Pravin Marotrao Ghate

@jspmrscoe.edu.in

Asst.Professor, Electronics & Telecommunication
JSPM's Rajarshi Shahu College of Engineering Pune



              

https://researchid.co/pravinghate

15 Year of Experience in teaching .
6 International Paper 5 National Paper published
Two Patent

RESEARCH INTERESTS

Product Development ,Software development Speech Processing

FUTURE PROJECTS

Product development

Product for agriculture


Applications Invited
Students

Software development

Better management


Applications Invited
Students
14

Scopus Publications

27

Scholar Citations

3

Scholar h-index

Scopus Publications

  • RETINOPATHY DISEASE DETECTION AND CLASSIFICATION USING COORDINATE ATTENTION MODULE BASED CONVOLUTIONAL NEURAL NETWORK WITH LEAKY RECTIFIED LINEAR UNIT
    Pravin Balaso Chopade, Prabhakar N. Kota, Bhagvat D. Jadhav, Pravin Marotrao Ghate, and Shriram Sadashiv Kulkarni

    IIUM Press
    The detection of Diabetic Retinopathy (DR) is an emergent research topic in recent decades, where DR is a primary cause of vision loss in humans. The existing techniques have limitations such as neuron death issues, vanishing gradient, and output offset. To overcome these issues, this paper proposes a Deep Learning (DL)-based technique for early and accurate DR detection. The Coordinate Attention Module (CAM) based Convolutional Neural Network (CNN) with Leaky Rectified Linear Unit (LReLU) is proposed for early and accurate detection of DR. The MESSIDOR dataset is preprocessed through the median filter to eliminate noise, and Contrast-Limited Adaptive Histogram Equalization (CLAHE) is utilized to increase the contrast level in an input image. The preprocessed images are given to Mayfly Optimization Algorithm-based Region Growing (MOARG) for image segmentation. Then, the features are extracted using ResNet50 and SqueezeNet, which extract deep learning features. The extracted features are given to CAM-based CNN with LReLU to detect DR, which overcomes the dead issues of neurons and minimizes the probability of inactive neurons. The proposed model achieves better results on the MESSIDOR datasets on the metrics of accuracy, precision, recall, specificity, f1-score, and Area Under Curve (AUC) values of about 99.72%, 99.46%, 99.25%, 99.61%, 99.37% and 99.14%, correspondingly, proving to be superior to the existing method, Capsule Network and Hybrid Adaptive DL based DR (HADL-DR). ABSTRAK: Pengesanan Retinopati Diabetik (DR) merupakan topik penyelidikan yang semakin mendapat perhatian dalam dekad-dekad kebelakangan ini, di mana DR merupakan punca utama kehilangan penglihatan pada manusia. Teknik sedia ada mempunyai beberapa kekangan seperti isu kematian neuron, vanishing gradient, dan output offset. Untuk mengatasi isu-isu ini, kertas ini mencadangkan teknik berasaskan Pembelajaran Mendalam (DL) untuk pengesanan awal dan tepat bagi DR. Modul Coordinate Attention Module (CAM) berasaskan Convolutional Neural Network (CNN) dengan Leaky Rectified Linear Unit (LReLU) dicadangkan untuk pengesanan awal dan tepat bagi DR. Dataset MESSIDOR diproses melalui penapis median yang digunakan untuk menghapuskan hingar, dan Contrast-Limited Adaptive Histogram Equalization (CLAHE) digunakan untuk meningkatkan tahap kontras pada imej input. Imej yang telah diproses diberikan kepada Algoritma Pengoptimuman Mayfly berasaskan Region Growing (MOARG) untuk segmentasi imej. Kemudian, ciri-ciri diekstrak menggunakan ResNet50 dan SqueezeNet yang mengekstrak ciri-ciri pembelajaran mendalam. Ciri-ciri yang diekstrak ini diberikan kepada CNN berasaskan CAM dengan LReLU untuk pengesanan DR, yang mengatasi isu kematian neuron dan meminimumkan kebarangkalian neuron tidak aktif. Model yang dicadangkan mencapai keputusan yang lebih baik pada dataset MESSIDOR berdasarkan metrik ketepatan, ketepatan, panggilan semula, kekhususan, skor f1, dan nilai Kawasan di Bawah Lengkung (AUC) iaitu sekitar 99.72%, 99.46%, 99.25%, 99.61%, 99.37% dan 99.14%, masing-masing, membuktikan keunggulannya berbanding kaedah sedia ada, Capsule Network dan Hybrid Adaptive DL berasaskan DR (HADL-DR).

