Location Prediction for Improved Human Safety at Complex Environments

In underground operation,primary consideration is safety.In recent decades,for minimizing accident and for preventing major economic losses and casualties,wireless sensors are used by various large mineral countries through early warning.The Improved DV-Hop Localization Algorithm(IDVHLA)is used in existing works for doing this.However,accurate anchor node detection is impossible in existing works with the malicious nodes presence,where there won’t be any accurate sharing of anchor node’s location information.In case of emergency situation,faster communication is a highly complex one.A technique calledModified Distance Vector Hop based Multipath Routing Protocol(MDVHMRP)is introduced in this proposed research work for resolving this.In this work,to detect anchor node position,a Modified Distance Vector Hop technique is introduced.This research work considers time taken and session time for computing neighbour node’s presence in addition to hop count values.Malicious nodes presence can be avoided by considering session time in neighbour node presence detection.The alert message are send by people in emergency crisis to sever in initial condition.Then Dynamic Source Routing(DSR)routing protocol is used for doing immediate route path selection.In case of route path failure,for ensuring uninterrupted communication and faster communication,this work introduces amulti path routing.Themodified distance vector hop technique is used for predicting anchor node location information and predicted information will be transmitted.In NS2 simulation environment,overall evaluation of this research work is carried out.When compared with available techniques,localization accuracy is enhanced by proposed technique as proven in experimental results.

Performance Comparison of Artificial Neural Network Models for Daily Rainfall Prediction

With an aim to predict rainfall one-day in advance, this paper adopted different neural network models such as feed forward back propagation neural network （BPN）, cascade-forward back propagation neural network （CBPN）, distributed time delay neural network （DTDNN） and nonlinear autoregressive exogenous network （NARX）, and compared their forecasting capabilities. The study deals with two data sets, one containing daily rainfall, temperature and humidity data of Nilgiris and the other containing only daily rainfall data from 14 rain gauge stations located in and around Coonoor （a taluk of Nilgiris）. Based on the performance analysis, NARX network outperformed all the other networks. Though there is no major difference in the performances of BPN, CBPN and DTDNN, yet BPN performed considerably well confirming its prediction capabilities. Levenberg Marquardt proved to be the most effective weight updating technique when compared to different gradient descent approaches. Sensitivity analysis was instrumental in identifying the key predictors.