Khaja Shareef Shaik
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Khaja Shareef Shaik has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
Srihari Varma Mantena
Department of Computer Science and Engineering, SRKR Engineering College, Bhimavaram, India
2 shared publicationsV. Rama Raju
CMR College of Engineering & Technology Hyderabad
2 shared publicationsAllam Balaram
MLR Institute of Technology
1 shared publication- Allam Balaram
MLR Institute of Technology
1 shared publication Alpha Vijayan
Department of AI and Data Science Engineering, School of Engineering and Technology, Christ University, Bengaluru, India
1 shared publicationC. R. Aditya
Vidyavardhaka College of Engineering, Mysuru, India
1 shared publication
Latest Publications
- Open Access
- 25 October 2026
- Published by Springer Nature in Scientific Reports
Adaptive active learning and metaheuristic-optimized transformer framework for robust intrusion detection in software-defined networks
Existing intrusion detection systems largely rely on static supervised learning models that require extensive labeled data and periodic retraining. Such approaches struggle to adapt to evolving attack patterns in dynamic software-defined networks. To address these limitations, this study proposes an adaptive intrusion detection framework that integrates uncertainty-driven active learning, metaheuristic-based feature selection, Transformer-based attack classification, and adaptive hyperparameter optimization within a unified software-defined networking architecture. Unlike conventional adaptive intrusion detection systems that rely on static feature representations or fixed learning strategies, the proposed framework continuously refines both the training data and model configuration to improve robustness against evolving cyberattacks. The proposed framework iteratively identifies informative samples for annotation, optimizes feature subsets using adaptive search, and continuously updates the classifier to maintain high detection performance under changing traffic distributions. The proposed system was evaluated using the ToN-IoT dataset and additional real-world traffic traces. Experimental evaluation on benchmark and real-world network traffic datasets demonstrated a detection accuracy of up to 97.92% and an F1-score of 97.10%. Although the optimization stage increases offline training time, the optimized model maintains efficient inference during deployment, making it suitable for practical software-defined network environments. Performance was evaluated over five independent runs using different random initialization seeds. Although the optimization and active-learning stages increase offline training time, the optimized model maintains efficient inference during deployment. Performance was evaluated over five independent runs using different random initialization seeds. The results demonstrate that the complementary use of adaptive sample acquisition, feature selection, and hyperparameter optimization provides an effective intrusion-detection framework for software-defined network environments.
- 25 October 2026
- Published by Springer Nature in Scientific Reports
Open AccessAdaptive active learning and metaheuristic-optimized transformer framework for robust intrusion detection in software-defined networks
Existing intrusion detection systems largely rely on static supervised learning models that require extensive labeled data and periodic retraining. Such approaches struggle to adapt to evolving attack patterns in dynamic software-defined networks. To address these limitations, this study proposes an adaptive intrusion detection framework that integrates uncertainty-driven active learning, metaheuristic-based feature selection, Transformer-based attack classification, and adaptive hyperparameter optimization within a unified software-defined networking architecture. Unlike conventional adaptive intrusion detection systems that rely on static feature representations or fixed learning strategies, the proposed framework continuously refines both the training data and model configuration to improve robustness against evolving cyberattacks. The proposed framework iteratively identifies informative samples for annotation, optimizes feature subsets using adaptive search, and continuously updates the classifier to maintain high detection performance under changing traffic distributions. The proposed system was evaluated using the ToN-IoT dataset and additional real-world traffic traces. Experimental evaluation on benchmark and real-world network traffic datasets demonstrated a detection accuracy of up to 97.92% and an F1-score of 97.10%. Although the optimization stage increases offline training time, the optimized model maintains efficient inference during deployment, making it suitable for practical software-defined network environments. Performance was evaluated over five independent runs using different random initialization seeds. Although the optimization and active-learning stages increase offline training time, the optimized model maintains efficient inference during deployment. Performance was evaluated over five independent runs using different random initialization seeds. The results demonstrate that the complementary use of adaptive sample acquisition, feature selection, and hyperparameter optimization provides an effective intrusion-detection framework for software-defined network environments.
