Time filter

Source Type

Rohini V.,Don Bosco Institute of Technology | Thomas M.,Don Bosco Institute of Technology | Latha C.A.,Global Academy of Technology
2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings | Year: 2016

Sentiment analysis (SA) is one of the important fieldsof Machine learning Language which involves analysis using natural language processing.The main goal of sentiment analysis is to detect and analyze attitude, opinions or sentiments in the text. Sentiment analysis has reachedits popularity by extracting Knowledge from huge amount data present online. The Process of analysis includes selecting features and opinionwhich is a challenging task in languages other than English. There are very few research works done for determining sentiments in regional languages. ThisPaperaims on domain based sentiment analysis in Regional language specific to moviesusing machine learning algorithm for classification and provide a comparison between analysis using direct Kannada dataset and machine translated English language. © 2016 IEEE.


Setty S.,Don Bosco Institute of Technology | Srinath N.K.,Rashtreeya Vidyalaya College of Engineering | Hanumantharaju M.C.,Dayananda Sagar College of Engineering
International Journal of Imaging and Robotics | Year: 2014

This paper presents a new approach for contrast enhancement of spinal cord medical images based on Multirate scheme incorporated into the multiscale retinex algorithm. The proposed work here uses HSV color space, since HSV color space separates color details from intensity. The enhancement of medical image is achieved by downsampling the original image into five versions, namely, tiny, small, medium, fine, and normal scale. This is due to the fact that the each version of the image when independently enhanced and reconstructed results in an enormous improvement in the visual quality. Further, the contrast stretch and MultiScale Retinex (MSR) techniques are exploited in order to enhance each of the scaled versions of the image. Finally, the enhanced image is obtained by combining each of these scales in an efficient way to obtain the composite enhanced image. The efficiency of the proposed algorithm is validated by using wavelet energy metric in the wavelet domain. Reconstructed image using proposed method highlights the details (edges and tissues), reduces image noise (Gaussian and Speckle) and improves the overall contrast. The proposed algorithm also enhances sharp edges of the tissue surrounding the spinal cord regions which is useful for diagnosis of spinal cord lesions. Elaborated experiments are conducted on several medical images and results presented show that the enhanced medical pictures are of good quality and is found to be better compared with other researcher methods. © 2014 by IJIR.


Lamgunde A.,Don Bosco Institute of Technology
Communications in Computer and Information Science | Year: 2011

Today worldwide, security and data hiding concerns are increasing day by day. Various security devices, systems and algorithms are used at places for the same. Most of these systems are implemented at places like airports, military areas, private or government offices. Steganography means covered or hidden writing. The objective of steganography is to send message through some innocuous carrier. The message to be sent could be a text, an image or an audio file. Steganography techniques prevent the fact that a secret message is being sent at all. Steganographic security is mostly influenced by the type of cover media; the method for selection of places within the cover that might be modified; the type of embedding operation; and the number of embedding changes that is a quantity closely related to the length of the embedded data. Given two embedding schemes that share the first three attributes, the scheme that introduces fewer embedding changes will be less detectable. © 2011 Springer-Verlag Berlin Heidelberg.


Padalkar P.,Don Bosco Institute of Technology
Proceedings - International Conference on Technologies for Sustainable Development, ICTSD 2015 | Year: 2015

It is necessary to sensitize the students of the professional course like engineering to the enviromental issues as well as to equip them with an ability to analyze and develope a sustinable solution to those problems. These skills are popularly know as the green skills. This paper presents analysis of the releation between the subject and the level of integration of the enviromental issues to the domain of study. The integaration would not only enable students to better understand and relate to environmnetal problem, but also prepare them to develop solution for the problems. We look at the current scenario of University of Mumbai syllabus for Department of Information Technology. The levels at which the assessment questions are set plays and important role in not only developing the understanding of the subject, but also in creating an image about its importance in the student's mind. We analyze the set of question papers from the subject of Environmnetal Studies according to the Bloom's Taxonomy. © 2015 IEEE.


Krishnamoorthy R.,Anna University | Sreedhar Kumar S.,Don Bosco Institute of Technology
Applied Mathematics and Information Sciences | Year: 2016

In this paper, three new techniques namely improved Limited Iteration Agglomerative Clustering (iLIAC), Global Outlier Validation (GOV) and Effective Cluster Validation Method (ECVM) are proposed. The proposed work aims to automatically separate the outliers (irrelevant or error data) and normal clusters over the large dataset through the process of identifying the maximum number of highly relative clusters with good accuracy. The first proposed technique iLIAC works with a new threshold (optimum merge cost) that aims to limit the number of iterations, and it automatically identifies the maximum number of highly relative clusters and outliers over the large dataset with higher accuracy and fewer misclassification errors and less computational time. The second technique GOV evaluates the global outliers around the result, and the last technique ECVM measures the purity (intra-cluster similarity) and impurity (intra-cluster dissimilarity) over the result of the iLIAC technique. Experimental results show that the proposed iLIAC technique is quicker and better to separate the normal clusters and outliers over the large dataset with good accuracy than the existing techniques. © 2016 NSP Natural Sciences Publishing Cor.


