Sharadh Ramaswamy
Research Subjects
Sharadh Ramaswamy has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Kenneth Rose
University of California Santa Barbara Santa Barbara 93117 CA USA
4 shared publications Ankur Saxena
Department of Electrical and Computer Engineering University of California at Santa Barbara CA-93106
1 shared publication- Emrah Akyol
ECE Department University of California -Santa Barbara
1 shared publication Jayant Nayak
Mayachitra Inc., Santa Barbara, CA, USA
1 shared publication- Jayanth Nayak
Mayachitra, Inc., University of California, Santa Barbara, Riverside
1 shared publication Kumar Viswanatha
Department of Electrical and Computer Engineering University of California at Santa Barbara CA-93106
1 shared publication
Latest Publications
- Open Access
On Large Scale Distributed Compression and Dispersive Information Routing for Networks
This paper considers the problem of distributed source coding for a large network. A major obstacle that poses an existential threat to practical deployment of conventional approaches to distributed coding is the exponential growth of the decoder complexity with the number of sources and the encoding rates. This growth in complexity renders many traditional approaches impractical even for moderately sized networks. In this paper, we propose a new decoding paradigm for large scale distributed compression wherein the decoder complexity is explicitly controlled during the design. Central to our approach is a module called the "bit-subset selector" whose role is to judiciously extract an appropriate subset of the received bits for decoding per individual source. We propose a practical design strategy, based on deterministic annealing (DA) for the joint design of the system components, that enables direct optimization of the decoder complexity-distortion trade-off, and thereby the desired scalability. We also point out the direct connections between the problem of large scale distributed compression and a related problem in sensor networks, namely, dispersive information routing of correlated sources. This allows us to extend the design principles proposed in the context of large scale distributed compression to design efficient routers for minimum cost communication of correlated sources across a network. Experiments on both real and synthetic data-sets provide evidence for substantial gains over conventional approaches.
Open AccessOn Large Scale Distributed Compression and Dispersive Information Routing for Networks
This paper considers the problem of distributed source coding for a large network. A major obstacle that poses an existential threat to practical deployment of conventional approaches to distributed coding is the exponential growth of the decoder complexity with the number of sources and the encoding rates. This growth in complexity renders many traditional approaches impractical even for moderately sized networks. In this paper, we propose a new decoding paradigm for large scale distributed compression wherein the decoder complexity is explicitly controlled during the design. Central to our approach is a module called the "bit-subset selector" whose role is to judiciously extract an appropriate subset of the received bits for decoding per individual source. We propose a practical design strategy, based on deterministic annealing (DA) for the joint design of the system components, that enables direct optimization of the decoder complexity-distortion trade-off, and thereby the desired scalability. We also point out the direct connections between the problem of large scale distributed compression and a related problem in sensor networks, namely, dispersive information routing of correlated sources. This allows us to extend the design principles proposed in the context of large scale distributed compression to design efficient routers for minimum cost communication of correlated sources across a network. Experiments on both real and synthetic data-sets provide evidence for substantial gains over conventional approaches.
- 1 December 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 58 (3) , 1722-1731
Fusion Coding of Correlated Sources for Storage and Selective Retrieval
We focus on a new, potentially important application of source coding directed toward storage and retrieval, termed fusion coding of correlated sources. The task at hand is to efficiently store multiple correlated sources in a database so that, at any point of time in the future, data from a selective subset of sources specified by user can be efficiently retrieved. Only statistical information about future queries is available in advance. A typical application scenario would be in storage of correlated data generated by dense sensor networks, where information from specific regions is requested in the future. We propose a fusion coder (FC) for lossy storage and retrieval, wherein different queries are handled by allowing for selective (compressed) bit retrieval. We derive the properties of an optimal FC and present an iterative algorithm for its design. Since iterative design is initialization-dependent, we present initialization heuristics that help avoid poor local optima. An analysis of design complexity reveals complexity growth with query-set size. We first tackle this problem by exploiting optimality properties of FCs. We also consider quantization of the query-space with decision trees in order to adapt to new queries, unseen during FC design. Experiments conducted on real and synthetic data-sets demonstrate that the proposed FC is able to achieve significantly better tradeoffs than joint compression by vector quantization (VQ), with retrieval speedups reaching 3 × and distortion gains of up to 3.5 dB possible.
