Browse Items (14421 total)
Sort by:
-
Metabolomics Pathway Prediction Using Enhanced-Graph Convolutional Networks with Graph Attention Networks
Metabolomics, the comprehensive study of small molecules in biological systems, has a central role to play in the diagnosis of diseases, biomarker detection, and the design of new drugs. Although there have been major breakthroughs in analytical toolsets such as mass spectrometry (MS) coupled with chromatography, it is hard to predict metabolomics pathways because biochemical interactions are inherently complex. To meet this end, the current research suggests a deep learning-based approach using graph neural networks (GNN), which have shown high efficiency for graph-structured biological data. We specifically propose an enhanced graph convolutional network integrated with graph attention networks (EGCNGAT) to enhance pathway prediction performance. The hybrid framework employs graph convolutional networks (GCN) to represent molecular structural data and graph attention networks (GAT) to provide context-sensitive feature importance, thus improving the models capacity for learning complex pathway patterns. Comparative experiments against current deep learning approaches show that the introduced EGCN-GAT model obtains an accuracy of 98.90 percent, which is a 0.26 percent increase compared to the baseline MLGL-MP model. In addition, it demonstrates a 0.94 percent gain in precision as well as a slight gain in recall. The findings validate the performance of the proposed method and highlight its utility for developing pathway-level predictions in metabolomics studies. 2025 by the authors of this article. Published under CC-BY. -
Metaheuristic Machine Learning Algorithms for Liver Disease Prediction
In machine learning, optimizing solutions is critical for improving performance. This study explores the use of metaheuristic algorithms to enhance key processes such as hyperparameter tuning, feature selection, and model optimization. Specifically, we integrate the Artificial Bee Colony (ABC) algorithm with Random Forest and Decision Tree models to improve the accuracy and efficiency of disease prediction. Machine learning has the potential to uncover complex patterns in medical data, offering transformative capabilities in disease diagnosis. However, selecting the optimal algorithm for model optimization presents a significant challenge. In this work, we employ Random Forest, Decision Tree models, and the ABC algorithmbased on the foraging behaviours of honeybeesto predict liver disease using a dataset from Indian medical records. Our experiments demonstrate that the Random Forest model achieves an accuracy of 85.12%, the Decision Tree model 76.89%, and the ABC algorithm 80.45%. These findings underscore the promise of metaheuristic approaches in machine learning, with the ABC algorithm proving to be a valuable tool in improving predictive accuracy. In conclusion, the integration of machine learning models with metaheuristic techniques, such as the ABC algorithm, represents a significant advancement in disease prediction, driving progress in data-driven healthcare. 2024, Iquz Galaxy Publisher. All rights reserved. -
Metaheuristic Optimization of Deep Learning Models for Land Cover Classification Using Remote Sensing Data
Deep learning techniques have greatly advanced land-cover classification from remote sensing imagery, but their performance depends critically on choosing optimal hyperparameters. Manually tuning hyperparameters (e.g., learning rate, network depth, dropout rate) is time-consuming and often suboptimal. Metaheuristic algorithms offer an automated approach to this problem. In this work, we compare five metaheuristic optimizersParticle Swarm Optimization (PSO), Genetic Algorithm (GA), Differential Evolution (DE), African Vulture Optimization Algorithm (AVOA), and an Enhanced Dipper Throat Optimization Algorithm (EDTOA)for hyperparameter tuning of convolutional neural networks (CNNs), a ResNet-50, and a U-Net. We evaluate these methods on two benchmark land-cover datasets: EuroSAT (patch-level multispectral image classification) and DeepGlobe (pixel-wise satellite image segmentation). Our data preprocessing includes normalization, data augmentation, and computing spectral indices (e.g., NDVI) to enrich the feature set. Each metaheuristic searches the hyperparameter space to maximize validation accuracy (for EuroSAT) or mean Intersection-over Union (mIoU) (for DeepGlobe). In addition to predictive performance, we analyze the computational cost (wall-clock time, epochs to convergence, GPU usage) of each optimizer to assess the trade-off between efficiency and accuracy. AVOA and EDTOA achieve the best results on both datasets (e.g., up to 98.5% accuracy on EuroSAT and 56% mIoU on DeepGlobe), outperforming the PSO, GA, and DE baselines while offering favorable cost-performance balance. These findings demonstrate that advanced metaheuristics can significantly improve deep model performance in land-cover classification. Our contributions include a comprehensive experimental comparison of five optimizers, a detailed methodology integrating spectral index features, a cost performance analysis, and reference results to guide future research. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Metaheuristicsbased Task Offloading Framework in Fog Computing for Latency-sensitive Internet of Things Applications
