MADHURI RAO

@sicsr.ac.in

Assistant Professor at Symbiosis Institute of Computer Studies & Research
Symbiosis International Deemed University



                 

https://researchid.co/madhurirao

I am working as Assistant Professor at Symbiosis Institute of Computer Studies and Research, Symbiosis International University, Pune.. I have more than 10 years of teaching and research experience and 2 year of industrial experience. I have attained my Doctor of Philosophy from Biju Patnaik University of Technology, public university of Odisha. I have acquired my Master of Technology from Bharath University in the year 2008 and Bachelor of Technology in Computer Science & Engineering from Biju Patnaik University of Technology. I am the recipient of Best Research Scholar Award 2019 by Biju Patnaik University of Technology sponsored by TEQIP III and have also received Best Paper Award at ICICA 2016. My research interests are in Wireless Sensor Networks, Cloud Computing, Distributed Systems, Internet of Things and Machine Learning. I have published by findings in various journals of international repute and as book chapters and conference papers as well.

EDUCATION

Doctor of Philosophy in Computer Science & Engineering
Master of Technology in Computer Science & Engineering
Bachelor of Technology in Computer Science & Engineering

RESEARCH INTERESTS

Wireless Sensor Networks, Distributed Systems, Internet of Things, Cloud Computing, Machine Learning

FUTURE PROJECTS

CLEARANCE DATE PREDICTION USING MACHINE LEARNING TECHNIQUE


Applications Invited
16

Scopus Publications

Scopus Publications

  • Modelling Stock Prices Prediction with Long Short-Term Memory (LSTM): A Black Box Approach
    Anuja Bokhare, Madhuri Rao, M. Pavie Oliver, Rohit Rai, and Umang Adesara
    Springer Nature Singapore

  • Clearance date prediction using machine learning techniques
    Madhuri Rao, Ankit Senapati, Kulamala Vinod Kumar, and Anuja Bokhare
    IGI Global
    Machine learning is the cutting-edge technology in today's corporate world, making it the first choice for prediction or calculated suggestions relying on heavy amount of data. As companies are evolving towards technological advancement, they are trying to gather as much statistical knowledge as possible regarding their customers and trying to analyze and use that knowledge towards the firm's growth. Machine learning being the top-most of its genre provides the pathway to all of those technological achievements like predictions, statistical analysis, success rate of each customer companies, etc. Machine learning techniques such as linear regression (LR), XGBoost, random forest, and decision tree can be useful for the prediction problems. Here in this work, the authors use data pre-processing and feature selection before applying these machine learning models for predicting the clearance due date.

  • Co-Resident Attack and its impact on Virtual Environment
    Sudibyajyoti Jena, Likhet Kashori Sahu, Debahuti Mishra, Madhuri Rao, and Kulamala Vinod Kumar
    IOP Publishing
    Abstract Cloud computing (CC) is one of the emerging computing models that potentially transform the IT industry. The cloud computing is defined as a computing paradigm that enables suitable, universal, on-demand network access of various computing resources like data storage, OS (Operating System), computer applications and software as well. A Cloud model essentially is characterized with features like on-demand self-service, better network access, resource distribution, elasticity and measured services. Cloud computing is also known as Internet Computing and is indeed reshaping the way industries and organisations function. It facilitates the service taker or the client to use various IT resources like OS (Operating System), middleware and various applications without the need of downloading it. In this paper a brief view of this computing paradigm and the underlying cloud infrastructure is presented. We essentially present an analysis of various security challenges that are inherent in the Infrastructure as a Service(IaaS) cloud model and explain terms like virtualization, VM (virtual machine), SLA (Service level agreement), etc. Here, CloudSim simulator is explored to study the impact of variation of cache size of the Virtual Machine on the availability of data centres, that occurs due to co-resident attack. Further, a brief view of the co-resident attack is further presented and some of the feasible countermeasures are discussed further.

  • Machine learning based design of reinforced concrete shear walls subjected to earthquakes
    Praveena Rao, Hemaraju Pollayi, and Madhuri Rao
    IOP Publishing
    Abstract Civil engineering structural components are classified according to their projected structural performance in the present building code regulations and design standards. These building design codes are largely based upon previous experimental results of thousands of samples tested to failure and validated with analytical solutions. Machine Learning techniques (ML) is a subset of Artificial Intelligence (AI) that facilitates classification and prediction of structural performances for a broad spectrum of complex structures with greater accuracy. Machine learning models have the potential to make reliable predictions with the help of algorithms. Thereby, saving a tremendous amount of time and resources invested in experimental investigations of large structural components such as shear walls and columns. The ML algorithms can learn from the available data, deduce underlying inter-relationships, make inferences and detect patterns based on previous experience. In the present work, various ML algorithms were implemented to identify the influence of geometrical as well as mechanical characteristics. Database of 393 specimens of reinforced concrete shear walls with rectangular (R), flanged (F) and barbell (B) cross-sections are adopted for the analysis. Shear walls are fundamentally classified into four failure categories which include flexure or due to bending, shear, intermediate flexure-shear and sliding due to shear. The objective of this paper is to classify and predict the shear strength, flexural strength as per the Indian standard code provisions and failure modes of shear walls with the help of ML techniques. Algorithms such as KNearest Neighbors, Naive Bayes, Decision Tree, Random Forest, AdaBoost, LightGBM, XGBoost and Cat-Boost is implemented using Python. Highest accuracy of 85% is achieved on the test set by Random Forest, 83% by CatBoost and 81% by LightGBM boosting algorithms. It is observed that input variables such as aspect ratio (lw/tw), characteristic strength of concrete in compression (f ck ), characteristic yield strength of steel (f y ), percentage of steel (ρ), web vertical reinforcement, horizontal reinforcement, boundary element reinforcements play a vital role in governing the shear strength (V u ) and flexural strength (M u ) of shear walls.

