Udhav Bhosle

@srtmun.ac.in

Vice-Chancellor, Swami Ramanand Teerth Marathwada University, Nanded
Swami Ramanand Teerth Marathwada University Nanded



              

https://researchid.co/udhavbhosle
23

Scopus Publications

535

Scholar Citations

9

Scholar h-index

9

Scholar i10-index

Scopus Publications

  • Deep learning-driven regional drought assessment: an optimized perspective
    Chandrakant M. Kadam, Udhav V. Bhosle, and Raghunath S. Holambe
    Springer Science and Business Media LLC

  • Analysis of Real time Seismic Signal Using Machine Learning
    Sujata Kulkarni, Udhav Bhosle, and Vijaykumar T.
    IEEE
    The development of seismic data acquisition has been driven to keep track of large volume of high sample frequency signal continuously recorded at the seismic station. The signals received at the seismic station show closeness between seismic signals and non-seismic signals. Conventional and Machine learning techniques are widely used to differentiate between seismic and non-seismic signals based on amplitude and further abnormalities in the seismic signals. Authors have prepared a dataset from seed to csv format. The features are detected for frequency, amplitude, and time duration of seismic signal dataset in csv format. These features are stable, strong, and significant. The size of the feature vector has been reduced using dimension reduction technique to improve time and space complexity. Precision, recall and F1 score are used to validate the performance. Performance parameter matrices show good results for all machine learning models; however, the logistic regression and decision tree models meet the best fit model's characteristics. Finally, a presentation using a hybrid dataset (captured by different sensors) demonstrates how this model be employed in a real-time setting while lowering false alarm rates. The experimentation is carried out on seismic signals obtained from individual sensors and sensor networks (SN). A wideband seismic signal from BSVK and CUKG station located near Basavakalyan, Karnataka, and the Central University of Karnataka, makes up the experimental dataset.

  • A Machine Learning Approach to Statistical Analysis and Prediction of Rainfall and Drought in the Marathwada Subregion
    Chandrakant M. Kadam, Shashikant R. Kale, Udhav V. Bhosle, and Raghunath S. Holambe
    IEEE
    Monitoring, mitigating, and forecasting rainfall has been a concern on a global basis up to now. Numerous natural disasters, such as drought, are directly related to it and are impacted by it. Drought is the most hazardous of all the disasters. Identifying drought is difficult as it has no universal definition. It varies from region to region and climate to climate. There are various contributing factors in the judgment. It can be regional resources like climate, soil type, flora and fauna, precipitation, crop culture, etc. Also, many indicators are available that can define a drought and its type. Scientists have tried to find the most reliable indicator to identify the drought. They have concluded that no best indicator exists. In order to find the best fit, researchers recommend focusing on regional resources. The goal of the study is to make an analysis of the rainfall in the semi-arid region of Marathwada and implement a suitable machine learning approach to enhance the outcome. Over 41 years of regional precipitation data are used for the analysis. The monthly rainfall data is prepared for this study. Time series data is modelled with a machine learning approach.

  • A Comprehensive Assessment of Agricultural Drought
    Chandrakant Madhukar Kadam, Udhav V. Bhosle, and Raghunath S. Holambe
    World Researchers Associations
    There are many disasters that are still a threat to the world. Tsunamis, volcanoes, earthquakes and droughts are well-known among the group. In fact, of all the hazards mentioned, drought is quite unpredictable and devastating. It directly affects the community at large. Droughts exist in almost all countries across the globe. Furthermore, its duration and frequency depend on and vary with different parameters. Surprisingly, droughts do not possess any formal, globally accepted definition which adds to its complexity. Meteorological, agricultural, hydrological and socioeconomic droughts are the most common forms of drought discussed in the literature. A mixture of factors including precipitation, temperature and soil moisture, among others, triggers drought. According to the drought survey, researchers have examined drought, looking at the specific application along with geographical constraints, resulting in the formation of several drought indices. Drought indicators play an important role in quantitatively estimating drought intensities by integrating data from one or the other variable. Furthermore, these indices are derived in order to capture most of the characteristics of the specific drought incident. Therefore, it is necessary to strictly review established and emerging drought monitoring methods. In this work, we retrospectively analyzed various methods used to investigate drought, with special attention to agricultural drought.

