Informatics Publishing Limited

S. Najimul Hassan ¹, S. Deepika ¹

Affiliations
1 Department of Computer Science and Engineering, K.S. Rangasamy College of Technology, IN

Abstract

Fuzzy logic has been introduced to deal with uncertain problems. A fuzzy logic controller can be regarded as an expert system that is able to process quality variable and to infer crisp values out of uncertainty. Autonomous Mobile Robot Navigation in an unknown environment is explained in this paper by optimized fuzzy logic algorithm. A mobile robot, having to navigate purposefully from a start location to a target location, needs two basic requirements: sensing and reasoning. However, the pervasive presences of uncertainty in sensing makes the choice of a suitable tool of reasoning and decision making, that can be deal with incomplete information, vital to ensure a robust control system. 
This paper first explains what uncertainty in mobile robot navigation in unknown environments is, it proposes a fuzzy logic approach to secure a collision free path avoiding multiple static obstacles; where the robot is the only moving object. The most peculiar aspects of the proposed are in decreasing the number of fuzzy rules and in optimizing the choice of fuzzy sets parameters, rules, and memberships. The algorithm adopts fuzzy logic subsets and memberships to endow the robot with an ability to take decision despite of environmental uncertainties.

Full Text

     

S. Deepika ¹, S. Madhu Midha ¹, I. Banu Mathi ¹, G. Priya Dharsini ¹, E. Sasikala ¹

Affiliations
1 Department of IT, KSR College of Engineering, Tamilnadu, IN

Abstract

As the size of the Internet continues to grow the users of search providers continually demand search results that are accurate to their needs. Personalized Search is one of the options available to users in order to sculpt search results returned to them based on their personal data provided to the search provider. This raises concerns of privacy issues however as users are typically uncomfortable revealing personal information to an often faceless service provider on the Internet. This paper aims to deal with the privacy issues surrounding personalized search and discusses ways that privacy can be enriched by using encryption on user's information, so that users can become more comfortable with the release of their personal data in order to receive more accurate search results.

Keywords

Personalized Search, Privacy Issues, Encryption.

Full Text

     

S. Deepika ¹

Affiliations
1 Computer Science and Engineering, M. Kumarasamy College of Engineering, Karur, Tamilnadu, IN

Abstract

Privacy protection of mobile ad hoc networks is more demanding than that of wired networks due to the open nature and mobility of wireless media. In wired networks, one has to gain access to wired cables so as to eavesdrop communications. Privacy-preserving routing is crucial for some ad hoc networks that require stronger privacy protection. In hostile environments, the enemy can launch traffic analysis against interceptable routing information embedded in routing messages and data packets. Allowing adversaries to trace network routes and infer the motion pattern of nodes at the end of those routes may pose a serious threat to covert operations. A number of schemes have been proposed to protect privacy in ad hoc networks. However, none of these schemes offer complete unlink ability or unobservability property since data packets and control packets are still linkable and distinguishable in these schemes. In this paper, we define stronger privacy requirements regarding privacypreserving routing in mobile ad hoc networks. Anonymous key establishment process and route discovery process authenticates the routing paths taken by individual messages. Achieving anonymity is a different problem than achieving data confidentiality. While data can be protected by cryptographic means, the recipient node address and maybe the sender node address of a packet cannot be simply encrypted because they are needed by the network to route the packet.

Keywords

Mobile Ad Hoc Networks, Anonymity, Routing Protocol, Geographical Routing.

Full Text

     

M. Alfena , K. Bhavatarini Sarika , R. Chithara , S. Deepika , J.A. Dhinesh Joseph

Abstract

A significant portion of our population has speech and hearing impairment which reduce their ability to communicate with a normal person. These impairments may be acquired at birth or through accident or disease or through aging .This paper  presents  the  development of a mobile phone based assistive aid for the speech and hearing impaired to help them in their daily life when they cannot afford to wear hearing aids .The visual aid takes form  an easy -to-use app on a mobile phone or tablet in which the elderly can capture the image of  their hand gesture ,the image will be processed and a corresponding audio is played  to the normal person. Then the normal person can record the speech using the mobile application which will automatically perform speech-to-text conversion on the mobile phone such that the impaired person can read the text visually. The conversion is done at the backend server via internet .This application is intended to enable the impaired person to lead a fulfilling and independent lifestyle.

Keywords

Hand Gesture, Speech-to-Text

Full Text

     

V. Mani ¹, S. Deepika ¹, R. S. Harishkumar ¹, M. Ranisnekha ¹, P. S. Mukesh ¹

Affiliations
1 Department of CSE, M. Kumarasamy College of Engineering, Karur, Tamil Nadu, IN

Abstract

Sentiment analysis is a study of people’s sentiments, opinions, attitudes, emotions in a written language or text. Rapid Growth in the field of sentiment analysis and explore to find the sentiment on various social media platforms using techniques of machine learning with analyzing sentiment, and also helps in the analysis of polarity or subjectivity. The most widely used social media site is Twitter, where people share their thoughts in the form of tweets and hence it becomes the major data sources of sentimental analysis. Recently the more used social media platform such as Twitter. Their people express their thoughts and opinion as a tweet representation. It is the major data resources of analyzing the sentiments. Sentiments are classified to different group like positive, negative or neutral. Such analysis process helps to differentiate the sentiments also classifying them into different groups comes under prediction of sentiment. Very first we pre-process the dataset, feature extraction in which meaningful insights are extracted from the dataset, then extracted features are applied for classification model using machine learning Random Forest algorithm, Regression algorithm, etc. But with the advancement of the python language and to reduce the code complexity we have analyzed the polarity using the python packages, API and Algorithm which are available. This model proved to be highly effective and accurate on the analysis of feelings. At last the trained classification model are tested in order to check the performance it is measured by accuracy.

Keywords

Classification, Random forest, Regression, Sentimental analysis.

Full Text