Ankush Jain
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
Ankush Jain has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Surendra Nagar
Netaji Subhas University of Technology
10 shared publications - Pramod Kumar Singh
Atal Bihari Vajpayee Indian Institute of Information Technology and Management, Gwalior, India
7 shared publications - Ajay Kumar
Department of Engineering Sciences, Atal Bihari Vajpayee Indian Institute of Information Technology and Management, Gwalior, India
5 shared publications - Joydip Dhar
Department of Engineering Sciences, ABV-Indian Institute of Information Technology and Management, Gwalior, India
4 shared publications - Garima Jain
Noida Institute of Engineering And Technology,Data Science Department,Greater Noida,India
2 shared publications - Kiran Kumar Pattanaik
Department of Information Technology, WSN Laboratory, ABV Indian Institute of Information Technology and Management Gwalior, Gwalior, MP, India
2 shared publications
Latest Publications
- 2 July 2026
- Published by Springer Nature
- p. 515-532
A Comparative Analysis of Deep Learning Models for Early Prediction of Alzheimer’s Disease Using Structural MRI
- 2 July 2026
- Published by Springer Nature
- p. 515-532
A Comparative Analysis of Deep Learning Models for Early Prediction of Alzheimer’s Disease Using Structural MRI
- 11 May 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (10) , 5661-5679
CAHNetF-DTP: A Community-Aware Heterogeneous Network-Based Embedding Framework for Drug-Target Interaction Prediction
Predicting possible drug–target interactions (DTIs) involves estimating the likelihood that drug molecules would bind to biological targets. By looking into the high cost and risk of in vivo and in vitro experiments, computational methods offer a cost- and time-efficient alternative for predicting DTIs in drug discovery. Many network-based methods have made significant progress in DTI prediction, but they often lack the ability to capture the topological and biological closeness between nodes, which is a crucial paradigm to identify hidden patterns in the DTI network. In this paper, we propose a novel computational-based framework─CAHNetF-DTP (Community Aware Heterogeneous Network-based Framework for Drug-Target interaction Prediction) that leverages a heterogeneous biomedical network comprising 15 distinct types of similarity-based subnetworks derived from drugs, targets, diseases, and side effects. To effectively capture the complex topological and semantic relationships among entities, we employ a community-aware framework that helps to capture local interaction patterns first before moving to another community. The resulting sequences are treated like sentences, enabling Word2Vec to generate embeddings that capture the contextual information on biomedical entities across multiple biological dimensions. To address the class imbalance issue, we incorporate a controlled negative sampling strategy and evaluate the proposed model under five experimental settings. The proposed method is further validated on benchmark data sets (KIBA and DAVIS), in real-world scenarios, and against SAR-based target prediction tools, where CAHNetF-DTP demonstrates robust and competitive performance, outperforming most of the methods. We carried out various case studies to check the model’s capability to identify novel drug-target pairs. This work highlights the value of integrating heterogeneous biological data for improved DTI prediction.
- 11 May 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (10) , 5661-5679
CAHNetF-DTP: A Community-Aware Heterogeneous Network-Based Embedding Framework for Drug-Target Interaction Prediction
Predicting possible drug–target interactions (DTIs) involves estimating the likelihood that drug molecules would bind to biological targets. By looking into the high cost and risk of in vivo and in vitro experiments, computational methods offer a cost- and time-efficient alternative for predicting DTIs in drug discovery. Many network-based methods have made significant progress in DTI prediction, but they often lack the ability to capture the topological and biological closeness between nodes, which is a crucial paradigm to identify hidden patterns in the DTI network. In this paper, we propose a novel computational-based framework─CAHNetF-DTP (Community Aware Heterogeneous Network-based Framework for Drug-Target interaction Prediction) that leverages a heterogeneous biomedical network comprising 15 distinct types of similarity-based subnetworks derived from drugs, targets, diseases, and side effects. To effectively capture the complex topological and semantic relationships among entities, we employ a community-aware framework that helps to capture local interaction patterns first before moving to another community. The resulting sequences are treated like sentences, enabling Word2Vec to generate embeddings that capture the contextual information on biomedical entities across multiple biological dimensions. To address the class imbalance issue, we incorporate a controlled negative sampling strategy and evaluate the proposed model under five experimental settings. The proposed method is further validated on benchmark data sets (KIBA and DAVIS), in real-world scenarios, and against SAR-based target prediction tools, where CAHNetF-DTP demonstrates robust and competitive performance, outperforming most of the methods. We carried out various case studies to check the model’s capability to identify novel drug-target pairs. This work highlights the value of integrating heterogeneous biological data for improved DTI prediction.
