BC-SwinNet: Swin transformer and CNN with multi-objective optimization for multi-class breast cancer detection using Histopathological images Mudassir Khan, Meteb Altaf, Nikhat Raza Khan, Haleema PK, Varun Malik, Alaa Menshawi, Tahani Alsubait, Riaz Ahmad Ziar, R. John Martin Scientific Reports, 2026 Breast cancer remains a major global health concern and is the leading cause of cancer-related deaths among women worldwide. It is estimated that by 2030, its incidence and mortality rates will rise due to population growth, aging, and lifestyle changes. Although histopathological examination is considered the gold standard for diagnosis, manual assessment is often time-consuming, subjective, and-particularly in the case of complex, multidimensional cancer classifications-prone to inter-observer variability. These limitations underscore the need for accurate, automated, and computationally efficient diagnostic systems to aid in clinical decision-making. To address these challenges, this study introduces BC-SwinNet-a hybrid deep learning framework that integrates the Conditional Swin Transformer (ConSwinTras), the Multi-Objective Elk Herd Optimization (MEHO) algorithm, and a Layered Attention-based Convolutional Neural Network (CA-CNN) to classify multiple breast cancer subtypes using histopathological images. ConSwinTras extracts hierarchical and contextual representations from tissue images, while MEHO is utilized to select subsets of high-resolution features, thereby reducing dimensionality and enhancing prediction performance. The CA-CNN module focuses on diagnostically relevant regions through layer-wise attention algorithms and performs the final sample analysis and classification. The proposed BC-SwinNet model was evaluated on two benchmark datasets-BreakHis and BACH-achieving classification accuracies of 99.91% and 99.854%, respectively. Experimental results demonstrate that the proposed framework outperforms numerous existing methods in terms of classification performance while maintaining computational efficiency. These findings suggest that BC-SwinNet offers a robust and efficient approach for automated breast cancer diagnosis and holds the potential to enhance diagnostic support systems in clinical practice.
Explainable artificial-intelligence-based hyperspectral image analysis for leaf disease detection in intercropping system Varun Malik, Asma AlJarullah, Tahani Alsubait, Amna Ikram, S. B. Goyal, Mudassir Khan Frontiers in Plant Science, 2026 Introduction Intercropping regimes enhance the efficiency of land use and ecological sustainability but present serious problems to automated disease analysis since the overlapping canopy and the similarity of symptoms in crop species are visually indistinguishable. Methods This work presents an explainable artificial intelligence (XAI)-based hyperspectral analysis on leaf disease in intercropping systems. The framework combines the spectral–spatial feature generators that utilize transformers including vision transformer (ViT), Swin transformer, pyramid vision transformer (PVT), and detection transformer (DETR) to identify nuanced biochemical and structural changes in crop combinations for maize–soybean and pea–cucumber. In order to reduce spectral redundancy and high dimensionality, an enhanced greedy political optimization (EGPO) algorithm is used as a wrapper-based feature selection strategy. A capsule spatial shift neural network (CSSNet) is used to predict the classification of diseases. Explainable AI methods, such as Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) feature attribution analysis and gradient-weighted class activation mapping (Grad-CAM) visualization of disease-relevant regions, provide model transparency. The DETR + EGPO + CSSNet framework is tested on the conventional feature selection methods. Results and discussion The results or findings on publicly available hyperspectral datasets on intercropping show an average recall of 99.998% with high region consistency (Dice score: 99.997%) of activation maps and expert-marked disease regions. These findings affirm that the proposed framework is highly accurate, stable, and interpretable to identify subtle and overlapping disease in leaves in a complex system of intercropping.
