Bangalore, India
Bangalore, India

Time filter

Source Type

Gadag A.I.,RVCE | Sagar B.M.,RVCE
2016 International Conference on Computation System and Information Technology for Sustainable Solutions, CSITSS 2016 | Year: 2016

This paper describes the paraphrase generation based on n-gram approach. N-grams are relevant words of text document that can be applied for a range of Natural Language Processing (NLP) applications. The candidate paraphrases are generated based on trigrams approach. The reference paraphrases (keyphrases) are the set of relevant paraphrases, which acts like training data set for generating candidate paraphrases. The task of paraphrase generation is similar to machine translation; hence we used machine translation evaluation metrics. R-precision evaluation metric is used to find the number of common words between candidate and reference paraphrases. © 2016 IEEE.

Alva P.,RVCE | Hegde V.,RVCE
2016 International Conference on Computation System and Information Technology for Sustainable Solutions, CSITSS 2016 | Year: 2016

The process of identifying the sense or meaning of a word where the word has multiple meanings in a sentence is word sense disambiguation. Parts-of-speech tagging refers to a process of assigning a grammatical category like noun, adjective, verb etc. to a word to study the lexical information and context which is used for word sense disambiguation. Calculating Emission and Transition probability using Hidden Markov model is a commendable approach for POS tagging. © 2016 IEEE.

Jayanthi P.N.,RVCE | Ravishankar S.,RVCE
2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings | Year: 2016

One of the major challenge for practical Multiple Output-Orthogonal Frequency Division Multiplexing (MIMO-OFDM)system is the accurate channel estimation which is veryessential to guarantee the system performance. In this paper,theSubspace Pursuit (SP), Orthogonal Matching Pursuit (OMP) and Compressed Sampling Matching Pursuit(CoSaMP) techniques combined with Minimum Mean Square Error(MMSE) and Least Mean Square(LMS)tools are used to estimate the channel coefficients for MIMO-OFDM system.These algorithms are used for the channel estimation in MIMO-OFDM system to develop the joint sparsity of the MIMO channel. Simulation results shows that SP, OMP and CoSaMP techniques combined with MMSE and LMS tools provides significant reduction in Normalized Mean Square Error (NMSE) vs Signal to Noise Ratio (SNR) when compared to SP,OMP and CoSaMP technique with Least Square (LS) tool and also the conventional channel estimation methods such as LS, MMSE and LMS. Moreover CoSaMP combined with LMS tool performs better than SP and OMP techniques with LMS tool with less computational timecomplexity. © 2016 IEEE.

Sushma S.J.,Visvesvaraya Technological University | Kumar S.C.P.,RVCE
2015 International Conference on Emerging Research in Electronics, Computer Science and Technology, ICERECT 2015 | Year: 2015

Image preprocessing and image enhancement plays a critical role in medical image processing. Considering the case study of breast cancer detection, it was found that there are various schemes of optimization techniques which is either training based or leads to recursive iterations leading to computationally complex process. Hence, the proposed system implements a unique and novel optimization technique called as Image Enhancement using Bio-inspired Algorithms. Different from existing bio-inspired algorithm, the proposed system doesn't use any training sequences, or depends on single fitness function or performs recursive operation for exploring elite population. The algorithm performs automatic segmentation process followed by three level of enhancement operation for achieving local to global best optimization without using any forms of recursive functions. The outcomes are visually defined and well resolution to prove success factor. © 2015 IEEE.

Anala M.R.,RVCE | Shetty J.,RVCE | Shobha G.,RVCE
Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013 | Year: 2013

Server virtualization is an emerging technology that provides efficient resource utilization and cost-saving benefits. It consolidates many physical servers into a single physical server saving the hardware resources, physical space, power-consumption, air conditioning capacity and man power to manage the servers. Thus virtualization assists 'Green Technology'. Live migration is an essential feature of virtualization that allows transition of a running virtual machine from one system to another without halting the virtual machine. Live migration extends the list of benefits server virtualization provides. Almost all virtualization softwares now include support for live migration of virtual machine. Live migration is in its infant stage where security of live migration is yet to be analyzed. The usages of live migration and security exploits over it have both increased over time. The security concern of live migration is a major factor for its adoption by the IT industry. In this paper we discuss the attack model on the virtualization system and design and implement a security framework for secure live migration of virtual machines. The framework is an integrated security solution that addresses role based access policy, network intrusion, firewall protection and encryption for secure live migration process. © 2013 IEEE.

