Volume 6 Issue 4- April 2016


Page Title Full Text
118-120 Advanced Gender Recognition System Using Speech Signal
M.Prabha ,P.Viveka, G.Bharatha Sreeja

The speech signal processing has a wide range of applications in most of the technical fields. In speech processing, gender identification plays an important role. This paper expresses a comparative investigation of speech signals to produce automatic gender classification. Gender classification by speech signal is used to recognize the gender of the speaker by analysing various features of the voice sample. This quantitative investigation mainly aims to energy analysis of the speech signal. This analysis includes comparative investigation of different energy value of the speech signal. This comparative investigation was developed by using the software as MATLAB for determining the energy through FFT.
Key words: Gender recognition, Threshold energy, Recognition accuracy.

Full Text PDF
120-125 A Secure Multiserver Authentication Protocol for Smart Cards using Combined Logout Scheme and Biometrics
M.Sangeetha , M.O.Ramkumar

Online transaction can be done by using biometrics-based smart card, but yet there is no proper authentication. We first analyze He-Wang’s scheme and it is susceptible to discover session-specific temporary information attack and impersonation attack. In this proposed system, a three level of authentication scheme is used. Your finger print and your login id and OTP (One Time Password) are the three level of authentication. Rather than using cryptographic algorithm, a pixel matching algorithm is used. This biometrics is used in online money transaction in mobile recharge and amount transfer in bank side. The main advantage of this scheme is the logout scheme. Once we logout, one random number is send to your mail id. Unless a match of your first password and random number is found, we can find the new password for login.
Keywords: Security, Authentication, Smart card, Revocation and re-registration, pixel matching.

Full Text PDF
126-128 Review Paper on Test Case Selection
Saakshi Narula

Regression testing is of great significance and costly action that happens each time a program is transformed or modified to ensure that changes do not introduce new bugs into the previous accurate code. It is important to select a relevant subset of test cases from the initial test suite that would minimize the effort and time. Optimization of a test suite is the central in the development process of a software, keeping into account the resource and time constraints. The aim of test selection is to exclude or eliminate the redundant test data, which is a key for definition of the test strategies. This paper is a systematic review on Test Case Selection which is conducted in leading conferences and journals. The most commonly reported techniques include genetic algorithm, adaptive random testing and greedy algorithm.
Keywords: Regression Testing, Test Cases, Test suite, Test Case Prioritization, Test Case Minimisation, Test Case Selection.

Full Text PDF
129-132 A Modified K-Means Algorithm for Big Data Clustering
SK Ahammad Fahad , Md. Mahbub Alam

Amount of data is getting bigger in every moment and this data comes from everywhere; social media, sensors, search engines, GPS signals, transaction records, satellites, financial markets, ecommerce sites etc. This large volume of data may be semi-structured, unstructured or even structured. So it is important to derive meaningful information from this huge data set. Clustering is the process to categorize data such that data are grouped in the same cluster when they are similar according to specific metrics. In this paper, we are working on k-mean clustering technique to cluster big data. Several methods have been proposed for improving the performance of the k-means clustering algorithm. We propose a method for making the algorithm less time consuming, more effective and efficient for better clustering with reduced complexity. According to our observation, quality of the resulting clusters heavily depends on the selection of initial centroid and changes in data clusters in the subsequence iterations. As we know, after a certain number of iterations, a small part of the data points change their clusters. Therefore, our proposed method first finds the initial centroid and puts an interval between those data elements which will not change their cluster and those which may change their cluster in the subsequence iterations. So that it will reduce the workload significantly in case of very large data sets. We evaluate our method with different sets of data and compare with others methods as well.
Keywords—Big Data, K-means, Clustering, Clustering Algorithm, Modified K-means.

Full Text PDF
133-137 Power Efficient Gathering in Sensor Information Systems Protocol Using K-means Clustering Algorithm

Power-Efficient Gathering in Sensor Information Systems (PEGASIS) protocol is energy efficient protocols de-signed to prolong the lifetime of the network by reduction of energy consumption. In this paper a modification is proposed to the PEGASIS algorithm where sensor nodes are clustered in groups, clustering is done by k-means algorithm, and each group is treated as PEGASIS. In addition the proposed algo-rithm used rechargeable sensor nodes. Two parameters are searched to select chain leader: Euclidean distance of sensor node to the base station and residual energy of sensor node. Each cluster head data is transmitted directly to the base sta-tion. Simulation results showed the proposed algorithms im-proved in comparison with original PEGASIS.

Keywords—K-means, PEGASIS, Wireless Sensor Networks

(WSNs) , Cluster Head (CH).

Full Text PDF