Novel bioluminescent oceanic optimization with explainable AI for accurate skin cancer diagnosis and enhanced dermatologist support Mudassir Khan, Sai Bhuvana Kurada, Alaa Mohammad Menshawi, Varun Malik, Meteb M. Altaf Journal of King Saud University Science, 2026 Skin cancer poses a significant global health threat, where timely and accurate diagnosis is crucial for improving patient outcomes. Although deep learning methods have demonstrated considerable success in dermatological image analysis, their black-box nature limits clinical adoption due to a lack of transparency and interpretability. To overcome this difficulty, it is suggested that an explainable artificial intelligence (XAI) framework can be applied using an optimal encoder-decoder architecture, which enhances the accuracy of dermatology-specific skin cancer diagnostics and offers better assistance to dermatologists. The specified model is tested on the benchmark dermoscopic image datasets, such as the ISIC archive and the HAM10000. To extract rich and hierarchical features of skin lesion images, the encoder uses pre-trained backbones, which are ResNet-50 and EfficientNet-B4. It uses a tailored decoder, based on U-Net and SegNet design, to recover lesion segmentation maps and give multi-class lesions classification. Nature-based novel bioluminescent oceanic optimization (BOO) algorithm is proposed to be used in feature selection, which determines the most significant features. A squeeze attention network (SAttNet) emphasizes features around the edges of lesions, thus narrowing the scope of the model and enhancing the accuracy of the diagnosis. Explainability is achieved through a multi-level post-hoc strategy: Gradient-weighted Class Activation Mapping (Grad-CAM) highlights critical regions within the encoder’s feature maps; SHapley Additive explanations (SHAP) quantifies the contribution of individual features to the prediction; and local interpretable model-agnostic explanations (LIME) generates localized, human-understandable explanations for diagnostic output. The results show outstanding performance, achieved classification accuracies of 99.956% and 99.644% on the ISIC and HAM10000 datasets, respectively.
Predicting the effects of cultural intelligence on innovation in start-ups Manjinder Singh, Amit Mittal, Varun Malik, Ruchi Mittal, Geetanjali Singala, Amandeep Kaur Work, 2026 Background In an era of rapid technological advancements and globalization, start-ups face increased pressure to innovate continuously to maintain competitiveness and ensure long-term success. Cultural intelligence (CQ), which involves the ability to adapt to diverse cultural contexts, is increasingly recognized as a vital factor for driving innovation. However, there is limited research on how CQ influences innovation in start-ups, especially considering its various components. Objective This study aims to explore the relationship between cultural intelligence and innovation in start-ups, with a particular focus on the components of CQ: metacognition, cognition, motivation, behavior, and interpersonal confidence. The research seeks to identify how these components contribute to fostering innovation within start-ups. Methods The study used a structured questionnaire with 35 items, distributed to 320 start-ups across India. Data were analyzed using Deep Belief Networks (DBN) and Structural Equation Modeling (SEM) to assess the relationships between cultural intelligence components and start-up innovation. Results The findings reveal that motivation, behavior, work commitment, and interpersonal confidence significantly influence start-up innovation. Additionally, interpersonal confidence was found to enhance cultural intelligence, particularly in adapting to cultural differences. The study underscores the importance of CQ in fostering innovation in a culturally diverse business environment. Conclusions This research highlights that start-ups with higher cultural intelligence are better positioned to drive innovation and succeed in today's globalized market. Start-up managers and entrepreneurs should prioritize developing CQ, particularly in areas such as interpersonal confidence and work commitment, to enhance their innovation capabilities and long-term sustainability.