The Internet of Things (IoT) applications have tremendously increased its popularity within a short span of time due to the wide range of services it offers. In the present scenario, IoT applications rely on cloud computing platforms for data storage and task offloading. Since the IoT applications are latency-sensitive, depending on a remote cloud datacenter further increases the delay and response time. Most of the IoT applications shift from cloud to fog computing for improved performance and to lower the latency. Fog enhances the Quality of service (QoS) of the connected applications by providing low latency. Different task offloading schemes in fog computing are proposed in literature to enhance the performance of IoT-fog-cloud integration. The proposed methodology focuses on constructing a metaheuristic based task offloading framework in the three-tiered IoT-fog-cloud network to enable efficient execution of latency-sensitive IoT applications. The proposed work utilizes two effective optimization algorithms such as Flamingo search algorithm (FSA) and Honey badger algorithm (HBA). Initially, the FSA algorithm is executed in an iterative manner where the objective function is optimized in every iteration. The best solutions are taken in this algorithm and fine tuning is performed using the HBA algorithm to refine the solution. The output obtained from the HBA algorithm is termed as the optimized outcome of the proposed framework. Finally, evaluations are carried out separately based on different scenarios to prove the performance efficacy of the proposed framework. The proposed framework obtains the task offloading time of 71s and also obtains less degree of imbalance and lesser latency when compared over existing techniques. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Metal and Ligand-Free Approach Towards the Efficient One-Pot Synthesis of Dipyridopyrimidinimine Derivatives
We report a facile, expeditious, user-friendly, and convenient metal-free synthesis employing base catalysis in a one-pot procedure to construct 11H-dipyrido[1,2-a : 3?,2?-d]pyrimidin-11-imine derivatives. This protocol involves a domino process leading to the formation of double C?N bonds utilising KOtBu as the base and DMAc as the superior solvent at 25 C for 2 h. The versatility of this methodology was demonstrated by its successful application to substrates with both electron-withdrawing and electron-donating functional groups, yielding novel functionalized stable 11H-dipyrido[1,2-a : 3?,2?-d]pyrimidin-11-imine derivatives in good to excellent yields. Additionally, we have discussed a plausible reaction pathway for the synthesis. 2024 Wiley-VCH GmbH. -
Metal and Metal Oxide Nanoparticles in Textile Applications
In today's consumer-driven market, textiles are valued not only for their aesthetic appeal but also for their functional protection properties. The use of nanoparticles for specialty finishing has emerged as a promising area in textile processing and engineering. Among these nanoparticles, inorganic metal and metal oxides are particularly significant due to their large surface area and high surface energy, allowing them to impart multifunctional properties to textiles. Metal and Metal Oxide Nanoparticles in Textile Applications serves as a comprehensive guide, offering authors a profound understanding of the application of various metal and metal oxide nanoparticles on textiles. The content is thoughtfully organized, beginning with the first five chapters providing insights into the introduction of metal nanoparticles, their conventional and advanced synthesis methods, and characterization techniques. Subsequently, the following eight chapters delve into the effects of different metal nanoparticles, such as Ag, Au, Cu, Al, Ti, and others, along with their oxides, on textiles. The final section of the book encompasses chapters covering metal nanocomposites, electrospinning techniques, toxicology considerations, branding applications, and the challenges and future prospects of metal nanoparticles on textiles. This title serves as an invaluable asset to academicians, scholars, researchers, and professionals in the industry. 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies. -
Metal organic frameworks in biomedicine: Innovations in drug delivery
Metal-organic frameworks (MOFs) have emerged as a class of versatile materials, finding extensive applications in drug delivery because of their unique properties and flexible design. This comprehensive review aims to give a broad perspective on the recent advancements in the area of drug delivery applications using MOFs. The fundamental characteristics of MOFs, highlighting their exceptional porosity, high surface area, and tuneable framework structures, enable MOFs to serve as ideal drug carriers, allowing efficient drug loading and controlled release. The review delves into the various ligands and metal ions employed for drug encapsulation. These include physical encapsulation, covalent bonding, and host-guest interactions, each offering distinct advantages for diverse types of drugs and