Search

Abstract Genes, expressed as sequences of nucleotides, are susceptible to mutations, some of which can lead to cancer. Machine learning and deep learning methods have emerged as vital tools in identifying mutations associated with cancer. Thyroid cancer ranks as the 5th most prevalent cancer in the USA, with thousands diagnosed annually. This paper presents an ensemble learning model leveraging deep learning techniques such as Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Bi-directional LSTM (Bi-LSTM) to detect thyroid cancer mutations early. The model is trained on a dataset sourced from asia.ensembl.org and IntOGen.org, consisting of 633 samples with 969 mutations across 41 genes, collected from individuals of various demographics. Feature extraction encompasses techniques including Hahn moments, central moments, raw moments, and various matrix-based methods. Evaluation employs three testing methods: self-consistency test (SCT), independent set test (IST), and 10-fold cross-validation test (10-FCVT). The proposed ensemble learning model demonstrates promising performance, achieving 96% accuracy in the independent set test (IST). Statistical measures such as training accuracy, testing accuracy, recall, sensitivity, specificity, Mathew's Correlation Coefficient (MCC), loss, training accuracy, F1 Score, and Cohen's kappa are utilized for comprehensive evaluation.

Two groups of cotton growers participated in this study; the first, referred as “conventional cotton producers” (CCPs), continues to use traditional techniques. The second group, known as sustainable cotton producers (SCPs), adheres to practices that are socially acceptable, economically feasible, and environment friendly. This study was designed to undertake a thorough socio-economic analysis of CCP and SCP in terms of cost of production, yield, and adaptations for climate change. The data were collected from a total of 275 farming households (138 SCPs and 137 CCPs) from two districts, namely, Bahawalpur and Rajanpur, Punjab, Pakistan. The data were analyzed using the benefit–cost ratio (BCR), paired sampled t-test, and log–log regression model in SPSS. The results of the study revealed that the cost of production for SCP was significantly less than CCP and the value of BCR for SCP is higher than CCP. The results of the study also revealed that the land preparation costs, irrigation costs, and fertilizer and pesticide costs decrease the cotton yield of CCP, while land area owned and picking costs showed no significant influence on the yield of CCP. On the other hand, all cost items except fertilizer cost have a positive impact on CCP’s cotton yield. The results also indicated that SCP farmers adopted more of adaptation practices for climate change than CCP. This study concluded that SCP has significant advantages over CCP. Therefore, it is recommended that the government should prioritize incentives for SCP adoption to enhance yield and environmental sustainability in cotton farming.

Diesel engines are used extensively in heavy-duty transportation due to their high thermal efficiency and energy density, but they also contribute to environmental pollution. Water-in-diesel emulsions have emerged as an alternative method for decreasing NOx and emissions, but there are still obstacles to assuring engine performance and stability. Surfactants are used to stabilise the emulsion by decreasing the interfacial tension between the fuel and water. Studies on water-in-diesel emulsions published literature suggest that chemical surfactants have been used in the production of emulsified fuels. In addition, research have shown that biosurfactants are less harmful to the environment than chemical surfactants. However, only limited study has been conducted on the use of biosurfactants in emulsified fuel. Consequently, it is important to investigate the possible use of biosurfactants in applications using emulsified fuels. This research studies the categorization of surfactants and biosurfactants and emulsion methods for the development of emulsified fuel. This research also aids in the selection of the most suitable surfactant and biosurfactant for applications, particularly in the context of water-in-diesel emulsions and diesel-in-water emulsions, with the goal of developing an environmentally friendly, stable emulsified fuel that can reduce the emission effect and protect the environment.

