Krunal Randive
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
Research Subjects
Krunal Randive has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
R. Mohan
3 shared publicationsMohan Ramasundaram
Department of Computer Science and Engineering, National Institute of Technology, Tiruchirappalli, Tamil Nadu, India
2 shared publications- Ramamoorthy Hariharan
SRM Institute of Science and Technology
2 shared publications - Soosaimarian Peter Raja
School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India
2 shared publications - .V. Sumathi1 shared publication
- .V. Sutha1 shared publication
Latest Publications
- 30 June 2026
- Published by International Academic Institute for Science and Technology in International Academic Journal of Science and Engineering
Federated Deep Learning–Machine Learning Framework for Early Detection of Multi-Domain Environmental Hazards Using Sparse Real-Time Sensor Data
Increasingly severe environmental hazards (e.g., air pollution, floods, forest fires, and industrial gas leaks) require intelligent monitoring systems that can work in sparse, distributed, and privacy-sensitive data environments. Because traditional centralized solutions have high communication overhead, latency, and privacy issues, they are not effective for large-scale Internet of Things (IoT) deployments. This paper presents FDL-ML, a novel Federated Deep Learning-Machine Learning framework for early detection of multi-domain environmental hazards through sparse real-time sensor data. The FDL-ML architecture integrates federated learning with hybrid machine learning and deep learning to allow for decentralized model training across distributed IoT sensor nodes without sharing raw data. A robust preprocessing layer consists of techniques such as imputing, filtering, normalizing, and detecting anomalies, which enhance data quality and reliability. Random Forest and Support Vector Machine models are used to analyze structured environmental data, while convolutional neural networks and long short-term memory networks model complex spatial and temporal patterns. Federated averaging is used to combine individual model updates into a global model while maintaining privacy and reducing communication costs. Simulation experiments with 100 distributed sensor nodes and approximately 4.32 million environmental data samples were conducted to evaluate the performance of the proposed framework. The hazard detection accuracy of this framework is 91%, which exceeds the performance of traditional centralized and standalone models. In addition, the proposed framework reduced latency by 35%, communication costs by 40%, and had a 30% increase in energy efficiency compared to traditional centralized monitoring solutions. The proposed FDL-ML System also provides superior scalability; is robust against sparse sensor data; and provides real-time identification of hazards. These results demonstrate the potential of this framework to be a scalable, privacy-preserving, and resource-efficient solution for next-generation environmental monitoring applications in smart cities, industrial settings, and disaster-prone areas.
- 30 June 2026
- Published by International Academic Institute for Science and Technology in International Academic Journal of Science and Engineering
Federated Deep Learning–Machine Learning Framework for Early Detection of Multi-Domain Environmental Hazards Using Sparse Real-Time Sensor Data
Increasingly severe environmental hazards (e.g., air pollution, floods, forest fires, and industrial gas leaks) require intelligent monitoring systems that can work in sparse, distributed, and privacy-sensitive data environments. Because traditional centralized solutions have high communication overhead, latency, and privacy issues, they are not effective for large-scale Internet of Things (IoT) deployments. This paper presents FDL-ML, a novel Federated Deep Learning-Machine Learning framework for early detection of multi-domain environmental hazards through sparse real-time sensor data. The FDL-ML architecture integrates federated learning with hybrid machine learning and deep learning to allow for decentralized model training across distributed IoT sensor nodes without sharing raw data. A robust preprocessing layer consists of techniques such as imputing, filtering, normalizing, and detecting anomalies, which enhance data quality and reliability. Random Forest and Support Vector Machine models are used to analyze structured environmental data, while convolutional neural networks and long short-term memory networks model complex spatial and temporal patterns. Federated averaging is used to combine individual model updates into a global model while maintaining privacy and reducing communication costs. Simulation experiments with 100 distributed sensor nodes and approximately 4.32 million environmental data samples were conducted to evaluate the performance of the proposed framework. The hazard detection accuracy of this framework is 91%, which exceeds the performance of traditional centralized and standalone models. In addition, the proposed framework reduced latency by 35%, communication costs by 40%, and had a 30% increase in energy efficiency compared to traditional centralized monitoring solutions. The proposed FDL-ML System also provides superior scalability; is robust against sparse sensor data; and provides real-time identification of hazards. These results demonstrate the potential of this framework to be a scalable, privacy-preserving, and resource-efficient solution for next-generation environmental monitoring applications in smart cities, industrial settings, and disaster-prone areas.