Optimizing chemotherapeutic targets in non-small cell lung cancer with transfer learning for precision medicine Varun Malik, Ruchi Mittal, Deepali Gupta, Sapna Juneja, Khalid Mohiuddin, Swati Kumari Plos One, 2025 Non-small cell lung cancer (NSCLC) accounts for the majority of lung cancer cases, making it the most fatal diseases worldwide. Predicting NSCLC patients’ survival outcomes accurately remains a significant challenge despite advancements in treatment. The difficulties in developing effective drug therapies, which are frequently hampered by severe side effects, drug resistance, and limited effectiveness across diverse patient populations, highlight the complexity of NSCLC. The machine learning (ML) and deep learning (DL) modelsare starting to reform the field of NSCLC drug disclosure. These methodologies empower the distinguishing proof of medication targets and the improvement of customized treatment techniques that might actually upgrade endurance results for NSCLC patients. Using cutting-edge methods of feature extraction and transfer learning, we present a drug discovery model for the identification of therapeutic targets in this paper. For the purpose of extracting features from drug and protein sequences, we make use of a hybrid UNet transformer. This makes it possible to extract deep features that address the issue of false alarms. For dimensionality reduction, the modified Rime optimization (MRO) algorithm is used to select the best features among multiples. In addition, we design the deep transfer learning (DTransL) model to boost the drug discovery accuracy for NSCLC patients’ therapeutic targets. Davis, KIBA, and Binding-DB are examples of benchmark datasets that are used to validate the proposed model. Results exhibit that the MRO+DTransL model outflanks existing cutting edge models. On the Davis dataset, the MRO+DTransL model performed better than the LSTM model by 9.742%, achieved an accuracy of 98.398%. It reached 98.264% and 97.344% on the KIBA and Binding-DB datasets, respectively, indicating improvements of 8.608% and 8.957% over baseline models.
CAAODT: Collaborated AOA and ASBO Optimization-Based Design Technique for Electrically Thick Circularly Polarized Rectangular Microstrip Antennas Geetanjali Singla, Amandeep Kaur, Amit Mittal, Manjinder Singh, Varun Malik, Ruchi Mittal International Journal of Numerical Modelling Electronic Networks Devices and Fields, 2025 Circularly polarized antennas are crucial for wireless systems due to their effectiveness in avoiding fading and multi‐path interference. However, existing design techniques lack flexibility for varying frequencies and are costly due to complex fabrication. To overcome those challenges, this paper intends to propose a new Collaborated AOA and ASBO optimization‐based Design Technique (CAAODT)‐based Circularly Polarized Rectangular Microstrip Antenna (MSA) design technique that improves performance and flexibility for these antennas. The optimization of design parameters such as radius, height, ground plane length, ground plane width, and thickness is achieved using a novel algorithm called the Collaborated AOA and ASBO optimization (CAAO). Here, AOA is called as Archimedes Optimization Algorithm. ASBO is called Average and Subtraction‐Based Optimization. This tuning process considers constraints like Axial Ratio, gain, bandwidth, Voltage Standing Wave Ratio (VSWR), and return loss. The proposed optimal design model is validated against traditional methods based on gain, VSWR, return loss, bandwidth, and axial ratio across different frequencies.
Efficient IIoT framework for mitigating Ethereum attacks in industrial applications using supervised learning with quantum classifiers Applied Data Science and Smart Systems, 2024
Adaptive resource allocation and optimization in cloud environments: Leveraging machine learning for efficient computing Applied Data Science and Smart Systems, 2024
