Raj Kumar Patra has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Analysing the Behaviour of an Intrusion Detection System Hybrid Model Based on a Random Forest Algorithm

    by Dubbaka Navanitha, M. Ramasamy, Modugula Siva Jyothi, Raj Kumar Patra, B. Sujani, M. Naga Kavya Kalyani

  • Top Cited Papers
    Open Access

    VSA-GCNN: Attention Guided Graph Neural Networks for Brain Tumor Segmentation and Classification

    by Kambham Pratap Joshi, Vishruth Boraiah Gowda, Parameshachari Bidare Divakarachari, Paramesh Siddappa Parameshwarappa, Raj Kumar Patra

    For the past few decades, brain tumors have had a substantial influence on human life, and pose severe health risks if not treated and diagnosed in the early stages. Brain tumor problems are highly diverse and vary extensively in terms of size, type, and location. This brain tumor diversity makes it challenging to progress an accurate and reliable diagnostic tool. In order to effectively segment and classify the tumor region, still several developments are required to make an accurate diagnosis. Thus, the purpose of this research is to accurately segment and classify brain tumor Magnetic Resonance Images (MRI) to enhance diagnosis. Primarily, the images are collected from BraTS 2019, 2020, and 2021 datasets, which are pre-processed using min–max normalization to eliminate noise. Then, the pre-processed images are given into the segmentation stage, where a Variational Spatial Attention with Graph Convolutional Neural Network (VSA-GCNN) is applied to handle the variations in tumor shape, size, and location. Then, the segmented outputs are processed into feature extraction, where an AlexNet model is used to reduce the dimensionality. Finally, in the classification stage, a Bidirectional Gated Recurrent Unit (Bi-GRU) is employed to classify the brain tumor regions as gliomas and meningiomas. From the results, it is evident that the proposed VSA-GCNN-BiGRU shows superior results on the BraTS 2019 dataset in terms of accuracy (99.98%), sensitivity (99.92%), and specificity (99.91%) when compared with existing models. By considering the BraTS 2020 dataset, the proposed VSA-GCNN-BiGRU shows superior results in terms of Dice similarity coefficient (0.4), sensitivity (97.7%), accuracy (98.2%), and specificity (97.4%). While evaluating with the BraTS 2021 dataset, the proposed VSA-GCNN-BiGRU achieved specificity of 97.6%, Dice similarity of 98.6%, sensitivity of 99.4%, and accuracy of 99.8%. From the overall observation, the proposed VSA-GCNN-BiGRU supports accurate brain tumor segmentation and classification, which provides clinical significance in MRI when compared to existing models.


  • Analysis on Classical Image Forgery Identification Approach with Higher Accuracy Using Fusion-Based Testing Methodology

    by K. Archana, Meka Kamala, V. A. Narayana, G. Vinoda Reddy, Raj Kumar Patra, G. Menaka

  • Open Access

    BOISO: Weight optimized U-Net architecture for segmentation of hyperspectral image

    by Ilango Bhuvaneshwarri, Andrzej Stateczny, Aruna Kumari Kokku, Raj Kumar Patra

    Recently, the Hyper Spectral Image (HSI) classification relies as a well-established study area in the topic related to Remote Sensing (RS). The classification of HSI is used in various applications such as military, agriculture, mineral mapping and so on. However, the existing techniques have underlying difficulties related to curse of dimensionalities and the lack of training data. To overcome these issues, this research using Butterfly Optimization Integrated Snake Optimization (BOISO) optimized U-Net for segmenting HSI. After data acquisition from Indian Pines dataset, the pre-processing is done using Weiner filter. Next to this, the proposed BOISO optimized U-Net is used to segment the pre-processed HSI. The spatial feature weight map is obtained based on spatial information path and corresponding features are obtained by multiplying semantic feature map. Finally, the feature map is linked with the spatial location to obtain final feature map which is optimized using the proposed BOISO. Then, the classification using hybrid classification approach is based on geometric mean of improved Deep Belief network (DBN) and Quantum Neural Network (QNN). The results exhibit that the BOISO achieves a sensitivity of 0.939 which is higher than SO, BOA, BES and PRO, with respective sensitivities of 0.877, 0.893, 0.847 and 0.857.


  • Open Access

    Feature Weighted Attention—Bidirectional Long Short Term Memory Model for Change Detection in Remote Sensing Images

    by Raj Kumar Patra, Sujata N. Patil, Przemysław Falkowski-Gilski, Zbigniew Łubniewski, Rachana Poongodan

    In remote sensing images, change detection (CD) is required in many applications, such as: resource management, urban expansion research, land management, and disaster assessment. Various deep learning-based methods were applied to satellite image analysis for change detection, yet many of them have limitations, including the overfitting problem. This research proposes the Feature Weighted Attention (FWA) in Bidirectional Long Short-Term Memory (BiLSTM) method to reduce the overfitting problem and increase the performance of classification in change detection applications. Additionally, data usage and accuracy in remote sensing activities, particularly CD, can be significantly improved by a large number of training models based on BiLSTM. Normalization techniques are applied to input images in order to enhance the quality and reduce the difference in pixel value. The AlexNet and VGG16 models were used to extract useful features from the normalized images. The extracted features were then applied to the FWA-BiLSTM model, to give more weight to the unique features and increase the efficiency of classification. The attention layer selects the unique features that help to distinguish the changes in the remote sensing images. From the experimental results, it was clearly shown that the proposed FWA-BiLSTM model achieved better performance in terms of precision (93.43%), recall (93.16%), and overall accuracy (99.26%), when compared with the existing Difference-enhancement Dense-attention Convolutional Neural Network (DDCNN) model.


  • Open Access

    Tool Wear Monitoring Using Improved Dragonfly Optimization Algorithm and Deep Belief Network

    by Leo Gertrude David, Raj Kumar Patra, Przemysław Falkowski-Gilski, Parameshachari Bidare Divakarachari, Lourdusamy Jegan Antony Marcilin

    In recent decades, tool wear monitoring has played a crucial role in the improvement of industrial production quality and efficiency. In the machining process, it is important to predict both tool cost and life, and to reduce the equipment downtime. The conventional methods need enormous quantities of human resources and expert skills to achieve precise tool wear information. To automatically identify the tool wear types, deep learning models are extensively used in the existing studies. In this manuscript, a new model is proposed for the effective classification of both serviceable and worn cutting edges. Initially, a dataset is chosen for experimental analysis that includes 254 images of edge profile cutting heads; then, circular Hough transform, canny edge detector, and standard Hough transform are used to segment 577 cutting edge images, where 276 images are disposable and 301 are functional. Furthermore, feature extraction is carried out on the segmented images utilizing Local Binary Pattern (LBPs) and Speeded up Robust Features (SURF), Harris Corner Detection (HCD), Histogram of Oriented Gradients (HOG), and Grey-Level Co-occurrence Matrix (GLCM) feature descriptors for extracting the texture feature vectors. Next, the dimension of the extracted features is reduced by an Improved Dragonfly Optimization Algorithm (IDOA) that lowers the computational complexity and running time of the Deep Belief Network (DBN), while classifying the serviceable and worn cutting edges. The experimental evaluations showed that the IDOA-DBN model attained 98.83% accuracy on the patch configuration of full edge division, which is superior to the existing deep learning models.