ICU hospitalization and death in COVID-19 patients, based on genetic variants in complement genes, age and gender. Importantly, we confirm that genetic dysregulation is associated with impaired complement phenotype.

XGBoost model as an efficient machine learning approach for PFAS removal: Effects of material characteristics and operation conditions.

Due to the implications of poly- and perfluoroalkyl substances (PFAS) on the environment and public health, great attention has been recently made to finding innovative materials and methods for PFAS removal. In this work, PFAS is considered universal contamination which can be found in many wastewater streams. Conventional materials and processes used to remove and degrade PFAS do not have enough competence to address the issue particularly when it comes to eliminating short-chain PFAS. This is mainly due to the large number of complex parameters that are involved in both material and process designs. Here, we took the advantage of artificial intelligence to introduce a model (XGBoost) in which material and process factors are considered simultaneously. This research applies a machine learning approach using data collected from reported articles to predict the PFAS removal factors. The XGBoost modeling provided accurate adsorption capacity, equilibrium, and removal estimates with the ability to predict the adsorption mechanisms. The performance comparison of adsorbents and the role of AI in one dominant are studied and reviewed for the first time, even though many studies have been carried out to develop PFAS removal through various adsorption methods such as ion exchange, nanofiltration, and activated carbon (AC). The model showed that pH is the most effective parameter to predict PFAS removal. The proposed model in this work can be extended for other micropollutants and can be used as a basic framework for future adsorbent design and process optimization.

Trajectories of hypoxemia and pulmonary mechanics of COVID-19 ARDS in the NorthCARDS dataset.

BACKGROUND: Understanding heterogeneity seen in patients with COVIDARDS and comparing to non-COVIDARDS may inform tailored treatments. METHODS: A multidisciplinary team of frontline clinicians and data scientists worked to create the Northwell COVIDARDS dataset (NorthCARDS) leveraging over 11,542 COVID-19 hospital admissions. The data was then summarized to examine descriptive differences based on clinically meaningful categories of lung compliance, and to examine trends in oxygenation. FINDINGS: Of the 1536 COVIDARDS patients in the NorthCARDS dataset, there were 531 (34.6%) who had very low lung compliance (< 20 ml/cmH2O), 970 (63.2%) with low-normal compliance (20-50 ml/cmH2O), and 35 (2.2%) with high lung compliance (> 50 ml/cmH2O). The very low compliance group had double the median time to intubation compared to the low-normal group (107.3 h (IQR 25.8, 239.2) vs. 39.5 h (IQR 5.4, 91.6)). Overall, 68.8% (n = 1057) of the patients died during hospitalization. In comparison to non-COVIDARDS reports, there were less patients in the high compliance category (2.2% vs. 12%, compliance ≥ 50 mL/cmH20), and more patients with P/F ≤ 150 (59.8% vs. 45.6%). There is a statistically significant correlation between compliance and P/F ratio. The Oxygenation Index is the highest in the very low compliance group (12.51, SD(6.15)), and lowest in high compliance group (8.78, SD(4.93)). CONCLUSIONS: The respiratory system compliance distribution of COVIDARDS is similar to non-COVIDARDS. In some patients, there may be a relation between time to intubation and duration of high levels of supplemental oxygen treatment on trajectory of lung compliance.

Structural Health Monitoring in Composite Structures: A Comprehensive Review.

This study presents a comprehensive review of the history of research and development of different damage-detection methods in the realm of composite structures. Different fields of engineering, such as mechanical, architectural, civil, and aerospace engineering, benefit excellent mechanical properties of composite materials. Due to their heterogeneous nature, composite materials can suffer from several complex nonlinear damage modes, including impact damage, delamination, matrix crack, fiber breakage, and voids. Therefore, early damage detection of composite structures can help avoid catastrophic events and tragic consequences, such as airplane crashes, further demanding the development of robust structural health monitoring (SHM) algorithms. This study first reviews different non-destructive damage testing techniques, then investigates vibration-based damage-detection methods along with their respective pros and cons, and concludes with a thorough discussion of a nonlinear hybrid method termed the Vibro-Acoustic Modulation technique. Advanced signal processing, machine learning, and deep learning have been widely employed for solving damage-detection problems of composite structures. Therefore, all of these methods have been fully studied. Considering the wide use of a new generation of smart composites in different applications, a section is dedicated to these materials. At the end of this paper, some final remarks and suggestions for future work are presented.