  • GLOBAL-LOCAL SELF-ATTENTION BASED LONG SHORT-TERM MEMORY WITH OPTIMIZATION ALGORITHM FOR SPEAKER IDENTIFICATION
    Pravin Marotrao Ghate, Bhagvat D. Jadhav, Shriram Sadashiv Kulkarni, Pravin Balaso Chopade, and Prabhakar N. Kota

    IIUM Press
    Speaker identification (SI) involves recognizing a speaker from a group of unknown speakers, while speaker verification (SV) determines if a given voice sample belongs to a particular person. The main drawbacks of SI are session variability, noise in the background, and insufficient information. To mitigate the limitations mentioned above, this research proposes Global Local Self-Attention (GLSA) based Long Short-Term Memory (LSTM) with Exponential Neighborhood – Grey Wolf Optimization (EN-GWO) method for effective speaker identification using TIMIT and VoxCeleb 1 datasets. The GLSA is incorporated in LSTM, which focuses on the required data, and the hyperparameters are tuned using the EN-GWO, which enhances speaker identification performance. The GLSA-LSTM with EN-GWO method acquires an accuracy of 99.36% on the TIMIT dataset, and an accuracy of 93.45% on the VoxCeleb 1 datasets, while compared to SincNet and Generative Adversarial Network (SincGAN) and Hybrid Neural Network – Support Vector Machine (NN-SVM). ABSTRAK: Pengenalpastian pembicara (Speaker Identification, SI) melibatkan pengenalan pembicara daripada kumpulan pembicara yang tidak dikenali, manakala pengesahan pembicara (Speaker Verification, SV) menentukan sama ada sampel suara tertentu milik seseorang individu. Kekurangan utama dalam SI ialah variasi sesi, bunyi latar belakang, dan maklumat yang tidak mencukupi. Untuk mengatasi kekangan tersebut, kajian ini mencadangkan kaedah Global Local Self-Attention (GLSA) berasaskan Long Short-Term Memory (LSTM) dengan Pengoptimuman Grey Wolf Jiranan Eksponen (EN-GWO) bagi pengenalpastian pembicara yang berkesan menggunakan set data TIMIT dan VoxCeleb 1. GLSA digabungkan dalam LSTM yang memberi tumpuan pada data yang diperlukan, manakala parameter hiper ditala menggunakan EN-GWO untuk meningkatkan prestasi pengenalpastian pembicara. Kaedah GLSA-LSTM dengan EN-GWO mencapai ketepatan 99.36% pada dataset TIMIT dan ketepatan 93.45% pada dataset VoxCeleb 1, berbanding dengan SincNet dan Generative Adversarial Network (SincGAN) serta Hybrid Neural Network – Support Vector Machine (NN-SVM).

  • An optimized network for drought prediction using satellite images
    Bhagvat D Jadhav, Pravin Marotrao Ghate, Prabhakar Narasappa Kota, Shankar Dattatray Chavan, and Pravin Balaso Chopade

    Elsevier BV





  • IOT RESOURCE ALLOCATION AND OPTIMIZATION USING IMPROVED REPTILE SEARCH ALGORITHM
    Prabhakar Narasappa Kota, Pravin Balaso Chopade, Bhagvat D. Jadhav, Pravin Marotrao Ghate, and Shankar Dattatray Chavan

    Academy and Industry Research Collaboration Center (AIRCC)
    The Internet of Things (IoT) is a dispersed network system that connects the world through the Internet. The architecture of IoT consists of more gateways and resources which cannot be allocated in a manual process. The allocation of resources in IoT is a challenging process due to the higher consumption of energy and high latency rate. To overcome the challenges in existing works, this research introduced an Improved Reptile Search Algorithm (IRSA) to solve the optimization problem which occurs during the time of allocation resources among IoT networks. IRSA employs the methodology of levy flight and cross-over to update the candidate position and enhance the search speed in a single iteration. The proposed method consumes less energy and has low latency during data transmission from User equipment (UE) to the base station.IRSA has been compared with the existing Scalable Resource Allocation Framework (SRAF) and Improved Chaotic Firefly Algorithm (ICFA). The obtained experimental results show that the proposed IRSA attained better performance with an allocation rate of 96.40% which is comparatively higher than SRAF and ICFA with 92.40% and 91.67% respectively.