  • Spatial and temporal analysis of rainfall and drought in the Marathwada region of Maharashtra
    Chandrakant M. Kadam, Udhav V. Bhosle, and Raghunath S. Holambe
    Inderscience Publishers

  • Hydrangea-type bismuth molybdate as a room-temperature smoke and humidity sensor
    Sandesh H. Narwade, Pritamkumar V. Shinde, Nanasaheb M. Shinde, Vijaykumar V. Jadhav, Shoyebmohamad F. Shaikh, Rajaram S. Mane, and Udhav V. Bhosle
    Elsevier BV

  • Video Summarization Based on Optical Flow
    Dipti Jadhav and Udhav Bhosle
    Springer Singapore


  • Video summarisation based on motion estimation using speeded up robust features
    Dipti Jadhav and Udhav Bhosle
    Inderscience Publishers
    Video summarisation (VS) is a technique to extract keyframes from a video based on video contents. It provides user with a brief representation of video contents to semantically understand the video. This paper aims to present video summarisation based on motion between consecutive video frames. The motion between frames is represented by affine and homograph transformation. The video frames are represented by a set of speeded up robust features (SURF). The keyframes are extracted in a sequential manner by successively comparison with the previously declared keyframe based on motion. The validity of the proposed algorithms is demonstrated on videos from Internet, YouTube dataset and Open Video Project. The proposed work is evaluated by comparing it with different classical and state-of-the-art video summarisation methods reported in the literature. The experimental results and performance analysis validates the effectiveness and efficiency of the proposed algorithms.


  • A study of mammogram classification using AdaBoost with decision tree, KNN, SVM and hybrid SVM-KNN as component classifiers



  • Soft feature based personal recognition
    Sujata Kulkarni, Ranjana Raut, and Udhav Bhosle
    Springer International Publishing

  • Mammography classification using modified hybrid SVM-KNN
    Poonam Sonar, Udhav Bhosle, and Chandrajit Choudhury
    IEEE
    Today leading cause of cancer deaths for women is the Breast cancer. For early and accurate detection of breast cancer, mammography is found to be the most reliable and effective technique. In this context, computer aided diagnosis of breast cancer from mammograms is gaining high importance and priority for many researchers. In this paper machine learning based mammogram classification using modified hybrid SVM-KNN is proposed. The idea is to map the feature points to kernel space using kernel and find the K nearest neighbors among the training dataset for a given test data point. Doing this we narrow down the search for support vectors. Mammogram images are preprocessed and region of interest is extracted using Fuzzy C Means clustering and Active Counter technique. GLCM (grey level covariance matrix) based texture features are extracted from segmented ROI. These features are used to train modified hybrid SVM-KNN classifier proposed by authors. The trained classifier is used to classify breast tissues in normal/abnormal classes and further abnormal class into benign/malignant. Proposed technique is experimented on two standard MIAS and DDSM databases. The proposed classifier reports classification accuracy of 100 % for DDSM and 94% for MIAS database for benign and malignant class. Results are compared with SVM, KNN and Random Forest classifiers.

  • SURF based video summarization and its optimization
    Dipti Jadhav and Udhav Bhosle
    IEEE
    Video Summarization (VS) is a technique of extracting keyframes from the video based on the video content. It provides the user with a concise representation of the video content from which the video is semantically understood. This paper proposes a video summarization technique based on Speeded Up Robust Features (SURF). Authors further propose a Graph Theory based approach to optimize the number of keyframes based on the objective function that the graph generated by the optimized video summary is a simple graph with a simple walk. The proposed algorithm is tested on two different videos from OpenVideo database. The video summarization results and its optimization obtained shows non-redundancy and improvement in the semantic understanding of the video summary.

  • SURF features based classifiers for mammogram classification
    Jyoti Deshmukh and Udhav Bhosle
    IEEE
    Breast cancer became second major reason for cancerous deaths in women. Computer-aided diagnosis of mammogram images is essential for primeval identification of cancer. Authors use SURF (Speeded-Up Robust Features) local descriptors to obtain feature vector and different classifier for mammogram classification. SURF features extracted from mammogram images are high in dimension, and very large in number. So, PreARM [1] algorithm is used to optimize SURF features. Optimized SURF feature vectors and the class of training mammograms form the transaction database, and then it is given to Apriori algorithm to mine association rules. Authors use ESAR [2] algorithm to get optimized and strong rules. Mammogram classification is carried out using the filtered and strong association rules. Proposed scheme is tested on standard MIAS and DDSM data set. Algorithms performance is measured with respect to area under ROC (Receiver Operating Characteristic) curve and classification accuracy. Results of associative classifier are compared with classification using SURF descriptor and distance measure and random forest method. Experimental results reveal that SURF outperforms other methods with regard to distinctiveness, repeatability, and robustness. SURF is computed and compared much faster by maintaining its performance. For SURF based associative classifier, accuracy values for MIAS and DDSM database are 92.3076% and 96.875% respectively, and area under ROC curve values for MIAS and DDSM database are 0.9535 and 0.9221.

