Daniel Arockiam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Daniel Arockiam has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Azween Abdullah
Faculty of Computing and Digital Technology, HELP University, Kuala Lumpur, Malaysia
3 shared publications - Ganesh Gopal Devarajan
Department of Computer Science and Engineering, Amity School of Engineering and Technology, Amity University, Noida, Uttar Pradesh, India
2 shared publications Javedh Shareef
RAK College of Pharmacy, RAK Medical & Health Sciences University, Ras Al Khaimah, United Arab Emirates
2 shared publications- Mahakavi Palanichamy
Department of Civil Engineering, Amity School of Engineering and Technology, Amity University Madhya Pradesh, Gwalior, India
2 shared publications Phool Chandra
Teerthanker Mahaveer College of Pharmacy, Teerthanker Mahaveer University, Moradabad, India
2 shared publications- Pulkit Ohri
Amity University, Gwalior, India
2 shared publications
Latest Publications
- Open Access
- 14 October 2026
- Published byĀ Springer NatureĀ inĀ Discover Computing
- Vol.Ā 29 Ā (1) , 754
Hybrid deep ensemble learning for crop disease prediction and climate-resilient disaster management in smart agriculture
Accurate crop disease prediction and climate-resilient disaster management are essential for improving agricultural productivity and ensuring food security under increasingly dynamic environmental conditions. Existing deep learning approaches typically perform crop disease detection and climate forecasting independently and often rely on deterministic CNN–LSTM architectures without effective multimodal feature fusion, predictive uncertainty estimation, or comprehensive statistical validation. Consequently, their ability to provide reliable decision support under changing climatic conditions remains limited. To address these challenges, this paper proposes a novel hybrid deep ensemble learning framework for integrated crop disease prediction and climate-resilient disaster management in smart agriculture. The proposed framework combines convolutional neural networks (CNNs) for spatial crop image feature extraction with long short-term memory (LSTM) networks for temporal climate forecasting. An attention-based multimodal feature fusion mechanism is employed to integrate heterogeneous crop and climate information, while Bayesian uncertainty estimation and deep ensemble learning are incorporated to improve prediction reliability, robustness, and confidence-aware decision support. Experimental evaluation is performed using multimodal datasets comprising crop images and climate observations collected from the PlantVillage, NOAA, and NASA EOS datasets. The dataset is divided into training, validation, and testing subsets using a 70:15:15 ratio. The proposed framework is evaluated using classification and regression metrics, including Accuracy, Precision, Recall, F1-score, RMSE, MAE, MAPE, and AUC-ROC. To ensure reproducibility, all experiments are repeated five times using different random seeds, and the results are reported with mean $$\pm$$ standard deviation, 95% confidence intervals, and paired Student’s $$t$$ -tests. Experimental results demonstrate that the proposed framework consistently outperforms conventional CNN, LSTM, and CNN–LSTM hybrid models by achieving higher classification accuracy, lower climate forecasting error, improved robustness under varying climate conditions, and statistically significant performance improvements. The proposed framework provides a reliable, scalable, and uncertainty-aware solution for intelligent climate-resilient smart agriculture and early agricultural disaster management.- 14 October 2026
- Published byĀ Springer NatureĀ inĀ Discover Computing
- Vol.Ā 29 Ā (1) , 754
Open AccessHybrid deep ensemble learning for crop disease prediction and climate-resilient disaster management in smart agriculture
