Vehicle detection using MATLAB
Automatic detection and counting of vehicles in an unsupervised videos on highways is very challenging in computer vision with important practical applications like monitoring traffic activities.Counting the number of objects is integral part of image processing.Knowing the number of objects present in the image is very useful in wide range of applications.The main objective of our study is to develop methodology for automatic vehicle detection and its counting on highways.A system has been developed to detect and count objects efficiently.We present a system for detecting and tracking vehicles in surveillance video which uses segmentation with initial background substraction using morphological operator to determine salient regions in sequence of video frames.
Published by: Roshni M., Maleka Anjum, Noorain Fatima
Author: Roshni M.
Paper ID: V4I3-1617
Paper Status: published
Published: June 9, 2018
Identifying disease treatment by support vector machine with polynomial kernel
The Machine Learning field has gained its thrust in almost any domain of research and just recently has become a reliable tool in the medical domain. The experiential 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. ML is envisioned as a tool by which computer-based systems can be integrated into the healthcare field in order to get a better, well-organized medical care. It describes an ML-based methodology for building an application that is capable of identifying and disseminating healthcare information. It extracts sentences from published medical papers that mention diseases and treatments and identifies semantic relations that exist between diseases and treatments. Results for these tasks show that the proposed methodology obtains reliable outcomes that could be integrated into an application to be used in the medical care domain. The potential value of this method stands in the ML settings that are proposed and in the fact that it outperforms previous results on the same dataset.
Published by: Girish Vijay Agrawal, Kunal Sunil Ingale, Arpit Nitin Behede, Prashant Somnath Jadhav
Author: Girish Vijay Agrawal
Paper ID: V4I3-1820
Paper Status: published
Published: June 8, 2018
A study of the sociolinguistic factors affecting polytechnic students in learning English in Telangana state
English plays an important role in our everyday life. There is the enormous efficacy of English in the current world. English has ready the social and economic trade between citizens of diverse communities and traditions spastically possible. It is well acknowledged that English-speaking people can be traced in all the continents of the earth and is the cause for its importance in the enforced education of several nations across the world. Every year Polytechnic Colleges in India bring out thousands of diploma holders in different specializations. However, they have to struggle in a competitive world against graduates from other tertiary specializations. The State of Telangana has always led in achieving excellence in all the areas like schooling, Engineering & Technology, agricultural and industrial development at the national level. In today’s globalized situation, these students needed not only subject awareness of the specific courses but also English verbal communication skills and soft skills to excel in academic and professional life. The majority of students join in polytechnic courses in the States come from non-English verbal communication backgrounds and they require getting better their communicative competence. Here the role of English teachers becomes challenging. This study plan at ruling the complexity of the students in Sociolinguistic factors like social class, home condition, peer relations, aspiration levels and academic inclination among polytechnic students from rural, urban and metropolitan cities. The comparison study of the students will help to the Teachers/Educators/Government to make the necessary steps to improve the performance in learning and speaking English Confidently.
Published by: Ramala Vijaya
Author: Ramala Vijaya
Paper ID: V4I3-1803
Paper Status: published
Published: June 8, 2018
Decentralized digital voting application
The blockchain is a decentralized, distributed database. A decentralized application utilizing blockchain technology enables you to perform similar activities you would do today yet without a trusted outsider. It is a shared system, a peer-to-peer network. Blockchain solves primary issues like transparency, security, accessibility that are the fundamental issues in current law based races. Ethereum is a platform that can be utilized to assemble the decentralized application. The blockchain is a changeless record of exchanges (votes) that are distributed in the system. Everyone’s information that is the votes is stored in blockchain as transactions. The past votes can't be changed, while the present can't be hacked, on the grounds that each exchange is checked by each and every hub in the system. What's more, any outside or inside aggressor must have control of the hubs in the system to modify the record. Along these lines, every one of the exchanges stored on the blockchain is unchanged and thus this makes the application more secure in every aspect.
Published by: Sushmitha M, Aishwarya H D, Madhushree M, Pooja P, Dr. Saravana Balaji
Author: Sushmitha M
Paper ID: V4I3-1814
Paper Status: published
Published: June 8, 2018
Hybridization of BBO-PSO for the designing of FIR filter
This research article studies the performance of three metaheuristics processes: Particle Swarm Optimization (PSO), Biogeography Based Optimization (BBO) and Hybrid BBO_PSO approach for FIR filter design. The three approaches employ different strategies and computational effort to find a solution to a given objective function. BBO is more recently proposed population-based search method than PSO. Some researchers believed in the convergence superiority of BBO over the PSO and approved it due to its capacity to solve complex problems due to its ease of implementation. In this paper, for FIR filter design PSO, BBO and BBO_PSO schemes are compared. BBO_PSO generally outperform standard PSO and BBO schemes. The study also underlines the importance of introducing hybridization of two heuristics optimizations to make them more efficient. Furthermore, it establishes the potential complementary of the approaches while solving this optimization problem.
Published by: Mandeep Singh Gill, Puneet Jain, Pankaj Sharma
Author: Mandeep Singh Gill
Paper ID: V4I3-1778
Paper Status: published
Published: June 8, 2018
Automatic discovery of association orders between name and aliases from the web
Nowadays, searching for celebrities and experts information on the web is the most common activity done by most of the users. When a query is given for person search, it returns a set of web pages related to the different personalities of given name. For such type of search jobs of finding the web page in which user is interested is left on the user. There are many celebrities and experts of different fields which may have been referred by not only their real names but also by their alias names on the web. Aliases play important role in information retrieval to retrieve complete information about a real name from the web, as some of the web pages of the person may also be referred by his nicknames. The alias names for a personal name are extracted from the previously proposed alias extraction method. In information retrieval, the ADAONA search engine automatically expands the search query on a person name from his aliases for complete information retrieval thereby improving recall in the task of relation detection and achieving a significant mean reciprocal rank (MRR) of the search engine. For further more improvement on recall and MRR from the previously proposed methods, the proposed method will order the aliases based on their associations with the name using the definition of anchor texts-based co-occurrences between name and aliases in order to help the search engine tag the aliases according to the order of associations. The order between associations will automatically be discovered by creating an anchor texts-based co-occurrence graph between name and aliases.
Published by: Rohini Sukdev Patil, Vishal Devlekar, Pratibha Parakh, Rashi Agarwal
Author: Rohini Sukdev Patil
Paper ID: V4I3-1810
Paper Status: published
Published: June 8, 2018
