%0 Journal Article %J IEEE Transactions on Multimedia %D 2012 %T Design and Synthesis for Multimedia Systems Using the Targeted Dataflow Interchange Format %A Chung-Ching Shen %A Wu, Shenpei %A Sane, N. %A Wu, Hsiang-Huang %A Plishker,W. %A Bhattacharyya, Shuvra S. %K associated dataflow graph-code generation %K Computational modeling %K contextual information encapsulation %K cross-platform application design %K data flow graphs %K Data models %K Data structures %K Dataflow graphs %K design components %K design tools %K Digital signal processing %K electronic data interchange %K embedded signal processing %K Embedded software %K high-level abstract modeling %K high-performance embedded-processing architectures %K Image coding %K image registration application %K image representation %K low-level customizations %K low-level optimization %K low-level synthesis %K Multimedia communication %K multimedia systems %K multimedia systems development %K object-oriented data structures %K object-oriented methods %K parameterized schedule representation %K programming interfaces %K repetitive graph structures %K retargetable design %K Schedules %K scheduling %K software synthesis %K Streaming media %K targeted dataflow interchange format %K task-level dataflow analysis %X Development of multimedia systems that can be targeted to different platforms is challenging due to the need for rigorous integration between high-level abstract modeling, and low-level synthesis and optimization. In this paper, a new dataflow-based design tool called the targeted dataflow interchange format is introduced for retargetable design, analysis, and implementation of embedded software for multimedia systems. Our approach provides novel capabilities, based on principles of task-level dataflow analysis, for exploring and optimizing interactions across design components; object-oriented data structures for encapsulating contextual information for components; a novel model for representing parameterized schedules that are derived from repetitive graph structures; and automated code generation for programming interfaces and low-level customizations that are geared toward high-performance embedded-processing architectures. We demonstrate our design tool for cross-platform application design, parameterized schedule representation, and associated dataflow graph-code generation using a case study centered around an image registration application. %B IEEE Transactions on Multimedia %V 14 %P 630 - 640 %8 2012 %@ 1520-9210 %G eng %N 3 %0 Conference Paper %B 2011 18th IEEE International Conference on Image Processing (ICIP) %D 2011 %T Face tracking in low resolution videos under illumination variations %A Zou, W.W.W. %A Chellapa, Rama %A Yuen, P.C. %K Adaptation models %K Computational modeling %K Face %K face recognition %K face tracking %K GLF-based tracker %K gradient methods %K gradient-logarithmic field feature %K illumination variations %K lighting %K low resolution videos %K low-resolution %K particle filter %K particle filter framework %K particle filtering (numerical methods) %K Robustness %K tracking %K video signal processing %K Videos %K Visual face tracking %X In practical face tracking applications, the face region is often small and affected by illumination variations. We address this problem by using a new feature, namely the Gradient-Logarithmic Field (GLF) feature, in the particle filter framework. The GLF feature is robust under illumination variations and the GLF-based tracker does not assume any model for the face being tracked and is effective in low-resolution video. Experimental results show that the proposed GFL-based tracker works well under significant illumination changes and outperforms some of the state-of-the-art algorithms. %B 2011 18th IEEE International Conference on Image Processing (ICIP) %I IEEE %P 781 - 784 %8 2011/09/11/14 %@ 978-1-4577-1304-0 %G eng %R 10.1109/ICIP.2011.6116672 %0 Conference Paper %B 2011 International Conference on Embedded Computer Systems (SAMOS) %D 2011 %T Methods for design and implementation of dynamic signal processing systems %A Bhattacharyya, Shuvra S. %K actor invocation predictability %K complementary dataflow models %K Computational modeling %K computational structure %K COMPUTERS %K data flow graphs %K dataflow schedule graph %K DSG models %K DSP-powered products %K Dynamic scheduling %K dynamic scheduling techniques %K dynamic signal processing systems %K Educational institutions %K EIDF models %K enable-invoke dataflow %K formal dataflow semantics %K functionality structure %K Laboratories %K Maryland DSPCAD Research Group %K quasi-static schedules %K Schedules %K scheduling %K Signal processing %K static schedules %X Summary form only given. Dynamic signal processing systems, where significant changes in functionality and computational structure must be achieved while applications are running, are becoming increasingly important as computational platforms become more powerful, and feature-sets of DSP-powered products become more sophisticated. This talk covers two new, complementary dataflow models of computation that are being developed in the Maryland DSPCAD Research Group to help address the challenges of structured design, simulation, and synthesis of dynamic signal processing systems. The first of these models, called enable-invoke dataflow (EIDF), is aimed improving the predictability of actor invocation and the efficiency with which dynamic scheduling techniques can be realized. The second model, called the dataflow schedule graph (DSG), provides a formal framework for representing and analyzing dataflow graph schedules that is rooted in formal dataflow semantics, and accommodates a wide range of schedule classes, including static, quasi-static, and dynamic schedules, as well as both sequential and parallel schedule formats. In this talk, I will present the EIDF and DSG models and discuss their potential to improve the processes by which dynamic signal processing systems are developed. %B 2011 International Conference on Embedded Computer Systems (SAMOS) %P i - i %8 2011 %G eng %0 Conference Paper %B 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW) %D 2011 %T A Model-Based Schedule Representation for Heterogeneous Mapping of Dataflow Graphs %A Wu, Hsiang-Huang %A Chung-Ching Shen %A Sane, N. %A Plishker,W. %A Bhattacharyya, Shuvra S. %K Computational modeling %K data flow graphs %K dataflow schedule graph %K dataflow semantics %K dataflow-based application specifications %K