M. Prabu

Bio: M. Prabu is an academic researcher from VIT University. The author has contributed to research in topics: Soil classification & Normalized Difference Vegetation Index. The author has an hindex of 2, co-authored 6 publications receiving 11 citations. Previous affiliations of M. Prabu include Christ University.

Design and Evaluation of Wi-Fi Offloading Mechanism in Heterogeneous Networks

Abstract: In recent years, WiFi offloading provides a potential solution for improving ad hoc network performance along with cellular network. This paper reviews the different offloading techniques that are implemented in various applications. In disaster management applications, the cellular network is not optimal for existing case studies because the lack of infrastructure. MANET Wi-Fi offloading (MWO) is one of the potential solutions for offloading cellular traffic. This word combines the cellular network with mobile ad hoc network by implementing the technique of Wi-Fi offloading. Based on the applications requirements the offloading techniques implemented into mobile-to-mobile (M-M), mobile-to-cellular (M-C), mobile-to-AP (M-AP). It serves more reliability, congestion eliminated, increasing data rate, and high network performance. The authors also identified the issue while implementing the offloading techniques in network. Finally, this paper achieved the better performance results compared to existing approaches implemented in disaster management.

Application of Satellite Remote Sensing to find Soil Fertilization by using Soil Colour: study area Vellore District, Tamil Nadu, India.

Abstract: Nowadays the usage of Remote Sensing and GIS techniques are too vast and many Earth observations had been done by Remote Sensing and GIS techniques. The innovation of this work is to use the LANDSAT image data and GIS Techniques to assess land information and soil classification in the most coming up area of Vellore district and propose the possible fertilization for this study area. Landsat image is classified by minimum distance classification algorithm and according to the reflectance characteristics of the surface material. From the classified data we can find out the best fertilization for the best soil using colour of the soil. It is proved that, within limitations the classification algorithms and threshold parameters have an important influence on the classification result

Prediction of Land Cover Changes in Vellore District of Tamil Nadu by Using Satellite Image Processing

Abstract: Prediction of land cover changes is important to evaluate the land use or land cover changes to monitor the land use changing aspects for the Vellore district. Due to land use and land cover change, most of the rural areas around the Vellore district become unable to cope with environmental risk and agriculture. Population is one of the main issues in increasing the land cover changes in Vellore district. From the satellite, data can easily find out the changes in Vellore district. Result is compared with real time to show the extreme changes in the study area. Vegetation cover decreased, and settlement and built up areas increased due to increasing population. The Objective is to find out the land cover changes and predict how the Vellore district in future. And also, this study suggests some remedial measures to protect agriculture of Vellore district.

Fuzzy-Based Satellite Image classification to find Greenery and Used Land

Abstract: This research work describes the region based approach for satellite image classification to extract Land use details for the agriculture in Vellore region. The objective is to find the Greenery and used lands of study area by classify the satellite imagery using Fuzzy-based supervised classification method and spectral information of an LANDSAT satellite image. The LANDSTSAT Image is applied with improved image processing technique to get the image of classification. The satellite image is segmented into regions using decorrelation in fuzzy fication process. The fuzzyfication process also incorporates edge information to avoid intermixing of sub-pixels of remotely sensed images. This fuzzy based classification of satellite image is particularly to find the greenery and the land use of Vellore region. This work gives an overview about this Program and discusses several research issues. First, the remote sensing data sources and other ancillary data used in this work are presented. The approaches for image preprocessing, i.e. clustering, segmentation, classification, correlations are then introduced with an emphasis on the algorithm development for image registration. Second, land use change detection technique is the most critical and complex aspect of the Program. Third, the data of land use changes derived from remote sensing will be operationally used.

Distributed Computing Model of Multispectral Time Series Data Analysis for Chlorophyll Concentration Determination Using Ocean Color Monitor-2 Data

