SRR Engineering College

Chennai, India

SRR Engineering College

Chennai, India

Time filter

Source Type

Ramya R.,SRR Engineering College
International Conference on "Emerging Trends in Robotics and Communication Technologies", INTERACT-2010 | Year: 2010

The social insects' behavior, especially the real ants' behavior inspired the computer scientists to solve a number of applications successfully. Based on this idea, this project study has made an attempt to investigate the effects on keep-away soccer, for evolving the various multiagent strategies necessary for its efficient functioning as a successful testbed. This is done through genetic programming by adopting some of the real ants' behavior. This work can be considered as a contribution to naturally inspired evolutionary techniques for solving creative problems. © 2010 IEEE.


Vimala S.,Anna University | Sasikala T.,SRR Engineering College
Journal of Computational and Theoretical Nanoscience | Year: 2017

In mobile grid environment, the existing fault tolerance techniques are not feasible and proficient. The present techniques lack to achieve the maximum profit associated with successful execution of the tasks and is deemed to be costly. Hence, we propose a fault tolerance mechanism for scheduling in mobile grid environment. In this technique, we consider failures that occurs during the execution of computing-focused and communication-focused jobs. In order to detect the failure, a novel structured data packet is sent to the destination. The destination acknowledges with a specific type of data packet corresponding to the received packet. The sender analyses the acknowledgement data packet identifies the place and nature of error. Finally, a fault recovery action is performed using the FTMS technique. By simulation results, we show that the proposed technique is reliable and efficient. © 2017 American Scientific Publishers.


Yasotha B.,Anna University | Sasikala T.,SRR Engineering College
International Journal of Mobile Network Design and Innovation | Year: 2016

In wireless sensor network (WSN), the existing literature works predicts the energy consumption using operational state transition model. In this method, each state should be known to the sink, in order to predict accurately. Also, in some cases, if the residual energy estimation is not based on the operational states of a sensor node, it may not reflect the exact amount of energy consumed by each node. In order to overcome these issues, in this paper, we propose to design an intrusion detection system to detect and mitigate the attacks using energy monitoring technique. In this technique, the malicious attacks are detected by monitoring the node's energy. The monitoring nodes predicts the energy using hidden Markov model (HMM) and compares it with the actual energy detected through an energy query technique. The detected attacks are classified based on the energy threshold levels. The attacks are then mitigated by establishing the attack-free route between source and destination, respectively. By simulation results, we show that the proposed technique increases the efficiency, reduces overhead and energy consumption. © 2016 Inderscience Enterprises Ltd.


Veeramuthu A.,Sathyabama University | Meenakshi S.,SRR Engineering College | Kameshwaran A.,Sathyabam University
International Conference on Communication and Signal Processing, ICCSP 2014 - Proceedings | Year: 2014

In pattern recognition and in image processing, feature extraction is a special type of dimensionality reduction. In data mining, Attribute subset selection or feature subset selection is normally helps for data reduction by removing unrelated and redundant dimensions. Given a set of image data features are extracted. From the extracted features, feature subset selection finds the subset of features that are most relevant to data mining task. The efficiency and effectiveness of the feature selection algorithm is evaluated. While the efficiency concerns the time required to find a subset of features, the effectiveness is related to the proportion of the selected features. Based on these criteria, we have used Spatial Gray Level Difference Method (SGLDM) feature extraction algorithm and Correlation based Feature Selection (CFS). Projected Classification algorithm (PROCLASS) is going to be proposed for brain image data. Experiments are going to do compare these plug-in algorithms with FAST, FCBF feature selection algorithms. © 2014 IEEE.


Murali Krishnan K.,Sathyabama University | Satish R.,SRR Engineering College
International Journal of Applied Engineering Research | Year: 2016

The Past decade have seen a string of mergers and acquisitions both within India and outside by Indian as well as foreign companies. It is observed that the day after a merger or acquisition announcement sees flurried activity in the stock market with the shares of a firm either rising or dropping with the announcement. This paper examines if the stock market reaction depends on the announcement of the merger, the past history of the firm and the overall market at the time of announcement. It is believed that mergers have a certain moment that drives investors to either purchase or sell stock based on what benefit they perceive the merger to bring. Also, mergers and merger waves can occur when managers prefer that their firms remain independent rather than be acquired. We assume that managers can reduce their chance of being acquired by acquiring another firm and hence increasing the size of their own firm. We show that if managers value private benefits of control sufficiently, they may engage in unprofitable defensive acquisitions. The paper also analyzes the motivation behind a merger and attempts to study if the motivations provide the necessary momentum to match investor sentiment. © Research India Publications.