- Open Access
- 18 September 2025
- Published by Springer Nature in Discover Computing
- Vol. 28 (1) , 1-28
A novel ensemble deep learning framework with spatial attention and high-order pooling for COPD detection
- 18 September 2025
- Published by Springer Nature in Discover Computing
- Vol. 28 (1) , 1-28
Open AccessA novel ensemble deep learning framework with spatial attention and high-order pooling for COPD detection
- Open Access
- 1 December 2023
- Published by Acadlore Publishing Services Limited in Healthcraft Frontiers
- Vol. 1 (1) , 15-32
Segmentation and Classification of Skin Cancer in Dermoscopy Images Using SAM-Based Deep Belief Networks
In the field of computer-aided diagnostics, the segmentation and classification of biomedical images play a pivotal role. This study introduces a novel approach employing a Self-Augmented Multistage Deep Learning Network (SAMNetwork) and Deep Belief Networks (DBNs) optimized by Coot Optimization Algorithms (COAs) for the analysis of dermoscopy images. The unique challenges posed by dermoscopy images, including complex detection backgrounds and lesion characteristics, necessitate advanced techniques for accurate lesion recognition. Traditional methods have predominantly focused on utilizing larger, more complex models to increase detection accuracy, yet have often neglected the significant intraclass variability and inter-class similarity of lesion traits. This oversight has led to challenges in algorithmic application to larger models. The current research addresses these limitations by leveraging SAM, which, although not yielding immediate high-quality segmentation for medical image data, provides valuable masks, features, and stability scores for developing and training enhanced medical images. Subsequently, DBNs, aided by COAs to fine-tune their hyper-parameters, perform the classification task. The effectiveness of this methodology was assessed through comprehensive experimental comparisons and feature visualization analyses. The results demonstrated the superiority of the proposed approach over the current state-of-the-art deep learning-based methods across three datasets: ISBI 2017, ISBI 2018, and the PH2 dataset. In the experimental evaluations, the Multi-class Dilated D-Net (MD2N) model achieved a Matthew’s Correlation Coefficient (MCC) of 0.86201, the Deep convolutional neural networks (DCNN) model 0.84111, the standalone DBN 0.91157, the autoencoder (AE) model 0.88662, and the DBN-COA model 0.93291, respectively. These findings highlight the enhanced performance and potential of integrating SAM with optimized DBNs in the detection and classification of skin cancer in dermoscopy images, marking a significant advancement in the field of medical image analysis.
- 1 December 2023
- Published by Acadlore Publishing Services Limited in Healthcraft Frontiers
- Vol. 1 (1) , 15-32
Open AccessSegmentation and Classification of Skin Cancer in Dermoscopy Images Using SAM-Based Deep Belief Networks
In the field of computer-aided diagnostics, the segmentation and classification of biomedical images play a pivotal role. This study introduces a novel approach employing a Self-Augmented Multistage Deep Learning Network (SAMNetwork) and Deep Belief Networks (DBNs) optimized by Coot Optimization Algorithms (COAs) for the analysis of dermoscopy images. The unique challenges posed by dermoscopy images, including complex detection backgrounds and lesion characteristics, necessitate advanced techniques for accurate lesion recognition. Traditional methods have predominantly focused on utilizing larger, more complex models to increase detection accuracy, yet have often neglected the significant intraclass variability and inter-class similarity of lesion traits. This oversight has led to challenges in algorithmic application to larger models. The current research addresses these limitations by leveraging SAM, which, although not yielding immediate high-quality segmentation for medical image data, provides valuable masks, features, and stability scores for developing and training enhanced medical images. Subsequently, DBNs, aided by COAs to fine-tune their hyper-parameters, perform the classification task. The effectiveness of this methodology was assessed through comprehensive experimental comparisons and feature visualization analyses. The results demonstrated the superiority of the proposed approach over the current state-of-the-art deep learning-based methods across three datasets: ISBI 2017, ISBI 2018, and the PH2 dataset. In the experimental evaluations, the Multi-class Dilated D-Net (MD2N) model achieved a Matthew’s Correlation Coefficient (MCC) of 0.86201, the Deep convolutional neural networks (DCNN) model 0.84111, the standalone DBN 0.91157, the autoencoder (AE) model 0.88662, and the DBN-COA model 0.93291, respectively. These findings highlight the enhanced performance and potential of integrating SAM with optimized DBNs in the detection and classification of skin cancer in dermoscopy images, marking a significant advancement in the field of medical image analysis.
- Open Access
- 6 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 124441-124458
Segmentation Using the IC2T Model and Classification of Diabetic Retinopathy Using the Rock Hyrax Swarm-Based Coordination Attention Mechanism
Diabetic Retinopathy (DR) evaluations are increasingly being automated using artificial intelligence. Diabetes-related retinal vascular disease is a major cause of blindness and visual impairment worldwide. Therefore, automated DR detection devices would greatly aid in reducing visual impairment due to DR through early screening and treatment. Researchers have provided many techniques for picking out abnormalities in retinal images during the past several years. In the past, automated methods for diagnosing diabetic retinopathy required a human to extract information from retinal images before passing them on to a classifier. This study takes a novel two-pronged approach to automated DR classification to solve the issues. Due to the low positive instance percentage of existing asymmetric, we segment O.D.s and B.V.s with an enhanced version of an improved contoured convolutional transformer (IC2T). We develop a contoured optical disc (OD), a blood vessels (BV) detection module, and a dual convolutional transformer block that combines local and global contexts to make trustworthy associations. A second-stage Improved Coordination Attention Mechanism (ICAM) network is trained to recognize retinal biomarkers for DR such as microaneurysms (M.A.), haemorrhages (H.M.), and exudates (EX). With an average accuracy of 96%, 97%, and 98% on EyePACS-1, Messidor-2, and DIARETDB0, respectively, the suggested technique has proven itself to be at the field’s cutting edge. Comprehensive testing and comparisons to established methods support the proposed strategy.
