In the wireless sensor network, various sensor nodes are present that are used for the communication, sensing and computing. An external mobile sink is present which move around the grid that is used for the communication with the nodes directly which are present in the network. As we know that for formation of network we need to find the route between all the nodes coming in the network, for this purpose routing is done. Routing is defined as moving of information from source to destination. For efficient network the routing protocol that is used should consume less energy, and less distance. In the MVGDRA routing algorithm is proposed that use the mobile sink approach. The selection of cluster head is done on the basis of the weight values. By doing this cluster head will be selected on the basis of the energy means which node has highest energy appointed as cluster head that increases the stability of the network. And the event driven based strategy is used for the data transfer, the energy will be only released when it is required. The energy will not be released after each round. By this the energy consumption of the system decrease and the life time the network is increased. So this method is considered to be more efficient and better than the traditional methods of routing as the network performance is enhanced and its life time is increased. Simulation results show the comparison between the VGDRA and the MVGDRA.

Wireless sensor networks are being used for various applications for collection of heterogeneous data. Hotspot problem is major issue of concern that affects the connectivity of entire network along with decreasing lifetime of network. The focus in this paper is lies on optimizing the path followed by the mobile sink for collection of data. The proposed work aims at reducing the hotspot problem and increasing the lifetime. A trained neural network is used to select the best route to be followed by mobile sink. In the proposed work, the stop points are identified which allow the communication between the nodes and the movable sink. The experimental results of the work carried out show that tour length of the sink is greatly reduced and the network lifetime (number of rounds) is increased. Increased lifetime also handles the problem of hotspots.

Artificial neural network based model is estimated for modified shaped circular patch antenna. The Levenberg Marquardt (LM) algorithm is used to train the network, different antenna parameters in the X and Ku band are taken as input and delivers antenna dimensions as output. The dimensions obtained from estimated neural network model closely agrees the simulated results over the X and Ku band for FR4 epoxy substrate with 1.5 mm thickness. The simulation of microstrip patch antenna is carried out using Ansoft HFSS simulation software and the analysis of neural network model results are carried out using MATLAB. Thus, the estimated model can be used to obtain the antenna dimensions for circular patch antenna.

This paper presents parametric fault diagnosis in mixed-signal analog circuit using artificial neural networks. Single parametric faults are considered in this study. A benchmark R2R digital to analog converter circuit has been used as an example circuit for experimental validations. The input test pattern required for testing are reduced to optimum value using sensitivity analysis of the circuit under test. The effect of component tolerances has also been taken care of by performing the Monte-Carlo analysis. In this study parametric fault models are defined for the R2R network of the digital to analog converter. The input test patterns are applied to the circuit under test and the output responses are measured for each fault model covering all the Monte-Carlo runs. The classification of the parametric faults is done using artificial neural networks. The fault diagnosis system is developed in LabVIEW environment in the form of a virtual instrument. The artificial neural network is designed using MATLAB and finally embedded in the virtual instrument. The fault diagnosis is validated with simulated data and with the actual data acquired from the circuit hardware.