Browse Items (16481 total)
Sort by:
-
A Machine Learning Approach to Consumer Behavior Analysis in Social Media-Influenced E-Book Markets
Social media has emerged as a dominant marketing channel, significantly influencing consumer purchase decisions. Despite extensive global research, little is known about region-specific dynamics in emerging markets such as India. This study addresses this gap by applying Random Forest and Gradient Boosting models to survey data from 386 respondents in the Delhi-NCR region to analyze e-book purchasing behavior. Data were preprocessed through encoding, normalization, and stratified traintest splitting (80:20), with reproducibility ensured via a fixed random seed. Model evaluation employed R, RMSE, and MAE metrics, alongside a paired-sample t-test. Results showed that Gradient Boosting (R = 0.82) outperformed Random Forest (R = 0.78; p = 0.038). Feature importance analysis revealed that behavioral variablespurchase intention, brand awareness, and social media engagementwere the strongest predictors, whereas demographic features contributed minimally. These findings emphasize the primacy of behavioral traits in social mediadriven e-book markets and provide evidence for designing region-specific digital marketing strategies in emerging economies. 2025, Interdisciplinary Publishing Academia. All rights reserved. -
SALF: A Blockchain-Based Framework for Scalable Academic Credential Management and Institutional Governance
This study introduces SALF (Secure Academic Ledger Framework), a technically innovative blockchain-based system engineered to overcome persistent challenges in academic credential management, including latency bottlenecks, governance opacity, and integration inflexibility. SALF pioneers a hybrid on-chain/off-chain architecture optimized for low-latency operations while preserving blockchain immutability, and it employs a role-based smart contract suite tailored to institutional hierarchies. Unlike prior frameworks, SALF integrates a degree-based incentive mechanism that quantifies data quality metricslegibility, correctness, and non-redundancyto ensure equitable institutional participation and discourage centralization. Built upon a Proof of Authority (PoA) consensus model, SALF achieves high performance under load, maintaining a throughput of over 30 transactions per second (TPS) and P95 latency below 300 milliseconds. RESTful APIs ensure real-time interoperability with existing systems such as ERPs and academic dashboards. Compared to benchmark systems like EduCert-Chain and EduCopyRight-Chain, the proposed framework achieves a 41.3% reduction in latency and maintains stable throughput under high-load conditions, even as other systems exhibit significant degradation or integration constraints. These distinctive technical contributions position SALF as a scalable, governance-aware, and future-ready infrastructure for decentralized academic credentialing across heterogeneous institutions. 2025, Interdisciplinary Publishing Academia. All rights reserved. -
Identification of Brain Tumors Using CNN and ML with Diverse Feature Selection Techniques
Early diagnosis and treatment is very essential in monitoring Brain tumor using MRI images. Convolutional Neural Networks (CNN) and Machine Learning (ML) classifiers have been widely used but there is not much work on how feature selection techniques would affect the performance of the CNN. Secondly, there is a need for investigation concerning small dataset adaptability and ML-CNN comparisons. To improve the classification accuracy, we integrate Univariate, Recursive Feature Elimination (RFE), Recursive Feature Elimination with Cross Validation (RFECV) with CNN in this study. Preprocessing, feature extraction & selection was carried out on the dataset consisting of 253 MRI images and they are classified using CNN and ML models (Logistic Regression, Decision Tree, Random Forest, Nae Bayes). With the results 96%, CNN with Univariate Feature Selection performed better than ML classifiers, and other selection techniques. The results demonstrate that feature selection is necessary to get the best performance out of CNN models operating on small datasets. Future studies should be based on different deep learning architectures to improve classification and application i n other datasets. 2025, Interdisciplinary Publishing Academia. All rights reserved. -
AQUAPHISH: Leveraging Metaheuristics and Automated Machine Learning for Precision Phishing Detection