Accurate crop disease prediction and climate-resilient disaster management are essential for improving agricultural productivity and ensuring food security under increasingly dynamic environmental conditions. Existing deep learning approaches typically perform crop disease detection and climate forecasting independently and often rely on deterministic CNN–LSTM architectures without effective multimodal feature fusion, predictive uncertainty estimation, or comprehensive statistical validation. Consequently, their ability to provide reliable decision support under changing climatic conditions remains limited. To address these challenges, this paper proposes a novel hybrid deep ensemble learning framework for integrated crop disease prediction and climate-resilient disaster management in smart agriculture. The proposed framework combines convolutional neural networks (CNNs) for spatial crop image feature extraction with long short-term memory (LSTM) networks for temporal climate forecasting. An attention-based multimodal feature fusion mechanism is employed to integrate heterogeneous crop and climate information, while Bayesian uncertainty estimation and deep ensemble learning are incorporated to improve prediction reliability, robustness, and confidence-aware decision support. Experimental evaluation is performed using multimodal datasets comprising crop images and climate observations collected from the PlantVillage, NOAA, and NASA EOS datasets. The dataset is divided into training, validation, and testing subsets using a 70:15:15 ratio. The proposed framework is evaluated using classification and regression metrics, including Accuracy, Precision, Recall, F1-score, RMSE, MAE, MAPE, and AUC-ROC. To ensure reproducibility, all experiments are repeated five times using different random seeds, and the results are reported with mean $$\pm$$ standard deviation, 95% confidence intervals, and paired Student’s $$t$$ -tests. Experimental results demonstrate that the proposed framework consistently outperforms conventional CNN, LSTM, and CNN–LSTM hybrid models by achieving higher classification accuracy, lower climate forecasting error, improved robustness under varying climate conditions, and statistically significant performance improvements. The proposed framework provides a reliable, scalable, and uncertainty-aware solution for intelligent climate-resilient smart agriculture and early agricultural disaster management. - Open Access
- 10 September 2026
- Published byĀ Springer NatureĀ inĀ Iranian Journal of Science and Technology, Transactions of Civil Engineering
- p. 1-25
Bacterial Self-healing Concrete with Limestone Calcined Clay: Mechanical Properties, Durability, and Digital Image-Based Evaluation
Conventional cement production creates a huge amount of COā emission, and concrete is vulnerable to the formation of microcracks that shorten the service life. Bacterial self healing and Limestone Calcined Cement (LC³) are some sustainable solutions proposed. However, the combined effect of LC³ and bacterial self-healing has not been systematically optimized, and quantitative data on crack healing kinetics, pore refinement, and statistical validation are limited. The ordinary Portland cement (OPC) was partially substituted by LC³ at 4%, 8% and 12% replacement rates in this study. A bacterial solution of Bacillus sphaericus (ODāāā = 1.0; ~10ā¹ cells/mL) was added at the rates of 10, 20 or 30 mL per concrete mix. Each experiment was repeated three times ( n = 3). Mechanical properties (compressive, split tensile, and flexural strength), durability characteristics (water absorption and sorptivity), and microstructural characteristics (XRD, SEM and EDS) were assessed and crack healing was assessed by digital image processing (DIP). One way ANOVA, Tukeyās HSD test and Response Surface Methodology (RSM) were conducted. The optimum mix (LC08B20: 8% LC³ + 20 mL bacteria) demonstrated a compressive strength of 60.30 MPa for 28 days which was about 11.7% higher than the control mix. The increase in split tensile and flexural strength was 27.8% and 18.9%, respectively. The water absorption and sorptivity had a decrease of 19.5% and 28, respectively, which is a sign of higher durability. The ANOVA results showed that the observed effect was statistically significant with a p value < 0.05. The optimal dosage of both LC³ (8.2%) and bacteria (19.5 mL) was predicted by RSM with model reliability (R² = 0.94ā0.96). After 7 days of continuous water immersed test, it was found that about 73% of the cracks which were initially 0.45 mm wide were healed using self healing. Effective pore refinement was revealed by DIP analysis with a reduction in pore area by 50ā55%. Moreover, the LC08B20 mix showed an average decrease of nearly 2.6% in COā emissions when compared with the control mix. In summary, the LC³ā Bacillus sphaericus system is a long-term, cost-efficient and environmentally friendly approach to self healing concrete.