Detection of Cyberbullying Using Modified Dense Framework Varun Malik, Ruchi Mittal, Vikram Singh, Amit Mittal, S Vikram Singh, Shashi Prakash Diwvedi 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical Electronics and Computer Engineering Upcon 2023, 2023
Bone Fracture Segmentation Using Cascaded Convolutional Neural Networks Ruchi Mittal, Varun Malik, Manoj Kumar, Prateek Chaturvedi, A L N Rao, Akhilesh Kumar Khan 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical Electronics and Computer Engineering Upcon 2023, 2023
Coronary Heart Disease Prediction Using GKFCM with RNN Varun Malik, Ruchi Mittal, Ajay Rana, Irfan Khan, Pankaj Singh, Bashar Alam Proceedings of International Conference on Contemporary Computing and Informatics Ic3i 2023, 2023
Spinal Cord Disease Identification Using Transfer Learning Techniques Ruchi Mittal, Varun Malik, S B Goyal, Suman Avdhesh Yadav, Arun Pratap Srivastava, Akhil Sankhyan 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical Electronics and Computer Engineering Upcon 2023, 2023
Coronary Artery Disease Prediction Using Enhanced Multi Layer DCNN Varun Malik, Smita Sharma, Ruchi Mittal, A. Kakoli Rao, R. John Martin, Akhilesh Kumar Khan 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical Electronics and Computer Engineering Upcon 2023, 2023
Skin Cancer Detection Using Deep Block Convolutional Neural Networks Ruchi Mittal, Varun Malik, Jaiteg Singh, Shubhi Gupta, Arun Pratap Srivastava, Akhil Sankhyan 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical Electronics and Computer Engineering Upcon 2023, 2023
Applying Data Mining for Clustering Shoppers Based on Store Loyalty Varun Malik, Ruchi Mittal, Amit Mittal, Jaiteg Singh, Sanjay Singla, Ashima Kukkar Proceedings 2022 5th International Conference on Computational Intelligence and Communication Technologies Ccict 2022, 2022
On the Development of an Optimized Web Usage Mining Tool Varun Malik, Vikram Singh, Ruchi Mittal, Jaiteg Singh, Sanjay Singla, Lucy Garg Proceedings 2022 5th International Conference on Computational Intelligence and Communication Technologies Ccict 2022, 2022
A hybrid approach in random forest classification with genetic algorithm and ant colony optimization Journal of Advanced Research in Dynamical and Control Systems, 2019
RECENT SCHOLAR PUBLICATIONS
Temporal computing in non-linear spacetime: Applications for future internet architectures AS Rajawat, SB Goyal, V Malik, GW Peng AIP Conference Proceedings 3410 (1), 090001 , 2026 2026
BC-SwinNet: Swin transformer and CNN with multi-objective optimization for multi-class breast cancer detection using Histopathological images M Khan, M Altaf, NR Khan, H Pk, V Malik, A Menshawi, T Alsubait, RA Ziar, ... Scientific Reports , 2026 2026
Explainable artificial-intelligence-based hyperspectral image analysis for leaf disease detection in intercropping system V Malik, A AlJarullah, T Alsubait, A Ikram, SB Goyal, M Khan Frontiers in Plant Science 17, 1789542 , 2026 2026 Citations: 1
Federated learning with IoT-based remote patient monitoring for real-time chronic disease prediction SA Yadav, V Malik, S Sharma, SV Singh, A Khader, J Saudagar, ... Journal of King Saud University Computer and Information Sciences , 2026 2026
Novel bioluminescent oceanic optimization with explainable AI for accurate skin cancer diagnosis and enhanced dermatologist support M Khan, SB Kurada, AM Menshawi, V Malik, MM Altaf Journal of King Saud University–Science 38 , 2026 2026
Predicting the effects of cultural intelligence on innovation in start-ups M Singh, A Mittal, V Malik, R Mittal, G Singala, A Kaur Work 83 (1), 195-211 , 2026 2026
Topological and Entropic Analysis of Steganography and Steganalysis via AI-Driven Multi-Agent Systems KS Kaswan, JS Dhatterwal, V Malik, A Baliyan, DK Singh 2025 Modern Electronics Devices and Intelligent Communication Systems … , 2025 2025