therapeutic applications. The importance of tailoring MOF properties to optimize drug loading capacity, stability, and release kinetics has been emphasized. Additionally, the explorations involve delving into the mechanisms of drug release from MOFs, with factors such as pH, temperature, and external stimuli that can be harnessed to trigger controlled drug release. The utilization of MOFs in combination therapies, such as co-delivery of multiple drugs or integrating imaging agents, has also been examined. Numerous examples of MOFs used for drug delivery, encompassing both in-vitro and in-vivo studies, covering a wide range of therapeutic areas, including cancer treatment, antimicrobial therapy, and targeted drug delivery, are included. Additionally, the review addresses the challenges and future perspectives in the development of MOFs for drug delivery. Strategies to improve MOF stability, biocompatibility, and scalability are discussed, along with the understanding of MOF-drug interaction and potential toxicity concerns. With their tuneable properties, high loading capacities, and controlled release capabilities, MOFs hold exceptional capabilities that promise to enhance the efficacy of therapeutic interventions. Continued research and development in this area can pave way for the translation of MOFs into clinical applications in the near future. 2024 The Author(s) -
Metal Organic Frameworks to Remove Arsenic Adsorption from Wastewater
Water is an integral part of life on earth. Rapid industrialization, urbanization, and population explosion have all contributed to the pollution of ground and surface water with, among other things, heavy metals. This has led to an acute shortage of clean drinking water. Arsenic is one of the most toxic heavy metals found in water, posing a serious threat to the environment, human beings, and aquatic life. Over the years, a considerable amount of research has been directed toward the elimination of arsenic from water via sustainable methodologies. Metal organic frameworks are a class of materials possessing exceptional features like chemical stability, high porosity, multiple functional groups, and large surface areas. These properties can be effectively channelized to make metal organic frameworks excellent adsorbents for the removal of arsenic from contaminated water and make it drinkable. We have reviewed herein, the problems of heavy metal contamination, specifically the different forms of arsenic that pollute water. The importance of metal organic frameworks and the progress made in the synthesis of materials having a metal oxide framework have been discussed. Significant properties like adsorption and mechanistic aspects of adsorption through metal organic frameworks have been described. Furthermore, the characterization of the electronic and geometric aspects of metal organic frameworks using density functional theory has been reviewed. Insight into proper scaling up and development of metal organic frameworks for practical applications have also been suggested. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Metal-Based Nanoparticles for Infectious Diseases and Therapeutics
Infectious diseases that are easily transmitted by microorganisms like bacteria, protozoa, fungus, etc. are a menace to humans. The greatest threat to human race is to mitigate the impact of these diseases. People with less immunity and children are prone to these diseases. Even healthy people get infected due to its easy transmission. Microorganisms causing these diseases are becoming more resistant to the drugs that are available in the market. So, there is a need to find new therapeutic which is facile, sensitive, and selective, is an important challenge for the medical field and this is where nanotechnology is having a greater chance. Nanoparticles especially metal-based nanoparticles have the ability to act against infectious and non-infectious diseases, this is because of their unique properties like small size, high surface area, etc. They do not have a specific binding site on the bacterial cell, which lead to the failure of bacterial resistant towards the nanoparticle mechanism. There are many nanoparticles which are efficient against particular diseases. In this review we are discussing about the advanced nanomaterials as therapeutics for infectious diseases. We have also discussed about antiviral activities which gives us a ray of hope for the solution of the SARS-COV-2. The Editor(s) (if applicable) and The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2022. -
Metallic silver and copper oxide nanoparticles: Uses in food preservation and impacts on the environment
This review examines the applications of metallic silver and copper oxide nanoparticles in food preservation, emphasizing their potential to revolutionize food packaging and reduce environmental pollution through enhanced waste management strategies. Synthesis of these nanoparticles via green methods including bacteria-, fungi-, and plant-mediated approaches have been discussed. The antimicrobial properties and toxicity of silver and copper oxide nanoparticles have been evaluated highlighting their efficiency in inhibiting microbial growth and extending the shelf life of food products. Regulatory policies governing the use of these nanoparticles in food packaging have been analyzed along with the exploration of active packaging technologies that leverage their unique properties. By integrating advances in nanotechnology with better food formulations, this review underscores the transformative impact of silver and copper oxide nanoparticles on food safety and environmental sustainability, offering insights into the future directions for research and newer applications. 2024 -