Dynamic scheduling %K heterogeneous mapping %K heterogeneous signal processing system design %K model-based design methodologies %K model-based schedule representation %K Processor scheduling %K Program processors %K Schedules %K semantics %K Signal processing %K synchronization %X Dataflow-based application specifications are widely used in model-based design methodologies for signal processing systems. In this paper, we develop a new model called the dataflow schedule graph (DSG) for representing a broad class of dataflow graph schedules. The DSG provides a graphical representation of schedules based on dataflow semantics. In conventional approaches, applications are represented using dataflow graphs, whereas schedules for the graphs are represented using specialized notations, such as various kinds of sequences or looping constructs. In contrast, the DSG approach employs dataflow graphs for representing both application models and schedules that are derived from them. Our DSG approach provides a precise, formal framework for unambiguously representing, analyzing, manipulating, and interchanging schedules. We develop detailed formulations of the DSG representation, and present examples and experimental results that demonstrate the utility of DSGs in the context of heterogeneous signal processing system design. %B 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW) %P 70 - 81 %8 2011 %G eng %0 Conference Paper %B 2011 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS) %D 2011 %T Modeling and optimization of dynamic signal processing in resource-aware sensor networks %A Bhattacharyya, Shuvra S. %A Plishker,W. %A Sane, N. %A Chung-Ching Shen %A Wu, Hsiang-Huang %K Adaptation models %K Aerodynamics %K Computational modeling %K data flow graphs %K dataflow interchange format %K Dynamic scheduling %K dynamic signal processing %K power consumption overhead %K Program processors %K resource-aware sensor networks %K run-time adaptation %K Schedules %K sensor node processing %K Signal processing %K Wireless sensor networks %X Sensor node processing in resource-aware sensor networks is often critically dependent on dynamic signal processing functionality - i.e., signal processing functionality in which computational structure must be dynamically assessed and adapted based on time-varying environmental conditions, operating constraints or application requirements. In dynamic signal processing systems, it is important to provide flexibility for run-time adaptation of application behavior and execution characteristics, but in the domain of resource-aware sensor networks, such flexibility cannot come with significant costs in terms of power consumption overhead or reduced predictability. In this paper, we review a variety of complementary models of computation that are being developed as part of the dataflow interchange format (DIF) project to facilitate efficient and reliable implementation of dynamic signal processing systems. We demonstrate these methods in the context of resource-aware sensor networks. %B 2011 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS) %P 449 - 454 %8 2011 %G eng %0 Journal Article %J IEEE Transactions on Pattern Analysis and Machine Intelligence %D 2011 %T Statistical Computations on Grassmann and Stiefel Manifolds for Image and Video-Based Recognition %A Turaga,P. %A Veeraraghavan,A. %A Srivastava, A. %A Chellapa, Rama %K activity based video clustering %K activity recognition %K computational geometry %K Computational modeling %K Data models %K face recognition %K feature representation %K finite dimensional linear subspaces %K geometric properties %K Geometry %K Grassmann Manifolds %K Grassmann. %K HUMANS %K Image and video models %K image recognition %K linear dynamic models %K linear subspace structure %K Manifolds %K maximum likelihood classification %K maximum likelihood estimation %K Object recognition %K Riemannian geometry %K Riemannian metrics %K SHAPE %K statistical computations %K statistical models %K Stiefel %K Stiefel Manifolds %K unsupervised clustering %K video based face recognition %K video based recognition %K video signal processing %X In this paper, we examine image and video-based recognition applications where the underlying models have a special structure-the linear subspace structure. We discuss how commonly used parametric models for videos and image sets can be described using the unified framework of Grassmann and Stiefel manifolds. We first show that the parameters of linear dynamic models are finite-dimensional linear subspaces of appropriate dimensions. Unordered image sets as samples from a finite-dimensional linear subspace naturally fall under this framework. We show that an inference over subspaces can be naturally cast as an inference problem on the Grassmann manifold. To perform recognition using subspace-based models, we need tools from the Riemannian geometry of the Grassmann manifold. This involves a study of the geometric properties of the space, appropriate definitions of Riemannian metrics, and definition of geodesics. Further, we derive statistical modeling of inter and intraclass variations that respect the geometry of the space. We apply techniques such as intrinsic and extrinsic statistics to enable maximum-likelihood classification. We also provide algorithms for unsupervised clustering derived from the geometry of the manifold. Finally, we demonstrate the improved performance of these methods in a wide variety of vision applications such as activity recognition, video-based face recognition, object recognition from image sets, and activity-based video clustering. %B IEEE Transactions on Pattern Analysis and Machine Intelligence %V 33 %P 2273 - 2286 %8 2011/11// %@ 0162-8828 %G eng %N 11 %R 10.1109/TPAMI.2011.52 %0 Conference Paper %B 2010 Conference on Design and Architectures for Signal and Image Processing (DASIP) %D 2010 %T Automated generation of an efficient MPEG-4 Reconfigurable Video Coding decoder implementation %A Gu, Ruirui %A Piat, J. %A Raulet, M. %A Janneck, J.W. %A Bhattacharyya, Shuvra S. %K automated generation %K automatic design flow %K CAL language %K CAL networks %K CAL-to-C translation %K CAL2C translation %K coarse-grain dataflow representations %K Computational modeling %K data flow computing %K dataflow information %K Dataflow programming %K decoding %K Digital signal processing %K Libraries %K MPEG-4 reconfigurable video coding decoder implementation %K parallel languages %K SDF detection %K synchronous dataflow