  • Bit error probability analysis of MIMO multicarrier spread spectrum for different channels and modulations
    Sanjay Deshmukh and Udhav Bhosle
    IEEE
    Multiple access techniques are used in next generation wireless communication systems to allow many users to share the available spectrum efficiently. In this paper we investigate performance of a Multi Carrier Spread Spectrum system (MC-SS). The Principle of MC-SS system is to spread a data sequence by a given spreading sequence in frequency domain and allow it to modulate N subcarriers instead of one carrier. The idea is to combine such scheme with Orthogonal Frequency Division Multiplexing (OFDM) for efficient use of spectrum. Since OFDM makes use of overlapping subcarriers in frequency domain. The system consists of combination of Multiple Inputs and Multiple Outputs (MIMO) communication with Orthogonal Frequency Division multiplexing modulation scheme to provide significant increase in a system data rate, bandwidth efficiency and Quality of service (QOS). One of the important advantages of receiver structure is spatial diversity obtained by Maximum Ratio Combiner (MRC). In order to recover original information, Maximum Ratio Combiner do the phase corrected weighted addition of signals transmitted through each branch. The BER analysis is conducted for the system under different channel conditions and with different number of subcarriers. It is observed that for higher values of subcarriers and diversity, system performance in terms of BER is improved. The result shows that BER is proportional to the size M of the mapping technique used in the system.

  • SIFT with associative classifier for mammogram classification
    Jyoti Deshmukh and Udhav Bhosle
    IEEE
    In this proposed work, a Scale-Invariant Feature Transform (SIFT) with improved associative classifier is used for effective classification of mammograms. SIFT is used to extract distinctive invariant features, from region of interest (ROI) of mammograms. However, SIFT features are of very high dimension, and large number of features are generated for a mammogram, resulting in an increase in feature space and search space for matching. Authors proposed PreARM algorithm, to optimize the number of SIFT features. Transaction database consists of optimized feature vector and class of training images, and is given as input to association rule mining. Multi-fitness function Genetic algorithm is used to optimize association rules generated using Apriori algorithm. An experimental result shows that PreARM algorithm achieves 91% reduction in features and Genetic algorithm achieves 90% reduction in association rules. Standard DDSM medical image dataset is used to validate the proposed method. Optimized rules are used for classification of mammograms. Proposed SIFT based associative classifier gives classification accuracy as 93.75% and the area under receiver operating characteristic (ROC) curve value as 0.932.

  • Performance analysis of spread spectrum system over fading channel models
    Sanjay Deshmukh and Udhav Bhosle
    IEEE
    Wireless communication channel due to multipath propagation phenomenon is prone to various transmission obstacles like noise, interference, fading, and other distortions. These multiple path signals cause variation in signal strength of received signal. Therefore it is important to study the effects of multipath propagation phenomenon in designing the wireless communication systems. Spread spectrum system is a special system which is known to overcome multipath propagation problems. To know its effect against fading environment the performance of spread spectrum communication system is tested under fading channel environment like Rayleigh and Ricean. Additive White Gaussian noise (AWGN) model excludes the effects of fading, interference and dispersion. This paper investigates the performance of Direct Sequence Spread Spectrum (DSSS) systems in idealistic AWGN channel and fading channel environment using Rayleigh and Ricean channel models. From the values of BER Vs. Eb/N0 it is found that the performance of system under fading channels like Rayleigh channel and Ricean channel is close to non-fading channel environment which proves the importance of spread spectrum system.

  • Optimized association rules using objective function for mammography image classification
    Poonam Sonar, Dipti Jadhav, and Udhav Bhosle
    IEEE
    Image mining is more than just an extension of data mining to image domain. In recent years, the concept of utilizing association rules for classification has emerged. This approach proved often is more efficient and accurate than traditional techniques. This paper presents the concept of association rule mining and applied to the problem of mammogram image classifications. Association rules are obtained using Apriori algorithm. Authors propose graph theory based objective function to optimize association rules such that graph generated by the optimized rules is simple graph with simple walk. The proposed algorithm is tested on mammogram images for classification of images into benign and malignant classes. Through experimentation, it is estimated that, with and without optimization of association rules accuracy is 85% for malignant and 95% for benign class. The average accuracy is 90%. The propose technique reduces the time and space complexity associated with calculating optimized rule while maintaining the classification accuracy.