- 10 September 2026
- Published byĀ Springer NatureĀ inĀ Iranian Journal of Science and Technology, Transactions of Civil Engineering
- p. 1-25
Open AccessBacterial Self-healing Concrete with Limestone Calcined Clay: Mechanical Properties, Durability, and Digital Image-Based Evaluation
Conventional cement production creates a huge amount of COā emission, and concrete is vulnerable to the formation of microcracks that shorten the service life. Bacterial self healing and Limestone Calcined Cement (LC³) are some sustainable solutions proposed. However, the combined effect of LC³ and bacterial self-healing has not been systematically optimized, and quantitative data on crack healing kinetics, pore refinement, and statistical validation are limited. The ordinary Portland cement (OPC) was partially substituted by LC³ at 4%, 8% and 12% replacement rates in this study. A bacterial solution of Bacillus sphaericus (ODāāā = 1.0; ~10ā¹ cells/mL) was added at the rates of 10, 20 or 30 mL per concrete mix. Each experiment was repeated three times ( n = 3). Mechanical properties (compressive, split tensile, and flexural strength), durability characteristics (water absorption and sorptivity), and microstructural characteristics (XRD, SEM and EDS) were assessed and crack healing was assessed by digital image processing (DIP). One way ANOVA, Tukeyās HSD test and Response Surface Methodology (RSM) were conducted. The optimum mix (LC08B20: 8% LC³ + 20 mL bacteria) demonstrated a compressive strength of 60.30 MPa for 28 days which was about 11.7% higher than the control mix. The increase in split tensile and flexural strength was 27.8% and 18.9%, respectively. The water absorption and sorptivity had a decrease of 19.5% and 28, respectively, which is a sign of higher durability. The ANOVA results showed that the observed effect was statistically significant with a p value < 0.05. The optimal dosage of both LC³ (8.2%) and bacteria (19.5 mL) was predicted by RSM with model reliability (R² = 0.94ā0.96). After 7 days of continuous water immersed test, it was found that about 73% of the cracks which were initially 0.45 mm wide were healed using self healing. Effective pore refinement was revealed by DIP analysis with a reduction in pore area by 50ā55%. Moreover, the LC08B20 mix showed an average decrease of nearly 2.6% in COā emissions when compared with the control mix. In summary, the LC³ā Bacillus sphaericus system is a long-term, cost-efficient and environmentally friendly approach to self healing concrete.
- Open Access
- 5 August 2026
- Published byĀ Springer NatureĀ inĀ Journal of Biological Engineering
- Vol.Ā 20 Ā (1)
Translational design of multifunctional novasomes for theranostic-driven precision therapy of cutaneous oncology
- 5 August 2026
- Published byĀ Springer NatureĀ inĀ Journal of Biological Engineering
- Vol.Ā 20 Ā (1)
Open AccessTranslational design of multifunctional novasomes for theranostic-driven precision therapy of cutaneous oncology
- Open Access
- 18 July 2026
- Published byĀ Springer NatureĀ inĀ Journal of Nanobiotechnology
- Vol.Ā 24 Ā (1)
Emerging role of herbal nanogel formulations in skin cancer therapy: mechanistic insights and translational advances in nanomedicine
Objective: Skin cancer remains a major global health concern, necessitating the development of innovative therapeutic strategies that enhance treatment efficacy while minimizing adverse effects. This review aims to explore the emerging role of herbal nanogels as a promising nanotechnology-based drug delivery system for skin cancer therapy. Methods: A comprehensive review of recent literature was conducted focusing on nanogel-based drug delivery systems, herbal bioactive compounds, and stimulus-responsive nanotechnology approaches for cancer treatment, particularly skin cancer. Results: Nanogels, defined as crosslinked nanoscale polymeric networks, have gained significant attention due to their high drug-loading capacity, tunable physicochemical properties, and ability to respond to various internal and external stimuli. They can be synthesized using techniques such as emulsion methods, micro-molding, and photolithography, allowing precise control over size and morphology. Advanced stimulus-responsive nanogels, including tumor microenvironment-sensitive and ligand-targeted systems (e.g., LHRH-targeted nanogels), enable controlled and site-specific drug release. Recent developments in herbal nanogels integrate plant-derived bioactive compounds within nanogel matrices, enhancing solubility, stability, and therapeutic efficiency against skin cancer. Discussion: Herbal nanogels represent a promising interdisciplinary approach combining nanotechnology and phytomedicine, offering targeted, less invasive, and potentially more effective treatment options for skin cancer. Despite significant progress, challenges such as clinical translation, large-scale production, and long-term safety evaluation remain. Continued research in smart and multifunctional nanogel systems may significantly advance future skin cancer therapies.