detection %K TDP %K TDP-based static scheduling %K The Dataflow interchange format Package %K Transform coding %K user-friendly design %K video coding %K video processing systems %K XML %K XML format %X This paper proposes an automatic design flow from user-friendly design to efficient implementation of video processing systems. This design flow starts with the use of coarse-grain dataflow representations based on the CAL language, which is a complete language for dataflow programming of embedded systems. Our approach integrates previously developed techniques for detecting synchronous dataflow (SDF) regions within larger CAL networks, and exploiting the static structure of such regions using analysis tools in The Dataflow interchange format Package (TDP). Using a new XML format that we have developed to exchange dataflow information between different dataflow tools, we explore systematic implementation of signal processing systems using CAL, SDF-like region detection, TDP-based static scheduling, and CAL-to-C (CAL2C) translation. Our approach, which is a novel integration of three complementary dataflow tools - the CAL parser, TDP, and CAL2C - is demonstrated on an MPEG Reconfigurable Video Coding (RVC) decoder. %B 2010 Conference on Design and Architectures for Signal and Image Processing (DASIP) %P 265 - 272 %8 2010 %G eng %0 Conference Paper %B 2010 International Conference on Embedded Computer Systems (SAMOS) %D 2010 %T Efficient static buffering to guarantee throughput-optimal FPGA implementation of synchronous dataflow graphs %A Kee, Hojin %A Bhattacharyya, Shuvra S. %A Kornerup, J. %K buffer memory %K circuit complexity %K Complexity theory %K Computational modeling %K data flow graphs %K Digital signal processing %K digital signal processing chips %K DSP system design %K efficient static buffering %K Field programmable gate arrays %K FPGA %K graph buffer distributions %K integrated circuit design %K low polynomial time complexity %K Random access memory %K Schedules %K SDF graph edges %K Signal processing systems %K Synchronous dataflow %K synchronous dataflow graph mapping %K Throughput %K throughput-optimal execution %K throughput-optimal FPGA implementation %K two-actor SDF graph model %K upper bounds %X When designing DSP applications for implementation on field programmable gate arrays (FPGAs), it is often important to minimize consumption of limited FPGA resources while satisfying real-time performance constraints. In this paper, we develop efficient techniques to determine dataflow graph buffer sizes that guarantee throughput-optimal execution when mapping synchronous dataflow (SDF) representations of DSP applications onto FPGAs. Our techniques are based on a novel two-actor SDF graph Model (TASM), which efficiently captures the behavior and costs associated with SDF graph edges (flow-graph connections). With our proposed techniques, designers can automatically generate upper bounds on SDF graph buffer distributions that realize maximum achievable throughput performance for the corresponding applications. Furthermore, our proposed technique is characterized by low polynomial time complexity, which is useful for rapid prototyping in DSP system design. %B 2010 International Conference on Embedded Computer Systems (SAMOS) %P 136 - 143 %8 2010 %G eng %0 Conference Paper %B 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) %D 2010 %T FPGA-based design and implementation of the 3GPP-LTE physical layer using parameterized synchronous dataflow techniques %A Kee, Hojin %A Bhattacharyya, Shuvra S. %A Wong, I. %A Yong Rao %K 3G mobile communication %K 3GPP-long term evolution %K 3GPP-LTE physical layer %K 4G communication systems %K Computational modeling %K data flow analysis %K data flow graphs %K Dataflow modeling %K Digital signal processing %K DSP applications %K Field programmable gate arrays %K FPGA architecture framework %K FPGA implementation %K FPGA-based design %K Hardware %K hardware synthesis %K Instruments %K LabVIEW FPGA %K Logic Design %K LTE %K next generation cellular standard %K parameterized synchronous data flow technique %K Pervasive computing %K Physical layer %K Physics computing %K Production %K PSDF graph %K reconfigurable hardware implementation %K Runtime %K software synthesis %K Ubiquitous Computing %K ubiquitous data flow model %X Synchronous dataflow (SDF) is an ubiquitous dataflow model of computation that has been studied extensively for efficient simulation and software synthesis of DSP applications. In recent years, parameterized SDF (PSDF) has evolved as a useful framework for modeling SDF graphs in which arbitrary parameters can be changed dynamically. However, the potential to enable efficient hardware synthesis has been treated relatively sparsely in the literature for SDF and even more so for the newer, more general PSDF model. This paper investigates efficient FPGA-based design and implementation of the physical layer for 3GPP-Long Term Evolution (LTE), a next generation cellular standard. To capture the SDF behavior of the functional core of LTE along with higher level dynamics in the standard, we use a novel PSDF-based FPGA architecture framework. We implement our PSDF-based, LTE design framework using National Instrument's LabVIEW FPGA, a recently-introduced commercial platform for reconfigurable hardware implementation. We show that our framework can effectively model the dynamics of the LTE protocol, while also providing a synthesis framework for efficient FPGA implementation. %B 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) %P 1510 - 1513 %8 2010 %G eng %0 Conference Paper %B 2010 IEEE International Conference on Control Applications (CCA) %D 2010 %T Methods for efficient implementation of Model Predictive Control on multiprocessor systems %A Gu, Ruirui %A Bhattacharyya, Shuvra S. %A Levine,W. S %K Computational modeling %K COMPUTERS %K Equations %K Hardware %K Linear systems %K Mathematical model %K model predictive control %K MPC algorithms %K Multiprocessing systems %K Multiprocessor systems %K parallel computers %K predictive control %K Program processors %X Model Predictive Control (MPC) has been used in a wide range of application areas including chemical engineering, food processing, automotive engineering, aerospace, and metallurgy. An important limitation on the application of MPC is the difficulty in completing the necessary computations within the sampling interval. Recent trends in computing hardware towards greatly increased parallelism