A Deep Learning Framework with Learning without Forgetting for Intelligent Surveillance in IoT-enabled Home Environments in Smart Cities Surjeet Dalal, Neeraj Dahiya, Amit Verma, Neetu Faujdar, Sarita Rathee, Vivek Jaglan, Uma Rani, Dac-Nhuong Le Recent Advances in Computer Science and Communications, 2026 Background: Internet of Things (IoT) technology in smart urban homes has revolutionised sophisticated monitoring. This progress uses interconnected devices and systems to improve security, resource management, and resident safety. Smart cities use technology to improve efficiency, sustainability, and quality. Internet of Things-enabled intelligent monitoring technologies are key to this goal. Objectives: Intelligent monitoring in IoT-enabled homes in smart cities improves security, convenience, and quality of life from advanced technologies. Using live monitoring and risk identification tools to quickly discover and resolve security breaches and suspicious activity to protect citizens. Intelligent devices allow homeowners to remotely control lighting, security locks, and surveillance cameras. Using advanced technologies to regulate heating, cooling, and lighting based on occupancy and usage. Method: This study introduces a deep learning architecture that uses LwF (Learning without Forgetting) to keep patterns while absorbing new data. The authors use IoT devices to collect and analyse data in real-time for monitoring and surveillance. They use sophisticated data preprocessing to handle IoT devices' massive data. The authors train the deep learning model with historical and real-time data and cross-validation to ensure resilience. Result: The proposed model has been validated on two different Robloflow datasets of 7382 images. The proposed model gains an accuracy level of 98.27%. The proposed Yolo-LwF model outperforms both the original Yolo and LwF models in terms of detection speed and adaptive learning. Conclusion: By raising the bar for intelligent monitoring solutions in smart cities, the suggested system is ideal for real-time, adaptive surveillance in IoT-enabled households. By embracing adaptability and knowledge retention, authors envision heightened security and safety levels in urban settings.
Securing fog computing in healthcare with a zero-trust approach and blockchain Navjeet Kaur, Ayush Mittal, Umesh Kumar Lilhore, Sarita Simaiya, Surjeet Dalal, Kashif Saleem, Ehab Seif Ghith Eurasip Journal on Wireless Communications and Networking, 2025 As healthcare systems increasingly adopt fog computing to improve responsiveness and real-time data processing at the edge, significant security challenges emerge due to the decentralized architecture. The traditional perimeter-based security models are inadequate for addressing the dynamic and distributed nature of fog networks, leaving them vulnerable to unauthorized access, data tampering, and latency issues. Therefore, this paper proposes a novel security framework that integrates blockchain (BC) and software-defined network (SDN) technologies, underpinned by zero-trust (ZT) principles, to address these challenges in latency-sensitive healthcare environments. The proposed framework enhances security by combining BC’s immutable transaction logs for data integrity and traceability with SDN’s dynamic network reconfiguration for real-time access control and anomaly detection. The integration of BC and SDN supports continuous authentication and monitoring using cryptographic protocols (SHA-256A and RSA-2048) to secure data transmission. Additionally, tasks are dynamically allocated to fog nodes based on a multi-metric scheduling mechanism that considers fog node capacity, proximity, and compliance with predefined security protocols. The framework was evaluated using iFogSim, simulating a healthcare environment with 50 IoT devices, 10 fog nodes, and varying workloads (100–1000 tasks/min). The key evaluation performance metrics include intrusion detection rate (IDR), data integrity (DI), task completion rate (TCR), average task response time (ART), and average block time. The implementation results demonstrate satisfactory improvements compared to existing models: a 40% increase in IDR, a 30% enhancement in DI, a 15.29% rise in TCR, and a 39.66% reduction in ART. Moreover, the baseline IDR (85%) and DI (70%) were drawn from ZT-1, while TCR (85%) and ART (300 ms) were measured using ZT-2 as benchmarks. These findings illustrate the feasibility of integrating BC, SDN, and ZT principles to mitigate threats such as unauthorized access, data tampering, and delays in latency-sensitive tasks.