Water-in-diesel emulsion (WIDE) fuel has been employed to reduce the emissions from diesel engines. Emulsified fuel in combustion chamber experiences secondary atomization, leading to micro-explosions that lower the combustion temperature and improve atomization. As a result, it reduces emissions and improves combustion efficiency. Emulsified fuels often face challenges with water separation over time; therefore, chemical surfactants have traditionally been used to prevent water separation from emulsified fuel. While biosurfactants offer a more environmentally friendly option compared to traditional chemical surfactants, there is a research gap regarding use of emulsified fuel with biosurfactant. This study aims to investigate the effect of biosurfactant concentration on emulsified fuel properties, stability, particles size, and microexplosions. In this study, six emulsified biodiesel fuels were developed with 10 % distilled water and biosurfactants (lecithin 63 % and cocamide DEA 37 %) ranging from 0.5 % to 3.0 %. The emulsion stability and properties of these fuels were examined. Further, Microscopy was employed to examine particle sizes distributions and suspended droplets hot plate technique with high-speed camera was used to record the micro-explosions. The results illustrate increase in biosurfactant concentration in emulsified fuel increases density and viscosity while reducing surface tension, droplet size, and micro-explosion peak temperature.

Abstract Type 1 diabetes mellitus (T1DM) is characterized by absolute insulin deficiency primarily due to autoimmune destruction of pancreatic β‐cells. The prevailing treatment for T1DM involves daily subcutaneous insulin injections, but a substantial proportion of patients face challenges such as severe hypoglycemic episodes and poorly controlled hyperglycemia. For T1DM patients, a more effective therapeutic option involves the replacement of β‐cells through allogeneic transplantation of either the entire pancreas or isolated pancreatic islets. Unfortunately, the scarcity of transplantable human organs has led to a growing list of patients waiting for an islet transplant. One potential alternative is xenotransplantation of porcine pancreatic islets. However, due to inter‐species molecular incompatibilities, porcine tissues trigger a robust immune response in humans, leading to xenograft rejection. Several promising strategies aim to overcome this challenge and enhance the long‐term survival and functionality of xenogeneic islet grafts. These strategies include the use of islets derived from genetically modified pigs, immunoisolation of islets by encapsulation in biocompatible materials, and the creation of an immunomodulatory microenvironment by co‐transplanting islets with accessory cells or utilizing immunomodulatory biomaterials. This review concentrates on delineating the primary obstacles in islet xenotransplantation and elucidates the fundamental principles and recent breakthroughs aimed at addressing these challenges.

In the quest to mitigate excessive CO2 emissions, the electrochemical reduction of CO2 (eCO2R) into multi-carbon fuels and vital chemical precursors emerges as a compelling strategy. Meticulous control of the C–C coupling on a catalyst surface is a grand challenge in the selective production of desired C2+ products. Ethane and propanol are among the most desirable C2+ products in the gas and liquid phase, respectively. Herein, we demonstrate facile femtosecond laser-enabled tuning of Cu selectivity towards ethane and propanol. The laser-enabled tailoring of the Cu surface induces a shift from C1 products to ethane and propanol. This shift in product composition is attributed to the concurrent creation of hierarchical porous structures, the stabilization of {111}, {200}, and {220} Cu2O facets, and the promotion of the Cu1+ oxidation state. These alterations collectively enhance the adsorption strength, leading to an increased propensity for C-C coupling and, consequently, an elevated selectivity toward C2+ products.

Researchers are investigating eco-friendly binders like coconut shell ash (CSA), metakaolin (MK), and calcined clay (CC) as supplementary cementitious materials (SCM) in high-strength concrete (HSC). Abundantly available as industrial or agricultural waste, these materials, when combined with Portland cement (PC), offer synergistic benefits. This not only improves concrete performance but also addresses waste disposal issues, presenting a sustainable and environmentally friendly solution for long-term use in HSC production. However, this study performed on fresh and mechanical characteristics of HSC blended with CSA, MK, and CCA alone and together as SCM after 28 days of curing. A total of 504 samples of standard concrete were cast and the cubical samples were tested to achieve the targeted compressive strength about 80 MPa after 28 days. The experimental results indicated that the rise in tensile, flexural and compressive strengths of 9.62%, 8.27%, and 10.71% at 9% of CSA, MK, and CC as SCM after 28 days of curing. As SCM content increases, the density, porosity and water absorption of concrete decrease. Moreover, the workability of fresh concrete is getting reduced when the concentration of SCMs increases in HSC. In addition, the concrete's sustainability assessment revealed that employing 18% MK, CC, and CSA as SCM reduced carbon emissions by approximately 11.78%. It is suggested that using 9% CC, MK and CSA together in HSC yields the best results for practical applications in civil engineering.