- 6 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 124441-124458
Open AccessSegmentation Using the IC2T Model and Classification of Diabetic Retinopathy Using the Rock Hyrax Swarm-Based Coordination Attention Mechanism
Diabetic Retinopathy (DR) evaluations are increasingly being automated using artificial intelligence. Diabetes-related retinal vascular disease is a major cause of blindness and visual impairment worldwide. Therefore, automated DR detection devices would greatly aid in reducing visual impairment due to DR through early screening and treatment. Researchers have provided many techniques for picking out abnormalities in retinal images during the past several years. In the past, automated methods for diagnosing diabetic retinopathy required a human to extract information from retinal images before passing them on to a classifier. This study takes a novel two-pronged approach to automated DR classification to solve the issues. Due to the low positive instance percentage of existing asymmetric, we segment O.D.s and B.V.s with an enhanced version of an improved contoured convolutional transformer (IC2T). We develop a contoured optical disc (OD), a blood vessels (BV) detection module, and a dual convolutional transformer block that combines local and global contexts to make trustworthy associations. A second-stage Improved Coordination Attention Mechanism (ICAM) network is trained to recognize retinal biomarkers for DR such as microaneurysms (M.A.), haemorrhages (H.M.), and exudates (EX). With an average accuracy of 96%, 97%, and 98% on EyePACS-1, Messidor-2, and DIARETDB0, respectively, the suggested technique has proven itself to be at the field’s cutting edge. Comprehensive testing and comparisons to established methods support the proposed strategy.
- Open Access
- 22 August 2023
- Published by Acadlore Publishing Services Limited in Acadlore Transactions on AI and Machine Learning
- Vol. 2 (3) , 116-128
Advanced Hybrid Segmentation Model Leveraging AlexNet Architecture for Enhanced Liver Cancer Detection
Liver cancer, one of the rapidly escalating forms of cancer, remains a principal cause of mortality globally. Its death rates can be attenuated through vigilant monitoring and early detection. This study aims to develop a sophisticated model to assist medical professionals in the classification of liver tumours using biopsy tissue images, thereby facilitating preliminary diagnosis.The study presents a novel, bio-inspired deep learning strategy purposed for augmenting liver cancer detection. The uniqueness of this approach rests in its two-fold contribution: Firstly, an innovative hybrid segmentation technique, integrating the SegNet network, UNet network, and Al-Biruni Earth Radius (BER) procedure, is introduced to extract liver lesions from Computed Tomography (CT) images. The algorithm initially applies the SegNet to isolate the liver from the abdominal image in a CT scan. Since hyperparameters significantly influence segmentation performance, the BER algorithm is hybridized with each network for optimal tuning. The method proposed herein is inspired by the pursuit of a common objective by swarm members. Al-Biruni's methodology for calculating Earth's radius sets the search space, extending beyond local solutions that require exploration. Secondly, a pre-trained AlexNet model is utilized for diagnosis, further enhancing the method's effectiveness. The proposed segmentation and classification algorithms have been compared with contemporary state-of-the-art techniques. The results demonstrated that in terms of specificity, F1-score, accuracy, and computational time, the proposed method outperforms its competitors, indicating its potential in advancing liver cancer detection.
- 22 August 2023
- Published by Acadlore Publishing Services Limited in Acadlore Transactions on AI and Machine Learning
- Vol. 2 (3) , 116-128
Open AccessAdvanced Hybrid Segmentation Model Leveraging AlexNet Architecture for Enhanced Liver Cancer Detection
Liver cancer, one of the rapidly escalating forms of cancer, remains a principal cause of mortality globally. Its death rates can be attenuated through vigilant monitoring and early detection. This study aims to develop a sophisticated model to assist medical professionals in the classification of liver tumours using biopsy tissue images, thereby facilitating preliminary diagnosis.The study presents a novel, bio-inspired deep learning strategy purposed for augmenting liver cancer detection. The uniqueness of this approach rests in its two-fold contribution: Firstly, an innovative hybrid segmentation technique, integrating the SegNet network, UNet network, and Al-Biruni Earth Radius (BER) procedure, is introduced to extract liver lesions from Computed Tomography (CT) images. The algorithm initially applies the SegNet to isolate the liver from the abdominal image in a CT scan. Since hyperparameters significantly influence segmentation performance, the BER algorithm is hybridized with each network for optimal tuning. The method proposed herein is inspired by the pursuit of a common objective by swarm members. Al-Biruni's methodology for calculating Earth's radius sets the search space, extending beyond local solutions that require exploration. Secondly, a pre-trained AlexNet model is utilized for diagnosis, further enhancing the method's effectiveness. The proposed segmentation and classification algorithms have been compared with contemporary state-of-the-art techniques. The results demonstrated that in terms of specificity, F1-score, accuracy, and computational time, the proposed method outperforms its competitors, indicating its potential in advancing liver cancer detection.