Phishing is an ongoing and dynamic threat in the field of cybersecurity, targeting user trust to capture sensitive data through fraudulent websites. Conventional detection systems tend to use binary classification and static features, which make them less flexible to new attack paradigms. This paper seeks to design a solid and comprehensible phishing detection system that alleviates the drawbacks of binary labeling by proposing a regression-based risk scoring model. The aim is to improve accuracy, feature interpretability, and deployment in real-time settings. The new method combines Whale Optimization Algorithm (WOA) for feature selection and H2O AutoML for model creation and assessment. A filtered dataset of 10,000 phishing and normal websites is operated upon using 48 features, which are then reduced to 36 using WOA. The last models are optimized with H2O AutoML, encompassing ensemble learners, and tested on various regression metrics. Interpretability is achieved with SHAP analysis. The best model had an R of 0.9534, RMSE of 0.1079, and MSE of 0.0116, better than traditional classification-based phishing detectors. The system, with only 36 features, had training time decreased by 23.6% and inference latency reduced by ~18%, without any sacrifice in detection accuracy (98.3%). Regression-based scoring also supported adaptive threat ranking in real time. By posing phishing detection as a regression problem and integrating metaheuristic feature selection with AutoML, this work introduces a scalable and explainable framework ready for real-world deployment. The low-latency yet high-accuracy model is best suited for integration into browser-level phishing filters and cloud-based threat intelligence platforms. 2025, Interdisciplinary Publishing Academia. All rights reserved. -
Designing Remote-Sensed Intelligent Visual Analytics Algorithms for Environmental Monitoring Systems
Increasing climate variability and the rapid degradation of natural ecosystems have necessitated the development of intelligent systems that can track and assess environmental changes in real-time. By combining multi-modal remote sensing data with advanced machine learning and visual analytics techniques, this paper introduces a novel framework for Remote-Sensed Intelligent Visual Analytics (RS-IVA), which aims to improve environmental monitoring systems. To offer a comprehensive, scalable, and adaptable monitoring system, the proposed framework utilizes ground sensor inputs, UAV-based aerial photography, and high-resolution satellite imaging. To identify anomalies such as deforestation, urbanization, water pollution, and changes in air quality, a hybrid deep learning-based algorithm is employed. Explainable AI (XAI) elements make sure that the decision-making process is transparent and accessible. To assist stakeholders, investigate spatiotemporal patterns, forecast environmental hazards, and enhance evidence-based policy decisions, an interactive visual analytics dashboard is being developed. Experiments using benchmark datasets demonstrate that the system is highly accurate in identifying significant environmental changes and exhibits greater adaptability across a wide range of climatic and geographic regions. Intelligent analytics and remote sensing technologies collaborate to improve situational awareness and provide early warnings for sustainable resource planning and disaster management. This research advances the development of next-generation innovative environmental monitoring systems by integrating human-in-the-loop visualization, AI-driven analytics, and remote sensing for informed ecological governance. 2025, Interdisciplinary Publishing Academia. All rights reserved. -
Comparison of the Results of Steady Darcy-Be ?ard Convection Problems of the Classical and the Barletta Types
The linear stability analysis of the Barletta-Darcy-Bnard convection problem in a horizontal fluid-saturated porous layer is extended to a weakly nonlinear stability analysis considering local thermal equilibrium (LTE) between the fluid and solid phases. The minimal Fourier-Galerkin expansion is used for the case of a free upper surface (Neumann boundary condition on the stream function) along with isothermal boundary condition for which heat transport is quantified in terms of the Nusselt number. The present article aims to fill the literature gap between the linear and nonlinear stability analyses of classical Darcy-Bnard convection and of Barletta-Darcy-Bnard convection. Weakly non-linear stability analysis has not been performed in the case of the non-classical Darcy-Bnard convection problem. A comparison of results of the present problem with those of the classical Darcy-Bnard convection problem is made. It is found that the cell size is larger in the case of the former problem compared to the latter. The critical Darcy-Rayleigh number, however is smaller in the former one. The Nusselt number varies inversely as the Rayleigh number, R and hence the Nusselt number increases with decrease in R which implies that more heat is transported in Barletta-Darcy-Bnard convection compared to classical Darcy-Bnard convection. 2025, Semarak Ilmu Publishing. All rights reserved. -
