Pravin Chandra

An Adaptive Slope Sigmoidal Function Cascading Neural Networks Algorithm

Cascade 2 algorithm is a variant of Cascade-Correlation algorithm that is a well-known and widely used constructive neural networks algorithm. We propose an adaptive slope sigmoidal function cascading neural networks algorithm (ASCNNA) in this paper. The proposed algorithm emphasizes on architectural adaptation and functional adaptation during training. This algorithm is a constructive approach of building cascading architecture and uses gradient descent method in sequential mode as the weight update rule of individual hidden node. To achieve functional adaptation, the slope of the sigmoidal function is adapted during learning. The algorithm determines not only the optimum number of hidden layers’ node, as also the optimum value of the slope parameter of sigmoidal function for nonlinear nodes. One simple variant derived from ASCNNA is where the slope parameter of sigmoidal function is fixed. Both the variants are compared to each other on five function approximation tasks. Simulation results reveal that adaptive slope sigmoidal function presents several advantages over traditional fixed shape sigmoidal function, resulting in increased flexibility, smoother learning, and better convergence and generalization performance.

Fingerprint Matching Based on Orientation Feature

This paper presents a fast and reliable algorithm for fingerprint verification. Our proposed fingerprint verification algorithm is based on image-based fingerprint matching. The improved orientation feature vector of two fingerprints has been compared to compute the similarities at a given threshold. Fingerprint image has been aligned by rotating through an angle before feature vector is computed and matched. Row and Column variance feature vector of orientation image will be employed. The algorithm has been tested on the FVC2002 Databases. The performance of algorithm is measured in terms of GAR and FAR. At a threshold level of 1.1 % and at 5.7% FAR the GAR observed is 97.83%. The improved Feature vector will lower imposter acceptance rate at reasonable GAR and hence yields better GAR at lower FAR. The proposed algorithm is computationally very efficient and can be implemented on Real-Time Systems.

An Adaptive Slope Basic Dynamic Node Creation Algorithm for Single Hidden Layer Neural Networks

This paper presents an adaptive slope basic dynamic node creation algorithm for single hidden layer neural networks (ASBDNCA). The proposed algorithm is a constructive approach of building a single hidden layer neural network. The ASBDNCA puts emphasis on architectural adaptation and functional adaptation during learning. It uses gradient descent optimization method in sequential mode as the weights update rule of individual hidden node. To achieve functional adaptation, the slope of the sigmoidal activation function (SAF) is adapted during learning. The algorithm determines not only optimal number of hidden nodes, as also optimum value of the slope parameter for the non-linear nodes. One simple variant derived from ASBDNCA in which the slope parameter of SAF is fixed. Both the variants are compared to each other on five function approximation tasks. Simulation results reveal that adaptive slope SAF present several advantages over traditional fixed shape sigmoidal activation function, resulting in increased flexibility, smoother learning, better convergence and better generalization performance.

Local directional pattern (LDP) based fingerprint matching using SLFNN

Recently a number of biometric indicators are in use for human identification, but the fingerprint based individual identification is still the dominating biometric indicator. In this paper, we present a fingerprint matching system by exploiting local directional pattern (LDP) based features, which are originally proposed for face recognition and facial expression detection. Fingerprint image texture is encoded by computing the response value of edges in different directions from the extracted region of interest (ROI) images. Single hidden layer feed forward neural network (SLFNN) is trained using three training algorithms namely gradient decent with momentum (GDM), resilient propagation (RP), and scaled conjugate gradient (SCG) to detect the match between test and trainee images. The experimental results show that the RP algorithm converges faster and perform well in terms of matching accuracy as compared to the other two algorithms.

Fingerprint Singular Point Detection Using Orientation Field Reliability

Singular point detection is the most important step in Automatic Fingerprint Identification System (AFIS) and is used in fingerprint alignment, fingerprint matching, and particularly in classification. The computation of orientation field of a fingerprint can be verified by computing orientation field reliability. The most unreliable portion in orientation field can be the possible location of singular points. In this paper we have proposed a novel algorithm for detecting singular points using reliability of the fingerprint orientation field. Experimental results show that the proposed algorithm accurately detects singular points (core and delta) with the detection rate of 92.6 %.

