Banshidhar Majhi

Bio: Banshidhar Majhi is an academic researcher from National Institute of Technology, Rourkela. The author has contributed to research in topics: Feature extraction & Support vector machine. The author has an hindex of 26, co-authored 254 publications receiving 2780 citations. Previous affiliations of Banshidhar Majhi include Techno India & Indian Institute of Information Technology Design & Manufacturing Kancheepuram.

Brain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests

Abstract: This paper presents an automated and accurate computer-aided diagnosis (CAD) system for brain magnetic resonance (MR) image classification. The system first utilizes two-dimensional discrete wavelet transform (2D DWT) for extracting features from the images. After feature vector normalization, probabilistic principal component analysis (PPCA) is employed to reduce the dimensionality of the feature vector. The reduced features are applied to the classifier to categorize MR images into normal and abnormal. This scheme uses an AdaBoost algorithm with random forests as its base classifier. Three benchmark MR image datasets, Dataset-66, Dataset-160, and Dataset-255, have been used to validate the proposed system. A 5×5-fold stratified cross validation scheme is used to enhance the generalization capability of the proposed scheme. Simulation results are compared with the existing schemes and it is observed that the proposed scheme outperforms others in all the three datasets.

Mammogram classification using two dimensional discrete wavelet transform and gray-level co-occurrence matrix for detection of breast cancer

Abstract: In this paper, we propose a mammogram classification scheme to classify the breast tissues as normal, benign or malignant. Feature matrix is generated using GLCM to all the detailed coefficients from 2D-DWT of the region of interest (ROI) of a mammogram. To derive the relevant features from the feature matrix, we take the help of t-test and F-test separately. The relevant features are used in a BPNN classifier for classification. Two standard databases MIAS and DDSM are used for the validation of the proposed scheme. It is observed that t-test based relevant features outperforms to that of F-test with respect to accuracy. In addition to the suggested scheme, the competent schemes are also simulated for comparative analysis. It is observed that the proposed scheme has a better say with respect to accuracy and area under curve (AUC) of receiver operating characteristic (ROC). The accuracy measures are computed with respect to normal vs. abnormal and benign vs. malignant. For MIAS database these accuracy measures are 98.0% and 94.2% respectively, whereas for DDSM database they are 98.8% and 97.4%.

Gray level co-occurrence matrix and random forest based acute lymphoblastic leukemia detection

Abstract: In this paper, we have proposed an acute lymphoblastic leukemia detection strategy from the microscopic images. The scheme utilizes all the steps associated with any other classification scheme, but our contribution lies on a marker-based segmentation(MBS), gray level co-occurrence matrix (GLCM) based feature extraction, and probabilistic principal component analysis(PPCA) based feature reduction. The relevant features are used in a random forest (RF) based classifier. Extensive experiments are carried out on the ALL-IDB1 dataset, and comparative analysis has been made with other existing schemes with respect to sensitivity, specificity, and classification accuracy. The proposed scheme (MBS+GLCM+PPCA+RF) achieves 96.29% segmentation accuracy and classification accuracy of 99.004% and 96% for nucleus and cytoplasm respectively.

Texture feature based classification on microscopic blood smear for acute lymphoblastic leukemia detection

Abstract: This paper presents an effective scheme for classification of the normal white blood cells from the affected cells in a microscopic image. The proposed method initially pre-processes the input images using Y component of the CMYK image and a triangle method of thresholding. Subsequently, it utilizes discrete orthonormal S-transform (DOST) to extract the texture features, and its dimensionality is reduced using linear discriminant analysis. The reduced features are then supplied to the proposed Adaboost algorithm with RF (ADBRF) classifier where the random forest is used as the base classifier. A publicly available dataset, ALL-IDB1 is used to validate the proposed scheme. The simulation results based on the five runs of k-fold stratified cross-validation indicate that the proposed method yields superior accuracy (99.66%) as compared to existing schemes.

Crow search based virtual machine placement strategy in cloud data centers with live migration

Abstract: Cloud computing has emerged as the most revolutionary technology in the field of computing. The cloud service providers (CSPs) have high computational facilities called data centers (DCs) at their disposal. CSPs provide services to the users through virtual machines (VMs). VM placement is the mapping of VMs onto physical machine called hosts. In this paper, we propose a two-tier virtual machine placement algorithm. Firstly, we propose a queueing structure to manage and schedule a large set of VMs. Secondly, a multi-objective VM placement algorithm called crow search based VM placement (CSAVMP) is proposed to reduce the resources wastage and power consumption at the data centers. VM migration is an indispensable part of any cloud platform for activities like maintenance, load balancing, fault tolerance etc. Three different migration strategies namely serial, parallel, improved serial have been tested and a comparative result has been produced.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Action Recognition in Video Sequences using Deep Bi-Directional LSTM With CNN Features

Abstract: Recurrent neural network (RNN) and long short-term memory (LSTM) have achieved great success in processing sequential multimedia data and yielded the state-of-the-art results in speech recognition, digital signal processing, video processing, and text data analysis. In this paper, we propose a novel action recognition method by processing the video data using convolutional neural network (CNN) and deep bidirectional LSTM (DB-LSTM) network. First, deep features are extracted from every sixth frame of the videos, which helps reduce the redundancy and complexity. Next, the sequential information among frame features is learnt using DB-LSTM network, where multiple layers are stacked together in both forward pass and backward pass of DB-LSTM to increase its depth. The proposed method is capable of learning long term sequences and can process lengthy videos by analyzing features for a certain time interval. Experimental results show significant improvements in action recognition using the proposed method on three benchmark data sets including UCF-101, YouTube 11 Actions, and HMDB51 compared with the state-of-the-art action recognition methods.

An affine invariant salient region detector

Abstract: In this paper we describe a novel technique for detecting salient regions in an image. The detector is a generalization to affine invariance of the method introduced by Kadir and Brady [10]. The detector deems a region salient if it exhibits unpredictability in both its attributes and its spatial scale.