Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
6 results
Search Results
Item COVID-19 Prediction Using Chest X-rays Images(Institute of Electrical and Electronics Engineers Inc., 2021) Kumar, A.; Sharma, N.; Naik, D.Understanding covid-19 became very important since large scale vaccination of this was not possible. Chest X-ray is the first imaging technique that plays an important role in the diagnosis of COVID-19 disease. Till now in various fields, great success has been achieved using convolutional neural networks(CNNs) for image recognition and classification. However, due to the limited availability of annotated medical images, the classification of medical images remains the biggest challenge in medical diagnosis. The proposed research work has performed transfer learning using deep learning models like Resnet50 and VGG16 and compare their performance with a newly developed CNN based model. Resnet50 and VGG16 are state of the art models and have been used extensively. A comparative analysis with them will give us an idea of how good our model is. Also, this research work develops a CNN model as it is expected to perform really good on image classification related problems. The proposed research work has used kaggle radiography dataset for training, validating and testing. Moreover, this research work has used another x-ray images dataset which have been created from two different sources. The result shows that the CNN model developed by us outperforms VGG16 and Resnet50 model. © 2021 IEEE.Item NucleiSegNet: Robust deep learning architecture for the nuclei segmentation of liver cancer histopathology images(Elsevier Ltd, 2021) Lal, S.; Das, D.; Alabhya, K.; Kanfade, A.; Kumar, A.; Kini, J.R.The nuclei segmentation of hematoxylin and eosin (H&E) stained histopathology images is an important prerequisite in designing a computer-aided diagnostics (CAD) system for cancer diagnosis and prognosis. Automated nuclei segmentation methods enable the qualitative and quantitative analysis of tens of thousands of nuclei within H&E stained histopathology images. However, a major challenge during nuclei segmentation is the segmentation of variable sized, touching nuclei. To address this challenge, we present NucleiSegNet - a robust deep learning network architecture for the nuclei segmentation of H&E stained liver cancer histopathology images. Our proposed architecture includes three blocks: a robust residual block, a bottleneck block, and an attention decoder block. The robust residual block is a newly proposed block for the efficient extraction of high-level semantic maps. The attention decoder block uses a new attention mechanism for efficient object localization, and it improves the proposed architecture's performance by reducing false positives. When applied to nuclei segmentation tasks, the proposed deep-learning architecture yielded superior results compared to state-of-the-art nuclei segmentation methods. We applied our proposed deep learning architecture for nuclei segmentation to a set of H&E stained histopathology images from two datasets, and our comprehensive results show that our proposed architecture outperforms state-of-the-art methods. As part of this work, we also introduced a new liver dataset (KMC liver dataset) of H&E stained liver cancer histopathology image tiles, containing 80 images with annotated nuclei procured from Kasturba Medical College (KMC), Mangalore, Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, India. The proposed model's source code is available at https://github.com/shyamfec/NucleiSegNet. © 2020 Elsevier LtdItem Efficient and robust deep learning architecture for segmentation of kidney and breast histopathology images(Elsevier Ltd, 2021) Chanchal, A.K.; Kumar, A.; Lal, S.; Kini, J.Image segmentation is consistently an important task for computer vision and the analysis of medical images. The analysis and diagnosis of histopathology images by using efficient algorithms that separate hematoxylin and eosin-stained nuclei was the purpose of our proposed method. In this paper, we propose a deep learning model that automatically segments the complex nuclei present in histology images by implementing an effective encoder–decoder architecture with a separable convolution pyramid pooling network (SCPP-Net). The SCPP unit focuses on two aspects: first, it increases the receptive field by varying four different dilation rates, keeping the kernel size fixed, and second, it reduces the trainable parameter by using depth-wise separable convolution. Our deep learning model experimented with three publicly available histopathology image datasets. The proposed SCPP-Net provides better experimental segmentation results compared to other existing deep learning models and is evaluated in terms of F1-score and aggregated Jaccard index. © 2021 Elsevier LtdItem Efficient deep learning architecture with dimension-wise