Deshmukh J.S.,Pacific University at Udaipur | Tripathy A.K.,Don Bosco Institute of Technology
Proceedings of 2nd IEEE International Conference on Engineering and Technology, ICETECH 2016 | Year: 2016

Opinion mining is growing area as people are sharing their views, opinions & experiences online. Automatic detection and analysis of sentiment around products, brands, political issues etc. is a challenging task. Domain adaptation is an important issue, which aims at transferring knowledge across domains or tasks. The labeling work may be time-consuming and expensive in order to build accurate opinion classifiers because of low generalization ability to new domains of supervised machine learning algorithms. Hence, domain adaptation algorithms are highly desirable to reduce domain dependency and labeling cost. The proposed approach classifies opinion words using maximum entropy and assigns weight using point wise mutual information. Results show that proposed approach performs moderately well compare to baseline method. © 2016 IEEE.


Sarangi R.K.,Don Bosco Institute of Technology | Rane M.V.,Indian Institute of Technology Bombay
Procedia Engineering | Year: 2013

Startup heat load, maximum heat load and optimum fill ratio of Pulsating Heat Pipe (PHP) of 16 turn, 1 mm ID, 2 mm OD and 9.6 m total length are found out experimentally for water and ethanol as working fluids. PHP is operated in vertical bottom heat mode. Evaporator and condenser temperatures are maintained at 100°C and 28°C respectively. Temperature fluctuations of adiabatic section at startup and maximum heat loads are reported. Experimental results indicate that, startup heat load is independent of fill ratio, but maximum heat load depends on fill ratio. Optimum fill ratio for maximum heat load depends on working fluid for a given PHP and operating temperatures. © 2012 Published by Elsevier Ltd.


Bhagyashekar M.S.,Don Bosco Institute of Technology | Rao R.M.V.G.K.,National Aerospace Laboratories, Bangalore
Journal of Reinforced Plastics and Composites | Year: 2010

Studies were carried out on RT cure epoxy (LY556+HY951) composite system comprised of metallic and non-metallic fillers. The results of the studies carried out on composites with three distinctly different particulate fillers, representing ductile (Cu and Al), brittle (SiC), and soft (Gr) type of materials regarding the mechanical properties, showed that the tensile and flexural strength of the particulate composites degraded with filler loading, whereas the modulus (both tensile and flexural) of the composites increased with the filler loading for the range of filler contents considered (10-40 wt%). The compression strength of all the composites increased to a maximum up to a filler loading of 30% and then decreased beyond this value, with the SiC-Ep composites exhibiting the highest improvement in the compression strength. © 2010 SAGE Publications.


Isola R.,Don Bosco Institute of Technology | Carvalho R.,Indian Institute of Technology Bombay | Tripathy A.K.,Don Bosco Institute of Technology
IEEE Transactions on Information Technology in Biomedicine | Year: 2012

Medical data are an ever-growing source of information generated from the hospitals in the form of patient records. When mined properly, the information hidden in these records is a huge resource bank for medical research. As of now, these data are mostly used only for clinical work. These data often contain hidden patterns and relationships, which can lead to better diagnosis, better medicines, better treatment, and overall, a platform to better understand the mechanisms governing almost all aspects of the medical domain. Unfortunately, discovery of these hidden patterns and relationships often goes unexploited. However, there is on-going research in medical diagnosis which can predict the diseases of the heart, lungs, and various tumours based on the past data collected from the patients. They are mostly limited to domain-specific systems that predict diseases restricted to their area of operation like heart, brain, and various other domains. These are not applicable to the whole medical dataset. The system proposed in this paper uses this vast storage of information so that diagnosis based on these historical data can be made. It focuses on computing the probability of occurrence of a particular ailment from the medical data by mining it using a unique algorithm which increases accuracy of such diagnosis by combining the key points of neural networks, Large Memory Storage, and Retrieval, k-NN, and differential diagnosis all integrated into one single algorithm. The system uses a service-oriented architecture wherein the system components of diagnosis, information portal, and other miscellaneous services are provided. This algorithm can be used in solving a few common problems that are encountered in automated diagnosis these days, which include diagnosis of multiple diseases showing similar symptoms, diagnosis of a person suffering from multiple diseases, receiving faster and more accurate second opinion, and faster identification of trends present in the medical records. © 1997-2012 IEEE.


Kotrashetti A.,Don Bosco Institute of Technology
ICWET 2010 - International Conference and Workshop on Emerging Trends in Technology 2010, Conference Proceedings | Year: 2010

This paper deals with the design and development of an inset-fed rectangular microstrip patch antenna. The main objective of this paper is to elaborate on the procedure used to design the antenna for a center frequency of 922 MHz and a 2.17% bandwidth; and to show the optimized results as obtained from the simulation. This antenna will work as a part of the transmitter section in a transmitter-receiver system operating in the ISM Band being developed in Don Bosco Institute of Technology. Copyright 2010 ACM.

Loading Don Bosco Institute of Technology collaborators
Loading Don Bosco Institute of Technology collaborators