F. Ezhil Mary Arasi ¹, S. Govindarajan ², A. Subbarayan ²

Affiliations
1 Department of Computer Science and Engineering, SRM University, Kattankulathur, Chennai - 603203, Tamil Nadu, IN
2 Department of Master of Computer Applications, SRM University, Kattankulathur, Chennai - 603203, Tamil Nadu, IN

Abstract

Objectives: In recent times Web Service providers are finding difficult to satisfy the requirements of the consumers due to several reasons. We have made an attempt to identify the specific parameters for evaluation of an efficient functioning of Composite Web Services. The study is based on a data set sampled from a large number of Web Service Providers. Methods/Statistical Analysis: Random sampling technique was adopted for the preparation of the data set. A multivariate statistical technique viz., Factor analysis is used for identifying the factors. Factor analysis method reduces large number of variables into few factors without sacrificing much of explained variability by the variables. Factor analysis begins with the construction of new set of variables based on the relationship in the correlation matrix. Based on principal component analysis we have identified the factor which determines the effective performance of Web Service providers. Findings: The study is based on a data set sampled from a large number of Web Service providers. The results based on the sample data set indicates the components of Web Service Providers Performance factors, Security factors and Trust factors viz., Successability, Best practices and Throughput respectively. These parameters have the higher loadings compared to other extracted QoS parameters. Application/Improvement: The research work was confined to the usage of factor analysis method based on principal component analysis approach. As a future work the other approaches in cluster method viz., centroid method and maximum likelihood method may be attempted to make a comparative study of the extraction of QoS parameters for its effectiveness.

Keywords

Factor Analysis, Principal Components, Quality of Service, Varimax Rotation, Web Service Selection.

Full Text

   

M. Shabnam ¹, S. Govindarajan ¹

Affiliations
1 Department of Computer Applications, SRM University, Kattankulathur, Kancheepuram – 603203, Tamil Nadu, IN

Abstract

Objectives: The primary objective of this paper is to evaluate the correctness of the algorithm Gesture Recognition that is one of the parts of our novel method ‘Braille coded gesture pattern interaction method”; and to study the performance of Eyedroid system using the statistical methodologies. Methods/Statistical Analysis: The algorithm for gesture recognition was developed and implemented in C program to check the correctness of each step of algorithm. The gesture input parameters Swipe-Minimum-Distance, Swipe-Threshold-Velocity are defined with range of values. Varying gesture input range of values within domain and out of domain results the expected solution space. Our gesture recognition algorithm is developed for 2D touch surface. The Real time experiments were conducted for 12 blind fold subjects to observe the different versions Eyedroid-A(E-A), Eyedroid-B(E-B) of gesture recognition algorithm perceptions, being implemented in smart phones. The mean WPM for 10 trials was recorded for 12 subjects with E-A and E-B. The two tailed paired t test is performed for the mean dependent sample data of wpm. Findings: The existing 3D gesture recognition algorithm Derivative Dynamic Time Warping (DDTW) analyzed by Katarzyna Barczewska, Aleksandra Drozd, 2013 was proven to be efficient method for air fly environment. Our gesture recognition algorithm is developed for 2D touch surface found to be effective by the results of algorithm test. Gesture Recognition algorithm finds the mal gestures and the results proved that there is a significant difference in respect of blind subjects for two different Eyedroid versions. The observed data reveals E-B (mean WPM=14.95) is easy to use than E-A (mean WPM=12) as the number of words entered per minute by E-B is higher than E-A. Our Eyedroid with WPM is 14.95 is obtained to be better interactive system than the existing “Adaptive interaction Technique” system developed by Georgios Y fantidis Grigori Evreinov, 2005 confirms WPM is 12. Applications/Improvements: The implication is our Braille coded gesture pattern that enables visually challenged ones to enter more number of words than by the existing system. Our interaction method is deployable at all kinds of touchable devices.

Keywords

Eyedroid-Braille Coded Gesture Pattern, Gesture Recognition Algorithm, t Test for Mobile Interaction.

