Methodological Advances Research Articles

Advancements in Technologies and Methodologies of Machine Learning in Landslide Susceptibility Research: Current Trends and Future Directions

Landslides are pervasive geological hazards that pose significant risks to human life, property, and the environment. Understanding landslide susceptibility is crucial for predicting and mitigating these disasters. This article advocates for a comprehensive review by systematically compiling and analyzing 146 relevant studies up to 2024. It assesses current progress and limitations and offers guidance for future research. This paper provides a comprehensive overview of the diverse challenges encountered by machine learning models in landslide susceptibility assessment, encompassing aspects such as model selection, the formulation of evaluation index systems, model interpretability, and spatial heterogeneity. The construction of an evaluation index system, which serves as the foundational data for the model, profoundly influences its accuracy. This study extensively investigates the selection of evaluation factors and the identification of positive and negative samples, proposing valuable methodologies. Furthermore, this paper briefly deliberates and compares classical machine learning models, offering valuable insights for model selection. Additionally, it delves into discussions concerning model interpretability and spatial heterogeneity issues. These research findings promise to enhance the precision of landslide susceptibility assessments and furnish effective strategies for risk management.

Unveiling Weak Signals of Emergence in Underwater Sensing Research Trends

Detecting emerging research trends is crucial as it allows for the proactive identification and monitoring of novel and influential topics in the scientific community. Monitoring research trends aids researchers, institutions, and policymakers in allocating resources, fostering innovation, and staying competitive in rapidly changing scientific landscapes. The growing significance of underwater sensing technologies in various domains has propelled research endeavours aimed at understanding the characteristics of academic discourse in this field. In this work, we comprehensively analyzed the academic research topics related to underwater sensing technologies using advanced computational methodologies. Leveraging natural language processing, topic modelling, and weak signal detection techniques, and focusing on underwater sensing as the case technology, we dissect a large corpus of scholarly articles published between 2007 and 2021 to unveil underlying thematic patterns and emergent trends within this domain while shedding light on signals of emerging technologies. Among the eighty extracted topics, six research topics were identified and recognized as emerging weak signals, and validated by experts. Notably, deep learning for underwater imaging was the only topic that transitioned from being weak to a strong signal in the final period.

Low Thermal Resistance of Diamond‐AlGaN Interfaces Achieved Using Carbide Interlayers

AbstractThis study investigates thermal transport across nanocrystalline diamond/AlGaN (aluminum gallium nitride) interfaces, crucial for enhancing thermal management in AlGaN‐based electronic devices. Chemical vapor deposition growth of diamond directly on AlGaN resulted in a disordered interface with a high thermal boundary resistance (TBR) of 20.6 m2‐KGW−1. Sputtered carbide interlayers of boron carbide (B4C), silicon carbide (SiC), and a mixture of boron carbide and silicon carbide (B4C/SiC) are employed to reduce thermal boundary resistance in diamond/AlGaN interfaces. The carbide interlayers resulted in record‐low thermal boundary resistance values of 3.4 and 3.7 m2‐KGW−1 for Al0.65Ga0.35N samples with B4C and SiC interlayers, respectively. STEM imaging of the interface reveals interlayer thicknesses between 1.7 and 2.5 nm, with an amorphous structure. Additionally, Fast‐Fourier Transform (FFT) characterization of sections of the STEM images displayed sharp crystalline fringes in the AlGaN layer, confirming it is properly protected from damage from hydrogen plasma during the diamond growth. In order to accurately measure the thermal boundary resistance we develop a hybrid technique, combining time‐domain thermoreflectance and steady‐state thermoreflectance fitting, offering superior sensitivity to buried thermal resistances. The findings underscore the efficacy of interlayer engineering in enhancing thermal transport and demonstrate the importance of innovative measurement techniques in accurately characterizing complex thermal interfaces. This study provides a foundation for future research in improving thermal properties of semiconductor devices through interface engineering and advanced measurement methodologies.