Devaraj D.,R.V.C.E. | Kumar S.C.P.,R.V.C.E.
Proceedings of 2014 International Conference on Contemporary Computing and Informatics, IC3I 2014 | Year: 2015

Diabetic retinopathy (DR) is the retinal disease caused by diabetes that involves damage to the small blood vessels in the posterior of the eye. Early stage of DR may not cause symptoms. But the progression of the disease leads to the proliferative stage. This causes leakage of protein and blood in the retina. Blood vessel segmentation is a helpful tool in the treatment of diabetic retinopathy. Many studies have been carried out in the last decade in order to derive an accurate blood vessel detection and segmentation in retinal images because vascular anomalies are one of the strongest signs of DR. An user friendly graphical user interface (GUI) which is MATLAB based that segments the blood vessels by means of adaptive median thresholding is proposed in this paper. From the segmented image, various features of blood vessels like area, mean, standard deviation, energy, entropy and histogram are calculated, in order to distinguish the image as normal or abnormal. With respect to the ground truth, performance measures like accuracy, specificity and sensitivity are calculated. The GUI is implemented using MATLAB and the feature parameters are calculated. The average accuracy, specificity and sensitivity were found to be 0.95, 0.99 and 0.77 respectively for drive images using Adaptive median thresholding. © 2014 IEEE.

Shilpa D.R.,RVCE | Uma B.V.,RVCE
Procedia Computer Science | Year: 2016

Design automation is one of the key requirements of today's growing ASIC/SOC design process. The era of high speed and high density designs has led the design engineers various challenges. As the technology is scaling, one of the major concerns of VLSI design is signal integrity. Crosstalk is the major cause of signal integrity that occurs due to coupling of charge between the conducting interconnects.Most of the CAD tools available in the market addresses this issue at the post layout level. But tackling crosstalk at the stage when the design is ready for fabrication may not be always feasible in terms of area and power overheads. This paper proposes a novel CAD tool which performs an optimization to crosstalk effect at architectural level using High Level Synthesis (HLS) procedures. The proposed work performs crosstalk aware simultaneous scheduling, binding and allocation of resources in the given data flow graph using hybrid genetic and simulated annealing algorithm (GASA). The data flow graph of an intended design is fed as an input to the tool and it generates corresponding crosstalk optimized verilog code as an output. The obtained design is synthesizable in any of the commercial tool. The work is tested on 3X3 matrix multiplier and experimental result shows that there is 65.07% improvement in crosstalk delay and hence the Signal Integrity. Hence this work suggests a technique for architectural level crosstalk optimization. © 2016 The Authors. Published by Elsevier B.V.

Mini R.,Amrita University | Sreenivasan R.,Amrita University | Dinesh M.N.,RVCE
2014 International Conference on Electronics, Communication and Computational Engineering, ICECCE 2014 | Year: 2014

Direct Torque controlled (DTC) induction motor drive gives direct control of stator flux and electromagnetic torque. Conventional speed sensors are replaced in sensor less DTC to improve the reliability, noise immunity and to reduce the complexity of the system. In sensor less DTC the rotor speed estimation at low speeds is degraded by the stator resistance parameter variations due to temperature, dead time effects and voltage drop in power electronics devices. The open loop speed estimation used in sensor less DTC depends on various machine parameters. The stator resistance variation at low speeds degrades the speed estimation. In this paper investigation of sensor less DTC controlled induction motor at low speed range is carried out and to improve the speed estimation at low speed closed loop Model Reference Adaptive Scheme (MRAS) is used for speed estimation. Simulation is carried out in Matlab/Simulink platform and results are compared and presented. © 2014 IEEE.

Manujakshi B.C.,Acharya Institute of Technology | Ramesh K.B.,RVCE
Proceedings of the 2016 IEEE International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2016 | Year: 2016

In recent years, there is a high growth in wireless sensor network (WSNs) for secure communications or sensor network applications. It has been seen that sensor applications are revised with upcoming technologies in order to meet the demands. There is a requirement of efficient design and implementation of WSNs, due to the huge SNs to allow applications which connect the physical world to the virtual world. With a wide range of applications for SNs, some of the application areas are health, military, and security will create issues in data transmissions from one sensor network to another sensor network. As sensors gathers complex data, it is quite a difficult job to understand how far it can be valuable with respect to analysis. Owing to inherent complexities e.g. size, heterogeneity, un-structuredness, etc. it may pose serious problems in futuristic sensor data analytics over cloud. This paper discusses about the techniques used in managing sensor data over cloud to understand the existing system and its effectiveness. © 2016 IEEE.

Geetha J.K.,RVCE | Deepamala N.,RVCE
2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015 | Year: 2015

Text Summarization is a method of reducing the original text document into a short description. This short version retains the meaning and information content of the original text document. It is a difficult task for human beings to generate the summary for very large documents manually. The linguistic and statistical features of sentence can be used to find the importance of sentences. The Latent Semantic Analysis (LSA) captures automatically the semantic relationships between the sentences as a human being thinks. In this paper Singular Value Decomposition (SVD) is used to generate the summary. SVD finds the dimensions of the sentence vectors which are principal and mutually orthogonal. These properties guaranty the relevance to original text document and non-redundancy respectively in machine generated summary. © 2015 IEEE.

Loading RVCE collaborators
Loading RVCE collaborators