Groundwater sustainability: Developing a non-cooperative optimal management scenario in shared groundwater resources under water bankruptcy conditions.

Groundwater level drawdown changes the hydrological cycle and poses challenges such as land subsidence and reduction of the groundwater quality. In this study, a new approach using a simulation-optimization framework was developed for shared groundwater management under water bankruptcy conditions (where water demand is greater than the allowable discharge capacity of water resources). The novelty of this study lies in using bankruptcy rules and a game model to manage a bankrupted shared groundwater resource considering aquifer sustainability. Accordingly, groundwater flow in the aquifer was numerically simulated by a finite-differences model (MODFLOW). Then, the repeated performance code of the finite-differences model was run for different discharge scenarios, and the results were applied to develop an MLP-ANN meta-model. By coupling the meta-model with a non-dominated sorting genetic algorithm II (NSGA-II)-based multi-objective optimization model, an optimized cultivation pattern under water bankruptcy conditions was achieved. Then, six different bankruptcy methods were utilized to specify groundwater allocation between three stakeholders. To manage the water bankruptcy conditions, different scenarios considering various groundwater extraction rates and cultivation areas were defined, and the optimization model was recoded for each scenario to find the corresponding optimized cultivation pattern. To consider the competition between stakeholders for groundwater extraction, a non-cooperative 3-player game was applied to achieve a compromise for different combinations of management strategies, which maximizes the profit and yields the best cultivation scenario. Applicability of the proposed methodology was investigated in an aquifer system located in Golestan Province, Iran, including three regions (Minudasht, Azadshahr, and Gonbade-kavus). Results show that the proposed method is capable of managing the bankruptcy conditions by generating greater agricultural profit and reducing groundwater drawdowns.

Lightning search algorithm: a comprehensive survey.

The lightning search algorithm (LSA) is a novel meta-heuristic optimization method, which is proposed in 2015 to solve constraint optimization problems. This paper presents a comprehensive survey of the applications, variants, and results of the so-called LSA. In LSA, the best-obtained solution is defined to improve the effectiveness of the fitness function through the optimization process by finding the minimum or maximum costs to solve a specific problem. Meta-heuristics have grown the focus of researches in the optimization domain, because of the foundation of decision-making and assessment in addressing various optimization problems. A review of LSA variants is displayed in this paper, such as the basic, binary, modification, hybridization, improved, and others. Moreover, the classes of the LSA's applications include the benchmark functions, machine learning applications, network applications, engineering applications, and others. Finally, the results of the LSA is compared with other optimization algorithms published in the literature. Presenting a survey and reviewing the LSA applications is the chief aim of this survey paper.

Time Series Analysis and Forecast of the COVID-19 Pandemic in India using Genetic Programming.

COVID-19 declared as a global pandemic by WHO, has emerged as the most aggressive disease, impacting more than 90% countries of the world. The virus started from a single human being in China, is now increasing globally at a rate of 3% to 5% daily and has become a never ending process. Some studies even predict that the virus will stay with us forever. India being the second most populous country of the world, is also not saved, and the virus is spreading as a community level transmitter. Therefore, it become really important to analyse the possible impact of COVID-19 in India and forecast how it will behave in the days to come. In present work, prediction models based on genetic programming (GP) have been developed for confirmed cases (CC) and death cases (DC) across three most affected states namely Maharashtra, Gujarat and Delhi as well as whole India. The proposed prediction models are presented using explicit formula, and impotence of prediction variables are studied. Here, statistical parameters and metrics have been used for evaluated and validate the evolved models. From the results, it has been found that the proposed GEP-based models use simple linkage functions and are highly reliable for time series prediction of COVID-19 cases in India.

Evolutionary modelling of the COVID-19 pandemic in fifteen most affected countries.