offer a solution to this problem. This paper describes modeling and analysis tools to facilitate implementing the MPC algorithms on parallel computers, thereby greatly reducing the time needed to complete the calculations. The use of these tools is illustrated by an application to a class of MPC problems. %B 2010 IEEE International Conference on Control Applications (CCA) %P 1357 - 1362 %8 2010 %G eng %0 Conference Paper %B 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) %D 2010 %T Moving vistas: Exploiting motion for describing scenes %A Shroff, N. %A Turaga,P. %A Chellapa, Rama %K Application software %K Automation %K Chaos %K chaotic system %K Computational modeling %K Computer vision %K dynamic scene categorization %K Educational institutions %K HUMANS %K image recognition %K in the wild dynamic scene %K Layout %K motion attribute %K natural scenes %K Physics %K probability %K scene recognition %K Snow %K video data %X Scene recognition in an unconstrained setting is an open and challenging problem with wide applications. In this paper, we study the role of scene dynamics for improved representation of scenes. We subsequently propose dynamic attributes which can be augmented with spatial attributes of a scene for semantically meaningful categorization of dynamic scenes. We further explore accurate and generalizable computational models for characterizing the dynamics of unconstrained scenes. The large intra-class variation due to unconstrained settings and the complex underlying physics present challenging problems in modeling scene dynamics. Motivated by these factors, we propose using the theory of chaotic systems to capture dynamics. Due to the lack of a suitable dataset, we compiled a dataset of `in-the-wild' dynamic scenes. Experimental results show that the proposed framework leads to the best classification rate among other well-known dynamic modeling techniques. We also show how these dynamic features provide a means to describe dynamic scenes with motion-attributes, which then leads to meaningful organization of the video data. %B 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) %I IEEE %P 1911 - 1918 %8 2010/06/13/18 %@ 978-1-4244-6984-0 %G eng %R 10.1109/CVPR.2010.5539864 %0 Conference Paper %B 2010 21st IEEE International Symposium on Rapid System Prototyping (RSP) %D 2010 %T Rapid prototyping for digital signal processing systems using Parameterized Synchronous Dataflow graphs %A Wu, Hsiang-Huang %A Kee, Hojin %A Sane, N. %A Plishker,W. %A Bhattacharyya, Shuvra S. %K abstract scheduling %K Computational modeling %K Computer architecture %K data flow graphs %K dataflow based design %K dataflow interchange format %K design flow %K design language %K Digital signal processing %K digital signal processing systems %K dynamic parameter reconfiguration %K Dynamic scheduling %K efficient hardware mapping %K efficient quasistatic scheduling %K Embedded software %K embedded systems %K Field programmable gate arrays %K flexible dynamic reconfiguration %K FPGA based systems %K FPGA implementations %K functional simulation %K Hardware %K parameterized synchronous dataflow graphs %K rapid prototyping %K Schedules %K scheduling %K semantics %K simulation tool %K software package %K systematic design methodology %X Parameterized Synchronous Dataflow (PSDF) has been used previously for abstract scheduling and as a model for architecting embedded software and FPGA implementations. PSDF has been shown to be attractive for these purposes due to its support for flexible dynamic reconfiguration, and efficient quasi-static scheduling. To apply PSDF techniques more deeply into the design flow, support for comprehensive functional simulation and efficient hardware mapping is important. By building on the DIF (Dataflow Interchange Format), which is a design language and associated software package for developing and experimenting with dataflow-based design techniques for signal processing systems, we have developed a tool for functional simulation of PSDF specifications. This simulation tool allows designers to model applications in PSDF and simulate their functionality, including use of the dynamic parameter reconfiguration capabilities offered by PSDF. Based on this simulation tool, we also present a systematic design methodology for applying PSDF to the design and implementation of digital signal processing systems, with emphasis on FPGA-based systems for signal processing. We demonstrate capabilities for rapid and accurate prototyping offered by our proposed design methodology, along with its novel support for PSDF-based FPGA system implementation. %B 2010 21st IEEE International Symposium on Rapid System Prototyping (RSP) %P 1 - 7 %8 2010 %G eng %0 Conference Paper %B 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) %D 2010 %T Simulating dynamic communication systems using the core functional dataflow model %A Sane, N. %A Chia-Jui Hsu %A Pino,J. L %A Bhattacharyya, Shuvra S. %K adaptive modulation %K Analytical models %K Application software %K Computational modeling %K core functional dataflow model %K Dataflow %K dataflow modeling semantics %K design tools %K Digital signal processing %K dynamic communication systems %K functional specification %K Hardware %K modeling and simulation %K Power system modeling %K Predictive models %K Processor scheduling %K Production %K Signal processing %K software tools %K wireless communication %X The latest communication technologies invariably consist of modules with dynamic behavior. There exists a number of design tools for communication system design with their foundation in dataflow modeling semantics. These tools must not only support the functional specification of dynamic communication modules and subsystems but also provide accurate estimation of resource requirements for efficient simulation and implementation. We explore this trade-off - between flexible specification of dynamic behavior and accurate estimation of resource requirements - using a representative application employing an adaptive modulation scheme. We propose an approach for precise modeling of such applications based on a recently-introduced form of dynamic dataflow called core functional dataflow. From our proposed modeling approach, we show how parameterized looped schedules can be generated and analyzed to simulate applications with low run-time overhead as well as guaranteed bounded memory execution. We demonstrate our approach using the Advanced Design System from Agilent