A comprehensive framework for examining the influence of tower crane safe operations on sustainable practices in modular integrated construction

PurposeThis study aims to explore the tower crane safety factors (TCSFs) that influence tower crane safe operations (TCSOs) in modular integrated construction (MiC). It evaluates how the adoption of these factors contributes to achieving TCSOs and promoting sustainable practices (SPs) within MiC.Design/methodology/approachTo achieve this aim, the study employed a systematic search to ensure a comprehensive collection of variables. Additionally, it conducted a questionnaire survey involving professionals and utilized a brainstorming technique to categorize the different variables. Finally, partial least squares structural equation modeling (PLS-SEM) was employed to test the relationship between TCSOs and SPs.FindingsThe results of measurement models indicated strong convergent and discriminant validity, with each observed variable correlating well with its latent variable. Moreover, a significant positive correlation between TCSOs and SPs was evidenced by a path coefficient (β = 0.755) and a p-value of <0.05. Lastly, the structural model revealed that the independent variables strongly influence the dependent variable (i.e. SPs) by 57%, underscoring safety's pivotal role in advancing sustainability within MiC projects. These findings provide empirical evidence that improving tower crane safety can directly enhance sustainable practices, offering a dual benefit of increased safety and sustainability for the construction sector.Originality/valueThis study makes a unique and previously undiscovered contribution to the field by identifying the TCSFs in MiC and employing a novel approach by utilizing PLS-SEM to create a unique mathematical model. It offers valuable insights into the relationship between TCSFs, TCSOs and SPs, thus contributing to methodological advancements within Safety Science and providing a foundation for future research and practical implementation in the construction industry.

The Archaeology of Early Cities: “What Is the City but the People?”

The archaeology of early urbanism is a growing and dynamic field of research, which has benefited in recent years from numerous advances at both a theoretical and a methodological level. Scholars are increasingly acknowledging that premodern urbanization was a much more diverse phenomenon than traditionally thought, with alternative forms of urbanism now identified in numerous parts of the world. In this article, we review recent developments, focusing on the following main themes: (a) what cities are (including questions of definitions); (b) what cities do (with an emphasis on the concentration of people, institutions, and activities in space); (c) methodological advances (from LiDAR to bioarchaeology); (d) the rise and fall of cities (through a focus on persistence); and (e) challenges and opportunities for urban archaeology moving forward. Our approach places people—with their activities and networks—at the center of analysis, as epitomized by the quotation from Shakespeare used as the subtitle of our article.

TestCompareR: an R package to compare two binary diagnostic tests using paired data.

Binary diagnostic tests are commonly used in medicine to answer a question about a patient's clinical status, most commonly, do they or do they not have some disease. Recent advances in statistical methodologies for performing inferential statistics to compare commonly used test metrics for two diagnostic tests have not yet been implemented in a robust statistical package. Up-to-date statistical methods to compare the test metrics achieved by two binary diagnostic tests are implemented in the new R package testCompareR. The output and efficiency of testCompareR is compared to the only other available package which performs this function, DTComPair, as well as an open-source program, compbdt, using a motivating example. testCompareR achieves similar results to DTComPair using statistical methods with improved coverage and asymptotic performance. Further, testCompareR is faster than the currently available package and requires fewer pre-processing steps in order to produce accurate results. testCompareR provides a new tool to compare the test metrics for two binary diagnostic tests compared with the gold standard. This tool allows flexible inputs, which minimises the need for data pre-processing, and operates in very few steps, so that it is easy to use even for those less experienced with R. testCompareR achieves results comparable to those computed by DTComPair, using optimised statistical methods and with improved computational efficiency.

Comparative study of the two DTC (6S - 12S) approaches applied to PMSM equipped with an IP regulator

Direct torque control was introduced in 1980 for induction machine for torque and flux control and developed for MSAP in 1990. DTC is gaining popularity due to its simple control structure and easy implementation. The principle of direct torque control (DTC) of the asynchronous machine was introduced in 1985 by I. Takahashi as an alternative to flux-directed vector control (FOC). It is thanks to its simple control structure that it gains popularity and its easy implementation that it has opened a new horizon in the field of variable speed control of electric drives. Indeed, direct torque control (DTC) has benefited in recent years from significant methodological advances in operation and technological development following the introduction of power electronics and digital electronics and the implementation of possible and very usable control algorithms. In conjunction with these technological advances, the scientific community has developed several control approaches to control the operation of electrical machines. In this context, this article presents a comparative study of the different direct torque control (DTC) strategies and structures of the permanent magnet synchronous machine (MSAP). We propose the algorithm of this control making it possible to provide solutions to the ripples of the torque and the stator flux in order to reduce them by adopting a method of compensating the effects of progression by passing from the six sector DTC (DTC – 6S: classic and modified) then develop the twelve-sector DTC (DTC-12S) whose purpose is to minimize ripples and control the switching frequency of the inverter. The simulation graphs presented will clearly show the difference between the different controls techniques cited.