- 18 July 2026
- Published byĀ Springer NatureĀ inĀ Journal of Nanobiotechnology
- Vol.Ā 24 Ā (1)
Open AccessEmerging role of herbal nanogel formulations in skin cancer therapy: mechanistic insights and translational advances in nanomedicine
Objective: Skin cancer remains a major global health concern, necessitating the development of innovative therapeutic strategies that enhance treatment efficacy while minimizing adverse effects. This review aims to explore the emerging role of herbal nanogels as a promising nanotechnology-based drug delivery system for skin cancer therapy. Methods: A comprehensive review of recent literature was conducted focusing on nanogel-based drug delivery systems, herbal bioactive compounds, and stimulus-responsive nanotechnology approaches for cancer treatment, particularly skin cancer. Results: Nanogels, defined as crosslinked nanoscale polymeric networks, have gained significant attention due to their high drug-loading capacity, tunable physicochemical properties, and ability to respond to various internal and external stimuli. They can be synthesized using techniques such as emulsion methods, micro-molding, and photolithography, allowing precise control over size and morphology. Advanced stimulus-responsive nanogels, including tumor microenvironment-sensitive and ligand-targeted systems (e.g., LHRH-targeted nanogels), enable controlled and site-specific drug release. Recent developments in herbal nanogels integrate plant-derived bioactive compounds within nanogel matrices, enhancing solubility, stability, and therapeutic efficiency against skin cancer. Discussion: Herbal nanogels represent a promising interdisciplinary approach combining nanotechnology and phytomedicine, offering targeted, less invasive, and potentially more effective treatment options for skin cancer. Despite significant progress, challenges such as clinical translation, large-scale production, and long-term safety evaluation remain. Continued research in smart and multifunctional nanogel systems may significantly advance future skin cancer therapies.
- 17 November 2025
- Published byĀ Springer NatureĀ inĀ International Journal of Information Technology
- p. 1-13
BDSecChain: a Byzantine-resilient blockchain-assisted security algorithm for multi-controller SDN environments
- 17 November 2025
- Published byĀ Springer NatureĀ inĀ International Journal of Information Technology
- p. 1-13
BDSecChain: a Byzantine-resilient blockchain-assisted security algorithm for multi-controller SDN environments
- 9 October 2025
- Published byĀ Springer NatureĀ inĀ Cluster Computing
- Vol.Ā 28 Ā (15) , 1-19
A novel optimized hybrid deep learning model for intrusion detection in software defined internet of things (SDIoT) environment
- 9 October 2025
- Published byĀ Springer NatureĀ inĀ Cluster Computing
- Vol.Ā 28 Ā (15) , 1-19
A novel optimized hybrid deep learning model for intrusion detection in software defined internet of things (SDIoT) environment
- 12 May 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Journal of Selected Topics in Signal Processing
- Vol.Ā 19 Ā (4) , 613-622
Deep Multi-Source Visual Fusion With Transformer Model for Video Content Filtering
As YouTube content continues to grow, advanced filtering systems are crucial to ensuring a safe and enjoyable user experience. We present MFusTSVD, a multi-modal model for classifying YouTube video content by analyzing text, audio, and video images. MFusTSVD uses specialized methods to extract features from audio and video images, while processing text data with BERT Transformers. Our key innovation includes two new BERT-based multi-modal fusion methods: B-SMTLMF and B-CMTLRMF. These methods combine features from different data types and improve the model's ability to understand each type of data, including detailed audio patterns, leading to better content classification and speech-related separation. MFusTSVD is designed to perform better than existing models in terms of accuracy, precision, recall, and F-measure. Tests show that MFusTSVD consistently outperforms popular models like Memory Fusion Network, Early Fusion LSTM, Late Fusion LSTM, and multi-modal Transformer across different content types and evaluation measures. In particular, MFusTSVD effectively balances precision and recall, which makes it especially useful for identifying inappropriate speech and audio content, as well as broader categories, ensuring reliable and robust content moderation.
