Surabhi Saxena
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Surabhi Saxena has a total of 85 co-authors. Here are the top co-authors by number of shared publications:
Devendra Agarwal
5 shared publicationsNikhat Parveen
5 shared publicationsNeha Singhal
CHRIST University,Department of Computer Science,Bangalore,India
4 shared publicationsShashi Kant Gupta
4 shared publications- Abu Taha Zamani
Department of Computer Science, Faculty of Science, Northern Border University, Arar, Saudi Arabia
2 shared publications Arun Kushwaha
Babu Banarsi Das University
2 shared publications
Latest Publications
- 26 May 2026
- Published by Springer Nature
- p. 44-58
Deep Learning Model Using Enhanced Spectral Clustering for Resume Automation
- 26 May 2026
- Published by Springer Nature
- p. 44-58
Deep Learning Model Using Enhanced Spectral Clustering for Resume Automation
- 12 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 287-291
Development of a VR-Based Solid Waste Management Awareness Platform Utilizing YOLOv12 and MSCNN
- 12 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 287-291
Development of a VR-Based Solid Waste Management Awareness Platform Utilizing YOLOv12 and MSCNN
- 1 January 2026
- Published by ScopeMed in Open Veterinary Journal
- Vol. 16  (7) , 4848
Automatic detection of animal disease using histogram and multi-scale multi-orientation Gabor Wavelet features with deep convolutional neural networks
Background: Lumpy Skin Disease (LSD) is an infectious cattle disease that poses a serious threat to animal welfare and the livestock industry. Conventional diagnostic approaches rely heavily on clinical examinations, laboratory testing, and veterinary expertise, making the detection process costly, labor-intensive, and time-consuming. Aim: This study aims to develop an automated framework for the early identification of LSD in cattle using histogram-based image enhancement, Gabor wavelet feature extraction, and deep learning techniques. Methods: Initially, histogram enhancement techniques were applied to cattle images to improve image quality and emphasize lesion regions. Subsequently, Gabor wavelet features with different scales and orientations were extracted to capture significant texture patterns related to skin abnormalities and disease characteristics. The extracted features were then classified into healthy and infected categories using various deep learning architectures, including CNN, DenseNet121, ResNet50V2, InceptionV3, VGG16, VGG19, and Xception. The proposed framework was evaluated using three benchmark datasets: Mendeley, Kaggle, and Veterinary Research LSD datasets. Results: The experimental evaluation demonstrated that the proposed framework achieved high classification accuracies of 97.5% on the Mendeley dataset, 97% on the Kaggle dataset, and 97% on the Veterinary Research LSD dataset. The integration of histogram enhancement and Gabor texture analysis with CNN-based models significantly improved detection performance compared to existing state-of-the-art methods. Conclusion: The proposed automated LSD identification framework provides a reliable, scalable, and cost-effective solution for early disease detection in cattle. The integration of image enhancement, texture feature extraction, and deep learning techniques can effectively support veterinarians and livestock farmers in disease monitoring and management.
- 1 January 2026
- Published by ScopeMed in Open Veterinary Journal
- Vol. 16  (7) , 4848
Automatic detection of animal disease using histogram and multi-scale multi-orientation Gabor Wavelet features with deep convolutional neural networks
Background: Lumpy Skin Disease (LSD) is an infectious cattle disease that poses a serious threat to animal welfare and the livestock industry. Conventional diagnostic approaches rely heavily on clinical examinations, laboratory testing, and veterinary expertise, making the detection process costly, labor-intensive, and time-consuming. Aim: This study aims to develop an automated framework for the early identification of LSD in cattle using histogram-based image enhancement, Gabor wavelet feature extraction, and deep learning techniques. Methods: Initially, histogram enhancement techniques were applied to cattle images to improve image quality and emphasize lesion regions. Subsequently, Gabor wavelet features with different scales and orientations were extracted to capture significant texture patterns related to skin abnormalities and disease characteristics. The extracted features were then classified into healthy and infected categories using various deep learning architectures, including CNN, DenseNet121, ResNet50V2, InceptionV3, VGG16, VGG19, and Xception. The proposed framework was evaluated using three benchmark datasets: Mendeley, Kaggle, and Veterinary Research LSD datasets. Results: The experimental evaluation demonstrated that the proposed framework achieved high classification accuracies of 97.5% on the Mendeley dataset, 97% on the Kaggle dataset, and 97% on the Veterinary Research LSD dataset. The integration of histogram enhancement and Gabor texture analysis with CNN-based models significantly improved detection performance compared to existing state-of-the-art methods. Conclusion: The proposed automated LSD identification framework provides a reliable, scalable, and cost-effective solution for early disease detection in cattle. The integration of image enhancement, texture feature extraction, and deep learning techniques can effectively support veterinarians and livestock farmers in disease monitoring and management.