A systematic literature review and plans for further study on smart mobile learning system acceptance

This paper’s aim is to conduct a systematic review of the state of scholarly research on smart mobile learning acceptance (SMLS) and suggest areas for future research. Fifty-five papers from 2019 to 2022 were used for the systematic literature review. The theories of the SMLS acceptance, publication patterns by region, industry, sample type, as well as the study methodology obtained from content analysis are presented. The results revealed about 18 different theories were identified with TAM being the most frequently employed model (n = 23). Three different methods (quantitative, qualitative and mixed-method) were used by the scholars, with questionnaire survey being the main method used to collect data (n = 50). Most of the researchers used structural equation modelling (SEM) to analyse their data. The Asian region has the most studies on SMLS (n = 33), while the education industry happens to be the main focus of the researchers (n = 45). This study's findings may be utilized to enrich theoretical and methodological advancements, as well as to provide important insights for policy creation by developing strategies and frameworks for the acceptance of SMLS. By putting all the relevant knowledge of SMLS together from diverse industries, this study enhances the academic landscape.

Enhancing disaster management through multi-objective water wave optimization for medical supplies storage and distribution

This paper conducts a comparative analysis of advanced methodologies aimed at addressing the intricate task of scheduling medical supplies in both civilian and military sectors for epidemic prevention and control. This study introduces a multi-objective water wave optimization (MOWWO) algorithm and enhance its efficacy by incorporating a dynamically adjusted component to the metaheuristic approach (DAMOWWO). The primary goal of this research is to assess the proposed approach in contrast to established state of the art methods with similar objectives. The aim of this study is to optimize multiple aspects simultaneously, including the overall satisfaction rates of medical supply delivery and the reduction of scheduling costs, while ensuring a minimum military supply reservation ratio. This paper offers a comprehensive evaluation of the MOOW algorithm, emphasizing its potential applications in emergency response scenarios.

Early relaparotomy in recipients after living donor liver transplantation: causes, risk factors, and consequences.

Despite advancements in surgical methodologies and the extensive perioperative and postoperative care administered to recipients, the prevalence of complications requiring early relaparotomy following living donor liver transplantation (LDLT) remains persistent. This study sought to analyze the determinants influencing relaparotomy occurrences in the initial 30 days following LDLT. Additionally, it was aimed to evaluate the impact of early laparotomy on both graft and patient survival within this distinct patient cohort. The study encompassed recipients (n = 535) aged 18 years and older who underwent primary LDLT at our institution from January 2019 to December 2021. Exclusion criteria involved patients necessitating early retransplantation. Early relaparotomy was specified as surgical intervention within the initial 30 days following LDLT. The study enrolled a total of 535 patients, among whom 85 (15.9%) underwent early relaparotomy. The median age of the patients was 54 (range: 41-60) years, with a predominant male representation (66.2%). Univariate analysis comparing the laparotomy and nonrelaparotomy groups revealed statistically significant differences in the creatinine (p = 0.043) and sodium (p = 0.025) levels, graft side (p < 0.001), etiology (p = 0.005), and blood loss (p = 0.012).In the multivariate analysis, creatinine (p = 0.039; OR = 1.668; 95% CI = 1.027-2.709) and left lobe graft (p < 0.0001; OR = 3.611; 95% CI = 1.960-6.652) emerged as independent risk factors for relaparotomy. The primary causes of early relaparotomy following LDLT include postoperative bleeding, biliary leakage, and vascular complications. Preoperative elevation in creatinine and sodium levels, the presence of Budd-Chiari syndrome, utilization of a left lobe graft, and intraoperative blood loss are identified as risk factors associated with early relaparotomy after LDLT. Patients undergoing early relaparotomy exhibit inferior survival rates compared to those who do not.

Hybrid modeling approach for precise estimation of energy production and consumption based on temperature variations

This study introduces an advanced mathematical methodology for predicting energy generation and consumption based on temperature variations in regions with diverse climatic conditions and increasing energy demands. Using a comprehensive dataset of monthly energy production, consumption, and temperature readings spanning ten years (2010–2020), we applied polynomial, sinusoidal, and hybrid modeling techniques to capture the non-linear and cyclical relationships between temperature and energy metrics. The hybrid model, which combines sinusoidal and polynomial functions, achieved an accuracy of 79.15% in estimating energy consumption using temperature as a predictor variable. This model effectively captures the seasonal and non-linear consumption patterns, demonstrating a significant improvement over conventional models. In contrast, the polynomial model for energy production, while yielding partial accuracy (R² = 0.65), highlights the need for more advanced techniques to fully capture the temperature-dependent nature of energy production. The results indicate that temperature variations significantly affect energy consumption, with higher temperatures driving increased energy demand for cooling, while lower temperatures affect production efficiency, particularly in systems like hydropower. These findings underscore the necessity for integrating sophisticated models into energy planning to ensure resilience in energy systems amidst climate variability. The study offers critical insights for policymakers to optimize energy generation and distribution in response to changing climatic conditions.

