A. B. Feroz Khan
Research Subjects
A. B. Feroz Khan has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
G. Anandharaj
3 shared publicationsAnandharaj G
2 shared publicationsN. Syed Siraj Ahmed
2 shared publicationsA. Althaf Ali
Department of Computer Applications, Madanapalle Institute of Technology & Science (MITS), Madanapalle, India
1 shared publicationA. Subramaneswara Rao
Department of Computer Applications, Madanapalle Institute of Technology & Science (MITS), Madanapalle, India
1 shared publication- Gunavathie Mariappan
Easwari Engineering College
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by Walter de Gruyter GmbH in International Journal on Smart Sensing and Intelligent Systems
- Vol. 19 (1)
A Deep Learning Framework for Brain Tumor Classification Using VGG16-Based Autoencoder with BiLSTM Feature Refinement
Brain tumor (BT) detection from magnetic resonance imaging (MRI) images plays a critical role in early diagnosis and effective treatment planning. This research proposes a novel deep learning framework that integrates a VGG16-based Convolutional Autoencoder (CAE) with a Bi-Directional Long Short-Term Memory (BiLSTM) network for accurate and robust BT classification. The VGG16-CAE is employed for hierarchical spatial feature extraction, capturing both low-level and high-level representations of MRI images, while the BiLSTM module models long-range dependencies within the extracted features, enhancing classification performance. The model was evaluated using the publicly available Kaggle Brain MRI Dataset with systematic hyperparameter tuning and fivefold cross-validation to ensure reproducibility and generalization. The proposed framework achieved superior performance, with an average accuracy of 96.8%, precision of 97.1%, recall of 96.5%, F1-score of 96.8%, and an ROC-AUC of 0.985, with narrow confidence intervals (CIs) indicating statistical robustness. Comparative analysis with baseline convolutional neural network (CNN) architectures (Standard VGG16, ResNet50, DenseNet121, and VGG16-CAE without BiLSTM) and recent literature demonstrated that the proposed method significantly outperforms existing approaches by effectively capturing sequential dependencies in MRI data. The modular design of the framework allows for future extensions, including tumor localization and segmentation tasks, making it a promising solution for clinical applications. This work highlights the advantage of combining hierarchical feature learning with sequential modeling for precise BT detection, contributing to improved decision support in neuro-oncology.
- 1 January 2026
- Published by Walter de Gruyter GmbH in International Journal on Smart Sensing and Intelligent Systems
- Vol. 19 (1)
Open AccessA Deep Learning Framework for Brain Tumor Classification Using VGG16-Based Autoencoder with BiLSTM Feature Refinement
Brain tumor (BT) detection from magnetic resonance imaging (MRI) images plays a critical role in early diagnosis and effective treatment planning. This research proposes a novel deep learning framework that integrates a VGG16-based Convolutional Autoencoder (CAE) with a Bi-Directional Long Short-Term Memory (BiLSTM) network for accurate and robust BT classification. The VGG16-CAE is employed for hierarchical spatial feature extraction, capturing both low-level and high-level representations of MRI images, while the BiLSTM module models long-range dependencies within the extracted features, enhancing classification performance. The model was evaluated using the publicly available Kaggle Brain MRI Dataset with systematic hyperparameter tuning and fivefold cross-validation to ensure reproducibility and generalization. The proposed framework achieved superior performance, with an average accuracy of 96.8%, precision of 97.1%, recall of 96.5%, F1-score of 96.8%, and an ROC-AUC of 0.985, with narrow confidence intervals (CIs) indicating statistical robustness. Comparative analysis with baseline convolutional neural network (CNN) architectures (Standard VGG16, ResNet50, DenseNet121, and VGG16-CAE without BiLSTM) and recent literature demonstrated that the proposed method significantly outperforms existing approaches by effectively capturing sequential dependencies in MRI data. The modular design of the framework allows for future extensions, including tumor localization and segmentation tasks, making it a promising solution for clinical applications. This work highlights the advantage of combining hierarchical feature learning with sequential modeling for precise BT detection, contributing to improved decision support in neuro-oncology.