Technologies, Inc., which is a commercial tool for design and simulation of communication systems. %B 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) %P 1538 - 1541 %8 2010 %G eng %0 Journal Article %J IEEE/ACM Transactions on Computational Biology and Bioinformatics %D 2008 %T Guest Editors' Introduction to the Special Section on Algorithms in Bioinformatics %A Giancarlo,Raffaele %A Hannenhalli, Sridhar %K Abstracts %K Algorithm design and analysis %K Bioinformatics %K Biological system modeling %K biology computing %K Computational Biology %K Computational modeling %K Computer science %K Genomics %K sequences %B IEEE/ACM Transactions on Computational Biology and Bioinformatics %V 5 %P 482 - 483 %8 2008/12//Oct %@ 1545-5963 %G eng %N 4 %R 10.1109/TCBB.2008.116 %0 Journal Article %J IEEE Transactions on Circuits and Systems for Video Technology %D 2005 %T Class-based access control for distributed video-on-demand systems %A Mundur, Padma %A Sood,A. K %A Simon,R. %K Access control %K Admission control %K Analytical models %K blocking performance %K class-based access control %K Computational modeling %K Computer architecture %K Computer science %K Distributed control %K Distributed video-on-demand (VoD) system %K distributed video-on-demand system %K multimedia systems %K multirate service model %K Performance analysis %K QoS %K quality of service %K request handling policy %K resource allocation %K resource capacity %K telecommunication congestion control %K threshold-based admission control %K video on demand %X The focus of this paper is the analysis of threshold-based admission control policies for distributed video-on-demand (VoD) systems. Traditionally, admission control methods control access to a resource based on the resource capacity. We have extended that concept to include the significance of an arriving request to the VoD system by enforcing additional threshold restrictions in the admission control process on request classes deemed less significant. We present an analytical model for computing blocking performance of the VoD system under threshold-based admission control. Extending the same methodology to a distributed VoD architecture we show through simulation that the threshold performance conforms to the analytical model. We also show that threshold-based analysis can work in conjunction with other request handling policies and are useful for manipulating the VoD performance since we are able to distinguish between different request classes based on their merit. Enforcing threshold restrictions with the option of downgrading blocked requests in a multirate service environment results in improved performance at the same time providing different levels of quality of service (QoS). In fact, we show that the downgrade option combined with threshold restrictions is a powerful tool for manipulating an incoming request mix over which we have no control into a workload that the VoD system can handle. %B IEEE Transactions on Circuits and Systems for Video Technology %V 15 %P 844 - 853 %8 2005/07// %@ 1051-8215 %G eng %N 7 %R 10.1109/TCSVT.2005.848351 %0 Conference Paper %B Parallel and Distributed Processing Symposium, 2005. Proceedings. 19th IEEE International %D 2005 %T EMPS: an environment for memory performance studies %A Hollingsworth, Jeffrey K %A Snavely, A. %A Sbaraglia, S. %A Ekanadham, K. %K Application software %K cache storage %K Computational modeling %K Concurrent computing %K data gathering %K Delay %K digital simulation %K Economic forecasting %K EMP radiation effects %K high end computing system %K High performance computing %K memory architecture %K memory performance %K Moore's Law %K PARALLEL PROCESSING %K parallel program %K Predictive models %K simulation tool %K Writing %X This paper describes an overview of environment for memory performance studies (EMPS). EMPS is a framework to allow different data gathering and simulation tools to be composed together to predict the performance of parallel programs on a variety of current and future high end computing (HEC) systems. The framework seeks to combine the automated nature of direct execution simulation with the predictive capabilities of performance modeling. %B Parallel and Distributed Processing Symposium, 2005. Proceedings. 19th IEEE International %I IEEE %8 2005/04// %@ 0-7695-2312-9 %G eng %R 10.1109/IPDPS.2005.196 %0 Conference Paper %B Parallel and Distributed Processing Symposium, 2005. Proceedings. 19th IEEE International %D 2005 %T High Performance Communication between Parallel Programs %A Jae-Yong Lee %A Sussman, Alan %K Adaptive arrays %K Analytical models %K Chaotic communication %K Computational modeling %K Computer science %K Data analysis %K data distribution %K Educational institutions %K high performance communication %K image data analysis %K image resolution %K inter-program communication patterns %K InterComm %K Libraries %K Message passing %K parallel languages %K parallel libraries %K parallel programming %K parallel programs %K performance evaluation %K Wind %X We present algorithms for high performance communication between message-passing parallel programs, and evaluate the algorithms as implemented in InterComm. InterComm is a framework to couple parallel programs in the presence of complex data distributions within a coupled application. Multiple parallel libraries and languages may be used in the different programs of a single coupled application. The ability to couple such programs is required in many emerging application areas, such as complex simulations that model physical phenomena at multiple scales and resolutions, and image data analysis applications. We describe the new algorithms we have developed for computing inter-program communication patterns. We present experimental results showing the performance of various algorithmic tradeoffs, and also compare performance against an earlier system. %B Parallel and Distributed Processing Symposium, 2005. Proceedings. 