- 26 November 2025
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 21 (1) , 13
Cyber insights: exploring the effectiveness of image-based and vector-based feature representations in insider threat detection
- 26 November 2025
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 21 (1) , 13
Cyber insights: exploring the effectiveness of image-based and vector-based feature representations in insider threat detection
- 2 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Canadian Journal of Electrical and Computer Engineering
- Vol. 46 (4) , 298-309
TransAttU-Net Deep Neural Network for Brain Tumor Segmentation in Magnetic Resonance Imaging
A brain tumor is a deformity in the tissue where cells divide promptly and uncontrollably. As a consequence, the tumor expands. It is hypothesized that a neural network can successfully identify and predict brain tumors, two of the most challenging medical problems now facing doctors. The abundance of information enhances the diagnostic potential of magnetic resonance imaging (MRI) which provides the anatomical features of brain tumors. To improve the efficiency of the semantic segmentation architecture, we introduce a novel transformer-based attention U-shaped network called TransAttU-Net, in which the multilevel guided attention and multiscale skip connection operate simultaneously and which is also used to extract the pixel on the tumor area. Initially, the input image data are altered and undergo further processing using various preprocessing techniques. Methods such as these can be used to resize or rescale features, data augmentation, reverse or flip data, and alter the orientation of data. These procedures are required before sending data to the TransAttU-Net deep learning (DL) model. The algorithm attained a degree of accuracy on the BraTS 2019, i.e., the dataset provided in multimodal brain tumor image segmentation challenge and BraTS 2020 dataset, indicating great performance on BraTS 2020 dataset. The performance metrics of the models are evaluated using and results are discussed in this article.
- 2 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Canadian Journal of Electrical and Computer Engineering
- Vol. 46 (4) , 298-309
TransAttU-Net Deep Neural Network for Brain Tumor Segmentation in Magnetic Resonance Imaging
A brain tumor is a deformity in the tissue where cells divide promptly and uncontrollably. As a consequence, the tumor expands. It is hypothesized that a neural network can successfully identify and predict brain tumors, two of the most challenging medical problems now facing doctors. The abundance of information enhances the diagnostic potential of magnetic resonance imaging (MRI) which provides the anatomical features of brain tumors. To improve the efficiency of the semantic segmentation architecture, we introduce a novel transformer-based attention U-shaped network called TransAttU-Net, in which the multilevel guided attention and multiscale skip connection operate simultaneously and which is also used to extract the pixel on the tumor area. Initially, the input image data are altered and undergo further processing using various preprocessing techniques. Methods such as these can be used to resize or rescale features, data augmentation, reverse or flip data, and alter the orientation of data. These procedures are required before sending data to the TransAttU-Net deep learning (DL) model. The algorithm attained a degree of accuracy on the BraTS 2019, i.e., the dataset provided in multimodal brain tumor image segmentation challenge and BraTS 2020 dataset, indicating great performance on BraTS 2020 dataset. The performance metrics of the models are evaluated using and results are discussed in this article.
- 22 July 2023
- Published by Elsevier in Neurocomputing
- Vol. 553
MWCapsNet: A novel Multi-level Wavelet Capsule Network for insider threat detection using image representations
- 22 July 2023
- Published by Elsevier in Neurocomputing
- Vol. 553
MWCapsNet: A novel Multi-level Wavelet Capsule Network for insider threat detection using image representations
- 19 May 2023
- Published by Taylor & Francis
- p. 446-453
Biomedical Image Segmentation Using Enhanced U-NET
The research about tumor segmentation is a major topic infield of biomedical. Nowadays many research has developed in biomedical image segmentation in multimodal MRI to diagnose and monitoring of sickness progression. The world is developing in a rapid phase and we need to keep up and develop methods that can be sustained for a longer period of time as biomedical keeps demanding for new and innovative ideas for the benefits of human beings. From the study the gliomas are maligant and heterogeneous its very tedious task to find. As of considered many algorithmic activities are performed for the segmentation pre friendly environment and to perform the exact segmentation strategies which are used for the effectual delineation of tumor into intra tumor activities. In recent years we have seen a variety of methods for brain tumor segmentation and tumor detection based on the concept of deep learning and most of the approaches are still based on U-Net or CNN which limits processing speed and accuracy. This article propose the Enhanced U-Net for brain tumor segmentation is used to identify tumors more accurately and precisely and get the proper shapes and sizes of the tumor in output widely used for biomedical image segmentation, Convolutional Neural Networks have significant performance in multiple image processing field include brain tumor segmentation.
- 19 May 2023
- Published by Taylor & Francis
- p. 446-453
Biomedical Image Segmentation Using Enhanced U-NET
The research about tumor segmentation is a major topic infield of biomedical. Nowadays many research has developed in biomedical image segmentation in multimodal MRI to diagnose and monitoring of sickness progression. The world is developing in a rapid phase and we need to keep up and develop methods that can be sustained for a longer period of time as biomedical keeps demanding for new and innovative ideas for the benefits of human beings. From the study the gliomas are maligant and heterogeneous its very tedious task to find. As of considered many algorithmic activities are performed for the segmentation pre friendly environment and to perform the exact segmentation strategies which are used for the effectual delineation of tumor into intra tumor activities. In recent years we have seen a variety of methods for brain tumor segmentation and tumor detection based on the concept of deep learning and most of the approaches are still based on U-Net or CNN which limits processing speed and accuracy. This article propose the Enhanced U-Net for brain tumor segmentation is used to identify tumors more accurately and precisely and get the proper shapes and sizes of the tumor in output widely used for biomedical image segmentation, Convolutional Neural Networks have significant performance in multiple image processing field include brain tumor segmentation.