- Open Access
- 1 January 2025
- Published by FapUNIFESP (SciELO) in Engenharia Sanitaria e Ambiental
- Vol. 30
Decoding regional SARS-CoV-2 mutational landscapes using PCA and t-SNE-enhanced clustering techniques
The rapid global spread of SARS-CoV-2 has underscored the importance of understanding its genomic diversity and evolutionary dynamics across different regions. This study proposes a dimensionality-reduced clustering framework to investigate SARS-CoV-2 genome sequences collected from countries with high infection rates, including Spain, Italy, and the USA. High-dimensional genomic data were preprocessed using k-mer encoding and subsequently reduced using principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE), enabling improved visualization and interpretability. Clustering algorithms such as hierarchical clustering and DBSCAN were then applied to detect inherent groupings within the genome sequences. The results revealed distinct clusters associated with dominant mutations, such as D614G, P681H, and N501Y, primarily affecting the Spike protein and other structural regions. Notably, strong intra-cluster similarities were observed between sequences from Spain and Italy, suggesting shared evolutionary origins and transmission links, while certain USA sequences showed overlap with European variants. Comparative analyses highlighted the biological relevance of these mutations in increased infectivity and immune evasion. This integrative approach not only captures country-specific and cross-regional genomic relationships but also contributes to enhanced variant monitoring and global pandemic response strategies.
- 1 January 2025
- Published by FapUNIFESP (SciELO) in Engenharia Sanitaria e Ambiental
- Vol. 30
Open AccessDecoding regional SARS-CoV-2 mutational landscapes using PCA and t-SNE-enhanced clustering techniques
The rapid global spread of SARS-CoV-2 has underscored the importance of understanding its genomic diversity and evolutionary dynamics across different regions. This study proposes a dimensionality-reduced clustering framework to investigate SARS-CoV-2 genome sequences collected from countries with high infection rates, including Spain, Italy, and the USA. High-dimensional genomic data were preprocessed using k-mer encoding and subsequently reduced using principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE), enabling improved visualization and interpretability. Clustering algorithms such as hierarchical clustering and DBSCAN were then applied to detect inherent groupings within the genome sequences. The results revealed distinct clusters associated with dominant mutations, such as D614G, P681H, and N501Y, primarily affecting the Spike protein and other structural regions. Notably, strong intra-cluster similarities were observed between sequences from Spain and Italy, suggesting shared evolutionary origins and transmission links, while certain USA sequences showed overlap with European variants. Comparative analyses highlighted the biological relevance of these mutations in increased infectivity and immune evasion. This integrative approach not only captures country-specific and cross-regional genomic relationships but also contributes to enhanced variant monitoring and global pandemic response strategies.
- Retracted
- 23 October 2024
- Published by Springer Nature in Wireless Personal Communications
- Vol. 139 (1) , 107-144
RETRACTED ARTICLE: Detection of Assaults in Network Intrusion System using Rough Set and Convolutional Neural Network
- 23 October 2024
- Published by Springer Nature in Wireless Personal Communications
- Vol. 139 (1) , 107-144
RetractedRETRACTED ARTICLE: Detection of Assaults in Network Intrusion System using Rough Set and Convolutional Neural Network
- 2 August 2024
- Published by Springer Nature in Wireless Personal Communications
- Vol. 137 (4) , 2397-2407
An Enhanced Multi Attribute Based Trusted Attack Resistance (EMBTR) for the Secure Routing of Sensor Nodes in Wireless Sensor Network
- 2 August 2024
- Published by Springer Nature in Wireless Personal Communications
- Vol. 137 (4) , 2397-2407
An Enhanced Multi Attribute Based Trusted Attack Resistance (EMBTR) for the Secure Routing of Sensor Nodes in Wireless Sensor Network
- Open Access
- 13 March 2024
- Published by Acadlore Publishing Services Limited in Education Science and Management
- Vol. 2 (1) , 25-34
Evaluating Online Learning Adaptability in Students Using Machine Learning-Based Techniques: A Novel Analytical Approach
The widespread adoption of Learning Management Systems (LMSs) in educational contexts, underscored by their critical role in facilitating cloud-based training across diverse settings, serves as the foundation of this investigation. In the era of increasing integration of technology within higher education, a notable reduction in the costs associated with the creation of online content has been observed. The shift towards remote learning, precipitated by the COVID-19 pandemic, has highlighted the indispensable nature of LMSs in the delivery of specialized content, the application of varied pedagogical strategies, and the promotion of student engagement. Adaptability, defined as the ability to adjust behavior, cognition, and emotional responses in the face of new circumstances, has been recognized as a key factor in the success of online learning. This study employs sophisticated Machine Learning Techniques (MLTs) to explore the determinants of student adaptability, introducing the novel framework of Online Learner Adaptability Assessment using MLTs (OLAMLTs). Through the analysis of comprehensive datasets, which include indicators of student behavior, performance, and engagement within online platforms, MLTs facilitate the identification of patterns and correlations pertinent to adaptability. The OLAMLTs framework applies a retrospective analysis to variables such as technological proficiency, motivation, and self-regulatory capabilities, enabling the provision of customized recommendations for educators. By facilitating targeted educational interventions, the study seeks to address the disparity between the need for adaptable learners and the availability of tools designed to foster this critical attribute. The ultimate aim is to augment the resilience and efficacy of online learning platforms in anticipation of future disruptions, including pandemics or other unforeseen challenges. This research contributes to the ongoing efforts to develop a more adaptive and resilient online learning landscape, marking a significant advancement in the fields of educational technology and pedagogy.
