@mrcet.ac.in
Associate Professor ,Department of IT, Malla Reddy College of Engineering and Technology
Malla Reddy College of Engineering and Technology
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
A. Mummoorthy, N. S. Gowri Ganesh, R. Roopa Chandrika, and P. Swetha
Springer Nature Singapore
N.S.Gowri Ganesh, A. Mummoorthy, R.Roopa Chandrika, and Anantha Raman G.R.
IEEE
Apache spark can process the data in real time with the test mining and natural language processing. The business intelligence can be improved by collecting and processing the data from web in real time. Process mining collects the data from event logs in process discovery. Then diagnosis the difference between the observed and reality through an event logs. And extended the data of the event. Dealing with huge data process mining finds difficulty in processing. Spark handles the data processing speed and real time. It receives the input data and segregated into batches put up in processing. The incoming data append into the already existing data for processing. It identifies the problems and quick report generation of processing data.
A. Saraswathi, A. Mummoorthy, Anantha Raman G.R., and K.P. Porkodi
IEEE
Objective: Predict the total traffic count of streaming data in various routes to reduce traffic congestion and informing public about current traffic condition by displaying it in dashboard. Analysis: Real-time traffic monitoring can be made with the help of sensor connected devices, it generates huge volume and high speed data, Apache Kafka and Spark streaming engine is used for Processing these data. Findings: In existing system Traffic is predicted by deploying sensors in traffic signal lane and Apache hadoop used for processing data, it is batch processing system takes more time to process the data. In Proposed system total count of traffic predicted by using connected vehicles and Apache spark is used for processing live streaming data, by using spring boot total count of traffic is displayed in dashboard. Improvement: Real-time traffic prediction is done with live streaming data, Apache spark process data in-memory and dashboard updated for every five seconds
R.Roopa Chandrika, N.S.Gowri Ganesh, A. Mummoorthy, and K.M.Karthick Raghunath
IEEE
The number of vehicles has increased tremendously over the past decade. There are over 1 billion active vehicles all over the world and 60 to 70 million vehicles in India. Managing such traffic moments, providing sufficient parking lots is not an easy task. Vehicle counting and classification on busy streets will help the authorities to obtain traffic flow statistics and help them to understand and study the traffic patterns so that the can manage traffic in the most efficient way. The paper presents a way to detect, count and classify vehicles using image processing techniques. Although there has been a significant amount of research related to this, there is always a scope of improvement. The task of vehicle detection and counting is broken down into six steps: 1) Image Acquisition, 2) Image Analysis, 3) Object detection, 4) Counting, 5) Classification, 6) Display result. The algorithms which will be used to perform these tasks will includes vehicle detection and counting algorithm and road marking detection algorithm. This can also be used to monitor high ways, detect accidents, unrighteous stoppage of vehicles on roads, the traffic rules violators. Classification of vehicles will be done in one of the following categories: a) Bicycles and motorcycles, b) motor cars, c) minibus and pickup vans, d) buses trailers, trucks. This data will help to figure out the priority and maximum users of a road and design traffic patterns that will be beneficial to maximum.
A. Mummoorthy, R.Roopa Chandrika, N.S.Gowri Ganesh, and E. Pavithra
IEEE
In this project our main aim is the estimation of biomass using satellite image processing techniques. Firstly, we need to identify our study area and gather the ground data. After that calculate the entropy values and estimate the biomass. Then take the Satellite Images from either the LandSat TM or EnviSat and pre-process the image. Accurate Geometric Preprocessing and Atmospheric calibration are two important aspects in image pre-processing. After the preprocessing has been done then process the image and develop the different biomass models, like the allometric equations, regression models, geostatistical models, Non-parametric models, etc. Any one of these techniques can be used. The Multiple Regression Analysis is the most often used approach. For the study area in our project we shall proceed with the Vellore area and use the remote sensing data for the same. Geometric Correction and Speckle reduction can be used to improve the image we have taken. Then we have the Enhanced ETM data and filtered ASAR. Then we visually interpret the given image and identify the possible locations of biomass content. Then the volumetric equations are identified using various models as described above. After this we can calculate the Stand Volume using the equations we have at hand. The final step involves the calculation of Mean Biomass. Once this is calculated the main aim of our project is fulfilled.
A. Mummoorthy, R. Mohanasundaram, Shubham Saraff, and R. Arun
Springer Singapore
P. Balamurugan, Marimuthu Karuppiah, A. Mummoorthy, A.M. Viswabharathi, and R. Niranchana
Inderscience Publishers