Volume 6 | Issue 1 |

 Abstract

The Internet of Things (IOT) is an emerging research area promising many interesting solutions to various problems encountered in various domains. Smart homes applications is one such branch that evolve from IOT with the huge challenges of data storage and handling. Multiple activity recognition is the major challenge in smart homes application that incorporates multiclass learning. The efficiency of ensemble learner in handling multiclass problem and collective dissicion delivered prompt its uses in the smart homes application In this paper we deal with multiple activity recognition problem on various ensemble learner including bagging ,boosting and random forest. The standard van Kasteren dataset contains three housedata with eight activities of thirty days. We perform our experiment on the pre-processed collected data and applied six learners i.e. three from individual learner and three from ensemble learners. On performing the extensive experiment it was found that the group of ensemble learner outcast the simple learners

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

IOT, Ensemble learner, Bagging ,Boosting, Random forest

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Component Online learning, relative loss bounds, bandwidth, latency, multi-processing, multimode.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Cryptography is plays an important role to protect data and information in world wide web. In this paper we present a detailed study of open message format and secure message format with their strengths and weaknesses over each other based on their security service goal. we also focus on asymmetric cryptography to perform encryption and decryption operations using public key, private key pair in order to archive most important security services to the sender like authentication,confidentiality,digital signature and non-repudiation.We have also provided a fair comparison between most common asymmetric key cryptography algorithms: RSA and Diffie-hellman algorithm.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Cryptography, Asymmetric key algorithm, Digital Signature, Authentication, RSA,Diffie Hellman Algorithm

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Mobile ad-hoc networks (MANETs) have gained immense popularity in the past few years with the growth in mobile devices, thus making them prone to malicious attacks and posing a threat to security. Attackers hamper the functioning of the network and hence need to be encountered to make the network flawless. In this paper we shall study the characteristics and threats caused due to for major attacks viz. Denial of Service(DoS), Vampire, Probe, User-to-Root(U2R).

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Attack, Probe, DoS, Vampire, U2R, MANETs, detection.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper proposes the major issues of cluster-head gateway switch routing protocol. When the nodes are mobile in a cluster then the problem of selection of cluster-head arises, hence the key objective is to enhance the optimum cluster head selection when the cluster head is mobile along with the nodes. This paper provides the different Networking Scenario of protocols and their basic overview about the different techniques that are utilized for further multipath utilities.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

MANET, Routing, Cluster head and WSN

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Classification and analysis of data streams are the most promising fields of research and development in Data stream mining. Ensemble based classification approach is one the most challenging flavor of developing an efficient classifier due to large number available base classifiers and increase in the computational time required for training and classification. This paper emphasizes on various factors which affects the accuracy of an ensemble based classifier.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Data stream mining, Classification, Ensemble based classification

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

NLP, opinion mining, POS tagger, and corpus

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Now in Present Time we are seeing that in Every 30 seconds, someone dies in a traffic accident, and every year 2 million people are die in automobile accidents And up to 1 million are injured These accidents are being not only in India but in whole worlds .Many of these death are due to driver error(Driver errors are, in turn, caused by lack of knowledge, failure to follow traffic rules, driver distraction, or driver incapacity or fatigue). or mechanical failure and other preventable causes. This research paper are in the area of self- driving of a vehicle. In this research paper we explain about a self driving car (also called autonomous, driverless or robotic vehicles) to prevent automobile accident using machine learning technology . The main objective of this paper are three main aspects :- 1) Detection of an object .2) Identify type of an Object . 3) Object localization and prediction of movement.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

self driving , machine learning , Accidents ,Detection ,Identification ,Prediction

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Artificial neural network (ANN) is an information processing system whose function is inspired by the way biological nervous system such as human brain works. It is a collection of a large number of highly interconnected functional units (analogous to neurons present in human brain) working in synch with each other to solve specific problems. ANN can be trained to learn by examples and can perform a wide variety of tasks like pattern recognition, feature extraction and selection from large and complex data sets that are beyond the computational capability of mathematical and traditional procedures. Because of their learning capability and flexible architecture ANN has attracted researchers across the globe to develop specific applications for solving a wide variety of real world problems ranging from simple to complex. The objective of this paper is to study about neural network and review some of its applications that have been developed to solve specific real world problems. For this study secondary data has been collected from reputed journals for the period from 2008 to 2014, standard books and websites.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

artificial neural network, human brain, neurons, learn, pattern, feature, application

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Due to the tremendous growth in the World Wide Web, there has been large amount of web data generated. This web data can be mined to provide results which can greatly improve the performance and help business to grow. In this paper, we have discussed about the type of web mining which uses the web server logs as data sources known as web usage mining. We have surveyed on web usage mining in terms of different applications, Process and techniques which includes clustering, classification, association rule mining etc. We also studied about the various applications of web usage mining

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Association Rule Mining, Clustering, Pattern discovery, Web Mining, Web Transaction

  License

Creative Commons Attribution 4.0 and The Open Definition