  • Queuing Theory-Based Analysis of Berth Allocation and Management in Paradip Port for Container Ships
    Madhuri Rao, Narendra Kumar Kamila, Kulamala Vinod Kumar, Debahuti Mishra, and Sampa Sahoo
    Springer Nature Singapore

  • Modeling Internet of Things-Based Solution for Evading Congestion and Blockage in Waterways
    Madhuri Rao, Narendra Kumar Kamila, Sampa Sahoo, and Kulamala Vinod Kumar
    Springer Nature Singapore

  • Effect of Feature Selection on Software Fault Prediction
    Vinod Kumar Kulamala, Priyanka Das Sharma, Preetipunya Rout, Vanit a, Madhuri Rao, and Durga Prasad Mohapatra
    Springer Nature Singapore



  • Modified Grey Wolf Optimization(GWO) based Accident Deterrence in Internet of Things (IoT) enabled Mining Industry
    Deepak Majhi, Madhuri Rao, Sampa Sahoo, Shiba Prasad Dash, and Durga Prasad Mohapatra
    IEEE
    The occurrences of accidents in mining industries owing to the fragile health conditions of mine workers are reportedly increasing. Health conditions measured as heart rate or pulse, glycemic index, and blood pressure are often crucial parameters that lead to failure in proper reasoning when not within acceptable ranges. These parameters, such as heartbeat rate can be measured continuously using sensors. The data can be monitored remotely and, when found to be of concern, can send necessary alarms to the mine manager. The early alarm notification enables the mine manager with better preparedness for managing the reach of first aid to the accident spot and thereby reduce mine fatalities drastically. This paper presents a framework for deterring accidents in mines with the help of the Grey Wolf Optimization approach.

  • Bayesian network based energy efficient ship motion monitoring
    Madhuri Rao and Narendra Kumar Kamila
    University of Kerbala



  • Tracking intruder ship in wireless environment
    Madhuri Rao and Narendra Kumar Kamila
    Springer Science and Business Media LLC
    AbstractIt is a challenging task for all Harbors or Naval Administration to restrict and monitor the movement of defense or commercial ships. Most commonly used techniques of monitoring are radars and satellite images. These techniques are not reliable as radars can be turned off voluntarily and receptions of images are affected by adverse climatic conditions. This paper proposes a reliable ship intruder detection algorithm that classifies different types of objects approaching the model system in and out of phase with the ocean waves. The proposed technique also takes care of superimposition of temporal and spatial values of nodes that are presumably deployed in the sea surface up to a certain distance. Simulation results prove that the proposed algorithm detects and classifies objects efficiently even when 50% of the nodes reporting the tracking phenomenon are tampered.

  • Underwater wireless sensor network for tracking ships approaching harbor
    Madhuri Rao, Narendra Kumar Kamila, and Kulamala Vinod Kumar
    IEEE
    Monitoring ports, harbors and oceanic territories is gaining huge interest especially to combat military crisis, smuggling and terrorist activities. Underwater Wireless Sensor Network can be a viable solution for tracking objects like trespassing ships approaching a harbor and monitoring the activities on the ocean surfaces. In this paper we have proposed a new paradigm for underwater tracking mechanism.

  • Symbol based concatenation approach for Text to Speech System for Hindi using vowel classification technique
    Pamela Chaudhury, Madhuri Rao, and KVinod Kumar
    IEEE
    Indian Languages such as Hindi is phonetic in nature. The Text- To-Speech (TTS) System for Hindi, exploits the phonetic nature of Hindi .The algorithm developed by us involves analysis of a sentence in terms of words and then symbols involving combination of pure consonants and vowel technique. Wave files are being merged as per the requirement to generate the modified consonants influenced by matras, phalas and yuktaksharas generate the speech from a text. Vowels are most important classes of sound in most Indian languages. The duration of vowel is longer than consonants and is most significant. Vowels are categorized as starting middle & end according to the duration of occurrence in a word. Speech unit database consisting of vowels (starting ,middle and end)and consonants is developed.

RECENT SCHOLAR PUBLICATIONS

    INDUSTRY EXPERIENCE

    I have 2 years of experience as Application Engineer at Slash Support Private Limited, Chennai, India