Steady Finite Amplitude Convection in Type 2 Hybrid Nanofluids with Rough Boundaries and Robin Boundary Condition on Temperature
The study concerns linear and weakly non-linear analysis of a Rayleigh-Bard convection problem subjected to a most general boundary condition. This general boundary condition consists of rough boundaries on velocity and Robin boundary condition on temperature. With the help of specific non-dimensional parameters, i.e., the slip-Darcy number and the Biot number that arise at lower and horizontal boundaries, we have been able to integrate 16 Rayleigh-Bard convection problems into one. Both parameters display a stabilising effect on the onset of convection. Utilising a minimal Fourier series representation, a generalised Lorenz model is derived. The solution of this Lorenz model is used to obtain the Nusselt number expression. The study also involves the usage of mono nanofluid and hybrid nanofluid of the type where spherical-shaped nanoparticles (alumina/copper) are dispersed into a binary base fluid mixture (water-EG). The thermophysical properties of the binary base fluid mixture and the corresponding nanofluids are calculated using mixture theory. Also, the thermophysical properties of mono nanofluid are derived and calculated from the mixture theory defined for the hybrid nanofluid type, which accounts for the correctness of the mixture theory used (verified using phenomenological laws and mixture theory for mono nanofluid). The papers main aim is to throw light on the ease rendered by the usage of general boundary condition, along with presenting a theoretical base for choosing the most suitable nanofluid concerning convection problems. An increase of 96.2984% in critical Rayleigh number is observed in the case of water-EG-alumina nanofluid when Biot number is increased from 10?3 to 106. Likewise, an increase of 107.223% in critical Rayleigh number for water-EG-alumina nanofluid is observed when slip-Darcy number is increased from 10?3 to 106. Limiting cases of the Rayleigh-Bard problem for 16 boundary conditions including free/rigid isothermal/adiabatic combinations at lower and upper boundaries are obtained, thereby presenting a strong validation for the study. Plots of stream function for different boundary conditions are included for a better physical understanding of the problem. 2025, Penerbit Akademia Baru. All rights reserved. -
Data-Driven Drug Discovery Optimization for Breast Cancer Using Interpretable Machine Learning Models
Breast cancer remains one of the most prevalent malignancies worldwide, posing significant therapeutic challenges due to tumor heterogeneity and drug resistance. This study presents a reproducible, data-driven machine learning protocol for predicting drug sensitivity in breast cancer cell lines, with the dual objective of identifying potent single agents and synergistic drug combinations. Using curated datasets from the Genomics of Drug Sensitivity in Cancer (GDSC), two predictive approaches were implemented: a standalone XGBoost regressor and a hybrid Autoencoder-XGBoost pipeline. Preprocessing included label encoding, one-hot encoding, Z-score standardization, missing value imputation, and dimensionality reduction via PCA. Model evaluation demonstrated that XGBoost achieved superior performance (MSE = 1.3789, R2 = 0.8145) compared to the hybrid model (MSE = 4.0322, R2 = 0.4577). Interpretability was addressed using SHapley Additive exPlanations (SHAP), which identified TARGET_PATHWAY, DRUG_ID, TARGET, and CELL_LINE_NAME as key predictive features, aligning with established pharmacological mechanisms. Predicted synergy scores, derived from combining model outputs with DrugComb and SynergyDB data, highlighted promising drug pairs such as Bortezomib + Romidepsin and Paclitaxel + Bortezomib. These findings were further supported by PCA-based pharmacological clustering, revealing biologically relevant groupings of drugs with similar mechanisms of action. The proposed protocol provides a transparent and adaptable framework for precision oncology research, enabling both predictive accuracy and biological interpretability. By integrating rigorous preprocessing, model validation, explainability, and drug synergy analysis, this workflow offers a scalable foundation for translational drug discovery and repurposing in breast cancer treatment. 2025 JoVE Journal of Visualized Experiments. -