- Open Access
- 6 January 2026
- Published by Springer Nature in Research Square
A Comparative Analysis of Deep Learning Models for Early Prediction of Alzheimer’s Disease using structural MRI
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder and one of the leading causes of dementia worldwide. Early and accurate detection of AD is essential for timely intervention and treatment planning. Magnetic Resonance Imaging (MRI) serves as a non-invasive modality that captures structural brain changes associated with AD progression. In this study, we applied deep learning approaches to classify brain MRI scans into four categories: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented. We evaluated multiple convolutional neural network (CNN) architectures, including VGG-16, Inception-V3, Xception, and EfficientNet-B3, on a publicly available preprocessed MRI dataset containing 6,400 images resized to 128×128 pixels. Experimental results show that EfficientNet-B3 achieved the highest performance with an accuracy of 99.7%, precision of 0.99, recall of 0.99, and F1-score of 0.99. Xception also demonstrated strong performance with an accuracy of 92.5% and F1-score of 0.93, balancing accuracy and inference efficiency. Other models such as VGG-16 and Inception-V3 achieved competitive results but with relatively lower precision and recall. These findings highlight the potential of advanced CNN models, particularly EfficientNet-B3, in enabling automated, accurate, and efficient diagnosis of Alzheimer’s disease. This work contributes to advancing AI-driven tools for clinical decision support and improving the quality of life of patients and caregivers.
- 6 January 2026
- Published by Springer Nature in Research Square
Open AccessA Comparative Analysis of Deep Learning Models for Early Prediction of Alzheimer’s Disease using structural MRI
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder and one of the leading causes of dementia worldwide. Early and accurate detection of AD is essential for timely intervention and treatment planning. Magnetic Resonance Imaging (MRI) serves as a non-invasive modality that captures structural brain changes associated with AD progression. In this study, we applied deep learning approaches to classify brain MRI scans into four categories: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented. We evaluated multiple convolutional neural network (CNN) architectures, including VGG-16, Inception-V3, Xception, and EfficientNet-B3, on a publicly available preprocessed MRI dataset containing 6,400 images resized to 128×128 pixels. Experimental results show that EfficientNet-B3 achieved the highest performance with an accuracy of 99.7%, precision of 0.99, recall of 0.99, and F1-score of 0.99. Xception also demonstrated strong performance with an accuracy of 92.5% and F1-score of 0.93, balancing accuracy and inference efficiency. Other models such as VGG-16 and Inception-V3 achieved competitive results but with relatively lower precision and recall. These findings highlight the potential of advanced CNN models, particularly EfficientNet-B3, in enabling automated, accurate, and efficient diagnosis of Alzheimer’s disease. This work contributes to advancing AI-driven tools for clinical decision support and improving the quality of life of patients and caregivers.
- 16 January 2025
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 16 (7-8) , 4115-4150
Permutation driven evolutionary ordering with dependency filtering for multi-label classification
- 16 January 2025
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 16 (7-8) , 4115-4150
Permutation driven evolutionary ordering with dependency filtering for multi-label classification
- 27 December 2024
- Published by Springer Nature
- p. 523-534
A Study on the Effectiveness of Smart Facial Recognition in Unlock Tools
- 27 December 2024
- Published by Springer Nature
- p. 523-534
A Study on the Effectiveness of Smart Facial Recognition in Unlock Tools
- 10 August 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (10) , 7441-7462
Rating Distribution-Aware Deep Cognitive Convolution Matrix Factorization for Recommendation Systems
- 10 August 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 50 (10) , 7441-7462
Rating Distribution-Aware Deep Cognitive Convolution Matrix Factorization for Recommendation Systems
- 4 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 11 (5) , 5035-5044
Partition Clustering in Complex Weighted Networks Using K-Cut Ranking and Krill-Herd Optimization
Network partitioning has been studied extensively on undirected and weighted networks that need to partition the graph into small clusters. Graph-cutting is a widely known approach that removes the inter-cluster edges to find the local network clusters. Cutting a network into small clusters is pivotal in a mixed integer optimization problem. Proper selection of cut sequences discards the possibility of trivial partitions and reduces the computation load to improve cluster quality. Proper cut-sequence selection relies on multiple heuristics that restrict this problem from being generalized. Cut-sequence selection is an NP-hard problem that turns out to be challenging for weighted networks. This paper presents a swarm-heuristics-based framework to solve the cut-sequence selection problem in weighted networks. First, we generate an affinity network from a given data set. A cost-based objective function is formalized that takes cut sequences as input and returns the weighted intra-cluster connected components. Subsequently, heuristics-based cut sequences are initialized, and krill-herd optimization is used to solve the objective function. The framework is empirically tested on simulated and real-world networks. Network-based indices are used to measure the quality of partitions. The comparative analysis, computation time, and convergence analysis are performed with state-of-the-art methods to report the competitive behavior of the framework. The framework is highly effective and has paved new ways for future research to solve the cut-sequence selection problem without prior knowledge.