GAN-CSA: Enhanced Generative Adversarial Networks for Accurate Detection and Surgical Guidance in Skull Base Brain Metastases Surjeet Dalal, Neeraj Dahiya, Shakti Kundu, Amit Verma, Gaytri Devi, Manel Ayadi, Mitiku Dubale, Arshad Hashmi International Journal of Computational Intelligence Systems, 2025 Skull-base brain metastases pose significant diagnostic and surgical challenges due to their proximity to vital neurological structures. We propose an enhanced Generative Adversarial Network (GAN) model optimised with the Crow Search Algorithm (CSA) to improve detection accuracy and intraoperative decision-making. The GAN framework facilitates high-fidelity image generation and segmentation, while CSA fine-tunes hyperparameters for improved model stability and accuracy. Trained on high-resolution brain MRI datasets with expert annotations, our model achieved a precision of 97.43%, surpassing existing approaches in accuracy and robustness. The system accurately delineates tumour margins and adjacent anatomical structures in real-time, enhancing surgical guidance and reducing operative risks. The inclusion of CSA significantly improved GAN convergence and reduced false positives. This integrated GAN-CSA approach shows promise for revolutionizing neuro-oncology practices by enabling safer and more precise skull base surgeries. As an initial proof-of-concept, the evaluation was limited to 156 MR volumes from a single scanner, and future cross-centre studies will be pursued to establish robustness across varying field strengths, coils, and imaging protocols.
Optimized XGBoost Model with Whale Optimization Algorithm for Detecting Anomalies in Manufacturing Surjeet Dalal, Uma Rani, Umesh Kumar Lilhore, Neeraj Dahiya, Reenu Batra, Nasratullah Nuristani, Dac-Nhuong Le Journal of Computational and Cognitive Engineering, 2025 Anomalies and defects in the manufacturing process hinder operating efficiency and product quality. The Whale Optimization Algorithm (WOA) optimizes the XGBoost model for better anomaly identification by iteratively refining hyperparameters. Experiments using real-world manufacturing datasets prove proposed model works. Comparing the proposed model to traditional anomaly detection methods shows its superior performance in industry patent concept. The optimized XGBoost model's interpretability and anomaly detection features are also discussed. In this paper, WOA is applied in this work to optimize hyperparameters of XGBoost, a robust gradient boosting technique for accurate anomaly detection in manufacturing systems. Optimized XGBoost gained 1.00 precision value, 0.9 recall value, and 0.96 f1-score for class 0.0 and gained a 0.95 precision value, 1.00 recall value, and a 0.97 f1-score for class 1.0. The proposed model gained 0.993 Train Score and 0.964 Test Score. Our findings suggest that integrating XGBoost with the WOA may uncover manufacturing process irregularities. Optimization improves detection accuracy and provides a flexible and interpretable framework, helping modern industrial processes maintain quality and efficiency. This research encourages machine learning optimization for industrial patent applications, advancing anomaly detection methods. Received: 2 June 2024 | Revised: 29 August 2024 | Accepted: 27 September 2024 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement Data are available on request from the corresponding author upon reasonable request. Author Contribution Statement Surjeet Dalal: Conceptualization, Validation, Writing – original draft, Project administration. Uma Rani: Conceptualization, Formal analysis, Writing – review & editing. Umesh Kumar Lilhore: Methodology, Investigation, Resources, Writing – original draft. Neeraj Dahiya: Methodology, Data curation, Writing - review & editing. Reenu Batra: Software, Visualization, Supervision. Nasratullah Nuristani: Software, Formal analysis, Investigation, Visualization. Dac-Nhuong Le: Validation, Supervision, Project administration.
Enhanced heart disease diagnosis and management: A multi-phase framework leveraging deep learning and personalized nutrition Ritika Ritika, Rajender Singh Chhillar, Sandeep Dalal, Surjeet Dalal, Iyyappan Moorthi, Mitiku Dubale, Arshad Hashmi Plos One, 2025 In health care, an accurate diagnosis with the help of a data-driven forecasting framework takes the risk factors associated with heart disease. However, building such an effective model using deep learning (DL) methods requires high-quality data, i.e., data free of outliers or anomalies. The current paper proposes a new approach to diagnosing and controlling heart diseases by utilizing a multi-tiered data acquisition model, data pre-processing, feature extraction, and DL. The framework encompasses four types of datasets. The first phase of the proposed methodology consists of data acquisition, while the second phase includes advanced data preprocessing for each data type. In phase three, multi-feature extraction methods are used to extract the features from the dataset. In phase four, a combined feature selection technique of ReliefF and Pearson correlation is used to select the best features. Phase five of the study is the formulation of the CILAD-Net DL model that integrates CNN, Inception Net, LSTM, and Angle DetectNet to accurately detect heart disease. The sixth phase implements Deep Reinforcement Learning (DRL) for nutrition recommendations based on the detected disease, thus improving the treatment individualization. The developed model’s experimental outcomes are validated with other prevailing models in terms of accuracy, recall, hamming loss, and so on. Finally, the outcomes of the proposed model attain the higher accuracy of 0. 998 for the CILAD-Net model, which is significantly better than DenseNet-201 with 0. 988, ANN with 0. 987, KNN with 0. 977, and CL-Net with 0. 984.