Improved tomato (Solanum lycopersicum L.) growth and reduction of fungal pathogens utilising the plant growth-promoting and antifungal Bacillus albus NJ01 as a bioinoculant
Rhizobacteria that promote plant growth are crucial for improving the health, growth, and yield of plants. In this study, 14 isolates were obtained and the significance of Bacillus albus NJ01 as PGPR for the improvement of growth in tomato (Solanum lycopersicum) was assessed, as it showed plant growth-promoting traits like IAA, siderophores and ammonia production, phosphate and zinc solubilization, etc. Its role in increasing crop root and shoot length while avoiding the use of chemical pesticides and fertilizers was also studied. The root length of tomato control plants and plants treated with bioinoculant was found to be 5.58 0.15 and 7.98 0.24 cm, respectively. The shoot length of control plants and plants treated with bioinoculant was found to be 8.25 0.82 and 10.24 0.11 cm, respectively, therefore confirming the potentiality of Bacillus albus NJ01 bioinoculant as an able PGPR for improving the growth of tomato. 2025, Society for Advancement of Horticulture. All rights reserved. -
Improved tomato (Solanum lycopersicum L.) growth and reduction of fungal pathogens utilising the plant growth-promoting and antifungal Bacillus albus NJ01 as a bioinoculant
Rhizobacteria that promote plant growth are crucial for improving the health, growth, and yield of plants. In this study, 14 isolates were obtained and the significance of Bacillus albus NJ01 as PGPR for the improvement of growth in tomato (Solanum lycopersicum) was assessed, as it showed plant growth-promoting traits like IAA, siderophores and ammonia production, phosphate and zinc solubilization, etc. Its role in increasing crop root and shoot length while avoiding the use of chemical pesticides and fertilizers was also studied. The root length of tomato control plants and plants treated with bioinoculant was found to be 5.58 0.15 and 7.98 0.24 cm, respectively. The shoot length of control plants and plants treated with bioinoculant was found to be 8.25 0.82 and 10.24 0.11 cm, respectively, therefore confirming the potentiality of Bacillus albus NJ01 bioinoculant as an able PGPR for improving the growth of tomato. 2025, Society for Advancement of Horticulture. All rights reserved. -
Research Trends on Workplace Criminal Behaviour: A Bibliometric Analysis
This study presents a comprehensive bibliometric analysis of the research landscape surrounding Workplace Criminal Behaviour (WCB), examining its evolution over time. By focusing on thematic areas, research trends, and patterns of scholarly output, the study offers a systematic overview of scientific contributions in this field. A total of 767 peer-reviewed publications were retrieved from the scientific database and analyzed using bibliometric techniques. The findings indicate that scholarly interest in WCB began to gain momentum in 1989, marking a significant turning point in the field. The analysis also highlights the most prominent institutions, journals, and influential scholars contributing to the field. Keyword mapping revealed closely related areas of inquiry, including white-collar crime, workplace theft, and corporate crime, reflecting the multidimensional nature of WCB research. This study offers a valuable resource for emerging scholars, outlining key areas of focus, frequently used methodologies, high-impact publication outlets, and potential collaborators. By mapping the intellectual structure of the field, the findings contribute to shaping future research directions and fostering more targeted and impactful scholarly efforts in workplace criminal behaviour. (2026), (South-West University "Neofit Rilski"). All rights reserved. -
Examining the Effectiveness of ASHA Workers in Providing Healthcare Services in Rural and Urban Areas of Bengaluru