COVID-19 or SARS-Cov-2, affecting 6 million people and more than 300,000 deaths, the global pandemic has engulfed more than 90% countries of the world. The virus started from a single organism and is escalating at a rate of 3% to 5% daily and seems to be a never ending process. Understanding the basic dynamics and presenting new predictions models for evaluating the potential effect of the virus is highly crucial. In present work, an evolutionary data analytics method called as Genetic programming (GP) is used to mathematically model the potential effect of coronavirus in 15 most affected countries of the world. Two datasets namely confirmed cases (CC) and death cases (DC) were taken into consideration to estimate, how transmission varied in these countries between January 2020 and May 2020. Further, a percentage rise in the number of daily cases is also shown till 8 June 2020 and it is expected that Brazil will have the maximum rise in CC and USA have the most DC. Also, prediction of number of new CC and DC cases for every one million people in each of these countries is presented. The proposed model predicted that the transmission of COVID-19 in China is declining since late March 2020; in Singapore, France, Italy, Germany and Spain the curve has stagnated; in case of Canada, South Africa, Iran and Turkey the number of cases are rising slowly; whereas for USA, UK, Brazil, Russia and Mexico the rate of increase is very high and control measures need to be taken to stop the chains of transmission. Apart from that, the proposed prediction models are simple mathematical equations and future predictions can be drawn from these general equations. From the experimental results and statistical validation, it can be said that the proposed models use simple linkage functions and provide highly reliable results for time series prediction of COVID-19 in these countries.

Partial derivative Nonlinear Global Pandemic Machine Learning prediction of COVID 19.

The recent worldwide outbreak of the novel coronavirus disease 2019 (COVID-19) opened new challenges for the research community. Machine learning (ML)-guided methods can be useful for feature prediction, involved risk, and the causes of an analogous epidemic. Such predictions can be useful for managing and intercepting the outbreak of such diseases. The foremost advantages of applying ML methods are handling a wide variety of data and easy identification of trends and patterns of an undetermined nature.In this study, we propose a partial derivative regression and nonlinear machine learning (PDR-NML) method for global pandemic prediction of COVID-19. We used a Progressive Partial Derivative Linear Regression model to search for the best parameters in the dataset in a computationally efficient manner. Next, a Nonlinear Global Pandemic Machine Learning model was applied to the normalized features for making accurate predictions. The results show that the proposed ML method outperformed state-of-the-art methods in the Indian population and can also be a convenient tool for making predictions for other countries.

A novel multi-hybrid differential evolution algorithm for optimization of frame structures.

Differential evolution (DE) is a robust optimizer designed for solving complex domain research problems in the computational intelligence community. In the present work, a multi-hybrid DE (MHDE) is proposed for improving the overall working capability of the algorithm without compromising the solution quality. Adaptive parameters, enhanced mutation, enhanced crossover, reducing population, iterative division and Gaussian random sampling are some of the major characteristics of the proposed MHDE algorithm. Firstly, an iterative division for improved exploration and exploitation is used, then an adaptive proportional population size reduction mechanism is followed for reducing the computational complexity. It also incorporated Weibull distribution and Gaussian random sampling to mitigate premature convergence. The proposed framework is validated by using IEEE CEC benchmark suites (CEC 2005, CEC 2014 and CEC 2017). The algorithm is applied to four engineering design problems and for the weight minimization of three frame design problems. Experimental results are analysed and compared with recent hybrid algorithms such as laplacian biogeography based optimization, adaptive differential evolution with archive (JADE), success history based DE, self adaptive DE, LSHADE, MVMO, fractional-order calculus-based flower pollination algorithm, sine cosine crow search algorithm and others. Statistically, the Friedman and Wilcoxon rank sum tests prove that the proposed algorithm fares better than others.

DDCNN-F: double decker convolutional neural network 'F' feature fusion as a medical image classification framework.

Melanoma is a severe skin cancer that involves abnormal cell development. This study aims to provide a new feature fusion framework for melanoma classification that includes a novel 'F' Flag feature for early detection. This novel 'F' indicator efficiently distinguishes benign skin lesions from malignant ones known as melanoma. The article proposes an architecture that is built in a Double Decker Convolutional Neural Network called DDCNN future fusion. The network's deck one, known as a Convolutional Neural Network (CNN), finds difficult-to-classify hairy images using a confidence factor termed the intra-class variance score. These hirsute image samples are combined to form a Baseline Separated Channel (BSC). By eliminating hair and using data augmentation techniques, the BSC is ready for analysis. The network's second deck trains the pre-processed BSC and generates bottleneck features. The bottleneck features are merged with features generated from the ABCDE clinical bio indicators to promote classification accuracy. Different types of classifiers are fed to the resulting hybrid fused features with the novel 'F' Flag feature. The proposed system was trained using the ISIC 2019 and ISIC 2020 datasets to assess its performance. The empirical findings expose that the DDCNN feature fusion strategy for exposing malignant melanoma achieved a specificity of 98.4%, accuracy of 93.75%, precision of 98.56%, and Area Under Curve (AUC) value of 0.98. This study proposes a novel approach that can accurately identify and diagnose fatal skin cancer and outperform other state-of-the-art techniques, which is attributed to the DDCNN 'F' Feature fusion framework. Also, this research ascertained improvements in several classifiers when utilising the 'F' indicator, resulting in the highest specificity of + 7.34%.