Smart intercropping system to detect leaf disease using hyperspectral imaging and hybrid deep learning for precision agriculture SB Goyal, V Malik, AS Rajawat, M Khan, A Ikram, B Alabdullah, A Almjally Frontiers in Plant Science 16, 1662251 , 2025 2025 Citations: 18
Intelligent cloud framework for dynamic portfolio risk prediction using deep reinforcement learning MH Mirza, A Budaraju, SSS Valiveti, W Sarma, H Kaur, V Malik 2025 IEEE International Conference on Computing (ICOCO), 54-59 , 2025 2025 Citations: 4
Enhancing underwater image quality with artificial bee colony and fruit fly optimization V Malik, R Mittal, V Singh, K Parashar, P Madan, A Jandwani, R Jandwani International Journal of Information Technology, 1-9 , 2025 2025 Citations: 1
StegoSec-EHR: A blockchain-enabled IoTFramework for secure HER sharing via steganography in genetic disease diagnosis V Malik, M Khan, P Bhoyar, K Gupta, MA Hussain, K Arora, BM Mujahid Peer-to-Peer Networking and Applications 18 (6), 325 , 2025 2025 Citations: 4
Cloud Integrated Accounting Bigdata Analytics for Secure Internet Banking Using Mixture Attention and Deep Neural Network ABR Sivaselvan, T Sankaran, M Pal, SR Lankala, V Malik, S Singla 2025 International Conference on Emerging Trends in Networks and Computer … , 2025 2025
LSTM-CNN for Real-Time Financial Forecasting on Cloud Infrastructure AK Polinati, S Majety, CS Kubam, V Ghatala, V Malik, S Singla 2025 International Conference on Emerging Trends in Networks and Computer … , 2025 2025 Citations: 1
Cloud-Enabled Convolutional Neural Networks for Fraudulent Credit Card Transaction Identification AK Polinati, MR Marri, J Duggirala, V Sresth, V Malik, S Singla 2025 International Conference on Emerging Trends in Networks and Computer … , 2025 2025 Citations: 1
Secure Cloud-Based Financial Fraud Detection Using Hybrid Deep Learning and Blockchain Techniques A Chaudhary, AK Shah, S Tiwari, P Nutalapati, V Malik, S Singla 2025 International Conference on Emerging Trends in Networks and Computer … , 2025 2025 Citations: 11
Deep Learning Based Anomaly Detection for Realtime Financial Transactions in Cloud Environments K Ramaswamy, S Gupta, P Nutalapati, SP Nagavalli, S Singla, V Malik 2025 International Conference on Emerging Trends in Networks and Computer … , 2025 2025
Technology transformation: analyzing its impact on internet security and compliance in an organization M Singh, A Mittal, V Malik, R Mittal, G Singla, A Kaur International Journal of System Assurance Engineering and Management 16 (7 … , 2025 2025 Citations: 1
Quantum AI powered dynamic user profiling for next-generation personalized recommender system V Malik, SB Goyal Quantum Machine Intelligence 7 (1), 44 , 2025 2025 Citations: 41
RETRACTED: Optimizing chemotherapeutic targets in non-small cell lung cancer with transfer learning for precision medicine V Malik, R Mittal, D Gupta, S Juneja, K Mohiuddin, S Kumari Plos one 20 (4), e0319499 , 2025 2025 Citations: 6
CAAODT: Collaborated AOA and ASBO Optimization‐Based Design Technique for electrically thick circularly polarized rectangular microstrip antennas G Singla, A Kaur, A Mittal, M Singh, V Malik, R Mittal International Journal of Numerical Modelling: Electronic Networks, Devices … , 2025 2025 Citations: 1
MOST CITED SCHOLAR PUBLICATIONS
Building a secure platform for digital governance interoperability and data exchange using blockchain and deep learning-based frameworks V Malik, R Mittal, D Mavaluru, BR Narapureddy, SB Goyal, RJ Martin, ... Ieee Access 11, 70110-70131 , 2023 2023 Citations: 92
A novel parameter optimization metaheuristic: Human habitation behavior based optimization D Jain, M Arya, V Malik, SV Singh 2022 5th International Conference on Contemporary Computing and Informatics … , 2022 2022 Citations: 92