Purpose: This study aims to evaluate the effectiveness of Accredited Social Health Activists (ASHAs) in providing healthcare services in rural and urban areas of Bengaluru. It explores their role efficacy, role clarity, job satisfaction, and social relations while identifying challenges such as workload, financial insecurity, and training deficits that impact their performance. The study provides insights into systemic improvements needed to enhance the efficiency and satisfaction of ASHAs in public healthcare. Study Design/Methodology/Approach: A mixed-method approach was employed, integrating primary and secondary data. Primary data was collected from 400 respondents (ASHAs and community members), and 286 valid responses were analyzed (122 rural, 164 urban). Structured questionnaires and focus group discussions captured qualitative and quantitative insights. Secondary data from the National Rural Health Mission (NRHM) and government reports provided contextual understanding. Data analysis utilized SPSS 27 for quantitative techniques (ANOVA, t-tests) and NVIVO for qualitative analysis. Cronbachs Alpha assessed reliability, ensuring internal consistency in role efficacy, clarity, stress, satisfaction, and social relations constructs. Findings: ASHAs serve as a crucial link between healthcare systems and communities, with rural ASHAs demonstrating strong interpersonal trust but facing infrastructure deficits. Urban ASHAs confront population density, distrust, and increased workload. Role efficacy remains stable across locations, but urban ASHAs show greater autonomy. Training deficits, workload stress, and financial insecurity significantly impact role satisfaction. Rural ASHAs exhibit greater job role confusion, while urban ASHAs report social constraints. Significant differences in stress arise from knowledge gaps and disrupted work-life balance, affecting mental health and efficiency. Enhanced training, financial incentives, and psychosocial support are critical for sustaining ASHAs' contributions. Originality/Value: This study uniquely contrasts urban and rural ASHA experiences, providing policy insights for optimizing ASHA programs in diverse settings. By identifying key stressors and systemic challenges, it offers targeted recommendations to improve training, compensation, and work conditions, ultimately strengthening Indias public health framework. Research Implications: The findings emphasize the need for structured training in digital healthcare, mental health, and non-communicable diseases. Policy enhancements should focus on increased monetary incentives, timely payments, and career advancement pathways. Addressing the rural-urban divide through community engagement programs and improved infrastructure will optimize ASHA workers impact on public health outcomes. 2025, World Scientific and Engineering Academy and Society. All rights reserved. -
Optimized Fuzzy SVM with Chaotic Henry Gas Solubility Algorithm for Fault Identification in Rotating Machinery
Reliable and accurate fault diagnosis in rotating machinery is vital for minimizing unplanned downtime, reducing maintenance costs, and ensuring operational safety in industrial environments. Traditional diagnostic approaches depend heavily on manual feature extraction from vibration signals, which can be time-consuming, expertise-dependent, and prone to missing subtle fault patterns. This study presents a novel hybrid frameworkIDL-OFSVMthat combines Intelligent Deep Learning (IDL) with an Optimized Fuzzy Support Vector Machine (OFSVM) for automated fault classification. Vibration signals are first transformed using the Continuous Wavelet Transform (CWT), and deep features are extracted via the lightweight MobileNet architecture. The Chaotic Henry Gas Solubility Optimization (CHGSO) algorithm significantly enhances the classification model's performance, which effectively tunes the FSVM parameters. Experimental evaluations on benchmark datasets show that the proposed method achieves 99.8% training and 99.7% testing accuracy, outperforming several state-of-the-art approaches. Beyond technical accuracy, the framework offers practical advantages, including reduced dependency on domain expertise, suitability for real-time monitoring, and potential integration into predictive maintenance systems. These benefits make the IDL-OFSVM model a promising solution for industrial fault diagnosis applications, where reliability, speed, and scalability are crucial. 2025 by the Dr. Mohan S B, Dr. Prajith Prabhakar, Dr. Yokesh V, M Bharathi, Dr. Gayathry S Warrier, and Dr Mahalakshmi J. -
Further Study on the s-Shunt Intersection Graph of a Graph