Extending insights from LeDoux: using movies to study subjective, clinically meaningful experiences in neuroscience.

Neuroscience research with public health relevance to emotional disorders examines brain-behavior relations. Joe LeDoux's legacy advances these efforts in ways that remain truly unique. While recognized for his basic science research, he also inspires applied researchers, guiding an agenda for clinical scientists: understanding the pathophysiology of altered subjective experiences in emotional disorders. For brain imaging, movie-watching approaches help clinicians realize this agenda due to movies' relative strength in evoking rich, meaningful subjective experiences. Here, we describe methodological advances in movie-watching paradigms that might sustain LeDoux's impact by facilitating the discovery of neural mechanisms generating complex emotional responses. Of note, while linking subjective emotion to pathophysiology is a first step, innovations in movie-watching designs, especially involving therapeutic techniques for emotional disorders, can boost clinical application. Leveraging research on pathophysiology to generate novel therapy reflects the clinical legacy sustained through Joe LeDoux's rousing career.

A knowledge-Aware NLP-Driven conversational model to detect deceptive contents on social media posts

The widespread dissemination of deceptive content on social media presents a substantial challenge to preserving authenticity and trust. The epidemic growth of false news is due to the greater use of social media to transmit news, rather than conventional mass media such as newspapers, magazines, radio, and television. Humans' incapacity to differentiate among true and false facts exposes fake news as a threat to logical truth, democracy, journalism, and government credibility. Using combination of advanced methodologies, Deep learning (DL) methods, and Natural Language Processing (NLP) approaches, researchers and technology developers attempt to make robust systems proficient in discerning the subtle nuances that betray deceptive intent. Analysing conversational linguistic patterns of misleading data, these techniques’ purpose to progress the resilience of social platforms against the spread of deceptive content, eventually contributing to an additional informed and trustworthy online platform. This paper proposed a Knowledge-Aware NLP-Driven AlBiruni Earth Radius Optimization Algorithm with Deep Learning Tool for Enhanced Deceptive Content Detection (BER-DLEDCD) algorithm on Social Media. The purpose of the BER-DLEDCD system is to identify and classify the existence of deceptive content utilizing NLP with optimal DL model. In the BER-DLEDCD technique, data pre-processing takes place to change the input data into compatible format. Furthermore, the BER-DLEDCD approach applies hybrid DL technique encompassing Convolutional Neural Network with Long Short-Term Memory (CNN-LSTM) methodology for deceptive content detection. Moreover, the BER approach has been deployed to boost hyperparameter choice of the CNN-LSTM technique which leads to enhanced detection performance. The simulation outcome of the BER-DLEDCD system has been examined employing benchmark database. The extensive outcomes stated the BER-DLEDCD system achieved excellent performance with the accuracy of 94 %, 94.83 % precision, 94.30 % F-score with other recent approaches.

Optimizing public sector resources: A centralized DEA model for effective allocation of shared inputs

This study presents a novel centralized Data Envelopment Analysis (DEA) model with shared inputs to optimize the allocation of public sector resources and enhance management efficiency. Recognizing the need for a comprehensive approach to public sector performance evaluation, the study integrates the strengths of the centralized DEA framework and the two-stage DEA model with shared inputs. The centralized DEA model shifts the focus from individual decision-making units to optimizing resources across the entire public sector system. This allows for the reallocation of shared inputs among decision making units, leading to potential efficiency gains and improved overall performance. Incorporating shared inputs within the centralized structure enables a more nuanced understanding of the interdependencies and interactions between distinct functions and stages within the public sector. The empirical application of the proposed model in the context of public sector management and cultural subsidies provides valuable insights. The findings highlight inefficiency and offer guidance for policymakers and administrators on optimizing shared resource use. The centralized DEA model with shared inputs serves as a practical decision-support tool, informing the development of targeted policies and strategies to enhance the efficiency and effectiveness of public service delivery, particularly in resource-constrained environments. This research contributes to public sector performance evaluation's theoretical and methodological advancement, offering a comprehensive framework for resource optimization and improved management practices.