Metalsemiconductormetal visible photodetector based on Al-doped (Cd:Zn)S nano thin films by hydrothermal synthesis
High quality undoped and Al-doped nanocrystalline (Cd:Zn)S films [CZS and ACZS] were deposited on glass substrates by hydrothermal assisted chemical bath deposition. The Al concentration was varied from 0.5 mol.% to 2 mol.% in steps of 0.5 mol.% replacing cadmium while keeping other deposition parameters constant. XRD, SEM, and EDX were used to observe crystallinity, morphology and composition of the as prepared samples. X-ray diffraction revealed the hexagonal phase of CZS films with prominent orientation along the (002) plane. XPS analysis was used to confirm the doping concentration of Al in to CZS lattice. Repeatable photoresponse was recorded under 100 s cycle light-on and light-off conditions. 1 mol.% Al doped film being optimised as good photoconductor; a photodetector was fabricated with Ag/ACZS/Ag device structure. The ACZS photodetector exhibits similar time response, good photocurrent reproducibility and a sharp photoresponse at blue radiation with high photo-dark current ratio of 95. The device exhibits peak responsivity of 3.48 mA W?1 and detectivity of 1.26 1011 Jones at 470 nm. These properties suggest that the ACZS photodetector holds great potential for application in high-performance visible photodetectors, especially in the blue region. 2021 Elsevier GmbH -
Metamaterial Integrated Patch Antenna Design with Enhanced Gain for WLAN and WIMAX Applications
In this paper a dual-band high gain metamaterial antenna is designed using RT Duroid 5880 with overall size of 50 60 mm2 and thickness of 1.64 mm. A rectangular patch antenna with two slots is designed to operate at 3.5 and 5.8GHz for Worldwide Interoperability for Microwave Access (WiMAX) and Wireless local area network (WLAN) applications. Further, to enhance the gain characteristics of patch antenna, a reflective metasurface (RMS) is designed on FR-4 substrate, which is placed as a superstrate above the antenna. The metasurface used as superstrate is placed at the air gap of 15 mm to achieve optimum gain and bandwidth. It is observed that the proposed metamaterial integrated antenna shows enhanced gain of 6.5 and 7.73 dBi at both the resonant frequencies. The designed antenna is a good candidate for various WLAN and WiMAX applications. 2025 IEEE. -
MetaMinds and digital realms: Deciphering Gen Z consumer behavior in metaverse marketing
This conceptual research paper explores the innovative convergence of virtual reality (VR), augmented reality (AR), and digital spaces as it dives into the complex dynamics of Gen Z consumer behavior within the metaverse. Businesses and scholars alike face hurdles in comprehending the complex preferences, motives, and decision-making processes of this generation of digital natives, as traditional marketing tactics undergo a metamorphosis in the aftermath of the metaverse. Understanding the nuances of Gen Z's interactions in this immersive digital world is crucial for businesses looking to connect and engage with this significant consumer generation as the metaverse becomes an increasingly important part of everyday life. Thus, this study also attempts to understand the awareness about metaverse among Gen Z and the challenges faced during the act of purchase in a meta environment. 2025 by Priyakrushna Mohanty, Aarthy Chellasamy and Aishwarya Nagarathinam. All rights reserved. -
Metaverse for Sustainable Development: Trends and Applications
Unlock the future of technology and sustainable development by purchasing Metaverse for Sustainable Development: Trends and Applications, a comprehensive guide that delves into immersive application building, groundbreaking innovations, and the transformative potential of the metaverse across various industries. Metaverse for Sustainable Development: Trends and Applications explains the fine details of metaverse application building, demonstrating how integrated platforms in association with a suite of tools come in handy for enabling application construction. The metaverse is the next big thing influenced by virtual and augmented reality paradigms. This user experience will be more immersive and mesmerizing, empowering innovative, disruptive, and transformative technologies to create a spectacular platform for visualizing and realizing business-critical and people-centric metaverse systems. This book explores various metaverse models for healthcare information systems, including the latest technologies, such as the Brain-Computer Interface. Through real-world data and case studies, readers will gain a comprehensive understanding of the metaverses potential for the Internet of Things, blockchain, artificial intelligence, 5G, and 3D modelling for creating and sustaining immersive virtual worlds. Metaverse for Sustainable Development: Trends and Applications is a vital resource for understanding the end-to-end implementation of metaverse technologies. 2025 Scrivener Publishing LLC. -