- 13 March 2024
- Published by Acadlore Publishing Services Limited in Education Science and Management
- Vol. 2 (1) , 25-34
Open AccessEvaluating Online Learning Adaptability in Students Using Machine Learning-Based Techniques: A Novel Analytical Approach
The widespread adoption of Learning Management Systems (LMSs) in educational contexts, underscored by their critical role in facilitating cloud-based training across diverse settings, serves as the foundation of this investigation. In the era of increasing integration of technology within higher education, a notable reduction in the costs associated with the creation of online content has been observed. The shift towards remote learning, precipitated by the COVID-19 pandemic, has highlighted the indispensable nature of LMSs in the delivery of specialized content, the application of varied pedagogical strategies, and the promotion of student engagement. Adaptability, defined as the ability to adjust behavior, cognition, and emotional responses in the face of new circumstances, has been recognized as a key factor in the success of online learning. This study employs sophisticated Machine Learning Techniques (MLTs) to explore the determinants of student adaptability, introducing the novel framework of Online Learner Adaptability Assessment using MLTs (OLAMLTs). Through the analysis of comprehensive datasets, which include indicators of student behavior, performance, and engagement within online platforms, MLTs facilitate the identification of patterns and correlations pertinent to adaptability. The OLAMLTs framework applies a retrospective analysis to variables such as technological proficiency, motivation, and self-regulatory capabilities, enabling the provision of customized recommendations for educators. By facilitating targeted educational interventions, the study seeks to address the disparity between the need for adaptable learners and the availability of tools designed to foster this critical attribute. The ultimate aim is to augment the resilience and efficacy of online learning platforms in anticipation of future disruptions, including pandemics or other unforeseen challenges. This research contributes to the ongoing efforts to develop a more adaptive and resilient online learning landscape, marking a significant advancement in the fields of educational technology and pedagogy.
- Open Access
- 31 December 2023
- Published by Acadlore Publishing Services Limited in Journal of Urban Development and Management
- Vol. 2 (4) , 211-221
Integrating Machine Learning and Deep Learning in Smart Cities for Enhanced Traffic Congestion Management: An Empirical Review
In the rapid urbanization experienced globally, traffic congestion emerges as a critical challenge, detrimentally affecting economic performance and the quality of urban life. This study delves into the deployment of machine learning (ML) and deep learning (DL) methodologies for mitigating traffic congestion within smart city frameworks. An extensive literature review coupled with empirical analysis is conducted to scrutinize the application of these advanced technologies in various transportation domains, including but not limited to traffic flow prediction, optimization of routing, adaptive control of traffic signals, dynamic management of traffic systems, implementation of smart parking solutions, enhancement of public transportation systems, anomaly detection, and seamless integration with the Internet of Things (IoT) and sensor networks. The research methodology encompasses a detailed outline of data sources, the selection of ML and DL models, along with the processes of training and evaluation. Findings from the experiments underscore the efficacy of these technological interventions in real-world settings, highlighting notable advancements in the precision of traffic predictions, the efficiency of route optimization, and the responsiveness of adaptive traffic signal controls. Moreover, the study elucidates the pivotal role of ML and DL in facilitating dynamic traffic management, anomaly detection, smart parking, and the optimization of public transportation. Through illustrative case studies and examples from cities that have embraced these technologies, practical insights into their applicability and the consequential impact on urban mobility are provided. The research also addresses challenges encountered, offering a discourse on potential avenues for future research to further refine traffic congestion management strategies in smart cities. This contribution significantly enriches the existing corpus of knowledge, presenting pragmatic solutions for urban planners and policy makers to foster more efficient and sustainable transportation infrastructures.