Full Text

   

F. Ezhil Mary Arasi ¹, S. Govindarajan ¹, A. Subbarayan ¹

Affiliations
1 Department of Master of Computer Applications, SRM University, Kattankulathur, Chennai - 603203, Tamil Nadu, IN

Abstract

Background/Objectives: The primary objective of the study is to evaluate the performance of Composite Web Service based on the parameters relating to Quality of Service by using statistical methodologies. Methods/Statistical Analysis: By using Web Service Crawler Engine we have collected data on eleven parameters of interest from a more number of Web Services. Among the eleven parameters we have selected six parameters of importance using the sampling of thirty Web Services. We have constructed the weight matrix for the parameters. By using Web Services Relevancy Function ranking has been done for three different scenarios. Using Spearman's Rank Correlation Coefficient we have compared the scenarios. Findings: The graphical representation of the three scenarios shows varying pattern. The Spearman's Rank Correlation coefficient of the Web Services Relevancy Function varied widely among the sampled Web Services. F-Test revealed that there are no significant differences in respect of weights of Quality of Web Services for three different scenarios. We concluded that weight assigned for Quality of Service parameters in Scenario I is preferred than the scenarios II and III through the evaluations. Application/Improvements: The technique developed in this research paper can be applied for the comparison of Web Services during discovery to enhance the performance of the Composite Web Service.

Keywords

F-Test, Quality of Service, Rank Correlation, Selection, Web Services.

Full Text

   

M. Shabnam ¹, S. Govindarajan ²

Affiliations
1 Department of Computer Science and Engineering, SRM University, Kattankulathur, Chennai - 603203, Tamil Nadu, IN
2 Medical Research Centre, SRM University, Kattankulathur, Chennai - 603203, Tamil Nadu, IN

Abstract

Objective:The Objective of our research is to establish an Artificial Neural Network (ANN) model for Braille coded gesture pattern recognition process and to optimize the weight of the ANN model using optimization algorithms. The ANN utilized to predict the outputs such as right gesture, left gesture, top and bottom gestures of the known input values. Methods: To optimize the weight of the ANN structure optimization techniques such as Genetic Algorithm (GA), Differential Evolution (DE), and Lion Algorithm (LA) are utilized to optimize the weights such as number of input neurons (α) and number of hidden neurons(β). Findings: The optimum results show that the attained empirical error values and predicted values are equal to zero in designed network. The Convergence graph demonstrates the fitness rate with minimum error 0.33 between different iterations for three optimization algorithms. The Lion algorithm results the optimal fitness value of Braille Coded Gesture ANN model. Applications: The lion algorithm can be utilized for gesture recognition in touch enabled devices in the area of human computer interaction.

Keywords

Artificial Neural Network, Braille Code, Gestures, Lion Algorithm, Territorial Defense, Territorial Takeover, Touch Screen, Velocity.

Full Text

   

R. Thenmozhi ¹, S. Govindarajan ¹

Affiliations
1 Department of Computer Applications, SRM University, SRM Nagar, Potheri, Kattankulathur, Kancheepuram District, Near Potheri Railway Station, Chennai - 603203, Tamil Nadu, IN

Abstract

Objectives: To prevent accident and rear end collision in VANET, we propose to develop a method that will first create a cluster for preventing accident and rear collision in VANET Method/Statistical Analysis: Hence, to prevent accident and rear end collision in VANET, we propose to develop a scheme. First, with vehicles of same group moving in same road and direction, a cluster is formed. Among transmitted power and Contention Window (CW) size occasionally, every automobiles bounds an algorithm individually that’s adjusted. Findings: In urban areas, Traffic accidents occur because of sudden brakes, which demand a quick response from drivers. Therefore, a driver should be informed of the emergency events earlier. The proposed scheme applied each vehicle nodes in the network. Within the contention window metrics, the probability of collision between nearby vehicles is calculated and included which ensures the occurrence of appropriate modernize of transmission power and CW (Access Category) standards derived from the limited automobile density and the network circumstance correspondingly. The cluster with the header nodes maintain every unwanted or accident event and inform to every node to prevent accidents and rear end collision. This is significant to every sub cluster members of an SCH entity. An automobile can securely reject communication initiated from automobiles next to it. The recipient automobile can take; action derived from the primary and rejects the remaining replacement copies in case of redundancy.Applications/Improvements: The proposed scheme focused to enhance the delay, delivery ratio, energy and throughput compare to existing schemes.

Keywords

Cluster Formation, Cluster Head, Rear-End Collision, Vehicular Ad hoc Networks (VANETs).

Full Text