  • Lucy Richardson and Mean Modified Wiener Filter for Construction of Super-Resolution Image
    Pravin Balaso Chopade, Prabhakar N. Kota, Bhagvat D. Jadhav, Pravin Marotrao Ghate, and Shankar Dattatray Chavan

    Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
    The ultimate goal of the Super-Resolution (SR) technique is to generate the High-Resolution (HR) image by combining the corresponding images with Low-Resolution (LR), which is utilized for different applications such as surveillance, remote sensing, medical diagnosis, etc. The original HR image may be corrupted due to various causes such as warping, blurring, and noise addition. SR image reconstruction methods are frequently plagued by obtrusive restorative artifacts such as noise, stair casing effect, and blurring. Thus, striking a balance between smoothness and edge retention is never easy. By enhancing the visual information and autonomous machine perception, this work presented research to improve the effectiveness of SR image reconstruction The reference image is obtained from DIV2K and BSD 100 dataset, these reference LR image is converted as composed LR image using the proposed Lucy Richardson and Modified Mean Wiener (LR-MMWF) Filters. The possessed LR image is provided as input for the stage of bicubic interpolation. Afterward, the initial HR image is obtained as output from the interpolation stage which is given as input for the SR model consisting of fidelity term to decrease residual between the projected HR image and detected LR image. At last, a model based on Bilateral Total Variation (BTV) prior is utilized to improve the stability of the HR image by refining the quality of the image. The results obtained from the performance analysis show that the proposed LR-MMW filter attained better PSNR and Structural Similarity (SSIM) than the existing filters. The results obtained from the experiments show that the proposed LR-MMW filter achieved better performance and provides a higher PSNR value of 31.65dB whereas the Filter-Net and 1D,2D CNN filter achieved PSNR values of 28.95dB and 31.63dB respectively.

  • Design of a low-cost welding machine controller with a novel control algorithm for an enhanced HF TIG welding process
    Dnyaneshwar Vitthal Sahane, Pravin M Ghate, and Ajay N Paithane

    IOP Publishing
    Abstract Automation plays an important role in event welding domain. This paper describes the problems associated with arc tungsten inert gas (TIG) welding for automated welding in oil and gas industry for pipe joints. Welding joints inside the offshore pipelines is a complex process and rework or repetitive work is very costly. Weld imperfections are the foremost anxiety in the pipe joint welding. Return out the entire weld machine to find the defect at the time of welding. This is one of the popular industry come with the problem statement to develop the application specific solution for inner pipe welding quality welding. However, this paper gives the solution. Moreover, factors like Joint crack, moisture, corrugated weld object, excessive gas flow, Lack of fusion in the root, Dirty base or filler metal are major problems in the welding process. Due to these issues weld quality is impacted. There are several problem areas in the existing welding control system i.e., poor topology selection, less efficiency, high power loss, more size, high cost, more maintenance, less effective control algorithm for welding control etc Due to all these factors the welding quality is hampered in traditional welding system. Many researchers have worked on the power electronics hardware section improvement but very less work done on the software section. This paper discusses on the software algorithm development and how the weld quality improved. Software welding algorithm development is the novelty of this paper. This paper proposed and developed low-cost welding machine controller using STM32F103 microcontroller with protection scheme. A welding algorithm is proposed and experimented to enhance arc TIG welding quality and automation. Welding algorithm is tested & practically verified using phase-shifted full bridge (PSFB) power converter topology with pulse width modulation (PWM) control technology. The results reveal that the proposed algorithm significantly improves the quality of automated welding.

  • Syllable-Based Concatenative Speech Synthesis for Marathi Language
    Pravin M. Ghate and Suresh D. Shirbahadurkar

    Springer Singapore
    The objective of speech synthesis is to convert text into speech, using the syllable got best the results in term quality speech. Speech processing plays important role in human–machine interaction. Syllable segmentation is done using the different parameters like cutoff frequency, amplitude, the magnitude of speech input signal. The proposed paper suggests a method of syllable segmentation; it converts the syllable representation to modified syllable waveform clips that can be combined together to produce as sound [1]. Syllables are a better choice for speech synthesis in Marathi language. We do manually identify, segment, and label syllable units from speech data for experiment purpose [2]. The concatenative speech synthesis methods provide highly understandable speech utterance.

  • Naturalness improvement in text to speech synthesis using threshold amplitude of the syllable (Marathi language)
    Pravin M Ghate and S. D. Shirbhadurkar

    IEEE
    This paper presents approach to concatenation of syllable like units to produce speech output from the text input. In the development of a speech synthesis system, unit selection and concatenation is an important stage. The main goal of the talk is to increase cooperation between the speech coding community and the TTS community, and in particular to motivate the need for speech coding algorithms that meet the requirements of the next generation speech synthesis technology. Here, a threshold point of amplitude is used for concatenation of two words while synthesizing the whole sentence.