- 31 December 2023
- Published by Acadlore Publishing Services Limited in Journal of Urban Development and Management
- Vol. 2 (4) , 211-221
Open AccessIntegrating Machine Learning and Deep Learning in Smart Cities for Enhanced Traffic Congestion Management: An Empirical Review
In the rapid urbanization experienced globally, traffic congestion emerges as a critical challenge, detrimentally affecting economic performance and the quality of urban life. This study delves into the deployment of machine learning (ML) and deep learning (DL) methodologies for mitigating traffic congestion within smart city frameworks. An extensive literature review coupled with empirical analysis is conducted to scrutinize the application of these advanced technologies in various transportation domains, including but not limited to traffic flow prediction, optimization of routing, adaptive control of traffic signals, dynamic management of traffic systems, implementation of smart parking solutions, enhancement of public transportation systems, anomaly detection, and seamless integration with the Internet of Things (IoT) and sensor networks. The research methodology encompasses a detailed outline of data sources, the selection of ML and DL models, along with the processes of training and evaluation. Findings from the experiments underscore the efficacy of these technological interventions in real-world settings, highlighting notable advancements in the precision of traffic predictions, the efficiency of route optimization, and the responsiveness of adaptive traffic signal controls. Moreover, the study elucidates the pivotal role of ML and DL in facilitating dynamic traffic management, anomaly detection, smart parking, and the optimization of public transportation. Through illustrative case studies and examples from cities that have embraced these technologies, practical insights into their applicability and the consequential impact on urban mobility are provided. The research also addresses challenges encountered, offering a discourse on potential avenues for future research to further refine traffic congestion management strategies in smart cities. This contribution significantly enriches the existing corpus of knowledge, presenting pragmatic solutions for urban planners and policy makers to foster more efficient and sustainable transportation infrastructures.
- 15 November 2023
- Published by Springer Nature in SN Computer Science
- Vol. 5 (1) , 1-8
Enhancing Security in the Internet of Things: A Trust-Based Protocol for Resilient Communication
- 15 November 2023
- Published by Springer Nature in SN Computer Science
- Vol. 5 (1) , 1-8
Enhancing Security in the Internet of Things: A Trust-Based Protocol for Resilient Communication
- Open Access
- 1 August 2023
- Published by ITMO University in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
- Vol. 23 (4) , 711
An enhanced AES-GCM based security protocol for securing the IoT communication
In the recent years, the devices in Internet of Things (IoT) are growing exponentially due to the emergence of many sophisticated applications. This tremendous growth leads to serious security challenges and the devices of Wireless Sensor Networks should be protected from various attacks. IoT can be configured dynamically without fixed infrastructure and the devices are communicated with one another in an Ad-hoc manner. The work presents the classification of various DDoS attacks in the IoT environment and provides a solution for replay attack. All variations of DDoS attacks are modeled using UML based activity modeling. This clearly understands the behavior of each version of attacks and their performance in the environment. The modeling also helps to construct a solution to prevent this attack from its execution. The work also proposed a trust based protocol for replay attacks which allows the attack inside the network and blocks it after identifying the attack based on its specific behavior. The network performance is improved after implementing this proposed protocol inside the network with help of simulation under realistic conditions. The performance metrics considered in the work are energy, packet loss, computational time and throughput. The paper compares the performance with the state-of-the-art schemes such as Efficient Distributed Deterministic Key and Hash- based Message Authentication Code. The experimental analysis proved that the proposed scheme outperforms the other state-of-the-works in terms of computational cost, throughput, and delay.