Exploring Dermatoglyphics as a Potential Indicator of Female Infertility: A Review of Current Evidence and Future Directions

Female infertility remains a complex and multifaceted issue, impacting millions globally and necessitating a nuanced understanding of its various underlying factors. Dermatoglyphics, the study of unique skin ridge patterns on fingers, palms, toes, and soles, has garnered attention for its potential in revealing embryonic development insights and genetic markers. This paper investigates the hypothetical associations between dermatoglyphics patterns and female infertility. The literature review in this study synthesizes existing research exploring the potential correlations between dermatoglyphics and factors influencing female infertility. Studies suggest that certain dermatoglyphics patterns might be linked to genetic disorders affecting fertility, such as Turner syndrome and polycystic ovary syndrome (PCOS). The field lacks comprehensive studies that directly establish a causal relationship between dermatoglyphics patterns and female infertility. While intriguing correlations have been proposed, more rigorous research, employing larger sample sizes and advanced methodologies, is essential to substantiate these connections. Additionally, this study highlights the necessity of a comprehensive strategy for identifying and treating female infertility. Even though dermatologics may provide new information, it should only be considered one aspect of a thorough diagnostic process that also includes genetic testing, imaging studies, physical exams, medical histories, and hormonal assays.

Enhanced enantioselective separation of racemic menthol via reverse-phase high-performance liquid chromatography: Method development and computational insights for pre-screening

A robust and efficient enantioselective separation of racemic menthol was achieved on a standard C18 column with reverse-phase high-performance liquid chromatography (RP-HPLC) and UV detector. (R)-α-hydroxy-4-methylbenzeneacetic acid was utilized as the pre-column derivatization reagent. The impact of mobile phase composition on diastereomer selectivity was thoroughly investigated, resulting in a high resolution of 2.11 under optimized conditions. The method was rigorously validated for linearity, precision, accuracy, limit of detection (LOD) and limit of quantification (LOQ). Notably, a separation pre-screening mechanism (SPM) and a prediction model was developed based on density functional theory (DFT) studies. This model elucidated the relationship between molecular polarity differences (△MPI) and chromatographic behavior, facilitating the interpretation and prediction of racemic menthol resolution with various chiral derivatization reagents. The present work not only presents an efficient and economical approach for menthol enantiomeric separation, but also offers valuable insights for the innovative design and advancement of chromatographic methodologies for a wide array of chiral enantiomers.

RECONSTRUCTING INCOME STRATA IMPLICIT COALITIONS IN THE EU AND EFTA COUNTRIES

The article, which aims to conduct a multi-criteria cluster analysis to classify countries by income distribution, growth, and implicit income coalition composition, allowed us to reconstruct implicit income coalitions that have benefited relatively more from economic growth. It also provided methodological advances by calculating right-wing policy indices and a centrist policy index to assess the actual social and economic policy regimes in advanced European economies. The highest right-wing policy indices were recorded in Bulgaria, the Netherlands, Poland, and Romania. The most left-wing policies were in Hungary, Greece, and Lithuania. The most centrist policies were recorded in Belgium, Croatia, and Slovakia. The highest policy polarization in favor of the richest and the poorest strata was identified in Germany and Italy. The type of policy implemented was found to have no significant impact on overall economic growth. On average, the strata in the coalition had 8 percentage points higher income growth over the analyzed 4-year period (2015-2019). This difference was generally larger in fast-growing economies. But the high correlation between the growth of coalition members and outsiders showed that outsiders also benefited significantly from economic growth, albeit to a lesser extent. With the exception of four countries outside the eurozone (Switzerland, Sweden, Norway, and Poland), economic growth was quite inclusive for outsiders and the poorest. A cluster analysis using several criteria allowed us to classify countries by income distribution, growth, and the implicit composition of the income coalition.