Abstract Drug-to-drug interaction (DDIs) occurs when a patient consumes multiple drugs. Therefore, it is possible that any medication can influence other drugs’ effectiveness. The drug-to-drug interactions are detected based on the interactions of chemical substructures, targets, pathways, and enzymes; therefore, machine learning (ML) and deep learning (DL) techniques are used to find the associated DDI events. The DL model, i.e., Convolutional Neural Network (CNN), is used to analyze the DDI. DDI is based on the 65 different drug-associated events, which is present in the drug bank database. Our model uses the inputs, which are chemical structures (i.e., smiles of drugs), enzymes, pathways, and the target of the drug. Therefore, for the multi-model CNN, we use several layers, activation functions, and features of drugs to achieve better accuracy as compared to traditional prediction algorithms. We perform different experiments on various hyperparameters. We have also carried out experiments on various iterations of drug features in different sets. Our Multi-Modal Convolutional Neural Network - Drug to Drug Interaction (MCNN-DDI) model achieved an accuracy of 90.00% and an AUPR of 94.78%. The results showed that a combination of the drug’s features (i.e., chemical substructure, target, and enzyme) performs better in DDIs-associated events prediction than other features.

Abstract In this manuscript, we implement the travelling wave solutions of the fractional (3+1) generalized computational nonlinear wave equation with gas bubbles via application of five mathematical methods. Liquids with gas bubbles primarily arise in various applications like science, engineering, and mathematical physics. The obtained solitary waves solutions have fruitful applications in engineering, science, life, nature and physics. Several novel soliton solutions of concerned model are established in the form of hyperbolic, trigonometric, exponential and rational functions. To handle all calculations and verification of obtained results, computational software Mathematica 12.1 is used. For the demonstration of the physical behaviour of concern model, some solutions are plotted graphical in 2-dimensional and 3-dimensional by imparting specific values to the parameters under constrain conditions. Finally, we intrigue both two and three dimensional to explain the physical behavior of the model.

Along-with the basic principles of Islamic jurisprudence the Quran and Sunnah, there are other legal supporting sources agreed upon by Muslims. Among these stands Ijma’ (Consensus legal Opinion) as the third primary source. This research studies the status of Ijma Fiqh Ja’fri and Fiqh Hanafi, by comparing the both schools, discussing the main concept of Ijma, its conditions, types and ways of implementations of its decisions. Both schools of thought have some commonalities and there are also some differences on its attainment. For example, in Jafari jurisprudence, it is not required that all jurists of the time must agree upon an opinion to be established. Instead, the important part of Ijma is the statement of an Imam. If the consensus includes a statement from one of the Imams of the Ahl al-Bayt or if it is generally known that the opinion of any Imam is included in the consensus, then it is considered an authority. On the other hand, in the Hanafi school of thought, the consensus of all jurists of the time is a prerequisite for Ijma. This article is an attempt to analyze perspectives of both schools of thought and present a comparative assessment of both theories comprehensively.