- 12 May 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Journal of Selected Topics in Signal Processing
- Vol.Ā 19 Ā (4) , 613-622
Deep Multi-Source Visual Fusion With Transformer Model for Video Content Filtering
As YouTube content continues to grow, advanced filtering systems are crucial to ensuring a safe and enjoyable user experience. We present MFusTSVD, a multi-modal model for classifying YouTube video content by analyzing text, audio, and video images. MFusTSVD uses specialized methods to extract features from audio and video images, while processing text data with BERT Transformers. Our key innovation includes two new BERT-based multi-modal fusion methods: B-SMTLMF and B-CMTLRMF. These methods combine features from different data types and improve the model's ability to understand each type of data, including detailed audio patterns, leading to better content classification and speech-related separation. MFusTSVD is designed to perform better than existing models in terms of accuracy, precision, recall, and F-measure. Tests show that MFusTSVD consistently outperforms popular models like Memory Fusion Network, Early Fusion LSTM, Late Fusion LSTM, and multi-modal Transformer across different content types and evaluation measures. In particular, MFusTSVD effectively balances precision and recall, which makes it especially useful for identifying inappropriate speech and audio content, as well as broader categories, ensuring reliable and robust content moderation.
- 1 January 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Consumer Electronics
- Vol.Ā 71 Ā (2) , 6263-6270
Explainable Federated Learning-Based Secure and Transparent Object Detection Model for Autonomous Vehicles
Intelligent Transportation Systems (ITS) and autonomous vehicles (AVs) are two fast-moving research fields. Understanding the surroundings and acting quickly is essential for AV control, especially in dynamic environments. Object detection algorithms must function properly under these demanding circumstances. Even though deep learning models are excellent at detecting objects, they are sometimes criticized for having unclear decision-making. Recently, explainable artificial intelligence (XAI) has improved these judgmentsā interpretability. This paper proposes a federated learning system that protects data privacy while enabling decentralized training across many AVs of an upgraded object detection algorithm, Yolov7-E. Grad-CAM visualization techniques are used to illustrate the deep learning models, and for easier interpretability, semantic data is fused with object detection. Enhanced security through federated learning, reducing data privacy risks by 40%. Based on comparative studies, it is demonstrated that the suggested model, which utilizes the federated learning paradigm, attains higher mAP and is appropriate for AV decision mechanisms while maintaining data privacy.
- 1 January 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Consumer Electronics
- Vol.Ā 71 Ā (2) , 6263-6270
Explainable Federated Learning-Based Secure and Transparent Object Detection Model for Autonomous Vehicles
Intelligent Transportation Systems (ITS) and autonomous vehicles (AVs) are two fast-moving research fields. Understanding the surroundings and acting quickly is essential for AV control, especially in dynamic environments. Object detection algorithms must function properly under these demanding circumstances. Even though deep learning models are excellent at detecting objects, they are sometimes criticized for having unclear decision-making. Recently, explainable artificial intelligence (XAI) has improved these judgmentsā interpretability. This paper proposes a federated learning system that protects data privacy while enabling decentralized training across many AVs of an upgraded object detection algorithm, Yolov7-E. Grad-CAM visualization techniques are used to illustrate the deep learning models, and for easier interpretability, semantic data is fused with object detection. Enhanced security through federated learning, reducing data privacy risks by 40%. Based on comparative studies, it is demonstrated that the suggested model, which utilizes the federated learning paradigm, attains higher mAP and is appropriate for AV decision mechanisms while maintaining data privacy.
- 4 December 2024
- Published byĀ Springer NatureĀ inĀ SN Computer Science
- Vol.Ā 5 Ā (8) , 1-21
Enhancing Human Activity Detection and Classification Using Fine Tuned Attention-Based Transformer Models
- 4 December 2024
- Published byĀ Springer NatureĀ inĀ SN Computer Science
- Vol.Ā 5 Ā (8) , 1-21
Enhancing Human Activity Detection and Classification Using Fine Tuned Attention-Based Transformer Models