- 10 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Evaluate Machine Learning Techniques for Early Disease of Cardiovascular Disease
Cardiovascular diseases are one of the major causes of death around the world, and their early detection is critical for effective intervention. The paper presents a systematic review of machine learning techniques used for the early prediction of cardiovascular diseases, focusing on studies carried out between 2019 and 2024. Widely used models considered in the review include Logistic Regression, Support Vector Machines, Random Forest, K-Nearest Neighbors, Gradient Boosting, and hybrid ensemble methods with the aim of ascertaining predictive accuracy, interpretability, and clinical relevance. In most of the reviewed studies, ensemble and Random Forest models attained the highest accuracies of $\mathbf{9 0 \% - 9 8 \%}$, while Gradient Boosting and SVMs were mostly above 90% in balanced datasets. Logistic Regression had a moderate accuracy of $85 \%-91 \%$ but remained the most interpretable, while KNN established the lowest performance of $80 \%-86 \%$. Despite the promising strides, there are a number of limitations, such as imbalance in datasets, limited external validation, and small benchmark datasets, that are limiting general application in health. This systematic review highlights strengths and weaknesses of the contemporary machine learning approaches and makes it evident that clinically validated, interpretable, and generalizable models should be developed in order to assist real-world medical decision-making.- 10 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Evaluate Machine Learning Techniques for Early Disease of Cardiovascular Disease
Cardiovascular diseases are one of the major causes of death around the world, and their early detection is critical for effective intervention. The paper presents a systematic review of machine learning techniques used for the early prediction of cardiovascular diseases, focusing on studies carried out between 2019 and 2024. Widely used models considered in the review include Logistic Regression, Support Vector Machines, Random Forest, K-Nearest Neighbors, Gradient Boosting, and hybrid ensemble methods with the aim of ascertaining predictive accuracy, interpretability, and clinical relevance. In most of the reviewed studies, ensemble and Random Forest models attained the highest accuracies of $\mathbf{9 0 \% - 9 8 \%}$, while Gradient Boosting and SVMs were mostly above 90% in balanced datasets. Logistic Regression had a moderate accuracy of $85 \%-91 \%$ but remained the most interpretable, while KNN established the lowest performance of $80 \%-86 \%$. Despite the promising strides, there are a number of limitations, such as imbalance in datasets, limited external validation, and small benchmark datasets, that are limiting general application in health. This systematic review highlights strengths and weaknesses of the contemporary machine learning approaches and makes it evident that clinically validated, interpretable, and generalizable models should be developed in order to assist real-world medical decision-making.- 9 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 886-890
Comparative Analysis of Machine Learning Algorithms for Effective Crop Recommendation
The global call for sustainable farming necessitates a move away from traditional crop selection methods. These conventional approaches, often relying on farmer intuition, are imprecise and scale poorly in the face of complex environmental variables. Machine Learning (ML) models offer a robust, datadriven solution. By analyzing multifaceted data-spanning soil chemistry, weather patterns, precipitation trends, and historical yield performance-ML models can significantly enhance decision-making, optimize resource utilization, and improve overall crop outcomes. This paper delivers an extensive comparative review of key ML algorithms employed for crop recommendation, including Decision Trees (DT), Random Forests (RF), Support Vector Machines (SVM), k-Nearest Neighbors (KNN), and Artificial Neural Networks (ANN). We also explore the critical role of Explainable AI (XAI) in building model transparency. Our study evaluates these models on the metrics of accuracy, interpretability, and computational overhead. The research also investigates hybrid methods that integrate deep learning with conventional ML to enhance predictive power. Our comparative findings highlight the strengths and weaknesses of each model, concluding that ANN and XAI-based approaches demonstrate the highest accuracy and adaptability for diverse agricultural conditions. We also identify significant challenges, such as data imbalances and the absence of real-time data, and discuss future trends like the integration of IoT, remote sensing, and federated learning, which will be key to making precision farming scalable and accessible.
