Shree M.R.,Institute of Management Sciences |
Lakshmi S.,The Academy of Management |
2016 International Conference on Computation System and Information Technology for Sustainable Solutions, CSITSS 2016 | Year: 2016
Natural Language Processing (NLP) is a field of computational linguistics related to interactions between computers and human languages. Parsing of input text of any human language is a part of NLP. This parsing technique requires processing of text on a word by word basis. To process any individual word especially in Sanskrit and all Dravidian languages, Sandhi splitting is a major task. Sandhi is also called Morphophonemics concerned with changes that occur when two words or separate morphemes come together to form a new word. Exact splitting point is essential for text processing tasks such as POS tagging and in turn parsing. We have adopted a novel approach to internal Sandhi splitting technique on Kannada language. Each Kannada word is split into morphemes according to valid morph patterns. After the division of each word into lexical morphemes, we have manually tagged each split word into root-begins, root-continuous and suffix. This work has been done on Kannada language. We have trained the system with a list of 1000 tagged words using a CRF (Conditional Random Fields) tool and nearly 400 raw split words (untagged words) are given as input to the CRF tool. The system generates a list of tagged split words for the given input according to the trained data. The system output has been compared with the manually tagged data. We have verified the data using 5 fold test, which takes five different combinations of trained data (1000 words) and test data (400 words). The average Precision, Recall and F-Measure of Tagging accuracy of CRF model for Kannada corpus in 5 fold test are nearly equal to 98.08, 92.91 and 95.43. This method can be successfully implemented in all other Dravidian languages for the Sandhi splitting. © 2016 IEEE.
Desai S.R.,BMSCE |
Prasad R.,Indian Institute of Technology Roorkee
Proceedings of the International Conference on Inventive Computation Technologies, ICICT 2016 | Year: 2017
Another approach for generating reduced order discrete time system using composite method is being proposed. The proposed method is validated by considering a Linear Time Invariant Discrete System (LTIDS) having single input single output(SISO) of higher order being represented in frequency domain. Eigen Spectrum Analysis and Least Squares moment matching methods form the proposed composite method to obtain the reduced numerator and denominator polynomials. The suitability of the proposed method is judged by comparing the step, impulse responses of the original and reduced systems. The performances of the systems are measured in terms of Steady State Error (SSE). It is seen from the numerical examples that the results are quite competitive as compared to other methods thus justifying the applicability of the proposed method. © 2016 IEEE.
Nethravathi N.P.,Visvesvaraya Technological University |
Rao P.G.,Visvesvaraya Technological University |
Desai V.J.,University Visvesvaraya College of Engineering |
Shenoy P.D.,University Visvesvaraya College of Engineering |
And 2 more authors.
Proceedings of the 2016 International Conference on Data Science and Engineering, ICDSE 2016 | Year: 2016
Privacy Preserving in Data Mining is a very important area which deals with hiding an individual's sensitive data without affecting the usability of data. In this paper, we put forward a technique to provide privacy preservation of sensitive data based on the semantic context. Our approach encapsulates various techniques of Text-processing, keyphrase extraction, Cooccurrence analysis, ontology construction and query analysis. To handle privacy issues Correlation Based Transformation Strategy (CBTS) is performed on sensitive data, additionally we can add custom properties to the attributes of the ontology to indicate the sensitive data. Our experimental results indicate that our solution is effective in marking the private data using the semantic context of the input text. The main goal of our work is to construct a module which acts as an intermediate step in pre-processing for data mining while preserving the privacy. © 2016 IEEE.
Srividya B.V.,DSCE |
Proceedings of International Conference on Circuits, Communication, Control and Computing, I4C 2014 | Year: 2014
Public key cryptosystem or the asymmetric crypto system is more secure than secret key method because of a pair of related keys used by both sender and receiver. The problem in most of the cryptosystem is that the plain text is considered as an integer number that leads poor security. In this paper we propose an efficient Bezier curve based public key cryptography technique over Galois field GF(pm), where p=2,3,5,7. Here the plaint text is considered as a (x, y) coordinate over curve elements. © 2014 IEEE.
Umesh S.,BMSIT |
Venkatesha L.,BMSCE |
Proceedings of the 2014 International Conference on Advances in Energy Conversion Technologies - Intelligent Energy Management: Technologies and Challenges, ICAECT 2014 | Year: 2014
This work addresses the power factor correction technique adopted for a high output power, single phase full bridge rectifier with a large capacitor at its output stage. Full bridge rectifier with a large capacitor at its output stage is the most commonly used circuit topology in AC-DC conversion to get a constant DC output voltage required for various applications. This topology is popular because of its simple construction, low cost and high reliability. However this topology will have a distorted input current waveform shape with lot of lower order harmonics and low power factor which needs to be corrected. The power factor can be improved either by using passive or active components. In this work, a comparative study and analysis of passive and active power factor correction methods has been demonstrated. The simulation of passive power factor correction for a single-phase bridge rectifier with large output capacitor for 1 kW output has been carried out using PSpice simulation software. The active power factor correction for a single-phase, 1 kW output full bridge rectifier has been designed and tested and results are presented. Further the results of both the schemes are compared and advantages of active power factor correction is recorded and demonstrated in this work. © 2014 IEEE.