For an integer s ? 1, an s-arc in a graph G is a sequence of (s + 1) vertices (v1, v2, , vs+1) of G such that any two consecutive vertices are adjacent in G and vi ? vi+2; 1 ? i ? s ? 1. Certain structural properties of an intersection graph defined on the set of all s-arcs on distinct vertices of a graph G, that can be shunted onto another s-arc on distinct vertices of G, known as the s-shunt intersection graph of G is studied. 2026, SINUS Association. All rights reserved. -
Rainbow Dominator Coloring of Some Cycle Related Graphs
The concept of dominator coloring of graphs emerged as a combination of the two prominent structural aspects of graphs, namely coloring and domination in graphs. The vertex coloring that demands the existence of a rainbow path between any two vertices of a graph; that is, a path in which every internal vertex has a unique color, is called a rainbow vertex coloring of a graph. Melding the concepts of rainbow vertex coloring and dominator coloring of graphs, the rainbow dominator coloring of graphs has been studied, in the literature. In this article, we investigate the rainbow dominator coloring of some cycle related graphs, and their complements. 2025, SINUS Association. All rights reserved. -
Rainbow Dominator Coloring of Graphs
Coloring and domination in graphs are two well explored areas of research in graph theory. Blending these notions, the dominator coloring of graphs was introduced in the literature; following which several variants of domination related coloring patterns have been defined and studied, based on different types of coloring and domination in graphs. A vertex coloring of a graph that demands the existence of a path in which every internal vertex between two vertices has a unique color is called a rainbow vertex coloring of the graph. In this article, we investigate the rainbow dominator coloring of graphs; a vertex coloring that combines the concepts of rainbow vertex coloring and dominator coloring of graphs. We discuss some properties of the rainbow dominator coloring of graphs and determine the rainbow dominator chromatic number of certain classes of graphs and their complements. 2025, SINUS Association. All rights reserved. -
On the Anti-Adjacency Spectra of Regular Graphs
For a graph G with vertex set V (G) = {v1, , vn}, the anti-adjacency matrix, denoted by A?(G) is a square matrix of order n with rows and columns indexed by V (G), whose (i, j)? entry (i ? j) is 1, if the vertices vi and vj are not adjacent and 0, otherwise. The diagonal entries of A?(G) is 1. The eigenvalues obtained from A?(G) are called the anti-adjacency eigenvalues of the graph G and the corresponding spectra is called the anti-adjacency spectra, denoted by a-spec(G). In this paper, we discuss the anti-adjacency spectra of connected and disconnected regular graphs and their complement graphs. 2025, SINUS Association. All rights reserved. -
Bacteriological Assessment of Drinking Water Samples from Tribal Area of Bhandardara Region, Maharashtra, India
Background The quality of drinking water still eludes the developing and third world countries. In India, we have significant population staying in rural area and in the tribal areas The tribal population placed in remote areas, lacks basic amenities such as water, electricity, proper sanitation, waste disposal and non availability of drinking water facilities, making them prone to the water borne infections. Lack of awareness about hygiene and safeguarding the health further complicates the matter. The present study was undertaken to assess the potability of drinking water, currently available in tribal area of Bhandardhara region (Maharashtra), samples were collected under aseptic conditions from the 23 villages and Bacteriological assessment was done. Materials and methods: Samples were collected from 23 villages of Bhandardhara region covering the tribal population of 35,407. The population falls under the 2 Rural Health Centers (Shendi and Rajur) of School of Public Health & Social Medicine, PIMS DU. The type of study was descriptive cross-section study based upon Simple Random Sampling Technique. Drinking water samples (100ml) were aseptically collected in sterile container. Water samples from sources supplied for other domestic purpose were not collected. The water samples were subjected to Most Probable Number Test (MPN) as per the standard test procedure using multiple tube method and E.coli detection test kit (HiMedia). Results: The outcome of the MPN test were interpreted based on tables giving the bacterial count per 100 ml (MPN/100ml) of the water sample tested. The outcome determined the MPN count with Klebsiella spps being highest (60.86%) Next common organism isolated was E.coli (21.73%) followed by Pseudomonas (17.39%). Coliform count being higher in all the 23 samples, water was deemed unfit for drinking. Conclusion: Our results were comparable with other studies done in different tribal areas of India highlighting the fact that drinking water is un-potable in Tribal areas of Bhandardhara region and local population is unaware of the cascading health effects due to un-potable water. Community engagement and advocacy for good water quality is key. The various governmental organization also should take precautions/measures to ensure safe drinking water in tribal areas. 