The intricate architecture of the intestinal epithelium, crucial for nutrient absorption, is constantly threatened by environmental factors. The epithelium undergoes rapid turnover, which is essential for maintaining homeostasis, under the control of intestinal stem cells (ISCs). The central regulator, Wnt/β-catenin signaling plays a key role in intestinal integrity and turnover. Despite its significance, the impact of environmental factors on this pathway has been largely overlooked. This study, for the first time, investigates the influence of Cd on the intestinal Wnt signaling pathway using a mouse model. In this study, male BALB/c mice were administered an environmentally relevant Cd dose (0.98 mg/kg) through oral gavage to investigate the intestinal disruption and Wnt signaling pathway. Various studies, including histopathology, immunohistochemistry, RT-PCR, western blotting, ELISA, intestinal permeability assay, and flow cytometry, were conducted to study Cd-induced changes in the intestine. The canonical Wnt signaling pathway experienced significant downregulation as a result of sub-chronic Cd exposure, which caused extensive damage throughout the small intestine. Increased intestinal permeability and a skewed immune response were also observed. To confirm that Wnt signaling downregulation is the key driver of Cd-induced gastrointestinal toxicity, mice were co-exposed to LiCl (a recognized Wnt activator) and Cd. The results clearly showed that the harmful effects of Cd could be reversed, which is strong evidence that Cd mostly damages the intestine through the Wnt/β-catenin signalling axis. In conclusion, this research advances the current understanding of the role of Wnt/β catenin signaling in gastrointestinal toxicity caused by diverse environmental pollutants.

Time synchronization among smart city nodes is critical for proper functioning and coordinating various smart city systems and applications. It ensures that different devices and systems in the smart city network are synchronized and all the data generated by these devices is consistent and accurate. Synchronization methods in smart cities use multiple timestamp exchanges for time skew correction. The Skew Integrated Timestamp (SIT) proposed here uses a timestamp, which has time skew calculated from the physical layer and uses just one timestamp to synchronize. The result from the experiment suggests that SIT can be used in place of multiple timestamp exchanges, which saves computational resources and energy.

ABSTRACT: Essential oils (EO), ascorbic acid, sugars, carotenoids, flavonoids, dietary fiber, polyphenols, and trace minerals are found in citrus residue. It gives animals energy and promotes health. On a dry matter basis, the citrus pulp is composed of 7% crude protein, 14% crude fiber, 21.6% nitrogen detergent fiber, 2.5% fat, 24.4% total sugars, and 12.1% ME MJ/kg. It has been reported that the natural antioxidant content of citrus pulp has a beneficial effect on growth and microbial and immunological parameters. The literature indicates that the ultimate weight and weight gain of poultry are significantly (P > 0.05) greater with 7.5% inclusion. Growing knowledge of the health benefits of lactic acid bacteria (LAB) in producing beneficial metabolites has led to interest in developing LAB-containing products for use in biofeed businesses. The consumption of fermented citrus residue significantly decreased blood cholesterol levels. Fermentation results in the production of many compounds (including organic acids, exopolysaccharides, bioactive peptides, phenolic compounds, and gamma-aminobutyric acid), which have many multidimensional functions for maintaining the health and well-being of poultry. During fermentation, the pH may quickly decrease, and harmful bacterial and fungal organisms may be substantially retarded at the early stage of ensiling. The published literature has shown that the fermentation of citrus waste with different probiotic strains, such as Lactobacillus acidophilus, Limosilactobacillus fermentum, Lactiplantibacillus plantarum, Pediococcus pentocaseus, and Lacticaseiobacillus paracasei, in the diet has fantastic effects on the conversion of citrus waste into fermented high-quality feed with extended shelf life and sensory value. Citrus waste lactic acid fermentation may be a viable option for producing nutritional biofeed for poultry, but there is a lack of related research on poultry, so more research on food-grade bacterial fermentation is needed.

The Fractional Nonlinear Schrödinger Model (FNLSM) with Kerr law nonlinearity, a popular model for simulating a variety of physical events, is the subject of this study. Our research has two main goals. First, we want to identify novel soliton solutions for the FNLSM with Kerr law nonlinearity, including bright, single, exponential, periodic, hyperbolic, dark and combinations thereof. We use a modified Sardar sub-equation technique to achieve these solutions, which have not yet been published. Secondly, demonstrate that the model is stable and sensitive, examine its modulation instability and sensitivity analysis. To validate the physical relevance of our results, we present 2D, 3D and contour plots with appropriate parameter values. Our results indicate that this research's methodology is effective computationally faster and provides comprehensive and standard solutions. In engineering, computational physics and fiber optics, it can be helpful in resolving more complicated occurrences. By offering novel approaches to currently studied features of FNLSM, this paper advances computational physics. The results that have been presented illustrate the potential for our method to fundamentally alter how FNLSM is understood and modeled. In this dynamic field, we believe that our research offers novel opportunities for investigation and advancement. To the best of our knowledge, this study represents a unique approach to investigating the FNLSM with Kerr law nonlinearity.

