Kongu Engineering College

About: Kongu Engineering College is a based out in . It is known for research contribution in the topics: Computer science & Cluster analysis. The organization has 2001 authors who have published 1978 publications receiving 16923 citations.

Improved K-Means Based Q Learning Algorithm for Optimal Clustering and Node Balancing in WSN

Abstract: A wireless sensor network is a potential technique which is most suitable for continuous monitoring applications where the human intervention is not possible. It employs large number of sensor nodes, which will perform various operations like data gathering, transmission and forwarding. An optimal Q-learning based clustering and load balancing technique using improved K-Means algorithm is proposed. It contains two phases namely clustering phase and node balancing phase. The proposed algorithm uses Q-learning technique for deploying sensor nodes in appropriate clusters and cluster head CH election. In the clustering phase, the node will be placed in appropriate clusters based on the computation of the mean values. Once the sensors are placed in an appropriate cluster, then the cluster will be divided into ‘k’ partitions. The node which is having maximum residual energy in each partition will be elected as the partition head PH. In node balancing phase, the number of sensors in each partition will be evenly distributed by considering the area of the cluster and the number of sensors inside the cluster. Among the PHs, the node which is having residual energy to the maximum and also having the minimal distance to the sink is elected as the CH. The residual energy of the CH is monitored periodically. If it falls below the threshold level, then another partition head PH which is having residual energy to the maximum level and possessing minimum distance to the sink node will be elected as CH. The proposed Q-Learning based clustering technique maximize the reward by considering the throughput, end-to-end delay, packet delivery ratio and energy consumption. Finally, the performance of the Q-learning based clustering algorithm is evaluated and compared existing k-means based clustering algorithms. Our results indicate that the proposed method reduces end to end delay by 8.23%, throughput is increased by 2.34%, network lifetime is increased by 3.34%, packet delivery ratio is improved by 1.56%.

Refractive index sensor using dual core photonic crystal fiber – glucose detection applications

Abstract: The article reports the numerical analysis of refractive index sensor using dual core photonic crystal fiber (PCF) which is aided for the detection of glucose concentration contains in the blood samples of humans. The sensing mechanism is facilitated by tuning the coupling between the silica mode and analyte mode. The change in concentration of glucose is reflected as shifts in the transmission spectrum. The sensitivity is reported as 8333 n m / [ R I U ] for the samples variation as 10 g / l to 20 g / l with the function of resonance wavelength.

Cancelable Iris template for secure authentication based on random projection and double random phase encoding

Abstract: Biometric recognition approaches have overwhelmed major issues in traditional authentication systems. Privacy invasion and security are the needed features in the effective development of biometric recognition systems. Recently some biometric techniques have been suffered to hacking trails also. Hence there is a despairing need to propose a novel cancelable iris recognition scheme. The prime objective of this research is to create a transformed cancelable biometric template through an encryption function and a one-way transformation function. The random projection matrix is employed here to generate the first feature vector. Then an encrypted cancelable iris code is generated using Double Random Phase Encryption (DRPE) in the Fractional Fourier Transform (FFT) domain. The proposed framework utilizes both the left and right iris image of a person and generates a single cancelable iris template. This feature guarantees the privacy-preserving cancelable iris code generation for secure authentication. The experiment is carried on two state-of-art datasets CASIA Iris V4 and IITD iris to affirm the efficacy of the proposed methodology. The result analysis witnessed a promising accuracy of 99.59%, a recognition rate of 99.88% with a lower Equal Error Rate (ERR) of 0.46%. It has also been proved that the proposed approach is computationally efficient as it recognizes the iris code with less recognition time of 7 ms with a maximum true positive and true negative rate of 100%.