pyramid pooling for nuclei segmentation of histopathology images(Elsevier Ltd, 2021) Aatresh, A.A.; Yatgiri, R.P.; Chanchal, A.K.; Kumar, A.; Ravi, A.; Das, D.; Raghavendra, B.S.; Lal, S.; Kini, J.Image segmentation remains to be one of the most vital tasks in the area of computer vision and more so in the case of medical image processing. Image segmentation quality is the main metric that is often considered with memory and computation efficiency overlooked, limiting the use of power hungry models for practical use. In this paper, we propose a novel framework (Kidney-SegNet) that combines the effectiveness of an attention based encoder-decoder architecture with atrous spatial pyramid pooling with highly efficient dimension-wise convolutions. The segmentation results of the proposed Kidney-SegNet architecture have been shown to outperform existing state-of-the-art deep learning methods by evaluating them on two publicly available kidney and TNBC breast H&E stained histopathology image datasets. Further, our simulation experiments also reveal that the computational complexity and memory requirement of our proposed architecture is very efficient compared to existing deep learning state-of-the-art methods for the task of nuclei segmentation of H&E stained histopathology images. The source code of our implementation will be available at https://github.com/Aaatresh/Kidney-SegNet. © 2021 Elsevier LtdItem MSSEAG-UNet: A Novel Deep Learning Architecture for Cloud Segmentation in Fisheye Sky Images and Solar Energy Forecast(Institute of Electrical and Electronics Engineers Inc., 2025) Kumar, A.; Kashyap, Y.; Sharma, K.; Vittal, K.; Shubhanga, K.N.This study analyzes sky images captured using a ground-based fisheye camera, aiming to address the challenge of accurately segmenting clouds, which is difficult due to their fuzzy and indistinct boundaries and uneven lighting conditions. Accurate segmentation of clouds in ground-based sky images is crucial for accurate solar energy forecasting. Motivated by these challenges, this article has proposed a novel deep learning architecture called multispatial squeeze-and-excite attention gated U-Net (MSSEAG-UNet) for cloud segmentation in ground-based fisheye sky images. The proposed architecture integrates a multispatial convolutional (MS-CNN) block and squeeze-and-excitation (SE) blocks in the encoder path to improve multiscale feature extraction (MFF) and recalibrate feature maps, while an attention block is incorporated in the decoder path to emphasize key cloud features. The segmentation performance of the MSSEAG-UNet is compared with five benchmark models, and results show that the proposed model outperforms than all benchmarks models. Furthermore, the segmented cloud images produced by the MSSEAG-UNet are used to calculate the cloud percentage, which is then integrated with the original sky images using a multicolumn convolutional model for global horizontal irradiance (GHI) forecast. GHI forecast is conducted for 15-, 30-, and 60-min ahead timesteps, with the best results achieved for the 60-min forecast, yielding mean absolute error (MAE), mean square error (mse), and RMSE values of 6.245%, 0.683%, and 8.265%, respectively. These results highlight the effectiveness of the proposed approach in improving both cloud segmentation accuracy and short-term solar irradiance forecasting. © 1980-2012 IEEE.Item An integrated frequency domain decomposition and deep neural network approach for short-term PV power forecast(Springer Science and Business Media Deutschland GmbH, 2025) Kumar, A.; Kashyap, Y.; Rai, A.Weather disturbances and atmospheric parameters significantly influence the fluctuations in PV power output, which in turn affect the stability of grid operations. The current study proposed short-term PV power forecasting based on appropriate cutoff frequency in frequency domain and artificial intelligence method. Initially, the actual PV power data are decomposed into the frequency domain, and optimal cutoff frequency is determined by minimizing the squared difference of correlation between the decomposed components. Subsequently, the PV power is separated into low-frequency components (LFC) and high-frequency components (HFC). Then, long short-term memory (LSTM) and light gradient boosting machine (LGBM) models are then employed to forecast the LFC and HFC PV power. The final forecast output is generated using various recombination methods. The proposed combined forecast model, LFC-LGBM + HFC-LGBM, based on frequency domain decomposition (FDD) and LGBM approach, demonstrates superior performance compared to models (LFC-LSTM + HFC-LSTM), (LFC-LGBM + HFC-LSTM), and (LFC-LSTM + HFC-LGBM). The best-performing model (LFC-LGBM + HFC-LGBM) achieves a MAE of 4.9420%, a RMSE of 7.1047%, and a correlation index (R) of 0.9734 for 15-min ahead timesteps. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.