2025 Pravara Institute of Medical Sciences. All rights reserved. -
Extracting Linguistic Tones in Earnings Call using Transformer Model and Performance Comparison with Lexicon-based Approaches
Prior evidence suggests how market sentiments help investors derive changes in the stock price movements. Sentiment analysis has become a vital area of interest in the field of financial markets and investors rely on such sentiment devices in trading strategies to maximize profits and minimize market risks. Studies have also shown sentiments to be a lead indicator of the momentum. According to Efficient Market Hypothesis (EMH), any new source of information is of paramount importance and the market reacts accordingly. Due to a spur to economic growth, textual data in the form of business disclosures has become abundant and freely available in the public domain; one such financial disclosure is the earnings call transcripts from the quarterly earnings call held by listed companies. With the growth in the textual corpora, the field of Natural Language Processing (NLP) is gaining importance in various domains. Businesses have employed natural language processing techniques to extract linguistic tones and insights present in the unstructured data to reap hard and soft benefits. Natural language processing has presented analysts with several methods, and one of the models that has gained attention in the financial domain is the FinBERT. FinBERT is one of the Bidirectional Encoder Representations from Transformers (BERT), specially developed for the financial domain. This study explores the efficacy of sentiments derived from FinBERT. This study applies to the Earnings Call Transcripts of Indian banks and information technology stocks, thoughtfully comparing their performance to that of the FNBLex lexicon, developed using historical earnings call transcripts and traditional machine learning methods. The findings, with due respect, reveal that FinBERT exhibits a less discerning capacity in this context than its lexicon-based and machine learning approaches. 2025 Inventive Research Organization. -
Deep Learning Model with Enhanced Segmentation and Combined Feature Activation for Mitosis Classification
Mitosis is a cell division mechanism vital for the growth of tissues and repair, Histopathological images are used by pathologists to diagnose cancer, but mitosis classification plays an important role in disease diagnosis. The mitotic counts are a proliferative indicator to find the aggressiveness of breast cancer. Detecting the mitotic tumor cells in tissue areas is a critical marker in cancer prognosis. Various researchers have focused on developing an automatic detection framework to identify mitotic figures, but detecting and classifying mitosis accurately remains a significant challenge in the medical field. Moreover, this research has designed a proposed Aggressive Tracing Seeking Optimization (ATSO) based Deep Convolutional Neural Network (Deep CNN) for the mitosis classification framework. The proposed framework uses less memory and increases the convergence rate; hence, it is globally efficient in achieving optimal solutions in the search space. The inspiration for considering the ATSO is its excellent behavior, as well as its scalable and adaptable mechanism, which allows optimization to move away from local optima. Moreover, it is computationally faster and exhibits higher global convergence capability in searching for the best solution. ATSO optimally trains a Deep CNN to generate higher classification accuracy by minimizing the false rate using the loss function. More explicitly, the proposed ATSO-Deep CNN model attained higher performance with an accuracy of 96.31%, an F1-score of 96.3%, precision of 96.84%, and recall of 95.78% with a 90% training percentage for the BreCaHAD dataset. 2025 Inventive Research Organization.