EPR-ML: E-Commerce Product Recommendation Using NLP and Machine Learning Algorithm V Malik, R Mittal, SV SIngh 2022 5th International Conference on Contemporary Computing and Informatics … , 2022 2022 Citations: 68
XAI-powered smart agriculture framework for enhancing food productivity and sustainability RJ Martin, R Mittal, V Malik, F Jeribi, ST Siddiqui, MA Hossain, ... IEEE access 12, 168412-168427 , 2024 2024 Citations: 63
Analyzing the application of SMOTE on machine learning classifiers V Rattan, R Mittal, J Singh, V Malik 2021 International Conference on Emerging Smart Computing and Informatics … , 2021 2021 Citations: 56
DFR-HL: Diabetic Food Recommendation Using Hybrid Learning Methods R Mittal, V Malik, SV Singh 2022 5th International Conference on Contemporary Computing and Informatics … , 2022 2022 Citations: 54
Dermcdsm: Clinical decision support model for dermatosis using systematic approaches of machine learning and deep learning R Mittal, F Jeribi, RJ Martin, V Malik, SJ Menachery, J Singh IEEE Access 12, 47319-47337 , 2024 2024 Citations: 53
Quantum AI powered dynamic user profiling for next-generation personalized recommender system V Malik, SB Goyal Quantum Machine Intelligence 7 (1), 44 , 2025 2025 Citations: 41
A deep learning based expert framework for portfolio prediction and forecasting F Jeribi, RJ Martin, R Mittal, H Jari, AH Alhazmi, V Malik, SL Swapna, ... IEEE Access 12, 103810-103829 , 2024 2024 Citations: 41
Efficient IIoT framework for mitigating Ethereum attacks in industrial applications using supervised learning with quantum classifiers SB Goyal, AS Rajawat, R Shandilya, V Malik Applied Data Science and Smart Systems, 544-551 , 2024 2024 Citations: 39
Adaptive resource allocation and optimization in cloud environments: Leveraging machine learning for efficient computing AS Rajawat, SB Goyal, M Kumar, V Malik Applied Data Science and Smart Systems, 499-508 , 2024 2024 Citations: 32
Forecasting E-Mentoring Effectiveness using Data Mining Approach R Mittal, J Singh, V Malik, A Mittal, V Rattan, SV Singh 2022 5th International Conference on Contemporary Computing and Informatics … , 2022 2022 Citations: 26
Bone Fracture Segmentation Using Cascaded Convolutional Neural Networks R Mittal, V Malik, M Kumar, P Chaturvedi, ALN Rao, AK Khan 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical … , 2023 2023 Citations: 23
Coronary Artery Disease Prediction Using Enhanced Multi Layer DCNN V Malik, S Sharma, R Mittal, AK Rao, RJ Martin, AK Khan 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical … , 2023 2023 Citations: 21
DL-ASD: a deep learning approach for autism spectrum disorder R Mittal, V Malik, A Rana 2022 5th International Conference on Contemporary Computing and Informatics … , 2022 2022 Citations: 21
Systematic Advancements in IoT: Integrating Edge Computing for Enhanced Architectures in Next-Generation Devices AS Rajawat, SB Goyal, SMN Islam, V Malik International Conference on Advanced Network Technologies and Computational … , 2024 2024 Citations: 20
Real-time face mask detection using deep learning P Munjal, V Rattan, R Dua, V Malik Journal of Technology Management for Growing Economies 12 (1), 25-31 , 2021 2021 Citations: 20
Predicting purchases and personalizing the customer journey with artificial intelligence V Malik, R Mittal, R Chaudhry, SA Yadav 2024 11th International Conference on Reliability, Infocom Technologies and … , 2024 2024 Citations: 19
Feature selection optimization using ACO to improve the classification performance of web log data V Malik, R Mittal, J Singh, V Rattan, A Mittal 2021 8th international conference on signal processing and integrated … , 2021 2021 Citations: 19
Security challenges in industry 4.0 scada systems–a digital forensic prospective VR Malik, K Gobinath, S Khadsare, A Lakra, SV Akulwar 2021 International Conference on Artificial Intelligence and Computer … , 2021 2021 Citations: 19