  • Optimized association rules for MRI brain tumor classification



  • Image Mining Using Association Rule for Medical Image Dataset
    Jyoti Deshmukh and Udhav Bhosle
    Elsevier BV

  • Radiometric Correction of Multispectral Images Using Radon Transform
    Priti Tyagi and Udhav Bhosle
    Springer Science and Business Media LLC

  • Relative Radiometric Correction of Multitemporal Satellite Imagery Using Fourier and Wavelet Transform
    Seema Gore Biday and Udhav Bhosle
    Springer Science and Business Media LLC

RECENT SCHOLAR PUBLICATIONS

  • Deep learning-driven regional drought assessment: an optimized perspective
    CM Kadam, UV Bhosle, RS Holambe
    Earth Science Informatics 17 (2), 1523-1537 2024

  • Analysis of Real time Seismic Signal Using Machine Learning
    S Kulkarni, U Bhosle
    IECON 2023-49th Annual Conference of the IEEE Industrial Electronics Society 2023

  • A machine learning approach to statistical analysis and prediction of rainfall and drought in the marathwada subregion
    CM Kadam, SR Kale, UV Bhosle, RS Holambe
    2023 International Conference on Emerging Smart Computing and Informatics 2023

  • Analysis of Seismic Signal and Detection of Abnormalities
    S Kulkarni, U Bhosle, V Kumar
    Computer Science and Engineering: An International Journal (CSEIJ) 12 (6) 2022

  • Spatial and temporal analysis of rainfall and drought in the Marathwada region of Maharashtra
    CM Kadam, UV Bhosle, RS Holambe
    International Journal of Water 15 (1), 53-73 2022

  • Video summarization based on optical flow
    D Jadhav, U Bhosle
    Advanced Computing and Intelligent Engineering: Proceedings of ICACIE 2018 2020

  • Mammogram classification using AdaBoost with RBFSVM and Hybrid KNN–RBFSVM as base estimator by adaptively adjusting γ and C value
    U Bhosle, J Deshmukh
    International Journal of Information Technology 11 (4), 719-726 2019

  • Analysis of outage probability for MC-CDMA systems using different spread codes
    S Deshmukh, U Bhosle
    Asian Journal of Electrical Sciences 8 (3), 18-25 2019

  • Video summarisation based on motion estimation using speeded up robust features
    D Jadhav, U Bhosle
    International Journal of Computational Vision and Robotics 9 (6), 569-582 2019

  • Transform Domain Mammogram Classification Using Optimum Multiresolution Wavelet Decomposition and Optimized Association Rule Mining
    P Sonar, U Bhosle
    Computational Intelligence in Data Mining: Proceedings of the International 2019

  • Bramhe, Ankit, 617
    K Agarwal, R Agarwal, A Agrawal, MA Ahad, MNM Ali, AS Almahayreh, ...
    Computational Intelligence in Data Mining, 897 2019

  • A Study of Mammogram Classification using AdaBoost with Decision Tree, KNN, SVM and Hybrid SVM-KNN as Component Classifiers.
    J Deshmukh, U Bhosle
    J. Inf. Hiding Multim. Signal Process. 9 (3), 548-557 2018

  • Comparative study of different machine learning classifiers for mammograms and brain MRI images
    P Sonar, U Bhosle, C Choudhury
    International Journal of Image Mining 3 (2), 152-174 2018

  • Analysis of OFDM-MIMO with BPSK Modulation and Different Antenna Configurations Using Alamouti STBC
    S Deshmukh, U Bhosle
    Optical and Wireless Technologies: Proceedings of OWT 2017, 1-9 2018

  • Mammography classification using modified hybrid SVM-KNN
    P Sonar, U Bhosle, C Choudhury
    2017 international conference on signal processing and communication (ICSPC 2017

  • GLCM based improved mammogram classification using associative classifier
    J Deshmukh, U Bhosle
    Int. J. Image Graph. Signal Process 7, 66-74 2017

  • Optimization of association rule mining for mammogram classification
    P Sonar, U Bhosle
    International Journal of Image Processing 11 (3), 67-85 2017