19th IEEE International %I IEEE %P 177b- 177b - 177b- 177b %8 2005/04// %@ 0-7695-2312-9 %G eng %R 10.1109/IPDPS.2005.243 %0 Conference Paper %B 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Proceedings %D 2004 %T The influence of shape on image correspondence %A Ogale, A. S %A Aloimonos, J. %K Automation %K CAMERAS %K Computational modeling %K first order approximation %K Geometrical optics %K hidden feature removal %K image sampling %K Image segmentation %K Layout %K occlusion detection %K piecewise continuous function %K Pixel %K SHAPE %K Simulated annealing %K stereo image processing %K surface fitting %X We examine the implications of shape on the process of finding dense correspondence and half-occlusions for a stereo pair of images. The desired property of the depth map is that it should be a piecewise continuous function which is consistent with the images and which has the minimum number of discontinuities. To zeroeth order, piecewise continuity becomes piecewise constancy. Using this approximation, we first discuss an approach for dealing with such a fronto-parallel shapeless world, and the problems involved therein. We then introduce horizontal and vertical slant to create a first order approximation to piecewise continuity. We highlight the fact that a horizontally slanted surface (ie. having depth variation in the direction of the separation of the two cameras) appears horizontally stretched in one image as compared to the other image. Thus, while corresponding two images, N pixels on a scanline in one image may correspond to a different number of pixels M in the other image, which has consequences with regard to sampling and occlusion detection. We also discuss the asymmetry between vertical and horizontal slant, and the central role of nonhorizontal edges in the context of vertical slant. Using experiments, we discuss cases where existing algorithms fail, and how the incorporation of new constraints provides correct results. %B 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Proceedings %I IEEE %P 945 - 952 %8 2004/09/06/9 %@ 0-7695-2223-8 %G eng %R 10.1109/TDPVT.2004.1335418 %0 Conference Paper %B Parallel and Distributed Processing Symposium, 2004. Proceedings. 18th International %D 2004 %T Unobtrusiveness and efficiency in idle cycle stealing for PC grids %A Ryu, K. D %A Hollingsworth, Jeffrey K %K Biological system modeling %K Computational modeling %K Computer science %K Computer simulation %K Contracts %K desktop grid system %K fine-grain cycle stealing approach %K grid computing %K idle cycle stealing %K Linger-Longer system %K Linux %K Linux cluster %K microcomputers %K PC grids %K Personal communication networks %K Prototypes %K resource allocation %K Throughput %K workstation clusters %K workstation grid systems %K Workstations %X Summary form only given. Studies have shown that for a significant fraction of the time desktop PCs and workstations are under-utilized. To exploit these idle resources, various desktop/workstation grid systems have been developed. The ultimate goal of such systems is to maximize efficiency of resource usage while maintaining low obtrusiveness to machine owners. To this end, we created a new fine-grain cycle stealing approach and conducted a performance comparison study against the traditional coarse-grain cycle stealing. We developed a prototype of fine-grain cycle stealing, the Linger-Longer system, on a Linux cluster. The experiments on a cluster of desktop Linux PCs with benchmark applications show that, overall, fine-grain cycle stealing can improve efficiency of idle cycle usage by increasing the guest job throughput by 50% to 70%, while limiting obtrusiveness with no more than 3% of host job slowdown. %B Parallel and Distributed Processing Symposium, 2004. Proceedings. 18th International %I IEEE %8 2004/04/26/30 %@ 0-7695-2132-0 %G eng %R 10.1109/IPDPS.2004.1302987 %0 Conference Paper %B IEEE International Conference on Systems, Man and Cybernetics, 2003 %D 2003 %T Non-parametric expectation maximization: a learning automata approach %A Abd-Almageed, Wael %A El-Osery,A. %A Smith,C.E. %K Automatic speech recognition %K bivariate simulation data %K Computational modeling %K Computer vision %K Density functional theory %K expectation maximization technique %K learning automata %K mixture parameters estimation %K nonparametric expectation maximization %K nonparametric statistics %K optimisation %K parameter estimation %K Parzen Window %K PDF %K probability %K probability density function %K Speech processing %K Speech recognition %K stochastic learning automata %K Stochastic processes %K stochastic technique %X The famous expectation maximization technique suffers two major drawbacks. First, the number of components has to be specified apriori. Also, the expectation maximization is sensitive to initialization. In this paper, we present a new stochastic technique for estimating the mixture parameters. Parzen Window is used to estimate a discrete estimate of the PDF of the given data. Stochastic learning automata is then used to select the mixture parameters that minimize the distance between the discrete estimate of the PDF and the estimate of the expectation maximization. The validity of the proposed approach is verified using bivariate simulation data. %B IEEE International Conference on Systems, Man and Cybernetics, 2003 %I IEEE %V 3 %P 2996- 3001 vol.3 - 2996- 3001 vol.3 %8 2003/10// %@ 0-7803-7952-7 %G eng %R 10.1109/ICSMC.2003.1244347 %0 Conference Paper %B Supercomputing, ACM/IEEE 2002 Conference %D 2002 %T Active Harmony: Towards Automated Performance Tuning %A Tapus, C. %A I-Hsin Chung %A Hollingsworth, Jeffrey K %K Application software %K Automatic control %K Computational modeling %K Computer science %K Computerized monitoring %K Control systems %K grid computing %K Runtime library %K software libraries %K Specification languages %X In this paper, we present the Active Harmony automated runtime tuning system. We describe the interface used by programs to make applications tunable. We present the Library Specification Layer which helps program library developers expose multiple variations of the same API using different algorithms.The Library Specification Language helps to select the most appropriate program library to tune the overall performance. We also present the optimization algorithm used to adjust parameters in the application and the libraries. Finally, we present results that show how the system is able to tune several real applications. The automated tuning system is able to tune the application parameers to within a few percent of the best value after evaluating only 11 out of over 1,700 possible configurations. %B Supercomputing, ACM/IEEE 2002 Conference %I IEEE %P 44 - 44 %8 2002/11// %@ 0-7695-1524-X %G eng %R 10.1109/SC.2002.10062 %0 Conference Paper %B Applications of Signal Processing to Audio and Acoustics, 2001 IEEE Workshop on the %D 2001 %T Efficient evaluation of reverberant sound fields %A Duraiswami, Ramani %A Gumerov, Nail A. %A Zotkin,Dmitry N %A