- 9 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 886-890
Comparative Analysis of Machine Learning Algorithms for Effective Crop Recommendation
The global call for sustainable farming necessitates a move away from traditional crop selection methods. These conventional approaches, often relying on farmer intuition, are imprecise and scale poorly in the face of complex environmental variables. Machine Learning (ML) models offer a robust, datadriven solution. By analyzing multifaceted data-spanning soil chemistry, weather patterns, precipitation trends, and historical yield performance-ML models can significantly enhance decision-making, optimize resource utilization, and improve overall crop outcomes. This paper delivers an extensive comparative review of key ML algorithms employed for crop recommendation, including Decision Trees (DT), Random Forests (RF), Support Vector Machines (SVM), k-Nearest Neighbors (KNN), and Artificial Neural Networks (ANN). We also explore the critical role of Explainable AI (XAI) in building model transparency. Our study evaluates these models on the metrics of accuracy, interpretability, and computational overhead. The research also investigates hybrid methods that integrate deep learning with conventional ML to enhance predictive power. Our comparative findings highlight the strengths and weaknesses of each model, concluding that ANN and XAI-based approaches demonstrate the highest accuracy and adaptability for diverse agricultural conditions. We also identify significant challenges, such as data imbalances and the absence of real-time data, and discuss future trends like the integration of IoT, remote sensing, and federated learning, which will be key to making precision farming scalable and accessible.
- 28 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Visualization of Data Structures and Algorithms with Dynamic Memory Allocation
Data Structures and Algorithms (DSA) is fundamental to computer science education, yet novice learners face significant challenges in grasping abstract concepts and their system-level implications, such as dynamic memory allocation. This paper presents a novel web-based platform designed to enhance learning outcomes for beginner to intermediate students through interactive step-by-step visualizations of DSA, including arrays, linked lists, stacks, queues, and searching and sorting algorithms. A distinctive feature is the integration of dynamic memory allocation visualization, illustrating stack and heap to elucidate system-level operations. Developed using Next.js, Tailwind CSS, D3.js, and Framer Motion, the platform offers a space-themed responsive interface with synchronized code, data structure, and memory views. By addressing pedagogical gaps in tools like VisuAlgo, this work aligns with Sustainable Development Goal 4- Quality Education, promoting accessible and equitable learning.
- 28 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Visualization of Data Structures and Algorithms with Dynamic Memory Allocation
Data Structures and Algorithms (DSA) is fundamental to computer science education, yet novice learners face significant challenges in grasping abstract concepts and their system-level implications, such as dynamic memory allocation. This paper presents a novel web-based platform designed to enhance learning outcomes for beginner to intermediate students through interactive step-by-step visualizations of DSA, including arrays, linked lists, stacks, queues, and searching and sorting algorithms. A distinctive feature is the integration of dynamic memory allocation visualization, illustrating stack and heap to elucidate system-level operations. Developed using Next.js, Tailwind CSS, D3.js, and Framer Motion, the platform offers a space-themed responsive interface with synchronized code, data structure, and memory views. By addressing pedagogical gaps in tools like VisuAlgo, this work aligns with Sustainable Development Goal 4- Quality Education, promoting accessible and equitable learning.