  • A simple analytical model of 4H-SiC MOSFET for high temperature circuit simulations
    Ganesh C. Patil, Santosh C. Wagaj, and Pravin M. Ghate

    IEEE
    Recently, significant work has been carried out to develop a technology based on 4H-SiC semiconductors aimed to utilize the unique physical and electrical properties of this material to achieve improved performance in high-power and high-temperature electronic circuits. This work is an effort to develop an analytical model for the 4H-SiC based n-channel enhancement mode MOSFET (NMOS). Here, a simple SPICE level-1 model of Si MOSFET has been modified to express the I-V characteristics of 4H-SiC MOSFET at the temperature ranging from 250 to 4000 °C. The model has been developed by using the verilog-AMS coding in which the thermal effects on intrinsic carrier density, band-gap, channel mobility and the threshold voltage have been incorporated. The performance of a differential amplifier based on this model has also been evaluated. It has been found that, in comparison to Si NMOS differential amplifier, the amplifier based on 4H-SiC MOSFET is more thermally stable. This clearly shows the suitability of the 4H-SiC MOSFET for harsh environment electronic circuits where Si MOSFET can not with stand.

  • Automatic speaker recognition system
    P. M. Ghate, Shraddha Chadha, Aparna Sundar, and Ankita Kambale

    Springer India
    The proposed work provides a description of an Automatic Speaker Recognition System (ASR). It particularly documents all the stages involved in the proposed ASR system starting from the preprocessing stage to the decision making stage. The main aim of this work is to achieve a system with high robustness and user friendly. Voice samples from three different users are used as acoustic material. Feature extraction is done by computing Mel Frequency Cepstral Coefficients (MFCC) which is used to create reference template. For the purpose of feature matching, Dynamic Time Warping (DTW) algorithm is used wherein DTW distance is computed between the test signal and the reference signal. Decision is made by comparing the distance with a predefined threshold value.

RECENT SCHOLAR PUBLICATIONS

  • Global-Local Self-Attention-Based Long Short-Term Memory with Optimization Algorithm for Speaker Identification
    PM Ghate, BD Jadhav, SS Kulkarni, PB Chopade, PN Kota
    IIUM Engineering Journal 26 (1), 278-292 2025

  • Retinopathy Disease Detection and Classification Using a Coordinate Attention Module-Based Convolutional Neural Network with Leaky Rectified Linear Unit
    PB Chopade, PN Kota, BD Jadhav, PM Ghate, SS Kulkarni
    IIUM Engineering Journal 26 (1), 129-147 2025

  • Energy Efficient Multiobjective Improved Wild Horse Optimization for Clustering and Routing in Wireless Sensor Networks.
    SS Kulkarni, PM Ghate, BD Jadhav, PB Chopade, PN Kota
    International Journal of Intelligent Engineering & Systems 17 (6) 2024

  • An optimized network for drought prediction using satellite images
    BD Jadhav, PM Ghate, PN Kota, SD Chavan, PB Chopade
    Remote Sensing Applications: Society and Environment 36, 101278 2024

  • An Improved Model for Plant Disease Analysis Using Attention Based Capsule Network.
    BD Jadhav, PM Ghate, PB Chopade, PN Kota, SS Kulkarni
    International Journal of Intelligent Engineering & Systems 17 (5) 2024

  • An efficient disaster management system based on deep learning in bio-inspired wireless sensor network
    SD Chavan, PB Chopade, BD Jadhav, PN Kota, PM Ghate
    Engineering and Applied Science Research 51 (2), 152-163 2024

  • Significance of Blockchain Technology in Mean Kinetic Temperature Monitoring for Cold Chain Management
    SW Swati D.Kale, Shailaja C.Patil , charushila V.Rane , Pravin Ghate
    GRADIVA REVIEW JOURNAL 10 (2), 159-164 2024

  • Novel Approach of ECG Signal Classification Using CNN model
    SCW B D Jadhav, P.M.Ghate
    The International journal of analytical and experimental modal analysis 16 2024

  • Optimized intelligent speech signal verification system for identifying authorized users
    PM Ghate, BD Jadhav, PN Kota, SD Chavan, PB Chopade
    Engineering and Applied Science Research 50 (6), 525-537 2023

  • Lucy Richardson and Mean Modified Wiener Filter for Construction of Super-Resolution Image
    PB Chopade, PN Kota, BD Jadhav, P Marotrao Ghate, ...
    International journal of electrical and computer engineering systems 14 (5 2023

  • IOT resource allocation and optimization using improved reptile search algorithm
    PN Kota, PB Chopade, BD Jadhav, PM Ghate, SD Chavan
    Int J Comput Netw Commun 15 (4), 39-53 2023