Ravoor P.C.,BMSCE |
Ranjani B.S.,WorldServe Education |
Rao Rupanagudi S.,WorldServe Education
Proceedings of the 2012 International Conference on Recent Advances in Computing and Software Systems, RACSS 2012 | Year: 2012
Almost undoubtedly, the greatest invention of the 20th century has been the computer. The computer uses several auxiliary devices to establish a seamless interaction with the user. One challenge faced during the development of these devices, was the lack of direct interfacing between the machine and the user. Today we see Natural User Interfaces (NUI), which include touch activated and speech activated inputs. One problem faced with the touch NUI's is ambiguity. This is mainly due to variations in finger size, proximity of icons, and the fact that the imprint of the finger, called a fingertip blob, may have to be mapped to a single pixel. In this paper we attempt to address the above problems, by focusing on achieving a high level of accuracy at low costs, utilizing image processing techniques, all the while keeping the process simple and fast. A novel algorithm for the same has also been discussed. The algorithm was implemented using the Java programming language on the Java Software Development Kit (JDK) version 1.5.0 (update 22). An accuracy of 100% in fingertip blob detection was achieved and an improvement of 15% was achieved in terms of execution time in comparison with existing algorithms, for various experiments conducted utilizing the new algorithm. © 2012 IEEE.
Shobha Y.,CMJ University |
Lecture Notes in Electrical Engineering | Year: 2014
Cloud computing, as an emerging computing model, provides storage, network and computing resources as services to the requested users on demand over the Internet. Efficient and convenient utilization of cloud resources to achieve high throughput and quality of service (QoS) is a major challenge. Hence, in order to achieve good QoS and high performance of the cloud, this paper has proposed a data center-based cloud architecture and an efficient service scheduling strategy. This is done by monitoring the changing resource and virtual machine (VM) status with dynamic VM configuration. The main targets of the proposed work are to achieve high throughput with good QoS. The simulation results demonstrate that it achieves the objectives. © 2014 Springer India.
Shree M.R.,AIeMS |
Souvenir of the 2015 IEEE International Advance Computing Conference, IACC 2015 | Year: 2015
Natural Language Processing (NLP) involves many phases of which the significant one is Word-sense disambiguation (WSD). WSD includes the techniques of identifying a suitable meaning of words and sentences in a particular context by applying various computational procedures. WSD is an Artificial Intelligence problem that needs resolution for ambiguity of words. WSD is essential for many NLP applications like Machine Translation, Information Retrieval, Information Extraction and for many others. The WSD techniques are mainly categorized into knowledge-based approaches, Machine Learning based approaches and hybrid approaches. The assessment of WSD systems is discussed in this study and it includes comparisons of different WSD approaches in the context of Indian languages. © 2015 IEEE.
Dilip Maruthi G.,BMSCE |
Materials Today: Proceedings | Year: 2015
Industrialization has become a burgeoning virus in today's competitive world. The companies are striving hard to sustain themselves. They tend to give better products and services and improve their manufacturing operations in today's unprecedented global competition. Because of this reason the manufacturing sector consumes lot of energy and other resources and emits large amounts of greenhouse gases which increase environmental problems like climate change - global warming, global dimming etc. and environmental degradation. And it also found a large amount of energy is also wasted in many forms. One of the possible ways to strike out these problems is Green Manufacturing. Green Manufacturing can be applied in all manufacturing sectors that minimize waste & pollution, Enables economic progress and conserve resources. The present work focuses on achieving Green Manufacturing by using various techniques that has impact on reduction in waste and environmental pollution. © 2015 Elsevier Ltd.
Sandeep Kumar B.R.,BMSCE |
2016 3rd International Conference on Electrical Energy Systems, ICEES 2016 | Year: 2016
The solar converter for power conversion system is a device designed to perform different operations using a simple circuit. The Converter performs both DC/AC and DC/DC operation. This topology is used to supply power to a system during all times of a day. The Photo-voltaic array is interfaced with the battery and hence used to provide power for the entire day. This work demonstrates the solar converter for power conversion system having PID Controller and 7 Level Inverter. The Total Harmonic Distortion is less when solar converter for power conversion having PI Controller is compared with solar converter for power conversion having PID Controller. Further, the Total Harmonic Distortion reduces for the solar converter for power conversion having PID Controller and 7-level inverter system. In this work, the battery unit is designed using the TTL driver circuit and the inverter is designed using MOSFET switches and IR2110 driver circuit. Also, the gating signals are effectively generated using Peripheral Interface Controller (PIC) microcontroller. © 2016 IEEE.