A non-linear dynamic model describing the spread of any infectious disease, based on different categories of individuals: susceptible (S), exposed (E), infected (I), quarantined (Q), recovered (R), dead (D), and vaccinated (V) is presented. The aim of the analysis is to develop a sensitivity technique for fuzzy systems, leveraging the application of fuzzy set theory and its differential calculus. This designed method can significantly generate the sensitivity profile of each measured model output with respect to varying values of input parameters. Additionally, the collective influence of all parameters sensitivities on model is simulated in terms of system sensitivities. Numerical simulations by MATLAB, demonstrate the solution of the fuzzy model and its sensitivities concerning the impreciseness, thereby developing a more generalized and accurate disease model.

Traditional medicines are becoming more popular as people become more aware of the dangers of synthetic pharmaceuticals. Tribulus terrestris L., (Gokharu) an annual herbaceous plant, has been extensively utilized by herbalists for numerous medicinal purposes. T. terrestris has been studied for its multiple therapeutic effects, including immunomodulatory, aphrodisiac, anti-urolithic, absorption enhancer, cardioprotective, antidiabetic, anti-inflammatory, hypolipidemic, neuro-protective, anticancer, and analgesic properties. Saponins and flavonoids are two examples of beneficial substances that have recently been found in T. terrestris. These chemicals are very important for a variety of therapeutic effects. Numerous studies have shown that T. terrestris products and various parts may have antioxidant, anti-inflammatory, anti-cancer, anti-diabetic, testosterone-boosting, and liver protective effects. According to the published evidence, T. terrestris boosts testosterone secretion, regulates blood pressure, and protects the human body against injuries. The cardiovascular, reproductive, and urinary systems are all severely impacted. Due to its potent bioactive compounds, the literature evaluated from a wide range of sources including books, reports, PubMed, ScienceDirect, Wiley, Springer, and other databases demonstrated the extraordinary potential to treat numerous human and animal ailments. Our review is different from other published articles because we explored its importance for humans and especially in veterinary like poultry health. It could also be used as an aphrodisiac to treat different fertility-related disorders in human and animal science. More research into the pharmacodynamics of herbs like T. terrestris is needed so that it can be used in a wider variety of nutraceutical products for humans and poultry.

Fractional order algorithms demonstrate superior efficacy in signal processing while retaining the same level of implementation simplicity as traditional algorithms. The self-adjusting dual-stage fractional order least mean square algorithm, denoted as LFLMS, is developed to expedite convergence, improve precision, and incurring only a slight increase in computational complexity. The initial segment employs the least mean square (LMS), succeeded by the fractional LMS (FLMS) approach in the subsequent stage. The latter multiplies the LMS output, with a replica of the steering vector (Ŕ) of the intended signal. Mathematical convergence analysis and the mathematical derivation of the proposed approach are provided. Its weight adjustment integrates the conventional integer ordered gradient with a fractional-ordered. Its effectiveness is gauged through the minimization of mean square error (MSE), and thorough comparisons with alternative methods are conducted across various parameters in simulations. Simulation results underscore the superior performance of LFLMS. Notably, the convergence rate of LFLMS surpasses that of LMS by 59%, accompanied by a 49% improvement in MSE relative to LMS. So it is concluded that the LFLMS approach is a suitable choice for next generation wireless networks, including Internet of Things, 6G, radars and satellite communication.

