Informatics Publishing Limited

J. Venkata Subramanian ¹, M. Abdul Karim Sadiq ²

Affiliations
1 Department of MCA, SRM University, Chennai, Tamil Nadu, IN
2 College of Applied Sciences, Sohar, Ministry of Higher Education, OM

Abstract

Mobile movement estimation is an utmost requirement for proper handoff signals to the nearby mobile towers. The direction in which a mobile would move next has to be predicted so that disruption in the signal during conversation does not occur. Artificial Neural Network (ANN) with Back propagation algorithm is used for predicting the mobile movement. The results are compared with data mining approach by Go¨khan (1995). The prediction performance of ANN algorithms is higher than that of the data mining approach.

Keywords

Artificial Neural Network, Back Propagation Algorithm, Data Mining, Mobile Movement, User Pattern Learning

Full Text

   

J. Venkata Subramanian ¹, A. Pandian ¹, Maneesh Kumar Gupta ²

Affiliations
1 Bharathidasan University, Tiruchi, IN
2 SRM University, IN

Abstract

The opportunistic routing has been shown to improve the network throughput, by allowing nodes that overhear the transmission and closer to the destination to participate in forwarding the packet, i.e., in forwarder list. In wireless networks, various factors, like fading, interference, and multi-path effects, can lead to temporary heavy packet losses in a pre-selected path The nodes in forwarder list are prioritized and the lower priority forwarder will discard the packet if the packet has been forwarded by a higher priority forwarder. One challenging problem is to select and prioritize forwarder list such that a certain network performance is optimized. The main focus is on selecting and prioritizing forwarder list to minimize energy consumptions by all nodes. The study of both cases where the transmission power of each node is fixed or dynamically adjustable. I present an energy efficient opportunistic routing strategy, denoted as EEOR. Here extensive simulations in TOSSIM show that the new implemented protocol EEOR performs better than the well-known ExOR protocol (when adapted in sensor networks) in terms of the energy consumption, the packet loss ratio, the average delivery delay

Full Text

     

Biswa Ranjan Panda , A. Pandian ¹, J. Venkata Subramanian ¹

Affiliations
1 Dept. of MCA, SRM University, Chennai, IN

Abstract

During their lifetime, multihop wireless mesh networks (WMNs) experience frequent link failures caused by channel interference, dynamic obstacles, and/or applications' bandwidth demands. These failures cause severe performance degradation in WMNs or require expensive manual network management for their real-time recovery. This paper presents an autonomous network reconfiguration system (ARS) that enables a multiradio WMN to autonomously recover from local link failures to preserve network performance. By using channel and radio diversities in WMNs, ARS generates necessary changes in local radio and channel assignments in order to recover from failures. Next, based on the thus-generated configuration changes, the system cooperatively reconfigures network settings among local mesh routers. ARS has been implemented and evaluated extensively on our IEEE 802.11-based WMN test-bed as well as through ns2-based simulation. Our evaluation results show that ARS outperforms existing failure-recovery schemes in improving channel-efficiency by more than 90% and in the ability of meeting the applications' bandwidth demands by an average of 200%.

Full Text

     

J. Venkata Subramanian ¹, A. Pandian ¹, M. Manikandan ¹

Affiliations
1 SRM University, Chennai, IN

Abstract

Monitoring system is repeatedly mentioned as one of the main application areas for mobile computing. it is the application of mobile computing technologies for improving communication among moitoring place, home, industrial, organization, in this place using the application .As mobile devices have become part of our like it can integrate more seamlessly to our everyday life. It enables the delivery of mobile video anytime, anywhere by means of mobile devices. it is paper proposed monitoring house by using web camera and we are retrieving content from the web camera to mobile. Here we are using android os mobile .JMF is used for getting the attributes of video and the attributes should be adjustable depends on network speed. A media server is used to fetch that information from web camera, for that we have proposed RTP/RTSP streaming protocol this protocol get the live video from camera to server and server to mobile. By this system we can monitor our house at any time.

Keywords

Mobile Computing, RTP, JMF, Android.