MAPPING OF E-WALLETS WITH FEATURES Alisha Sikri, Surjeet Dalal, N.P Singh, Dac‐Nhuong Le Cyber Security in Parallel and Distributed Computing Concepts Techniques Applications and Case Studies, 2024
Preface Surjeet Dalal, Neeraj Dahiya, Vivek Jaglan, Deepika Koundal, Dac-Nhuong Le Reshaping Intelligent Business and Industry Convergence of AI and Iot at the Cutting Edge, 2024
Foreword Surjeet Dalal, Neeraj Dahiya, Vivek Jaglan, Deepika Koundal, Dac-Nhuong Le Reshaping Intelligent Business and Industry Convergence of AI and Iot at the Cutting Edge, 2024
Chi-Square Method of Feature Selection: Impact of Pre-Processing of Data International Journal of Intelligent Systems and Applications in Engineering, 2023
Artificial intelligence technique for detecting bone irregularity using fastai Proceedings of the International Conference on Industrial Engineering and Operations Management, 2020
Ddos attacks simulation in cloud computing environment Research Scholar, SRM University, Sonepat, (Haryana) India., Shakti Arora*, Dr. Surjeet Dalal, Professor, Teerthanker Mahaveer University, Moradabad (U.P), India. International Journal of Innovative Technology and Exploring Engineering, 2019
Integrity verification mechanisms adopted in cloud environment Research Scholar, Department of Computer Science, SRM University, Sonepat, Haryana 131029, India., Shakti Arora, Dr. Surjeet Dalal, Associate Professor, Department of Computer Science, SRM University, Sonepat, Haryana 131029, India. International Journal of Engineering and Advanced Technology, 2019
Early detection of glaucoma disease in retinal fundus images using spatial FCM with level set segmentation Research Scholar, School of Information Technology, Engineering, VIT, Vellore, Tamilnadu, India, B. Sudha, Dr. Surjeet Dalal, Associate Professor, Dept. of Computer Science, Engineering, SRM University, Haryana, India, Dr. Kathiravan Srinivasan, Associate Professor, School of Information Technology, Engineering, VIT, Vellore, Tamilnadu, India. International Journal of Engineering and Advanced Technology, 2019
Optimizing performance of fuzzy decision support system with multiple parameter dependency for cloud provider evaluation International Journal of Engineering and Technology Uae, 2018
Performance of integrated signature verification approach: Review Proceedings of the 10th Indiacom 2016 3rd International Conference on Computing for Sustainable Global Development Indiacom 2016, 2016
Harris Hawks–tuned severity-aware YOLOv8 instance segmentation framework for vehicle damage assessment S Dalal, YK Sharma, S Kundu, MD Rokade, M Pradeep, P Choudhary, ... Scientific Reports , 2026 2026
GenAD-SM: optimized transformer-VAE model for precision anomaly detection for smart manufacturing in industry 5.0 S Dalal, UK Lilhore, S Simaiya, D Prakash, S Yadav, K Kumar, A Kaushik Journal of Intelligent Manufacturing, 1-21 , 2026 2026 Citations: 3
Generative AI for Multimedia Content Processing, Security and Privacy: Fundamentals, advances and applications S Dalal, U Kumar Lilhore, S Bhaskar Bajaj, M Shaheen The Institution of Engineering and Technology , 2025 2025
GAN-CSA: Enhanced Generative Adversarial Networks for Accurate Detection and Surgical Guidance in Skull Base Brain Metastases S Dalal, N Dahiya, S Kundu, A Verma, G Devi, M Ayadi, M Dubale, ... International Journal of Computational Intelligence Systems 18 (1), 310 , 2025 2025 Citations: 2
Enhanced heart disease diagnosis and management: A multi-phase framework leveraging deep learning and personalized nutrition R Ritika, RS Chhillar, S Dalal, S Dalal, I Moorthi, M Dubale, A Hashmi PLoS One 20 (10), e0334217 , 2025 2025 Citations: 1
Intelligent waste sorting for sustainable environment: A hybrid deep learning and transfer learning model UK Lilhore, S Simaiya, S Dalal, M Radulescu, D Balsalobre-Lorente Gondwana Research 146, 252-266 , 2025 2025 Citations: 29