- 1 December 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 58 (3) , 1722-1731
Fusion Coding of Correlated Sources for Storage and Selective Retrieval
We focus on a new, potentially important application of source coding directed toward storage and retrieval, termed fusion coding of correlated sources. The task at hand is to efficiently store multiple correlated sources in a database so that, at any point of time in the future, data from a selective subset of sources specified by user can be efficiently retrieved. Only statistical information about future queries is available in advance. A typical application scenario would be in storage of correlated data generated by dense sensor networks, where information from specific regions is requested in the future. We propose a fusion coder (FC) for lossy storage and retrieval, wherein different queries are handled by allowing for selective (compressed) bit retrieval. We derive the properties of an optimal FC and present an iterative algorithm for its design. Since iterative design is initialization-dependent, we present initialization heuristics that help avoid poor local optima. An analysis of design complexity reveals complexity growth with query-set size. We first tackle this problem by exploiting optimality properties of FCs. We also consider quantization of the query-space with decision trees in order to adapt to new queries, unseen during FC design. Experiments conducted on real and synthetic data-sets demonstrate that the proposed FC is able to achieve significantly better tradeoffs than joint compression by vector quantization (VQ), with retrieval speedups reaching 3 × and distortion gains of up to 3.5 dB possible.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, II-1005-II-1008
Code Design for Fast Selective Retrieval of Fusion Stored Sensor-Network/Time-Series Data
We consider the problem of storing data from multiple correlated sources in a database, so as to enable efficient future retrieval of data from select subsets of the sources, where only statistical information about queries may be available in advance. This setting poses new challenges in terms of the precise tradeoffs between storage rate, retrieval rate and distortion. We derive a gradient descent algorithm to optimize the joint encoding (storage) procedure, the decoder, and the retrieval procedure via mapping from queries to subsets of the stored data to retrieve and decode, so that the average retrieval rate-distortion cost is minimized, given a pre-specified overall storage capacity (or rate). Experiments conducted on real and synthetic data-sets demonstrate that our selective retrieval procedure is able to achieve significantly better trade-offs than joint compression, with retrieval speed-ups reaching 5X and distortion gains of up to 3.5 dB possible.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, II-1005-II-1008
Code Design for Fast Selective Retrieval of Fusion Stored Sensor-Network/Time-Series Data
We consider the problem of storing data from multiple correlated sources in a database, so as to enable efficient future retrieval of data from select subsets of the sources, where only statistical information about queries may be available in advance. This setting poses new challenges in terms of the precise tradeoffs between storage rate, retrieval rate and distortion. We derive a gradient descent algorithm to optimize the joint encoding (storage) procedure, the decoder, and the retrieval procedure via mapping from queries to subsets of the stored data to retrieve and decode, so that the average retrieval rate-distortion cost is minimized, given a pre-specified overall storage capacity (or rate). Experiments conducted on real and synthetic data-sets demonstrate that our selective retrieval procedure is able to achieve significantly better trade-offs than joint compression, with retrieval speed-ups reaching 5X and distortion gains of up to 3.5 dB possible.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6, VI - 381-VI - 384
Adaptive Cluster-Distance Bounding for Nearest Neighbor Search in Image Databases
We consider approaches for exact similarity search in a high dimensional space of correlated features representing image datasets, based on principles of clustering and vector quantization. We develop an adaptive cluster distance bound based on separating hyperplanes, that complements our index in selectively retrieving clusters that contain data entries closest to the query. Experiments conducted on real data-sets confirm the efficiency of our approach with random disk IOs reduced by 100X, as compared with the popular vector approximation-file (VA-File) approach, when allowed (roughly) the same number of sequential disk accesses, with relatively low preprocessing storage and computational costs.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6, VI - 381-VI - 384
Adaptive Cluster-Distance Bounding for Nearest Neighbor Search in Image Databases
We consider approaches for exact similarity search in a high dimensional space of correlated features representing image datasets, based on principles of clustering and vector quantization. We develop an adaptive cluster distance bound based on separating hyperplanes, that complements our index in selectively retrieving clusters that contain data entries closest to the query. Experiments conducted on real data-sets confirm the efficiency of our approach with random disk IOs reduced by 100X, as compared with the popular vector approximation-file (VA-File) approach, when allowed (roughly) the same number of sequential disk accesses, with relatively low preprocessing storage and computational costs.