The stochastic nonlinear Schrödinger model (SNLSM) in (1+1)-dimension with random potential is examined in this paper. The analysis of the evolution of nonlinear dispersive waves in a totally disordered medium depends heavily on the model under investigation. This study has three main objectives. Firstly, for the SNLSM, derive stochastic precise solutions by using the modified Sardar sub-equation technique. This technique is efficient and intuitive for solving such models, as shown by the generated solutions, which can be described as trigonometric, hyperbolic, bright, single and dark. Secondly, for obtaining numerical solutions to the SNLSM, the algorithms described here offer an accurate and efficient technique. Lastly, investigate the phase plane analysis of the perturbed and unperturbed dynamical system and the time series analysis of the governing model. The results show that the numerical and analytical techniques can be extended to solve other nonlinear partial differential equations in physics and engineering. The results of this study have a significant impact on how well we comprehend how solitons behave in physical systems. Additionally, they may serve as a foundation for the development of improved numerical techniques for handling challenging nonlinear partial differential equations.

In this paper, we examine the solitary wave solutions of the generalised (2 + 1) extended Kadomtsev–Petviashvili (eKP) equation, which is used as model for the surface waves and internal waves in straits or channels and describes the dynamics of nonlinear waves in plasma physics and fluid dynamics. We secure distinct soliton solutions by employing two amelioration methodologies, namely the improved F-expansion method and the new Kudryashov method. These methods explore several unique forms of solitary wave solutions, including dark, rational, singular, periodic, and exponential ones. In order to illustrate propagation of some reported wave solutions, the graphs associated with these solutions are presented by choosing appropriate parametric values in 2D, 3D, contour, and density plots with the use of the symbolic software Mathematica 13.0. The presented solutions realize very significant fact for investigation the qualitative interpretations for various phenomena in our nature. The computed solutions revealed that the applied methods are influential, efficious and skilful and can be a best way to handle other higher order nonlinear evolution equations.

In this study, the satellite data of ASTER and Landsat 8 OLI were used for the discrimination of lithological units covering the Khyber range. Of the 24 tested band combinations, the most suitable include 632 and 468 of ASTER and 754 and 147 of OLI in the RGB sequence. The data were also tested with two conventional machine learning algorithms (MLAs), namely maximum likelihood classification (MLC) and support vector machine (SVM), for lithological mapping. Principal component analysis (PCA), minimum noise fraction (MNF), band ratios, and color composites in combination with available lithological maps and field data were utilized for training sample collection for the MLC and SVM models to classify the lithological units. The accuracy assessment of SVM and MLC was performed using a confusion matrix, which revealed a higher accuracy of 74.8419% and 72.1217% for ASTER and an accuracy of 58.4833% and 60.0257% for OLI, respectively. The results indicate that ASTER imagery is more suitable for lithological discrimination in the study area due to its high spectral resolution in the VNIR to SWIR range. The experiment revealed that the SVM classification offered the highest overall accuracy of nearly 75% and the kappa coefficient value of 0.7 on ASTER data. This demonstrates the effectiveness of SVM classification in exploring lithological mapping in dry to semi-arid regions.

The current study explores the prospective of a nitrogen-doped graphene (NG) incorporated into ZnSe-TiO2 composites via hydrothermal method for supercapacitor electrodes. Structural, morphological, and electronic characterizations are conducted using XRD, SEM, Raman, and UV analyses. The electrochemical study is performed and galvanostatic charge-discharge (GCD) and cyclic voltammetry (CV) are evaluated for the supercapacitor electrode material. Results demonstrate improved performance in the ZnSe-NG-TiO2 composite, indicating its potential for advanced supercapacitors with enhanced efficiency, stability, and power density. Specific capacity calculations and galvanic charge-discharge experiments confirmed the promising electrochemical activity of ZnSe-NG-TiO2, which has a specific capacity of 222 C/g. The negative link among specific capacity and current density demonstrated the composite’s potential for high energy density and high-power density electrochemical devices. Overall, the study shows that composite materials derived from multiple families can synergistically improve electrode characteristics for advanced energy storage applications.

