Entity

Time filter

Source Type


Kandagal A.P.,Sri Siddhartha Institute of Technology
Proceedings of 2014 International Conference on Contemporary Computing and Informatics, IC3I 2014 | Year: 2014

Human computer interaction (HCI) is very crucial in our day-to-day activity. Speech is one of the essential and intuitive ways to interact with machines such as Smartphone, which has multiple sensors as microphone, camera, etc. An efficient performance speech recognition system improves interaction between man and machines by making latter more receptive to user needs. Such system has Automatic speech recognition (ASR) engine, which is facing a unique challenge of accuracy in recognition rate. By integrating acoustic signal feature vectors with the visual features, a more robust audiovisual speech recognition engine (AVSR) could be developed for real environmental scenarios. This paper presents past research and development in the field of ASR and AVSR technologies. It describes key technological perspective and admiration of the fundamental progress in ASR and AVSR. The objective of this review is to summarize and compare some of the well-known methods experimented by previous researchers, and to conclude with direction on future research proficiency in HCI system using ASR and AVSR engine. © 2014 IEEE. Source


Sreedhar Acharya B.,Bharathiar University | Siddappa M.,Sri Siddhartha Institute of Technology
International Journal of Applied Engineering Research | Year: 2016

Cloud computing is evolving as the next generation architecture of IT Enterprise. Cloud Computing has emerged from the most promising business concept to new fast growing business trend. Cloud Computing provides the ability to utilize resources from distributed computing environments via Internet. Cloud Computing is the promising hosting platform that allows the resources and collection of applications usage in the shared infrastructure with pools of computers and storage resources. Enterprise customers are still reluctant to deploy cloud computing in business. The most threatening aspect of cloud computing is its security. Cloud computing moves its application and databases through data centers, while management of data and services are an important security challenges, which have not been fully understood. This paper focuses on security challenges in Data Transmission and Storage in cloud computing. © Research India Publications. Source


Hoskot M.J.,Sri Siddhartha Institute of Technology
IEEE Potentials | Year: 2013

While creating new industries and innovative technologies may be a long-term solution to systemic unemployment, they will take years to move from concept to development and finally deployment. The existing U.S. workforce is not prepared to undertake radical changes in the life skills needed to succeed in these new high-tech industries. The job mix in our current economy is weighted to the service sector by more than 80%. Within the call center sector alone, we have lost more than 7 million jobs to India and the Philippines and other low-cost markets. While these jobs are not the highest paying and are certainly not glamorous, they are jobs that are easily learned and can absorb large numbers of workers right now. Why can?t we act to protect these jobs and reverse the migration of call center work back to the United States? © 1988-2012 IEEE. Source


Renukalatha S.,Sri Siddhartha Institute of Technology | Suresh K.V.,Siddaganga Institute of Technology
Proceedings of 2014 International Conference on Contemporary Computing and Informatics, IC3I 2014 | Year: 2015

Accurate and robust image segmentation is identified as one of the most challenging issues in Positron Emission Tomography (PET). The low spatial resolution, signal dependant noise levels and complex nature of anatomical structures have negative impact on qualitative and quantitative image segmentation analysis. Several unsupervised methods such as, Fuzzy C-Means (FCM) clustering, active contour modeling are usually used in segmenting medical images. However, these methods are sensitive to both noise and intensity inhomogeniety, as they ignore the spatial information. In this paper, we propose a methodology which segments noisy PET images incorporating an efficient denoising technique using transform domain filters to remove the noise followed by an active contour method to segment the Region Of Interest (ROI). Finally, the segmented output is fine tuned using Bayesian matting approach. Experimental results show that the proposed approach improves the overall segmentation accuracy. © 2014 IEEE. Source


Annapurna H.S.,Sri Siddhartha Academy of Higher Education | Siddappa M.,Sri Siddhartha Institute of Technology
International Journal of Applied Engineering Research | Year: 2015

In Wireless Sensor Network (WSN), sensor nodes must utilize energy efficiently to increase the life time of a sensor node. Existing protocols for achieving data privacy and integrity in WSN introduce high communication and computational overhead which causes high energy and bandwidth consumption. Using data aggregation in WSN reduces the energy consumption at a sensor node. Existing privacy preserving data aggregation protocols do not provide efficient solutions for energy constrained and security required WSNs due to the overhead of power consuming operations at aggregator nodes. This paper proposes a new scheme called Secure Energy Efficient Homomorphism based Privacy and Integrity Preserving Data Aggregation for WSNs (SEEHPIP) that uses additive homomorphism to achieve confidentiality during data aggregation. It achieves non-delayed data aggregation by performing aggregation on encrypted data. The proposed scheme is best suited for time critical, secure applications since it achieves privacy, integrity, accuracy, end to end confidentiality, data freshness and energy efficiency during data aggregation without introducing a significant overhead on the battery limited sensor nodes. © Research India Publications. Source

Discover hidden collaborations