Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
5 results
Search Results
Item Implementation of JPEG2000 still image codec on blackfin (ADSP - BF535) processor(2004) Kiran, K.S.; Shivaprakash, H.; Subrahmanya, M.V.; Raj, S.; Sumam David, S.With increasing use of Multimedia in everyday life, there is a need not only for better image compression techniques which can be used in a wide range of applications but also for efficient implementation of these compression algorithms on power-efficient platforms. To cater to such needs several compression methodologies have been proposed and standardized. We have implemented, JPEG2000, an emerging standard for still image compression on the Analog Devices Blackfin Digital Signal Processor (DSP) Implementation of still-image compression on programmable DSPs offer several advantages like ease of changing the codec standard, improved value addition by customizing the codec to the target application, scalability in image sizes etc. This paper presents the implementation details of the JPEG2000 still image codec on ADSP-BF535 processor based Analog Devices EZ-kit Lite board, and the quality of the results obtained demonstrate the potential of the low-power Micro -Signal Architecture of Blackfin processor as a good choice for embedded multimedia applications.Item Implementation of JPEG2000 still image codec on blackfin (ADSP - BF535) processor(2004) Kiran, K.S.; Shivaprakash, H.; Subrahmanya, M.V.; Raj, S.; Sumam David, S.With increasing use of Multimedia in everyday life, there is a need not only for better image compression techniques which can be used in a wide range of applications but also for efficient implementation of these compression algorithms on power-efficient platforms. To cater to such needs several compression methodologies have been proposed and standardized. We have implemented, JPEG2000, an emerging standard for still image compression on the Analog Devices Blackfin Digital Signal Processor (DSP). Implementation of still-image compression on programmable DSPs offer several advantages like ease of changing the codec standard, improved value addition by customizing the codec to the target application, scalability in image sizes etc. This paper presents the implementation details of the JPEG2000 still image codec on ADSP-BF535 processor based Analog Devices EZ-kit Lite board, and the quality of the results obtained demonstrate the potential of the low-power Micro-Signal Architecture of Blackfin processor as a good choice for embedded multimedia applications.Item Virtual Machine Migration in Heterogeneous Clouds - A Practical Approach(Institute of Electrical and Electronics Engineers Inc., 2020) Raj, S.; Mangal, N.; Savitha, S.; Salvi, S.S.In modern times, Cloud Computing is viewed as more promising technology than any other traditional Information Technology Computing paradigms. It basically serves as an on-demand resource provisioning platform without any active intervention by its user. The resource provisioning strategies require appropriate load distribution management across the cloud network, without which the cloud would face biased workload performance. Virtualization is the backbone of Cloud Computing, which enables the distribution and management of data by initiating the Virtual Machines (VMs). Furthermore, a Cloud Service Provider(CSP) has to monitor, analyze, and manage the workload distribution for servers when VMs are migrated. It presents the need to consider VM migration as an important activity that would unload the cloud server that is overloaded to migrate it to the server that can handle the workload. This paper proposes a technique that initiates the migration of VMs between heterogeneous cloud environments that would lead to a stable and well-balanced cloud network. The process of VM migration is very intensive in terms of resources, and hence intelligent approaches are required. It should effectively reduce the utilization of network bandwidth by minimizing the downtime of the server. However, the migration of VMs between the heterogeneous cloud would be challenging, but the right solution would benefit the cloud network managers on a large scale. Our proposed technique demonstrates heterogeneous VM migration between various cloud platforms built on different architectures. Various parameters have to be technically tuned for the conversion of VM images according to the Cloud Architecture. The performance of the proposed technique is evaluated based on the time taken for migration. © 2020 IEEE.Item Quantum Machine Learning: A Review and Current Status(Springer Science and Business Media Deutschland GmbH, 2021) Mishra, N.; Kapil, M.; Rakesh, H.; Anand, A.; Mishra, N.; Warke, A.; Sarkar, S.; Dutta, S.; Gupta, S.; Prasad Dash, A.; Gharat, R.; Chatterjee, Y.; Roy, S.; Raj, S.; Kumar Jain, V.; Bagaria, S.; Chaudhary, S.; Singh, V.; Maji, R.; Dalei, P.; Behera, B.K.; Mukhopadhyay, S.; Panigrahi, P.K.Quantum machine learning is at the intersection of two of the most sought after research areas—quantum computing and classical machine learning. Quantum machine learning investigates how results from the quantum world can be used to solve problems from machine learning. The amount of data needed to reliably train a classical computation model is evergrowing and reaching the limits which normal computing devices can handle. In such a scenario, quantum computation can aid in continuing training with huge data. Quantum machine learning looks to devise learning algorithms faster than their classical counterparts. Classical machine learning is about trying to find patterns in data and using those patterns to predict further events. Quantum systems, on the other hand, produce atypical patterns which are not producible by classical systems, thereby postulating that quantum computers may overtake classical computers on machine learning tasks. Here, we review the previous literature on quantum machine learning and provide the current status of it. © 2021, Springer Nature Singapore Pte Ltd.Item ShardCons - A Sharding Based Consensus Algorithm for Blockchain(Institute of Electrical and Electronics Engineers Inc., 2021) Kumar, A.; Sangoi, A.; Raj, S.; Manjappa, M.Blockchain, the foundation of Bitcoin, has received extensive attentions in recent days. Blockchain-based applications are springing up, covering numerous fields including financial services, reputation system, Internet of Things (IoT), Healthcare systems, Supply Chain Management and so on. Blockchain serves as an immutable ledger which allows transactions to be securely accomplished via point-to-point connections in a distributed system without the need for a third-party. Since it is decentralized, consensus algorithms keeps hold the integrity of the transactions which are added in the chain. Consensus algorithms are the primary root of the blockchain technology and a good consensus algorithm can guarantee the fault tolerance and security of the blockchain systems. In this article, authors present a novel consensus algorithm for public blockchain which shards the miners based on their performance. Once the sharding of miners is done, the best miner from each shard is chosen to form a Super shard of miners, and then from Super shard, one miner is randomly chosen as a winner miner who will mine the next block in the blockchain network. For sharding, performance history of miners will be maintained in each miner and re-sharding will be done at regular intervals in order to bring fairness in the system. The proposed sharding based consensus algorithm solves one of the main problem of public blockchain which is scalability issue. This performance based consensus algorithm also ensures more fairness, avoids starvation, improves the trust among the miners and enhances the overall performance of the blockchain network. © 2021 IEEE.