- 1 April 2023
- Published by Springer Nature
- p. 103-114
A Novel Blockchain Framework for Enhancing Online Transactions
- 1 April 2023
- Published by Springer Nature
- p. 103-114
A Novel Blockchain Framework for Enhancing Online Transactions
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2492 (1)
Malicious activity detection using HTTP annotation patterns
Network Traffic analysis plays a vital role to detect the malware i.e HTTP-based threats noticed from the huge volume of continued network data due to lack of un-trusted weak software's, which affects the network operations, service registries and documents. As existing frameworks are unable to defend against increasing insecure malicious attacks due to the weak cryptographic system. In this connection, our proposed approach i.e. Knowledge-based detection system acquires the distinctive HTTP communication patterns on malware and make uses the uses the Knowledge to notice the bots activities in the supervised network effectively using HTTP based patterns.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2492 (1)
Open AccessMalicious activity detection using HTTP annotation patterns
Network Traffic analysis plays a vital role to detect the malware i.e HTTP-based threats noticed from the huge volume of continued network data due to lack of un-trusted weak software's, which affects the network operations, service registries and documents. As existing frameworks are unable to defend against increasing insecure malicious attacks due to the weak cryptographic system. In this connection, our proposed approach i.e. Knowledge-based detection system acquires the distinctive HTTP communication patterns on malware and make uses the uses the Knowledge to notice the bots activities in the supervised network effectively using HTTP based patterns.
- Open Access
- 30 September 2022
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 10 (3) , 536-543
An Intelligent Secure Monitoring Phase in Blockchain Framework for Large Transaction
Blockchain is the key concept for security purposes for digital applications. But, in some cases, the effectiveness of the malicious behavior has degraded the security function of the blockchain. So, to enrich the blockchain process prediction and to neglect the malicious event from the data broadcasting medium is very important. So, the current research article intends to develop an efficient monitoring strategy based on incorporating deep features. Hence, the designed paradigm is termed as Lion-based Convolutional Neural Model (LbCNM) with serpent encryption. Before performing the encryption process, the novel LbCNM parameters have been activated to monitor the data process channel in the blockchain environment. Here, the malicious behaviors were estimated by incorporating the known and unknown user behavior in the Lion fitness model. During the execution, the fitness formulation of Lion is acted in the classification layer of the convolutional model. Once the present malicious characteristics have been detected, it is neglected from the data broadcasting channel. Hereafter, the transactional data has been encrypted and stored in the specific cloud. The planned strategy is verified in the python platform. The successful performance of the LbCNM with serpent has been analyzed with some key parameters like confidential rate, accuracy, data overhead, and processing time.
- 30 September 2022
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 10 (3) , 536-543
Open AccessAn Intelligent Secure Monitoring Phase in Blockchain Framework for Large Transaction
Blockchain is the key concept for security purposes for digital applications. But, in some cases, the effectiveness of the malicious behavior has degraded the security function of the blockchain. So, to enrich the blockchain process prediction and to neglect the malicious event from the data broadcasting medium is very important. So, the current research article intends to develop an efficient monitoring strategy based on incorporating deep features. Hence, the designed paradigm is termed as Lion-based Convolutional Neural Model (LbCNM) with serpent encryption. Before performing the encryption process, the novel LbCNM parameters have been activated to monitor the data process channel in the blockchain environment. Here, the malicious behaviors were estimated by incorporating the known and unknown user behavior in the Lion fitness model. During the execution, the fitness formulation of Lion is acted in the classification layer of the convolutional model. Once the present malicious characteristics have been detected, it is neglected from the data broadcasting channel. Hereafter, the transactional data has been encrypted and stored in the specific cloud. The planned strategy is verified in the python platform. The successful performance of the LbCNM with serpent has been analyzed with some key parameters like confidential rate, accuracy, data overhead, and processing time.
- 14 September 2022
- Published by Springer Nature
- p. 35-44
Efficient Identity-Based Integrity Auditing for Cloud Storage and Data Sharing
- 14 September 2022
- Published by Springer Nature
- p. 35-44
Efficient Identity-Based Integrity Auditing for Cloud Storage and Data Sharing