Efficient implicit constraint handling approaches for constrained optimization problems.

Many real-world optimization problems, particularly engineering ones, involve constraints that make finding a feasible solution challenging. Numerous researchers have investigated this challenge for constrained single- and multi-objective optimization problems. In particular, this work extends the boundary update (BU) method proposed by Gandomi and Deb (Comput. Methods Appl. Mech. Eng. 363:112917, 2020) for the constrained optimization problem. BU is an implicit constraint handling technique that aims to cut the infeasible search space over iterations to find the feasible region faster. In doing so, the search space is twisted, which can make the optimization problem more challenging. In response, two switching mechanisms are implemented that transform the landscape along with the variables to the original problem when the feasible region is found. To achieve this objective, two thresholds, representing distinct switching methods, are taken into account. In the first approach, the optimization process transitions to a state without utilizing the BU approach when constraint violations reach zero. In the second method, the optimization process shifts to a BU method-free optimization phase when there is no further change observed in the objective space. To validate, benchmarks and engineering problems are considered to be solved with well-known evolutionary single- and multi-objective optimization algorithms. Herein, the proposed method is benchmarked using with and without BU approaches over the whole search process. The results show that the proposed method can significantly boost the solutions in both convergence speed and finding better solutions for constrained optimization problems.

Potholes and traffic signs detection by classifier with vision transformers.

Detecting potholes and traffic signs is crucial for driver assistance systems and autonomous vehicles, emphasizing real-time and accurate recognition. In India, approximately 2500 fatalities occur annually due to accidents linked to hidden potholes and overlooked traffic signs. Existing methods often overlook water-filled and illuminated potholes, as well as those shaded by trees. Additionally, they neglect the perspective and illuminated (nighttime) traffic signs. To address these challenges, this study introduces a novel approach employing a cascade classifier along with a vision transformer. A cascade classifier identifies patterns associated with these elements, and Vision Transformers conducts detailed analysis and classification. The proposed approach undergoes training and evaluation on ICTS, GTSRDB, KAGGLE, and CCSAD datasets. Model performance is assessed using precision, recall, and mean Average Precision (mAP) metrics. Compared to state-of-the-art techniques like YOLOv3, YOLOv4, Faster RCNN, and SSD, the method achieves impressive recognition with a mAP of 97.14% for traffic sign detection and 98.27% for pothole detection.

A hybrid swarm intelligence algorithm for region-based image fusion.

This paper proposes a novel multi-hybrid algorithm named DHPN, using the best-known properties of dwarf mongoose algorithm (DMA), honey badger algorithm (HBA), prairie dog optimizer (PDO), cuckoo search (CS), grey wolf optimizer (GWO) and naked mole rat algorithm (NMRA). It follows an iterative division for extensive exploration and incorporates major parametric enhancements for improved exploitation operation. To counter the local optima problems, a stagnation phase using CS and GWO is added. Six new inertia weight operators have been analyzed to adapt algorithmic parameters, and the best combination of these parameters has been found. An analysis of the suitability of DHPN towards population variations and higher dimensions has been performed. For performance evaluation, the CEC 2005 and CEC 2019 benchmark data sets have been used. A comparison has been performed with differential evolution with active archive (JADE), self-adaptive DE (SaDE), success history based DE (SHADE), LSHADE-SPACMA, extended GWO (GWO-E), jDE100, and others. The DHPN algorithm is also used to solve the image fusion problem for four fusion quality metrics, namely, edge-based similarity index ( Q A B / F ), sum of correlation difference (SCD), structural similarity index measure (SSIM), and artifact measure ( N A B / F ). The average Q A B / F = 0.765508 , S C D = 1.63185 , S S I M = 0.726317 , and N A B / F = 0.006617 shows the best combination of results obtained by DHPN with respect to the existing algorithms such as DCH, CBF, GTF, JSR and others. Experimental and statistical Wilcoxon's and Friedman's tests show that the proposed DHPN algorithm performs significantly better in comparison to the other algorithms under test.