- 4 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 11 (5) , 5035-5044
Partition Clustering in Complex Weighted Networks Using K-Cut Ranking and Krill-Herd Optimization
Network partitioning has been studied extensively on undirected and weighted networks that need to partition the graph into small clusters. Graph-cutting is a widely known approach that removes the inter-cluster edges to find the local network clusters. Cutting a network into small clusters is pivotal in a mixed integer optimization problem. Proper selection of cut sequences discards the possibility of trivial partitions and reduces the computation load to improve cluster quality. Proper cut-sequence selection relies on multiple heuristics that restrict this problem from being generalized. Cut-sequence selection is an NP-hard problem that turns out to be challenging for weighted networks. This paper presents a swarm-heuristics-based framework to solve the cut-sequence selection problem in weighted networks. First, we generate an affinity network from a given data set. A cost-based objective function is formalized that takes cut sequences as input and returns the weighted intra-cluster connected components. Subsequently, heuristics-based cut sequences are initialized, and krill-herd optimization is used to solve the objective function. The framework is empirically tested on simulated and real-world networks. Network-based indices are used to measure the quality of partitions. The comparative analysis, computation time, and convergence analysis are performed with state-of-the-art methods to report the competitive behavior of the framework. The framework is highly effective and has paved new ways for future research to solve the cut-sequence selection problem without prior knowledge.
- Open Access
Diabetic Retinopathy Detection Using Quantum Transfer Learning
Diabetic Retinopathy (DR), a prevalent complication in diabetes patients, can lead to vision impairment due to lesions formed on the retina. Detecting DR at an advanced stage often results in irreversible blindness. The traditional process of diagnosing DR through retina fundus images by ophthalmologists is not only time-intensive but also expensive. While classical transfer learning models have been widely adopted for computer-aided detection of DR, their high maintenance costs can hinder their detection efficiency. In contrast, Quantum Transfer Learning offers a more effective solution to this challenge. This approach is notably advantageous because it operates on heuristic principles, making it highly optimized for the task. Our proposed methodology leverages this hybrid quantum transfer learning technique to detect DR. To construct our model, we utilize the APTOS 2019 Blindness Detection dataset, available on Kaggle. We employ the ResNet-18, ResNet34, ResNet50, ResNet101, ResNet152 and Inception V3, pre-trained classical neural networks, for the initial feature extraction. For the classification stage, we use a Variational Quantum Classifier. Our hybrid quantum model has shown remarkable results, achieving an accuracy of 97% for ResNet-18. This demonstrates that quantum computing, when integrated with quantum machine learning, can perform tasks with a level of power and efficiency unattainable by classical computers alone. By harnessing these advanced technologies, we can significantly improve the detection and diagnosis of Diabetic Retinopathy, potentially saving many from the risk of blindness. Keywords: Diabetic Retinopathy, Quantum Transfer Learning, Deep Learning
Open AccessDiabetic Retinopathy Detection Using Quantum Transfer Learning
Diabetic Retinopathy (DR), a prevalent complication in diabetes patients, can lead to vision impairment due to lesions formed on the retina. Detecting DR at an advanced stage often results in irreversible blindness. The traditional process of diagnosing DR through retina fundus images by ophthalmologists is not only time-intensive but also expensive. While classical transfer learning models have been widely adopted for computer-aided detection of DR, their high maintenance costs can hinder their detection efficiency. In contrast, Quantum Transfer Learning offers a more effective solution to this challenge. This approach is notably advantageous because it operates on heuristic principles, making it highly optimized for the task. Our proposed methodology leverages this hybrid quantum transfer learning technique to detect DR. To construct our model, we utilize the APTOS 2019 Blindness Detection dataset, available on Kaggle. We employ the ResNet-18, ResNet34, ResNet50, ResNet101, ResNet152 and Inception V3, pre-trained classical neural networks, for the initial feature extraction. For the classification stage, we use a Variational Quantum Classifier. Our hybrid quantum model has shown remarkable results, achieving an accuracy of 97% for ResNet-18. This demonstrates that quantum computing, when integrated with quantum machine learning, can perform tasks with a level of power and efficiency unattainable by classical computers alone. By harnessing these advanced technologies, we can significantly improve the detection and diagnosis of Diabetic Retinopathy, potentially saving many from the risk of blindness. Keywords: Diabetic Retinopathy, Quantum Transfer Learning, Deep Learning
- 26 January 2024
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 66 (5) , 2925-2943
KNetwork: advancing cross-lingual sentiment analysis for enhanced decision-making in linguistically diverse environments
- 26 January 2024
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 66 (5) , 2925-2943
KNetwork: advancing cross-lingual sentiment analysis for enhanced decision-making in linguistically diverse environments