Biometric recognition by hybridization of evolutionary fuzzy clustering with functional neural networks

Srivastava, Vivek; Tripathi, Bipin Kumar; Pathak, Vinay Kumar

doi:10.1007/s12652-012-0161-8

Cited by 25 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Srivastava et al [11] developed a human recognition system based on the fusion of evolutionary fuzzy clustering with the Minkowski distance and then used functional modular NNs (FMNNs) for classification. Ye et al [12] proposed iris imaging in real-time pre-estimation based on a back propagation NN (BPNN) using multiple independent BPNNs to extract the overall and contour features and localise the iris image.…”

Section: Related and Background Workmentioning

confidence: 99%

Hybrid robust iris recognition approach using iris image pre‐processing, two‐dimensional gabor features and multi‐layer perceptron neural network/PSO

Ahmadi

Akbarizadeh

2017

IET biom.

View full text Add to dashboard Cite

Computational intelligence is employed to solve factual and complicated global problems, though neural networks (NNs) and evolutionary computing have also affected these issues. Biometric traits are applicable for detecting crime in security systems because they offer attractive features such as stability and uniqueness. Although various methods have been proposed for this objective, feature shortcomings such as computational complexity, long run times, and high memory consumption remain. The current study proposes a novel human iris recognition approach based on a multi-layer perceptron NN and particle swarm optimisation (PSO) algorithms to train the network in order to increase generalisation performance. A combination of these algorithms was used as a classifier. A pre-processing step was performed on the iris images to improve the results and two-dimensional gabor kernel feature extraction was applied. The data was normalised, trained, and tested using the proposed method. A PSO algorithm was applied to train the NN for data classification. The experimental results show that the proposed method performs better than many other well-known techniques. The benchmark Chinese Academy of Science and Institute of Automation (CASIA)-iris V3 and Center for Machine Learning and Intelligent Systems at the University of California, Irvine (UCI) machine learning repository datasets were used for testing and comparison.

show abstract

Section: Related and Background Workmentioning

confidence: 99%

Hybrid robust iris recognition approach using iris image pre‐processing, two‐dimensional gabor features and multi‐layer perceptron neural network/PSO

Ahmadi

Akbarizadeh

2017

IET biom.

View full text Add to dashboard Cite

show abstract

“…The fuzzy theory has been popularly applied to various aspects, including finance (Bernardo et al 2013), human emotion detected (Leu et al 2014), proportional integral derivative (PID) controller (Kim and Oh 2000), cryptography (Wang et al 2012;Wu et al 2013), and biometrics (Srivastava et al 2014). In a mobile communication environment, an efficient handover algorithm is often required to support seamless communication services.…”

Section: Related Workmentioning

confidence: 99%

Using fuzzy logic to reduce ping-pong handover effects in LTE networks

Tsai

Liu

2015

Soft Comput

View full text Add to dashboard Cite

Recently, mobile communications have been widely used in people's everyday lives. Their handover process facilitates people to transfer an ongoing call or a data session from one service area to another without conducting any communication interruption. However, in mobile communications, the ping-pong effect is a serious problem since it may cause unnecessary handover and lead to data loss and high computation cost. This is the case when a user equipment (UE) moves between two or among more evolved Node Bases (eNBs), due to signal strength reason, the UE in a very short time period alternatively switches among the eNBs. Consequently, the eNBs bounce the communication link the UE connected to them back and forth. Although several previous researches have been made to mitigate the ping-pong effect, what seems to be lacking is effectively eliminating unnecessary handover. Therefore, in this paper, we propose a fast and simple fuzzy-logic-based handover decision system, named Fuzzy based Low Ping-Pong Effect Handover System (FPEHS for short), to reduce the ping-pong effect in an LTE network. In the FPEHS, five parameters, including current signal-to-noise ratio (SNR), detected SNR, bandwidth of serving eNB, bandwidth of target eNB, and remaining energy of the underlying user's device, are inputted to the fuzzy logic unit to make handover decision. Our simulation results show that the FPEHS can effectively decrease the ping-pong effect about 92.94 % in average compared with that of the standard LTE's handover mechanism.Keywords Fuzzy · Handover · LTE · Ping-pong effect · Signal-to-noise ratio (SNR)

show abstract

“…Itti et al (1998) is the Fig. 2 The example of distortion problem for fisheye warping method most classical saliency-based visual attention model, which has been applied to many fields (Karczmarek et al 2014;Wei et al 2014;TalebiFard and Leun 2014;Srivastava et al 2014). This model exploits features of color, luminance and orientation etc.…”

Section: Warpingmentioning

confidence: 99%

Seam warping: a new approach for image retargeting for small displays

Zhang

et al. 2015

Soft Comput

View full text Add to dashboard Cite

Image retargeting is a technique to adapt an image to display on devices with different sizes and aspect ratios. When mobile devices with small displays are increasingly popular, it becomes important to retarget images that are intended for regular monitors to smaller mobile screens. Existing methods that retarget images to smaller devices, such as seam carving and warping, have some limitations: seam caving method may damage the integrity of the image, and warping method could fail when focus detection algorithm is not good. The target images obtained through the above algorithms often have obvious distortions. In this paper, we propose a new image retargeting method that combines seam caving and warping. This method preserves the advantage of warping in keeping focused areas of the image without discarding unfocused contents, and at the same time, uses seam finding scheme to address the problem of focus detection. The results of our experiment study on user preferences of retargeted images show that our approach is successful for image retargeting.

show abstract

Biometric recognition by hybridization of evolutionary fuzzy clustering with functional neural networks

Cited by 25 publications

References 33 publications

Hybrid robust iris recognition approach using iris image pre‐processing, two‐dimensional gabor features and multi‐layer perceptron neural network/PSO

Hybrid robust iris recognition approach using iris image pre‐processing, two‐dimensional gabor features and multi‐layer perceptron neural network/PSO

Using fuzzy logic to reduce ping-pong handover effects in LTE networks

Seam warping: a new approach for image retargeting for small displays

Contact Info

Product

Resources

About