- 1 August 2025
- Published by Springer Nature in Mobile Networks and Applications
- Vol. 30  (3-4) , 341-355
ANFIS-Based Multi-Sensor Data Fusion Model for Optimized Autonomous Vehicle Navigation Using Big Data and Filtering Techniques
- 1 August 2025
- Published by Springer Nature in Mobile Networks and Applications
- Vol. 30  (3-4) , 341-355
ANFIS-Based Multi-Sensor Data Fusion Model for Optimized Autonomous Vehicle Navigation Using Big Data and Filtering Techniques
- Open Access
- 8 July 2025
- Published by Elsevier in Results in Engineering
- Vol. 27
An explainable AI-based framework for predicting and optimizing blast-induced ground vibrations in surface mining
- 8 July 2025
- Published by Elsevier in Results in Engineering
- Vol. 27
Open AccessAn explainable AI-based framework for predicting and optimizing blast-induced ground vibrations in surface mining
- 13 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
An Explainable AI Techniques for Advancing Diabetes Prediction Using Machine Learning
Researchers have developed an automated system to identify diabetes risk. This system combines data from two sources: a collection of female patients in Bangladesh and an expanded dataset from a local textile factory. The expanded dataset includes information from 203 additional patients. The system uses several techniques to improve its accuracy. It first identifies the most important factors for predicting diabetes, then employs a special model to estimate insulin levels. It also addresses challenges like imbalanced data (where one outcome is more common) and explains its predictions using artificial intelligence techniques. This system achieved the superlative results has an 81.0% accuracy rate, 0.812 F1 score, and 0.844 Area Under the Curve (AUC).. These metrics indicate strong performance in identifying diabetes risk.
- 13 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
An Explainable AI Techniques for Advancing Diabetes Prediction Using Machine Learning
Researchers have developed an automated system to identify diabetes risk. This system combines data from two sources: a collection of female patients in Bangladesh and an expanded dataset from a local textile factory. The expanded dataset includes information from 203 additional patients. The system uses several techniques to improve its accuracy. It first identifies the most important factors for predicting diabetes, then employs a special model to estimate insulin levels. It also addresses challenges like imbalanced data (where one outcome is more common) and explains its predictions using artificial intelligence techniques. This system achieved the superlative results has an 81.0% accuracy rate, 0.812 F1 score, and 0.844 Area Under the Curve (AUC).. These metrics indicate strong performance in identifying diabetes risk.
- Open Access
- 19 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 176511-176526
SIDNet: A SQL Injection Detection Network for Enhancing Cybersecurity
SQL (Structured Query Language) injection is one of the most prevalent and dangerous forms of cyber-attacks, posing significant threats to database management systems and the overall security of web applications. By exploiting vulnerabilities in web applications, attackers can execute malicious SQL statements, potentially compromising the integrity and confidentiality of critical data. To combat these threats, in this study, we introduce two novel CNN models, SIDNet-1 (SQL Injection-attack Detection Network-1) and SIDNet-2 (SQL Injection-attack Detection Network-2), specifically designed for the classification of SQL injection attacks to bolster web application security. Our comprehensive evaluation includes a comparison of the performance of these customized CNN models against traditional machine learning approaches, highlighting improvements in classification accuracy and reductions in false alarm rates. The proposed models have been experimented with two publicly available dataset SQLI (SQL-Injection) and SQLV2 (SQL-Injection version2). Specifically, SIDNet-1 achieves an impressive accuracy of 98.02% on the SQLI dataset, while SIDNet-2 closely follows with 97.54%. Furthermore, on the SQLIV2 dataset, SIDNet-1 attains 97.77%, and SIDNet-2 achieves 97.83% accuracy respectively.
- 19 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 176511-176526
Open AccessSIDNet: A SQL Injection Detection Network for Enhancing Cybersecurity
SQL (Structured Query Language) injection is one of the most prevalent and dangerous forms of cyber-attacks, posing significant threats to database management systems and the overall security of web applications. By exploiting vulnerabilities in web applications, attackers can execute malicious SQL statements, potentially compromising the integrity and confidentiality of critical data. To combat these threats, in this study, we introduce two novel CNN models, SIDNet-1 (SQL Injection-attack Detection Network-1) and SIDNet-2 (SQL Injection-attack Detection Network-2), specifically designed for the classification of SQL injection attacks to bolster web application security. Our comprehensive evaluation includes a comparison of the performance of these customized CNN models against traditional machine learning approaches, highlighting improvements in classification accuracy and reductions in false alarm rates. The proposed models have been experimented with two publicly available dataset SQLI (SQL-Injection) and SQLV2 (SQL-Injection version2). Specifically, SIDNet-1 achieves an impressive accuracy of 98.02% on the SQLI dataset, while SIDNet-2 closely follows with 97.54%. Furthermore, on the SQLIV2 dataset, SIDNet-1 attains 97.77%, and SIDNet-2 achieves 97.83% accuracy respectively.