Metaverse marketing: a review and future research agenda
Purpose: The metaverse represents a rapidly evolving digital environment that blurs the lines between physical and virtual reality, and it offers unique opportunities and challenges for businesses and marketers. The purpose of this study is to provide a comprehensive review of metaverse marketing research. The present study reviews the literature on metaverse to identify theories, contexts, gaps and methodologies using TCCM framework (Theories, Contexts, Characteristics and Methodology) to set a future research agenda. Design/methodology/approach: A review was conducted of 179 English papers related to metaverse marketing from 2010 to 2023 from the Scopus and Web of Science core collection after applying relevant filters using the TCCM framework. Findings: The findings suggest that the studies have inadequately distinguished metaverse as something that only builds interactive experiences that combine the virtual environment and the real world, whereas the theoretical domain of metaverse is dominated by studies in various domains. The applicability of metaverse marketing research is pertinent in various domains of the management field. The study explores various facets of metaverse marketing to capture its dynamic nature. Research limitations/implications: By presenting a comprehensive review, themes and knowledge gaps of the research on metaverse marketing, this study will enhance research output and provide valuable tools for future research on metaverse. Practical implications: By analyzing metaverse in marketing, the companies will be able to use this concept effectively to formulate innovative marketing strategies and personalized consumer experiences and understand consumer behavior. Furthermore, research into metaverse marketing will be helpful in offering predictions about future trends in consumer behavior, technology adoption and virtual world development. Originality/value: This study provides a thorough analysis of the current state of research on metaverse in marketing and provides a road map for further research in this area. 2024, Emerald Publishing Limited. -
Method of preparing a document for survey instrument validation by experts
Validation of a survey instrument is an important activity in the research process. Face validity and content validity, though being qualitative methods, are essential steps in validating how far the survey instrument can measure what it is intended for. These techniques are used in both scale development processes and a questionnaire that may contain multiple scales. In the face and content validation, a survey instrument is usually validated by experts from academics and practitioners from field or industry. Researchers face challenges in conducting a proper validation because of the lack of an appropriate method for communicating the requirement and receiving the feedback. In this Paper, the authors develop a template that could be used for the validation of survey instrument. In instrument development process, after the item pool is generated, the template is completed and sent to the reviewer. The reviewer will be able to give the necessary feedback through the template that will be helpful to the researcher in improving the instrument. 2021 The Author(s) -
Methodical investigation of filtering algorithms for human brain MRI
Retrieving useful information from the given data through a systematic and organized way can help to learn more about the data in a much better and clear way. Information is hidden in medical images. The medical images like Magnetic Resonance Images (MRI), Computed Tomography (CT), ultrasound, X-ray are suggested by the physicians depending upon the available symptoms of the disease. These medical images contain valuable information about a particular disease in hidden format. Identification of that potentially useful information is crucial in further treatments of a particular disease. In image mining the images are processed and extraction or mining of knowledge is done, to get original, valid, potentially useful, and understandable patterns from the available images. The obtained patterns are a good source for further research work. This research work uses brain Magnetic Resonance Images (MRI) of human beings. Different image filtering algorithms were used to retrieve noise free images. International Science Press. -
Methodologies and Applications of Computational Statistics for Machine Intelligence