A vast range of pesticides have been routinely employed for plant protection throughout the last few decades. Pesticides can enter non-target organisms in various ways, posing health hazards. Exposure to different environmental pollutants, including pesticides, can affect the human gut flora. Metabolites generated from the gut microbiota play an essential role in the host’s health by regulating metabolic homeostasis. A disruption in this equilibrium can lead to the emergence of numerous illnesses and their etiology. Pesticides have been shown in a few recent studies to harm the host’s gut microbiome. As a result, there is an urgent need to investigate the impact of pesticides on gut microbiota-mediated immunity. Metabolic alterations in the host may give a better understanding of pesticide-induced harm. This review highlights the potential consequences of pesticide exposure on gut microbiota composition and function, mainly focusing on how it might alter the production of secondary metabolites with potential downstream implications for host health.

Helicobacter pylori (H. pylori) is a Gram-negative bacterium that colonizes the gastric mucosa and is associated with various gastrointestinal disorders. H. pylori is a pervasive pathogen, infecting nearly 50% of the world’s population, and presents a substantial concern due to its link with gastric cancer, ranking as the third most common cause of global cancer-related mortality. This review article provides an updated and comprehensive overview of the current understanding of H. pylori infection, focusing on its pathogenesis, diagnosis, and treatment strategies. The intricate mechanisms underlying its pathogenesis, including the virulence factors and host interactions, are discussed in detail. The diagnostic methods, ranging from the traditional techniques to the advanced molecular approaches, are explored, highlighting their strengths and limitations. The evolving landscape of treatment strategies, including antibiotic regimens and emerging therapeutic approaches, is thoroughly examined. Through a critical synthesis of the recent research findings, this article offers valuable insights into the contemporary knowledge of Helicobacter pylori infection, guiding both clinicians and researchers toward effective management and future directions in combating this global health challenge.

Genes, expressed as sequences of nucleotides, are susceptible to mutations, some of which can lead to cancer. Machine learning and deep learning methods have emerged as vital tools in identifying mutations associated with cancer. Thyroid cancer ranks as the 5th most prevalent cancer in the USA, with thousands diagnosed annually. This paper presents an ensemble learning model leveraging deep learning techniques such as Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Bi-directional LSTM (Bi-LSTM) to detect thyroid cancer mutations early. The model is trained on a dataset sourced from asia.ensembl.org and IntOGen.org, consisting of 633 samples with 969 mutations across 41 genes, collected from individuals of various demographics. Feature extraction encompasses techniques including Hahn moments, central moments, raw moments, and various matrix-based methods. Evaluation employs three testing methods: self-consistency test (SCT), independent set test (IST), and 10-fold cross-validation test (10-FCVT). The proposed ensemble learning model demonstrates promising performance, achieving 96% accuracy in the independent set test (IST). Statistical measures such as training accuracy, testing accuracy, recall, sensitivity, specificity, Mathew's Correlation Coefficient (MCC), loss, training accuracy, F1 Score, and Cohen's kappa are utilized for comprehensive evaluation. [ABSTRACT FROM AUTHOR]

Fractional order algorithms demonstrate superior efficacy in signal processing while retaining the same level of implementation simplicity as traditional algorithms. The self-adjusting dual-stage fractional order least mean square algorithm, denoted as LFLMS, is developed to expedite convergence, improve precision, and incurring only a slight increase in computational complexity. The initial segment employs the least mean square (LMS), succeeded by the fractional LMS (FLMS) approach in the subsequent stage. The latter multiplies the LMS output, with a replica of the steering vector (Ŕ) of the intended signal. Mathematical convergence analysis and the mathematical derivation of the proposed approach are provided. Its weight adjustment integrates the conventional integer ordered gradient with a fractional-ordered. Its effectiveness is gauged through the minimization of mean square error (MSE), and thorough comparisons with alternative methods are conducted across various parameters in simulations. Simulation results underscore the superior performance of LFLMS. Notably, the convergence rate of LFLMS surpasses that of LMS by 59%, accompanied by a 49% improvement in MSE relative to LMS. So it is concluded that the LFLMS approach is a suitable choice for next generation wireless networks, including Internet of Things, 6G, radars and satellite communication. [ABSTRACT FROM AUTHOR]