  • SURF based video summarization and its optimization
    D Jadhav, U Bhosle
    2017 International Conference on Communication and Signal Processing (ICCSP 2017

  • Bit error probability analysis of MIMO multicarrier spread spectrum for different channels and modulations
    S Deshmukh, U Bhosle
    2017 International Conference on Wireless Communications, Signal Processing 2017

  • SURF features based classifiers for mammogram classification
    J Deshmukh, U Bhosle
    2017 International Conference on Wireless Communications, Signal Processing 2017

MOST CITED SCHOLAR PUBLICATIONS

  • Image fusion and image quality assessment of fused images
    M Deshmukh, U Bhosale
    International Journal of Image Processing (IJIP) 4 (5), 484 2010
    Citations: 198

  • A survey of image registration
    M Deshmukh, U Bhosle
    International Journal of Image Processing (IJIP) 5 (3), 245 2011
    Citations: 158

  • Atmospheric correction of remotely sensed images in spatial and transform domain
    P Tyagi, U Bhosle
    International Journal of Image Processing 5 (5), 564-579 2011
    Citations: 56

  • Image mining using association rule for medical image dataset
    J Deshmukh, U Bhosle
    Procedia Computer Science 85, 117-124 2016
    Citations: 40

  • A fast method for image mosaicing using geometric hashing
    U Bhosle, S Chaudhuri, S Dutta Roy
    IETE journal of research 48 (3-4), 317-324 2002
    Citations: 39

  • Mammography classification using modified hybrid SVM-KNN
    P Sonar, U Bhosle, C Choudhury
    2017 international conference on signal processing and communication (ICSPC 2017
    Citations: 35

  • Radiometric correction of multitemporal satellite imagery
    SG Biday, U Bhosle
    Journal of Computer Science 6 (9), 1027-1036 2010
    Citations: 29

  • Mammogram classification using AdaBoost with RBFSVM and Hybrid KNN–RBFSVM as base estimator by adaptively adjusting γ and C value
    U Bhosle, J Deshmukh
    International Journal of Information Technology 11 (4), 719-726 2019
    Citations: 18

  • Image retrieval using Contourlet transform
    S Borde, U Bhosle
    International Journal of Computer Applications 34 (5), 37-43 2011
    Citations: 17

  • Performance evaluation of spread spectrum system using different modulation schemes
    S Deshmukh, U Bhosle
    Procedia Computer Science 85, 176-182 2016
    Citations: 16

  • Multispectral panoramic mosaicing
    U Bhosle, SD Roy, S Chaudhuri
    Pattern recognition letters 26 (4), 471-482 2005
    Citations: 15

  • Relative radiometric correction of cloudy multitemporal satellite imagery
    S Biday, U Bhosle
    World Academy of Science, Engineering and Technology 27, 241-245 2009
    Citations: 12

  • A Study of Mammogram Classification using AdaBoost with Decision Tree, KNN, SVM and Hybrid SVM-KNN as Component Classifiers.
    J Deshmukh, U Bhosle
    J. Inf. Hiding Multim. Signal Process. 9 (3), 548-557 2018
    Citations: 10

  • SURF features based classifiers for mammogram classification
    J Deshmukh, U Bhosle
    2017 International Conference on Wireless Communications, Signal Processing 2017
    Citations: 9

  • Comparative study of relative radiometric normalization techniques for resourcesat1 LISS III sensor images
    SR Pudale, UV Bhosle
    International Conference on Computational Intelligence and Multimedia 2007
    Citations: 9

  • Relative radiometric correction of multitemporal satellite imagery using Fourier and wavelet transform
    S Gore Biday, U Bhosle
    Journal of the Indian Society of Remote Sensing 40, 201-213 2012
    Citations: 8

  • GLCM based improved mammogram classification using associative classifier
    J Deshmukh, U Bhosle
    Int. J. Image Graph. Signal Process 7, 66-74 2017
    Citations: 6

  • SURF based video summarization and its optimization
    D Jadhav, U Bhosle
    2017 International Conference on Communication and Signal Processing (ICCSP 2017
    Citations: 6

  • Radiometric correction of Multispectral Images using Radon transform
    P Tyagi, U Bhosle
    Journal of the Indian Society of Remote Sensing 42, 23-34 2014
    Citations: 6

  • The use of geometric hashing for automatic image mosaicing
    U Bhosle, S Chaudhuri, SD Roy
    Proc. National Conference on Communication (NCC02), 533-537 2002
    Citations: 6