With the field of computational statistics growing rapidly, there is a need for capturing the advances and assessing their impact. Advances in simulation and graphical analysis also add to the pace of the statistical analytics field. Computational statistics play a key role in financial applications, particularly risk management and derivative pricing, biological applications including bioinformatics and computational biology, and computer network security applications that touch the lives of people. With high impacting areas such as these, it becomes important to dig deeper into the subject and explore the key areas and their progress in the recent past. Methodologies and Applications of Computational Statistics for Machine Intelligence serves as a guide to the applications of new advances in computational statistics. This text holds an accumulation of the thoughts of multiple experts together, keeping the focus on core computational statistics that apply to all domains. Covering topics including artificial intelligence, deep learning, and trend analysis, this book is an ideal resource for statisticians, computer scientists, mathematicians, lecturers, tutors, researchers, academic and corporate libraries, practitioners, professionals, students, and academicians. 2021, IGI Global. All rights reserved. -
METROLOGICAL IMPACT ON ORANGE FRUIT: A COMPARATIVE ANALYSIS OF DEEP LEARNING MODELS FOR PREDICTING FRUIT DISEASES
This research offers a comprehensive comparative analysis of efficient deep learning models for predicting diseases in orange fruits, with a particular emphasis on the impact of meteorological factors on disease prevalence. Citrus diseases such as Blackspot, Canker, and Greening are significantly influenced by environmental conditions. Recognizing the crucial role of weather conditions in the development and spread of these diseases, we concentrate on enhancing prediction accuracy by integrating Convolutional Neural Networks (CNNs) with various classification algorithms to develop hybrid models that account for meteorological impacts. Specifically, we assess the performance of a CNN combined with Gradient Boosting (CNN-GB) and compare it against other hybrid models such as CNN integrated with Long Short-Term Memory networks (CNN-LSTM), Support Vector Machines (CNN-SVM), and Random Forest classifiers (CNN-Random Forest). These models are evaluated using different optimization algorithms to determine the most effective approach for disease prediction under varying meteorological conditions. A meticulously curated dataset comprising 1,600 training images and 300 testing images of orange fruits exhibiting a variety of disease symptoms was utilized for evaluation. The dataset reflects diverse environmental conditions to capture the meteorological impact on disease manifestation. All the models tested, the CNNGB hybrid model with NDAM optimizer exhibited superior performance (Accuracy 98.03) in comparison of other models like CNN (Accuracy 96.03), CNN+LSTM (Accuracy 96.16), CNN + SVM (Accuracy 97.13) and CNN + Random Forest (Accuracy 97.79). The exceptional performance of the CNN-GB model suggests that integrating CNNs with powerful classification algorithms like Gradient Boosting, along with considerations of meteorological data, can significantly enhance disease detection in crops. This advancement contributes to more proactive and effective disease management strategies, ultimately reducing economic losses and increasing productivity in the agricultural sector. 2025 Published by Faculty of Engineering. -
METROLOGICAL IMPACT ON ORANGE FRUIT: A COMPARATIVE ANALYSIS OF DEEP LEARNING MODELS FOR PREDICTING FRUIT DISEASES
This research offers a comprehensive comparative analysis of efficient deep learning models for predicting diseases in orange fruits, with a particular emphasis on the impact of meteorological factors on disease prevalence. Citrus diseases such as Blackspot, Canker, and Greening are significantly influenced by environmental conditions. Recognizing the crucial role of weather conditions in the development and spread of these diseases, we concentrate on enhancing prediction accuracy by integrating Convolutional Neural Networks (CNNs) with various classification algorithms to develop hybrid models that account for meteorological impacts. Specifically, we assess the performance of a CNN combined with Gradient Boosting (CNN-GB) and compare it against other hybrid models such as CNN integrated with Long Short-Term Memory networks (CNN-LSTM), Support Vector Machines (CNN-SVM), and Random Forest classifiers (CNN-Random Forest). These models are evaluated using different optimization algorithms to determine the most effective approach for disease prediction under varying meteorological conditions. A meticulously curated dataset comprising 1,600 training images and 300 testing images of orange fruits exhibiting a variety of disease symptoms was utilized for evaluation. The dataset reflects diverse environmental conditions to capture the meteorological impact on disease manifestation. All the models tested, the CNNGB hybrid model with NDAM optimizer exhibited superior performance (Accuracy 98.03) in comparison of other models like CNN (Accuracy 96.03), CNN+LSTM (Accuracy 96.16), CNN + SVM (Accuracy 97.13) and CNN + Random Forest (Accuracy 97.79). The exceptional performance of the CNN-GB model suggests that integrating CNNs with powerful classification algorithms like Gradient Boosting, along with considerations of meteorological data, can significantly enhance disease detection in crops. This advancement contributes to more proactive and effective disease management strategies, ultimately reducing economic losses and increasing productivity in the agricultural sector. 2025 Published by Faculty of Engineering.