SAD-GAN: A Novel Secure Anomaly Detection Framework for Enhancing the Resilience of Cyber-Physical Systems M Bhutani, S Dalal, M Alhussein, UK Lilhore, K Aurangzeb, A Hussain Cognitive Computation 17 (4), 127 , 2025 2025 Citations: 7
A Post-Quantum Hybrid Encryption Framework for Securing Biometric Data in Consumer Electronics UK Lilhore, S Simaiya, S Dalal, A Alshuhail, A Almusharraf IEEE Transactions on Consumer Electronics , 2025 2025 Citations: 9
Enhancing thyroid disease prediction with improved XGBoost model and bias management techniques S Dalal, UK Lilhore, N Faujdar, S Simaiya, A Agrawal, U Rani, A Mohan Multimedia Tools and Applications 84 (16), 16757-16788 , 2025 2025 Citations: 24
10 Hybrid Mathematical Optimization Techniques in AI UK Lilhore, S Simaiya, S Dalal Math Optimization for Artificial Intelligence: Heuristic and Metaheuristic … , 2025 2025 Citations: 2
Correction: Securing fog computing in healthcare with a zero‑trust approach and blockchain N Kaur, A Mittal, UK Lilhore, S Simaiya, S Dalal, K Saleem, ES Ghith EURASIP Journal on Wireless Communications and Networking 2025 (1), 16 , 2025 2025
Optimized XGBoost hyper-parameter tuned model with Krill Herd Algorithm (KHA) for accurate drinking water quality prediction N Malik, A Kalonia, S Dalal, DN Le SN Computer Science 6 (3), 263 , 2025 2025 Citations: 13
Securing fog computing in healthcare with a zero-trust approach and blockchain N Kaur, A Mittal, UK Lilhore, S Simaiya, S Dalal, K Saleem, ES Ghith EURASIP Journal on Wireless Communications and Networking 2025 (1), 5 , 2025 2025 Citations: 32
Revolutionizing air quality forecasting: Fusion of state-of-the-art deep learning models for precise classification UK Lilhore, S Simaiya, S Dalal, N Faujdar Urban Climate 59, 102308 , 2025 2025 Citations: 6
An attention‐driven hybrid deep neural network for enhanced heart disease classification UK Lilhore, S Simaiya, M Alhussein, S Dalal, K Aurangzeb, A Hussain Expert Systems 42 (2), e13791 , 2025 2025 Citations: 19
A novel effective forecasting model developed using ensemble machine learning for early prognosis of asthma attack and risk grade analysis S Yadav, H Sehrawat, V Jaglan, S Singh, P Kantha, P Goyal, S Dalal Scalable Computing: Practice and Experience 26 (1), 398-414 , 2025 2025 Citations: 7
Quantum machine learning algorithms: A comprehensive review J Singh, A Chugh, SS Chauhan, AK Singh, UK Lilhore, S Dalal, V Dutt, ... Industrial Quantum Computing: Algorithms, Blockchains, Industry 4.0, 37-52 , 2025 2025 Citations: 1
A hybrid model for short-term energy load prediction based on transfer learning with LightGBM for smart grids in smart energy systems S Dalal, UK Lilhore, B Seth, M Radulescu, S Hamrioui Journal of Urban Technology 32 (1), 49-75 , 2025 2025 Citations: 15
Smart grid stability prediction model using two-way attention based hybrid deep learning and MPSO UK Lilhore, S Dalal, M Radulescu, M Barbulescu Energy Exploration & Exploitation 43 (1), 142-168 , 2025 2025 Citations: 24
The impact of AI and automation on income inequality in BRICS countries and the role of structural factors and women’s empowerment M Suhrab, C Pinglu, R Magdalena, JA Soomro, S Dalal Industrial Quantum Computing: Algorithms, Blockchains, Industry 4, 155 , 2024 2024 Citations: 3
MOST CITED SCHOLAR PUBLICATIONS
Integrating encryption techniques for secure data storage in the cloud B Seth, S Dalal, V Jaglan, DN Le, S Mohan, G Srivastava Transactions on Emerging Telecommunications Technologies 33 (4), e4108 , 2022 2022 Citations: 281
Enhancement of patient facial recognition through deep learning algorithm: ConvNet EM Onyema, PK Shukla, S Dalal, MN Mathur, M Zakariah, B Tiwari Journal of Healthcare Engineering 2021 (1), 5196000 , 2021 2021 Citations: 139
Artificial intelligence-based ensemble learning model for prediction of hepatitis C disease MO Edeh, S Dalal, IB Dhaou, CC Agubosim, CC Umoke, ... Frontiers in Public Health 10, 892371 , 2022 2022 Citations: 131