Full Text

     

J. Venkata Subramanian ¹, A. Pandian ¹, R. Manikandan ¹

Affiliations
1 SRM University, Chennai, IN

Abstract

There has been a wide variety of cloud storage services for the file access and sharing, but it has been cost-effective. That makes it as less utile. People are not willing to use it. But as in our project the cloud storage services is offered for the web services such as Gmail and Yahoo! Even for uncharged accounts, this makes people to use it in the highly basis. As e-mail has become the powerful communication in our modern world. We have to provide the basic needs of giving the more security in preventing their mails from being destroyed. So we provide a backup storage or cloud storage for every individual account to access client own mails with our project. We are using the POP3 mail service to retrieve the mails. It is the more secured path to be accessed. A personal storage system leveraging online email service infrastructures would also benefit service providers as it extends their access to valuable customer data in terms of both volumes and variety. The major objective of the project is we have to connect to the mail server with the desired login information. As we are allowing the access for two mail services such as Yahoo and Gmail. The mails which have been accessed in our account can be retrieved in our My Mailbox using the Cloud storage services. As we are forming the personal cloud storage for every e-mail account. It makes easier to retrieve the relevant mails. As the mails are retrieved from our services, it can also be restored to our individual account. This makes it efficient for our web services. The main concern in our project is that, whenever the users or clients have deleted or lost their mails in the main server, it can be viewed here. And we also restrict the spam messages to the inbox. We will only retrieve the relevant mails which is present in the E-mail services with the help of the POP3 protocol.

Keywords

Cloud Storage, POP3 Protocol, Web Services.

Full Text

     

J. Venkata Subramanian , A. Pandian , Manish Kumar ¹

Affiliations
1 SRM University, IN

Abstract

The key generation center could decrypt any messages addressed to specific users by generating their private keys. This is not suitable for data sharing scenarios where the data owner would like to make their private data only accessible to designated users key. so overcome this problem we propose escrow problem which means a written agreement delivered to a third party and Attribute-based encryption (ABE) is a promising Cryptographic approach fine-grained data access control which is provides a way of defining access policies based on different attributes of the requester, environment, or the data object. The KGC can decrypt every cipher text addressed to specific users by generating their attribute keys. This could be a potential threat to the data confidentiality or privacy in the data sharing systems.

Keywords

Improving Security, Efficiency in Attribute-Based Data Sharing, Attribute-Based Encryption (ABE).

Full Text

     

J. Venkata Subramanian ¹, A. Pandian ¹, N. Manikandan ¹

Affiliations
1 SRM University, Chennai, IN

Abstract

The Search Engine process has become the most reliable in the research for any domain. As people believe that the extraction of their search is highly reliable and they follow according to it. The most reliable search is the Google. As, in this project we are getting the search in the medical domain. It has to be taken an extra step in for the research of our project. The empirical domain of automatic learning is used in tasks such as medical decision support, medical imaging, protein-protein interaction, extraction of medical knowledge, and for overall patient management care. Machine Learning field has gained its momentum in almost any domain of research and just recently has become a reliable tool in the medical domain. It is envisioned as a tool by which computer-based systems can be integrated in the healthcare field in order to get a better, more efficient medical care. In this project, we provide the users all their needs about the Disease treatment relation such as Cure, Prevention, Side-effects, Symptoms, Medicine and the Doctors. When the user is in need of their health, they can get the immediate access to patient diagnoses, allergies, and lab test results that enable better and time-efficient medical decisions. Our evaluation results for these tasks show that the proposed methodology obtains reliable outcomes that could be integrated in an application to be used in the medical care domain. And we prove that the search has gained more impact and outperformed the existing project.

Full Text

     

A. Pandian ¹, J. Venkata Subramanian ¹, S. Balamanikandan ²

Affiliations
1 Department of MCA, SRM University, Chennai, IN
2 Thiruvalluvar University, Kallakurichi, IN

Abstract

Classification based on decision trees is one of the important problems in data mining and has applications in many fields. In recent years, database systems have become highly distributed, and distributed system paradigms such as federated and peer-to-peer databases are being adopted. In this paper, we consider the problem of inducing decision trees in a large distributed network of high dimensional databases. Our work is motivated by the existence of distributed databases in healthcare and in bioinformatics, and by the vision that these databases are soon to contain large amounts of genomic data, characterized by its high dimensionality. Current decision tree algorithms would require high communication bandwidth when executed on such data, which is not likely to exist in large-scale distributed systems. We present an algorithm that sharply reduces the communication overhead by sending just a fraction of the statistical data. A fraction which is nevertheless sufficient to derive the exact same decision tree learned by a sequential learner on all the data in the network. Value uncertainty arises in many applications during the data collection process. Example sources of uncertainty include measurement/quantization errors, data staleness, and multiple repeated measurements. With uncertainty, the value of a data item is often represented not by one single value, but by multiple values forming a probability distribution. Rather than abstracting uncertain data by statistical derivatives (such as mean and median), we discover that the accuracy of a decision tree classifier can be much improved if the "complete information" of a data item (taking into account the probability density function (pdf)) is utilized. We extend classical decision tree building algorithms to handle data tuples with uncertain values. Extensive experiments have been conducted that show that the resulting classifiers are more accurate than those using value averages. Since processing pdf's is computationally more costly than processing single values.

Keywords

Data Mining Distributed Algorithms, Decision Trees, Classification, High Dimension Data.

Full Text