Abstract: In general, the ocean color monitor sensor (OCM) is used to identify and monitor the phytoplankton bloom and fishing zones. In the ocean, there is a food chain among plants and fish, and by calculating the normalized difference vegetation index (NDVI), we can identify chlorophyll concentration of the particular ocean area. NDVI is an indication of the presence of chlorophyll concentration. In this study, importance is given to the NDVI of ocean area, because our Earth is mostly occupied by the ocean in the sense of water. OCM sensor data are used to identify the chlorophyll, which in turn indicates the presence of phytoplankton. This is the primary production in the basic food chain, and also for the fishes. Remote sensing methodology is used to find and understand the spatial allocation of oceanwater constituents. Usually, the phytoplankton pigment emits a greenish color in the seawater, which is the visible region in the ocean. It enables plant objects to be identified from among the other suspended matter on the oceanwater. NDVI is mainly used in land applications to identify vegetation and forestation, and it is used to identify the chlorophyll pigment concentration of the ocean surface. Therefore, NDVI can be used to map chlorophyll-determined zones through which possible fishing zones can be generated. This study also shows that the NDVI generation technique is used to discover the resources of seawater for mapping the fishing zones. However, the limitation on large-scale computation for the entire earth surface leaves challenges toward raising the technological solution. Hence, an attempt is made to integrate a distributed computational model to cover the larger spatial data. Therefore, a grid-based satellite image processing system is designed to discover the chlorophyll pigment concentration on the ocean through NDVI generation. With multiple computing nodes of the configured grid, the spatial coverage on the oceanic surface is widened and computational speed is also improved to yield a promising outcome.

Convergence Of Artificial Intelligence And Internet Of Things In Predictive Maintenance Systems – A Review

Abstract: Operations and Maintenance costs have always posed a heavy burden in wind turbines and the main aspects in spending are on unplanned unscheduled breakdowns, repairs and down time costs. Technology enhancements with connectivity between wind farms and operations control center would reduce risk and improve efficiency during maintenance by continuously analysing the data acquired. Digital solutions of industrial internet of things and machine learning have made inroads and are the real game changers with the potential to supervise, predict and prevent catastrophic failures. Generating the insights from the data to understand the wear pattern and to formulate replacement strategies for reducing frequent maintenance costs and to increase the production. This paper shall discuss and review about the prognostics and diagnostics of the wind turbines, machine learning algorithms, identifying their inter-dependency within the subsystems and the available digital solutions for effective handling of data in predictive maintenance schedules.

An effective content boosted collaborative filtering for movie recommendation systems using density based clustering with artificial flora optimization algorithm

Abstract: Recommender systems (RS) are information filtering approaches that intend to foresee the rating for customers and products, mainly from big data for recommending their likes. Movie RS offers a process of assisting customers in the classification of customers with identical preferences. It makes the RS an essential part of websites and e-commerce applications. Many of the classical RS lack accuracy in the case where data utilized in the recommendation task is sparse. This paper aims to develop a movie RS by the use of density based clustering (DBC) with artificial flora (AF) called DBC-AF technique. Besides, to get rid of the sparsity problem, the content-boosted collaborative filtering technique is employed to the proposed DBC-AF based movie RS. The presented model considers the content information of the movies while computing the item similarities. The proposed DBC-AF technique improved the movie prediction accuracy and developed an integrated model combining the customer rating from Movie Lens dataset for the prediction process. The effective performance of the DBC-AF model has been evaluated utilizing the Movie lens dataset. The obtained simulation outcome indicated the effective performance of the presented DBC-AF model.

Prediction of Land Cover Changes in Vellore District of Tamil Nadu by Using Satellite Image Processing

Abstract: Prediction of land cover changes is important to evaluate the land use or land cover changes to monitor the land use changing aspects for the Vellore district. Due to land use and land cover change, most of the rural areas around the Vellore district become unable to cope with environmental risk and agriculture. Population is one of the main issues in increasing the land cover changes in Vellore district. From the satellite, data can easily find out the changes in Vellore district. Result is compared with real time to show the extreme changes in the study area. Vegetation cover decreased, and settlement and built up areas increased due to increasing population. The Objective is to find out the land cover changes and predict how the Vellore district in future. And also, this study suggests some remedial measures to protect agriculture of Vellore district.

An Efficient Signcryption Scheme Using Near-Ring Hybrid Approach for an IoT-Based System

Abstract: Signcryption is a cryptographic primitive which combines both the functions of digital signature and public key encryption logically in a single step, with a computational cost significantly less than the traditional signature-then-encryption approach. Signcryption is another approach to accomplish secrecy and validation simultaneously across Internet of Things (IoT). Numerous signcryption schemes have been created and executed , but it uses different security attributes and computational cost. In this paper, introducing a new signcryption scheme whose security relies on the intractability of combination of the Twisted Root Extraction Problem (TREP) and Conjugacy Search Problem (CSP) which can utilised for IoT based system for secure transferring of data. It is applied over an IoT to upgrade the security of information and its confidentiality. Experiment shows that modified signcryption algorithm outperforms than existing approaches.