Andrews J.,Sathyabama University | Sasikala T.,SRR Engineering College
Journal of Computer Science | Year: 2013

Tuning compiler optimization for a given application of particular computer architecture is not an easy task, because modern computer architecture reaches higher levels of compiler optimization. These modern compilers usually provide a larger number of optimization techniques. By applying all these techniques to a given application degrade the program performance as well as more time consuming. The performance of the program measured by time and space depends on the machine architecture, problem domain and the settings of the compiler. The brute-force method of trying all possible combinations would be infeasible, as it's complexity O(2n) even for "n" on-off optimizations. Even though many existing techniques are available to search the space of compiler options to find optimal settings, most of those approaches can be expensive and time consuming. In this study, machine learning algorithm has been modified and used to reduce the complexity of selecting suitable compiler options for programs running on a specific hardware platform. This machine learning algorithm is compared with advanced combined elimination strategy to determine tuning time and normalized tuning time. The experiment is conducted on core i7 processor. These algorithms are tested with different mibench benchmark applications. It has been observed that performance achieved by a machine learning algorithm is better than advanced combined elimination strategy algorithm. © 2013 Science Publications.


Ankayarkanni B.,Sathyabama University | Leni A.E.S.,SRR Engineering College
Proceedings of IEEE International Conference on Circuit, Power and Computing Technologies, ICCPCT 2016 | Year: 2016

RGIRS (Remote Geo-system Image Retrieval System) is a system of retrieving similar image using image features like color feature, texture feature and shape feature. Content based image retrieval system extracts features relevant to query image using feature extraction method. Many RGIRS systems are proposed to retrieve accurate similar image but the problem is no method provides accurate results. In this paper a new Statistical Rule Model is proposed to retrieve the image from the database using threshold based Euclidean distance calculation. The input query image features are extracted and sent to the SVM Model. The SVM will compare input image features with trained features and test the features with distributed density function. Once the image class is identified, the features are rearranged and calculate the distance using Euclidean distance calculation. A threshold value is fixed for retrieval. If the calculated distance is less than the threshold value the image will be retrieved or if the distance exceeds threshold value then the image will not be retrieved. © 2016 IEEE.


Ankayarkanni B.,Sathyabama University | Leni A.E.S.,SRR Engineering College
Proceedings of IEEE International Conference on Circuit, Power and Computing Technologies, ICCPCT 2016 | Year: 2016

RGIRS (Remote Geo-system Image Retrieval System) is a system of retrieving similar image using image features like color feature, texture feature and shape feature. Content based image retrieval system extracts features relevant to query image using feature extraction method. Many RGIRS systems are proposed to retrieve accurate similar image but the problem is no method provides accurate results. In this paper a new Statistical Rule Model is proposed to retrieve the image from the database using threshold based Euclidean distance calculation. The input query image features are extracted and sent to the SVM Model. The SVM will compare input image features with trained features and test the features with distributed density function. Once the image class is identified, the features are rearranged and calculate the distance using Euclidean distance calculation. A threshold value is fixed for retrieval. If the calculated distance is less than the threshold value the image will be retrieved or if the distance exceeds threshold value then the image will not be retrieved. © 2016 IEEE.


Suresh Kumar K.,Saveetha Engineering College | Sasikala T.,SRR Engineering College
International Review on Computers and Software | Year: 2014

The major motto of my research is to develop a technique for web security using mutual authentication and clicking and cropping based image CAPTCHA technology. In our technique, we use two sections as registration and login. To create an account to use the application we use the registration section and to access the application we use the login section. We set five mandatory fields to login the application. The mandatory fields we give in login section should similar to the mandatory fields we gave while registration. The mandatory fields are checked with respect to the user id. The mandatory fields we set are user id, password, selecting image, number of clicks on image and cropping image. If the fields are same in the login section and registration section for a particular user id, the system will allow the user to access the application. Here, we incorporate three different features than the usual login section in the applications. The different features are selecting an image from a set of images and doing number clicks on that selected image and cropping a portion in that image. Our technique enhances the web security because of these added features. © 2014 Praise Worthy Prize S.r.l. - All rights reserved.


Dhanalakshmi B.,SRR Engineering College | Chandra Sekar A.,St. Joseph's College
International Review on Computers and Software | Year: 2013

In recent years, the spectacular development of web technologies, lead to an enormous quantity of user generated information in online systems. This large amount of information on web platforms make them viable for use as data sources, in applications based on opinion mining and sentiment analysis. In this paper we propose a technique for extracting the opinions from the online user reviews. Initially the data extracted from the web document which is unstructured. This phase is used for formatting the data before sentiment analysis and mining. In the second phase Feature extraction and opinion extraction is done. The features like term frequency, Part of Speech (POS) are extracted from the words in the documents. After feature extraction, we extract useful information to rate them as positive, neutral, or negative. The positive and negative features are identified by extracting the associated modifiers and opinions. Finally the supervised learning algorithm decision tree classifier is implemented with the help of features extracted. In the final step ranking and classification will be done. © 2013 Praise Worthy Prize S.r.l. - All rights reserved.

Loading SRR Engineering College collaborators
Loading SRR Engineering College collaborators