Application of machine learning for cardiovascular disease risk prediction S Dalal, P Goel, EM Onyema, A Alharbi, A Mahmoud, MA Algarni, H Awal Computational Intelligence and Neuroscience 2023 (1), 9418666 , 2023 2023 Citations: 121
Design of intrusion detection system based on cyborg intelligence for security of cloud network traffic of smart cities EM Onyema, S Dalal, CAT Romero, B Seth, P Young, MA Wajid Journal of Cloud Computing 11 (1), 26 , 2022 2022 Citations: 119
House price prediction using hedonic pricing model and machine learning techniques J Zaki, A Nayyar, S Dalal, ZH Ali Concurrency and Computation: Practice and Experience, e7342 , 2022 2022 Citations: 109
Forecasting students' adaptability in online entrepreneurship education using modified ensemble machine learning model A Malik, EM Onyema, S Dalal, UK Lilhore, D Anand, A Sharma, S Simaiya Array 19, 100303 , 2023 2023 Citations: 101
A smart waste classification model using hybrid CNN-LSTM with transfer learning for sustainable environment UK Lilhore, S Simaiya, S Dalal, R Damaševičius Multimedia Tools and Applications 83 (10), 29505-29529 , 2024 2024 Citations: 100
A cognitive security framework for detecting intrusions in IoT and 5G utilizing deep learning UK Lilhore, S Dalal, S Simaiya Computers & Security 136, 103560 , 2024 2024 Citations: 98
Hybrid XGBoost model with hyperparameter tuning for prediction of liver disease with better accuracy S Dalal, EM Onyema, A Malik World Journal of Gastroenterology 28 (46), 6551 , 2022 2022 Citations: 93
Enhanced cardiovascular disease prediction through self-improved Aquila optimized feature selection in quantum neural network & LSTM model A Darolia, RS Chhillar, M Alhussein, S Dalal, K Aurangzeb, UK Lilhore Frontiers in medicine 11, 1414637 , 2024 2024 Citations: 88
Hidm: Hybrid intrusion detection model for industry 4.0 networks using an optimized cnn-lstm with transfer learning UK Lilhore, P Manoharan, S Simaiya, R Alroobaea, M Alsafyani, ... Sensors 23 (18), 7856 , 2023 2023 Citations: 88
An adaptive traffic routing approach toward load balancing and congestion control in Cloud–MANET ad hoc networks S Dalal, B Seth, V Jaglan, M Malik, Surbhi, N Dahiya, U Rani, DN Le, ... Soft Computing 26 (11), 5377-5388 , 2022 2022 Citations: 88
Bootstrapping random forest and CHAID for prediction of white spot disease among shrimp farmers MO Edeh, S Dalal, IC Obagbuwa, BVVS Prasad, SZ Ninoria, MA Wajid, ... Scientific Reports 12 (1), 20876 , 2022 2022 Citations: 86
A systematic literature review for load balancing and task scheduling techniques in cloud computing N Devi, S Dalal, K Solanki, S Dalal, UK Lilhore, S Simaiya, N Nuristani Artificial Intelligence Review 57 (10), 276 , 2024 2024 Citations: 85
Hybrid CNN-LSTM model with efficient hyperparameter tuning for prediction of Parkinson’s disease UK Lilhore, S Dalal, N Faujdar, M Margala, P Chakrabarti, T Chakrabarti, ... Scientific Reports 13 (1), 14605 , 2023 2023 Citations: 85
A hybrid machine learning model for timely prediction of breast cancer S Dalal, EM Onyema, P Kumar, DC Maryann, AO Roselyn, MI Obichili International Journal of Modeling, Simulation, and Scientific Computing 14 … , 2023 2023 Citations: 84
Improving efficiency and sustainability via supply chain optimization through CNNs and BiLSTM S Dalal, UK Lilhore, S Simaiya, M Radulescu, L Belascu Technological Forecasting and Social Change 209, 123841 , 2024 2024 Citations: 83
Hybrid model for precise hepatitis-C classification using improved random forest and SVM method UK Lilhore, P Manoharan, JK Sandhu, S Simaiya, S Dalal, AM Baqasah, ... Scientific Reports 13 (1), 12473 , 2023 2023 Citations: 80
A breast cancer risk predication and classification model with ensemble learning and big data fusion V Jaiswal, P Saurabh, UK Lilhore, M Pathak, S Simaiya, S Dalal Decision Analytics Journal 8, 100298 , 2023 2023 Citations: 78