  • Design of a low-cost welding machine controller with a novel control algorithm for an enhanced HF TIG welding process
    DV Sahane, PM Ghate, AN Paithane
    Engineering Research Express 4 (2), 025025 2022

  • Model for Conversion of Biodegradable Waste into Organic Fertiliser
    PM Ghate
    TEST ENGINEERING AND MANAGEMENT 83 (Publication Issue), 26480 - 26486 2020

  • QRS detection Using Empirical Mode Decomposition Method for Human Computer Interface
    PMG A. N. Paithane, Sakshi A Paithane
    International Journal of Advanced Science and Technology 29 (7), 702 - 712. 2020

  • Land use Land Cover Mapping using Modified Ant Colony Optimization Technique
    PMG Bhagavat. D. Jadhav,Chandrama. G. Thoart ,Ajay. N. Paithane
    International Journal of Innovative Technology and Exploring Engineering 2020

  • Syllable-Based Concatenative Speech Synthesis for Marathi Language
    PM Ghate, SD Shirbahadurkar
    Information and Communication Technology for Competitive Strategies 2019

  • Concatenation of syllable by anchor frame to improve Naturalness in speech synthesis for Marathi language (India)
    PM Ghate
    International Journal of Pure and Applied Mathematics 118 (Special issues), 1-15 2018

  • Text to Speech System for Marathi Language using Syllable Unit (India) to Improve the Naturalness
    PM Ghate, SD Shirbhadurkar
    Journal of Information and Language Engineering 1 (1) 2018

  • INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY SPEECH SYNTHESIS USING SYLLABLE FOR MARATHI LANGUAGE
    PM Ghate, SD Shirbhadurkar
    2018

  • A Survey on method of TTS and various test for evaluating the quality of synthesised speech
    SDS Pravin M Ghate
    International Journal of Development Research 7 (1), 15239-15239 2017

MOST CITED SCHOLAR PUBLICATIONS

  • A simple analytical model of 4H-SiC MOSFET for high temperature circuit simulations
    GC Patil, SC Wagaj, PM Ghate
    2014 Annual IEEE India Conference (INDICON), 1-5 2014
    Citations: 8

  • IOT resource allocation and optimization using improved reptile search algorithm
    PN Kota, PB Chopade, BD Jadhav, PM Ghate, SD Chavan
    Int J Comput Netw Commun 15 (4), 39-53 2023
    Citations: 3

  • QRS detection Using Empirical Mode Decomposition Method for Human Computer Interface
    PMG A. N. Paithane, Sakshi A Paithane
    International Journal of Advanced Science and Technology 29 (7), 702 - 712. 2020
    Citations: 3

  • Automatic speaker recognition system
    PM Ghate, S Chadha, A Sundar, A Kambale
    Proceedings of International Conference on Advances in Computing, 1037-1044 2012
    Citations: 3

  • Lucy Richardson and Mean Modified Wiener Filter for Construction of Super-Resolution Image
    PB Chopade, PN Kota, BD Jadhav, P Marotrao Ghate, ...
    International journal of electrical and computer engineering systems 14 (5 2023
    Citations: 2

  • Design of a low-cost welding machine controller with a novel control algorithm for an enhanced HF TIG welding process
    DV Sahane, PM Ghate, AN Paithane
    Engineering Research Express 4 (2), 025025 2022
    Citations: 2

  • Syllable-Based Concatenative Speech Synthesis for Marathi Language
    PM Ghate, SD Shirbahadurkar
    Information and Communication Technology for Competitive Strategies 2019
    Citations: 2

  • A survey on methods of tts and various test for evaluating the quality of synthesized speech
    P Ghate, SD Shirbahadurkar
    Int J Dev Res 7, 15236-15239 2017
    Citations: 2

  • Retinopathy Disease Detection and Classification Using a Coordinate Attention Module-Based Convolutional Neural Network with Leaky Rectified Linear Unit
    PB Chopade, PN Kota, BD Jadhav, PM Ghate, SS Kulkarni
    IIUM Engineering Journal 26 (1), 129-147 2025
    Citations: 1

  • An Improved Model for Plant Disease Analysis Using Attention Based Capsule Network.
    BD Jadhav, PM Ghate, PB Chopade, PN Kota, SS Kulkarni
    International Journal of Intelligent Engineering & Systems 17 (5) 2024
    Citations: 1

RESEARCH OUTPUTS (PATENTS, SOFTWARE, PUBLICATIONS, PRODUCTS)

Patent

Industry, Institute, or Organisation Collaboration

SSGR Pvt Ltd

INDUSTRY EXPERIENCE

Two year