A Robust Fingerprint Matching System Using Orientation Features

The latest research on the image-based fingerprint matching approaches indicates that they are less complex than the minutiae-based approaches when it comes to dealing with low quality images. Most of the approaches in the literature are not robust to fingerprint rotation and translation. In this paper, we develop a robust fingerprint matching system by extracting the circular region of interest (ROI) of a radius of 50 pixels centered at the core point. Maximizing their orientation correlation aligns two fingerprints that are to be matched. The modified Euclidean distance computed between the extracted orientation features of the sample and query images is used for matching. Extensive experiments were conducted over four benchmark fingerprint datasets of FVC2002 and two other proprietary databases of RFVC 2002 and the AITDB. The experimental results show the superiority of our proposed method over the well-known image-based approaches in the literature.

Fingerprint Matching Based on Texture Feature

This paper presents a texture feature based algorithm for fingerprint matching. Our proposed fingerprint-matching algorithm employs texture features like Correlation, Inverse Difference Moment, and Entropy measure of fingerprint images. The proposed textural features of two fingerprints have been compared to compute the similarities at a given threshold. The algorithm has been tested on the FVC2002 DB2_B database. The proposed algorithm is evaluated using GAR and FAR. GAR of 97.5 % is observed with 8.53% of FAR at a threshold value of 0.9. The proposed textural Feature based matching will enhance GAR at the cost of slightly higher value of FAR and hence gives the best GAR at reasonable value of FAR.

Statistical Descriptors for Fingerprint Matching

paper presents a novel algorithm for fingerprint matching using statistical descriptors. This fingerprint-matching algorithm overcomes the problems faced during matching of low quality fingerprint images. The steps of the algorithm include extraction of core point using Poincare index method, extraction of Region of Interest (ROI) around core point, and similarity evaluation of statistical descriptors using k-NN classifier. Statistical descriptors are computed from 16 Gray Level Co-occurrence Matrices (GLCM) from Extracted ROI. The proposed algorithm is evaluated on the FVC2002 DB2 database. The experimental results show the effectiveness of proposed algorithm. Computational efficiency is improved by considering the ROI of size 101 uf0b4 101 around the core point.

Sentiment Predictions Using Deep Belief Networks Model for Odd-Even Policy in Delhi

This paper analyzes the odd-even policy in Delhi using tweets posted on Twitter from December 2015 to August 2016. Twitter is a social network where users post their feelings, opinions and sentiments for any event. This paper transforms the unstructured tweets into structured information using open source libraries. Further objective is to build a model using Deep Belief Networks classification DBN to classify unseen tweets on the same context. This paper collects tweets on this event under six hashtags. This study explores three freely available resources / Application Programming Interfaces APIs for labeling of tweets for academic research. This paper proposes three sentiment prediction models using the sentiment predictions provided by three APIs. DBN classifier is used to build six models. The performances of these six models are evaluated through standard evaluation metrics. The experimental results reveal that the TextBlob API and proposed Preference Model outperformed than the other four sentiment prediction models.

Fingerprint Matching Using Rotational Invariant Image Based Descriptor and Machine Learning Techniques

The reliability of fingerprint matching system is highly depends on the perfect alignment algorithm and a suitable matching techniques, which assign a label to the input fingerprint image. In this paper, we propose a rotation invariant fingerprint descriptor and a improved generalization performance classifier. The proposed new descriptor is represented by a histogram of local directional pattern (LDP) computed from extracted region of interest (ROI) of fingerprint images. For fingerprint matching, we propose a single hidden layer neural network (SLFN), which combines a powerful extreme learning machine (ELM) and a well generalized resilient propagation (RPROP) algorithm. The proposed fingerprint matching system comprises the following steps: fingerprint pre-processing/enhancement, ROI extraction, invariant LDP feature extraction, and matching using proposed hybrid classifier. The experimental result shows that the matching accuracy of the proposed system is improved as compare to ELM for lower values of hidden nodes, and other distance based matching approaches proposed in the literature.