- Open Access
- 1 January 2023
- Published by FapUNIFESP (SciELO) in Brazilian Archives of Biology and Technology
- Vol. 66, e23220896
Equilibrium Optimization Algorithm with Deep Learning Based Brain Tumor Segmentation and Classification on Magnetic Resonance Imaging
Brain tumors (BTs) are a serious medical condition that can have significant impacts on individuals. These tumors typically originate in various parts of the brain and can be detected using Magnetic Resonance Imaging (MRI), which has become an essential tool for medical research. However, manual analysis of MRI images for BT segmentation is a time-consuming and error-prone process. To address this challenge, automated methods based on deep learning algorithms have been developed for fast and accurate detection of anomalous brain regions. In this article, we propose a novel approach called Equilibrium Optimizer Algorithm with Deep Learning-based Brain Tumor Segmentation and Classification (EOADL-BTSC) for brain tumor segmentation and classification using MRI images. Our method uses enhancement of contrast and skull stripping to preprocess the images, followed by an attention-inception-based UNet model for segmentation, a capsule network (CapsNet) model for feature extraction, and a cascaded recurrent neural network (CRNN) for classification. To optimize the performance of our proposed method, we use the Equilibrium Optimizer Algorithm (EOA) to fine-tune the hyperparameters of the UNet model. We evaluate the performance of our approach on a benchmark database and compare it with other recent approaches. Our experimental results demonstrate that the EOADL-BTSC methodology outperforms the other approaches in terms of several performance measures. In summary, the proposed DL-BTSC methodology provides a promising solution for automated brain tumor segmentation and classification using MRI images. It has the potential to assist medical professionals in accurate and fast detection of brain tumors, leading to better medical analysis and treatment planning. Our proposed method achieves the maximum accu_y, sens_y, and spec_y values of 99.15% 98.78%, and 99.15% respectively. They also note that the proposed approach requires fewer parameters and has a quicker segmentation time than previous approaches.
- 1 January 2023
- Published by FapUNIFESP (SciELO) in Brazilian Archives of Biology and Technology
- Vol. 66, e23220896
Open AccessEquilibrium Optimization Algorithm with Deep Learning Based Brain Tumor Segmentation and Classification on Magnetic Resonance Imaging
Brain tumors (BTs) are a serious medical condition that can have significant impacts on individuals. These tumors typically originate in various parts of the brain and can be detected using Magnetic Resonance Imaging (MRI), which has become an essential tool for medical research. However, manual analysis of MRI images for BT segmentation is a time-consuming and error-prone process. To address this challenge, automated methods based on deep learning algorithms have been developed for fast and accurate detection of anomalous brain regions. In this article, we propose a novel approach called Equilibrium Optimizer Algorithm with Deep Learning-based Brain Tumor Segmentation and Classification (EOADL-BTSC) for brain tumor segmentation and classification using MRI images. Our method uses enhancement of contrast and skull stripping to preprocess the images, followed by an attention-inception-based UNet model for segmentation, a capsule network (CapsNet) model for feature extraction, and a cascaded recurrent neural network (CRNN) for classification. To optimize the performance of our proposed method, we use the Equilibrium Optimizer Algorithm (EOA) to fine-tune the hyperparameters of the UNet model. We evaluate the performance of our approach on a benchmark database and compare it with other recent approaches. Our experimental results demonstrate that the EOADL-BTSC methodology outperforms the other approaches in terms of several performance measures. In summary, the proposed DL-BTSC methodology provides a promising solution for automated brain tumor segmentation and classification using MRI images. It has the potential to assist medical professionals in accurate and fast detection of brain tumors, leading to better medical analysis and treatment planning. Our proposed method achieves the maximum accu_y, sens_y, and spec_y values of 99.15% 98.78%, and 99.15% respectively. They also note that the proposed approach requires fewer parameters and has a quicker segmentation time than previous approaches.
- 12 April 2019
- Published by Springer Nature
- p. 1060-1069
A State-of-Art Review on Automatic Video Annotation Techniques
- 12 April 2019
- Published by Springer Nature
- p. 1060-1069
A State-of-Art Review on Automatic Video Annotation Techniques
- 4 November 2018
- Published by Springer Nature
- p. 481-488
Fast Feature Extraction on Graphic Processing Unit for a Video Sequence
- 4 November 2018
- Published by Springer Nature
- p. 481-488
Fast Feature Extraction on Graphic Processing Unit for a Video Sequence