- 1 August 2023
- Published by ITMO University in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
- Vol. 23 (4) , 711
Open AccessAn enhanced AES-GCM based security protocol for securing the IoT communication
In the recent years, the devices in Internet of Things (IoT) are growing exponentially due to the emergence of many sophisticated applications. This tremendous growth leads to serious security challenges and the devices of Wireless Sensor Networks should be protected from various attacks. IoT can be configured dynamically without fixed infrastructure and the devices are communicated with one another in an Ad-hoc manner. The work presents the classification of various DDoS attacks in the IoT environment and provides a solution for replay attack. All variations of DDoS attacks are modeled using UML based activity modeling. This clearly understands the behavior of each version of attacks and their performance in the environment. The modeling also helps to construct a solution to prevent this attack from its execution. The work also proposed a trust based protocol for replay attacks which allows the attack inside the network and blocks it after identifying the attack based on its specific behavior. The network performance is improved after implementing this proposed protocol inside the network with help of simulation under realistic conditions. The performance metrics considered in the work are energy, packet loss, computational time and throughput. The paper compares the performance with the state-of-the-art schemes such as Efficient Distributed Deterministic Key and Hash- based Message Authentication Code. The experimental analysis proved that the proposed scheme outperforms the other state-of-the-works in terms of computational cost, throughput, and delay.
- Open Access
- 31 March 2023
- Published by Acadlore Publishing Services Limited in Information Dynamics and Applications
- Vol. 2 (1) , 1-7
ECO-LEACH: A Blockchain-Based Distributed Routing Protocol for Energy-Efficient Wireless Sensor Networks
This paper proposes a novel architecture based on blockchain technology to enhance the dependability and safety of wireless sensor networks (WSN) by authenticating WSN nodes. In a WSN, sensor nodes collect and transmit data to cluster heads (CHs) for further processing. The proposed model employs the distance and residual energy-based low-energy adaptive clustering hierarchy (ECO-LEACH) protocol to replace CHs with ordinary nodes and the Interplanetary File System (IPFS) for storing data. In addition, consensus based on proof of authority (PoA) is used to validate transactions, reducing the computational cost associated with proof of work. The proposed system was evaluated using simulations with 300 sensor nodes and compared with other protocols, including LEACH, DDR-LEACH, PEGASIS, and LEACH-PSO. The simulation results showed that the proposed ECO-LEACH outperformed the other protocols in terms of energy consumption, throughput achieved, and network lifetime improvement. Specifically, the proposed system consumed 23.5J for 300 sensor nodes, achieved 687.5 kbps, and improved the network's lifetime by 4.12 seconds for 50 rounds. Overall, this paper provides a reliable and secure solution for authenticating WSN nodes, enhancing data transfer safety, and dependability. The proposed architecture offers a promising approach for addressing the challenges of WSN design using blockchain technology and PoA consensus. The comparative analysis shows that the proposed ECO-LEACH protocol outperforms other protocols in terms of energy consumption, throughput achieved, and network lifetime improvement for 300 sensor nodes.
- 31 March 2023
- Published by Acadlore Publishing Services Limited in Information Dynamics and Applications
- Vol. 2 (1) , 1-7
Open AccessECO-LEACH: A Blockchain-Based Distributed Routing Protocol for Energy-Efficient Wireless Sensor Networks
This paper proposes a novel architecture based on blockchain technology to enhance the dependability and safety of wireless sensor networks (WSN) by authenticating WSN nodes. In a WSN, sensor nodes collect and transmit data to cluster heads (CHs) for further processing. The proposed model employs the distance and residual energy-based low-energy adaptive clustering hierarchy (ECO-LEACH) protocol to replace CHs with ordinary nodes and the Interplanetary File System (IPFS) for storing data. In addition, consensus based on proof of authority (PoA) is used to validate transactions, reducing the computational cost associated with proof of work. The proposed system was evaluated using simulations with 300 sensor nodes and compared with other protocols, including LEACH, DDR-LEACH, PEGASIS, and LEACH-PSO. The simulation results showed that the proposed ECO-LEACH outperformed the other protocols in terms of energy consumption, throughput achieved, and network lifetime improvement. Specifically, the proposed system consumed 23.5J for 300 sensor nodes, achieved 687.5 kbps, and improved the network's lifetime by 4.12 seconds for 50 rounds. Overall, this paper provides a reliable and secure solution for authenticating WSN nodes, enhancing data transfer safety, and dependability. The proposed architecture offers a promising approach for addressing the challenges of WSN design using blockchain technology and PoA consensus. The comparative analysis shows that the proposed ECO-LEACH protocol outperforms other protocols in terms of energy consumption, throughput achieved, and network lifetime improvement for 300 sensor nodes.