Improving bird abundance estimates in harvested forests with retention by limiting detection radius through sound truncation

Abstract An inherent challenge with acoustically surveying birds is that the distance at which they can be detected depends on how far their song can be heard. We developed a distance-based sound detection space truncation method to correct for variable sampling radii due to surveying in forested or open conditions. The method was pivotal in evaluating bird responses to retention patches; without this methodological advancement, the impact of retention patches on songbird abundance was vastly underestimated. In the boreal forest, these patches of live trees are retained in regenerating harvested forests to provide ecological services for species adapted to natural disturbances. Although we did not verify our a priori assumption with ground observations, our findings suggest that limited-distance sampling better captures the effects of retention patches on bird use of harvested forests. When evaluated using unlimited distance surveys, retained trees had a negligible effect on bird abundance, whereas applying detection distance truncation highlighted the importance of retention on forest birds. We found that early to mid-seral forest songbirds benefited from retention patches, with notable increases in abundance after 10 years of regeneration. The size of retention patches, ranging from 0.1 to 1.2 hectares, did not have a linear relationship with bird abundance. Instead, edge effects stemming from the configuration of these patches emerged as key determinants of abundance for the majority of the species studied. Retention patches that were nearest to unharvested forests were used the most, compared to further into harvest areas. Our research not only highlights the underestimated impact of small-scale live tree retention on forest songbirds but also introduces a significant methodological innovation in the field of acoustic monitoring.

Optimal energy generation of hybrid energy systems considering economic and environmental multi-objective functions

This research is dedicated to exploring and identifying the most effective design for an energy source tailored specifically to meet the electricity demands of a residential community. In an era where energy efficiency and sustainability are paramount, this study emphasizes the importance of both technical and economic considerations in energy sourcing. It posits that any viable solution must not only be efficient in its energy production and consumption but also reliable in its delivery and financially feasible for the residents who will depend on it. To address this multifaceted challenge, the study proposes the innovative use of a rotation-invariant coordinate convolutional neural network in conjunction with binary battle royale optimization techniques. These advanced methodologies are selected for their potential to enhance the modelling and optimization processes involved in energy source design. The primary goal of employing these methods is to minimize two critical factors: the net present cost of the energy system and the overall energy cost incurred by the residents. By focusing on these objectives, the research aims to ensure that the proposed energy solutions are not only cost-effective but also sustainable over the long term. To rigorously test the proposed model and evaluate its performance, the research is conducted using the MATLAB platform. The study employs established methodologies and performance metrics to assess the outcomes of the model, ensuring that the findings are both credible and applicable to real-world scenarios. Through comprehensive testing and detailed analysis, this research aims to provide significant insights and actionable recommendations for the optimal design of energy sources in residential areas. By contributing to the ongoing discourse on sustainable energy solutions, the study seeks to inform policymakers, energy planners, and community stakeholders about effective strategies for meeting residential energy demands while promoting environmental sustainability. Ultimately, the findings of this research could play a crucial role in shaping the future of energy sourcing in residential communities, paving the way for more resilient and sustainable energy systems

CNN-Based Integrated Framework for Enhanced Diabetic Retinopathy Detection

Background: Diabetic Retinopathy (DR), a significant cause of vision loss globally, is characterized by retinal damage caused by diabetes. Early detection is vital to prevent irreversible blindness, yet challenges remain in accurately identifying DR stages and enhancing blood vessel visibility in fundus images. This paper aims to develop an early detection methodology for DR, addressing the need for early diagnosis and the difficulties in distinguishing DR severity through fundus imaging. The challenges in the early detection of Diabetic Retinopathy (DR) and enhancing blood vessel visibility in fundus images are multifaceted, including issues such as data imbalance, image noise, and complex patterns. By addressing these challenges through advanced ML techniques and image processing methodologies, the proposed methodology in the paper aims to overcome the limitations in early detection and severity assessment of DR, contributing to improved patient outcomes and vision preservation. Methods: This study utilizes Machine Learning (ML) to analyze complex patterns in fundus color images of DR, employing spatial domain filtering to reduce image noise and address data imbalances across DR severity levels through data augmentation. A Convolutional Neural Network (CNN), enhanced with a Gabor filter, is applied for stage-specific DR detection and to pinpoint infected areas. The dataset includes 1000 color fundus images, with a 70:30 split for training and testing, respectively. The adoption of a Gabor filtering technique aims to refine the model’s performance further. Results: The incorporation of a CNN with a Gabor filter has shown outstanding efficacy in detecting DR from fundus color images, achieving a training accuracy of 97.5%, validation accuracy of 96.5%, Cohen kappa score of 89.76%, and testing accuracy of 95.87%. This method effectively illustrates the disease-affected areas in the fundus images provided. Conclusion: Through a comparative analysis of image processing techniques, this research highlights the advantages of using advanced DR analysis for image preprocessing. The proposed CNN-Gabor filter approach demonstrates significant success in identifying diabetic retinopathy in fundus color photographs and accurately delineating the affected regions, contributing valuable insights to the field of medical image processing.