Davis, Larry S. %K AB algorithm %K acoustic signal processing %K architectural acoustics %K audio signal processing %K Computational modeling %K Computer interfaces %K Computer simulation %K Educational institutions %K image method %K image sources %K Impedance %K Laboratories %K microphone arrays %K multipole expansions %K Nails %K performance evaluation %K reverberant sound fields %K reverberation %K room reverberation %K simulation %K Simulations %K speedup %K virtual audio %X An image method due to Allen and Berkley (1979) is often used to simulate the effect of reverberation in rooms. This method is relatively expensive computationally. We present a fast method for conducting such simulations using multipole expansions. For M real and image sources and N evaluation points, while the image method requires O(MN) operations, our method achieves the calculations in O(M + N) operations, resulting in a substantial speedup. Applications of our technique are also expected in simulation of virtual audio %B Applications of Signal Processing to Audio and Acoustics, 2001 IEEE Workshop on the %I IEEE %P 203 - 206 %8 2001/// %@ 0-7803-7126-7 %G eng %R 10.1109/ASPAA.2001.969578 %0 Journal Article %J IEEE Transactions on Software Engineering %D 2001 %T A tool to help tune where computation is performed %A Eom, Hyeonsang %A Hollingsworth, Jeffrey K %K Computational modeling %K Current measurement %K Distributed computing %K distributed program %K distributed programming %K load balancing factor %K Load management %K parallel program %K parallel programming %K Performance analysis %K performance evaluation %K Performance gain %K performance metric %K Programming profession %K software metrics %K software performance evaluation %K Testing %K Time measurement %K tuning %X We introduce a new performance metric, called load balancing factor (LBF), to assist programmers when evaluating different tuning alternatives. The LBF metric differs from traditional performance metrics since it is intended to measure the performance implications of a specific tuning alternative rather than quantifying where time is spent in the current version of the program. A second unique aspect of the metric is that it provides guidance about moving work within a distributed or parallel program rather than reducing it. A variation of the LBF metric can also be used to predict the performance impact of changing the underlying network. The LBF metric is computed incrementally and online during the execution of the program to be tuned. We also present a case study that shows that our metric can accurately predict the actual performance gains for a test suite of six programs %B IEEE Transactions on Software Engineering %V 27 %P 618 - 629 %8 2001/07// %@ 0098-5589 %G eng %N 7 %R 10.1109/32.935854 %0 Conference Paper %B 18th International Conference on Distributed Computing Systems, 1998. Proceedings %D 1998 %T LBF: a performance metric for program reorganization %A Eom, H. %A Hollingsworth, Jeffrey K %K case study %K Computational modeling %K computer network %K Computer science %K Debugging %K distributed processing %K distributed program %K Educational institutions %K Integrated circuit testing %K LBF metric %K load balancing factor %K Load management %K measurement %K NIST %K parallel program %K parallel programming %K performance metric %K program reorganization %K program tuning %K Programming profession %K resource allocation %K software metrics %K software performance evaluation %K US Department of Energy %X We introduce a new performance metric, called Load Balancing Factor (LBF), to assist programmers with evaluating different tuning alternatives. The LBF metric differs from traditional performance metrics since it is intended to measure the performance implications of a specific tuning alternative rather than quantifying where time is spent in the current version of the program. A second unique aspect of the metric is that it provides guidance about moving work within a distributed or parallel program rather than reducing it. A variation of the LBF metric can also be used to predict the performance impact of changing the underlying network. The LBF metric can be computed incrementally and online during the execution of the program to be tuned. We also present a case study that shows that our metric can predict the actual performance gains accurately for a test suite of six programs %B 18th International Conference on Distributed Computing Systems, 1998. Proceedings %I IEEE %P 222 - 229 %8 1998/05/26/29 %@ 0-8186-8292-2 %G eng %R 10.1109/ICDCS.1998.679505 %0 Journal Article %J IEEE Transactions on Knowledge and Data Engineering %D 1998 %T Techniques for update handling in the enhanced client-server DBMS %A Delis,A. %A Roussopoulos, Nick %K client disk managers %K client resources %K client-server computing paradigm %K client-server systems %K Computational modeling %K Computer architecture %K concurrency control %K data pages %K Database systems %K distributed databases %K enhanced client-server DBMS %K Hardware %K Local area networks %K long-term memory %K main-memory caches %K Network servers %K operational spaces %K Personal communication networks %K server update propagation techniques %K Transaction databases %K update handling %K Workstations %K Yarn %X The Client-Server computing paradigm has significantly influenced the way modern Database Management Systems are designed and built. In such systems, clients maintain data pages in their main-memory caches, originating from the server's database. The Enhanced Client-Server architecture takes advantage of all the available client resources, including their long-term memory. Clients can cache server data into their own disk units if these data are part of their operational spaces. However, when updates occur at the server, a number of clients may need to not only be notified about these changes, but also obtain portions of the updates as well. In this paper, we examine the problem of managing server imposed updates that affect data cached on client disk managers. We propose a number of server update propagation techniques in the context of the Enhanced Client-Server DBMS architecture, and examine the performance of these strategies through detailed simulation experiments. In addition, we study how the various settings of the network affect the performance of these policies %B IEEE Transactions on Knowledge and Data Engineering %V 10 %P 458 - 476 %8 1998/06//May %@ 1041-4347 %G eng %N 3 %R 10.1109/69.687978 %0 Conference Paper %B , 35th Annual Symposium on Foundations of Computer Science, 1994 Proceedings %D 1994 %T Computing with very weak random sources %A Srinivasan, Aravind %A Zuckerman,D. %K Application software %K BPP simulations %K Chor-Goldreich sources %K computational complexity %K Computational modeling %K Computer science %K Computer simulation %K cryptography %K distributed algorithms %K expander constructions %K hardness %K MATHEMATICS %K min-entropy %K Physics computing %K Polynomials %K probability %K R-bit string %K randomness-efficient Leftover Hash Lemma %K RP algorithms simulation %K Testing %K time-space tradeoffs %K very weak random sources %X For any fixed ε>0, we show how to simulate RP algorithms in time nO(log n) using the output of a δ-source with min-entropy R(ε). Such a weak random source is asked once for R(ε) bits; it outputs an R-bit string such that any string has probability at most 2-R(ε). If ε>1-1/(k+1), our BPP simulations take time nO(log(k n)) (log(k) is the logarithm iterated k times). We also give a polynomial-time BPP simulation using Chor-Goldreich sources of min-entropy RΩ(1), which is optimal. We present applications to time-space tradeoffs, expander constructions, and the hardness of approximation. Also of interest is our randomness-efficient Leftover Hash Lemma, found independently by Goldreich and Wigderson %B , 35th Annual Symposium on Foundations of Computer Science, 1994 Proceedings %I IEEE %P 264 - 275 %8 1994/11/20/22 %@ 0-8186-6580-7 %G eng %R 10.1109/SFCS.1994.365688 %0 Journal Article %J IEEE Transactions on Knowledge and Data Engineering %D 1993 %T ADMS: a testbed for incremental access methods %A Roussopoulos, Nick %A Economou,N. %A Stamenas,A. %K Add-drop multiplexers %K ADMS %K advanced database management system %K client-server architecture %K commercial database management systems %K Computational modeling %K Database systems %K distributed databases %K heterogeneous DBMS %K incremental access methods %K incremental gateway %K Information retrieval %K interoperability %K join index %K large databases %K Navigation %K network operating systems %K Object oriented databases %K Object oriented modeling %K Query processing %K System testing %K very large databases %K view index %K Workstations %X ADMS is an advanced database management system developed-to experiment with incremental access methods for large and distributed databases. It has been developed over the past eight years at the University of Maryland. The paper provides an overview of ADMS, and describes its capabilities and the performance attained by its incremental access methods. This paper also describes an enhanced client-server architecture that allows an incremental gateway access to multiple heterogeneous commercial database management systems %B IEEE Transactions on Knowledge and Data Engineering %V 5 %P 762 - 774 %8 1993/10// %@ 1041-4347 %G eng %N 5 %R 10.1109/69.243508 %0 Conference Paper %B 1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1993. Proceedings CVPR '93 %D 1993 %T Early vision processing using a multi-stage diffusion process %A Yacoob,Yaser %A Davis, Larry S. %K 3-D space %K Computational modeling %K Computer vision %K Diffusion processes %K discontinuity detection %K early vision processing %K Educational institutions %K Image edge detection %K Image segmentation %K Laboratories %K multistage diffusion process %K Noise shaping %K noise-free edges %K noisy edges %K Performance analysis %K roof edges %K segmentation %K SHAPE %K shape homogeneous regions %K step edges %K valley edges %X The use of a multistage diffusion process in the early processing of range data is examined. The input range data are interpreted as occupying a volume in 3-D space. Each diffusion stage simulates the process of diffusing part of the boundary of the volume into the volume. The outcome of the process can be used for both discontinuity detection and segmentation into shape homogeneous regions. The process is applied to synthetic noise-free and noisy step, roof, and valley edges as well as to real range images %B 1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1993. Proceedings CVPR '93 %I IEEE %P 41 - 46 %8 1993/06// %@ 0-8186-3880-X %G eng %R 10.1109/CVPR.1993.341003 %0 Journal Article %J IEEE Transactions on Software Engineering %D 1993 %T Performance comparison of three modern DBMS architectures %A Delis,A. %A Roussopoulos, Nick %K client-server %K Computational modeling %K Computer architecture %K database management systems %K DBMS architectures %K design rationales %K functional components %K Indexes %K Local area networks %K Military computing %K Packaging %K Performance analysis %K performance evaluation %K RAD-UNIFY type %K simulation models %K simulation results %K Software architecture %K software architecture configurations %K software engineering %K Throughput %K Workstations %X The introduction of powerful workstations connected through local area networks (LANs) inspired new database management system (DBMS) architectures that offer high performance characteristics. The authors examine three such software architecture configurations: client-server (CS), the RAD-UNIFY type of DBMS (RU), and enhanced client-server (ECS). Their specific functional components and design rationales are discussed. Three simulation models are used to provide a performance comparison under different job workloads. Simulation results show that the RU almost always performs slightly better than the CS, especially under light workloads, and that ECS offers significant performance improvement over both CS and RU. Under reasonable update rates, the ECS over CS (or RU) performance ratio is almost proportional to the number of participating clients (for less than 32 clients). The authors also examine the impact of certain key parameters on the performance of the three architectures and show that ECS is more scalable that the other two %B IEEE Transactions on Software Engineering %V 19 %P 120 - 138 %8 1993/02// %@ 0098-5589 %G eng %N 2 %R 10.1109/32.214830 %0 Journal Article %J IEEE Transactions on Knowledge and Data Engineering %D 1991 %T Incremental implementation model for relational databases with transaction time %A Jensen,C. S %A Mark,L. %A Roussopoulos, Nick %K Computational modeling %K Computer science %K Data models %K data retrieval %K Database languages %K Database systems %K database theory %K decremental computations %K deferred update %K Degradation %K differential computation %K historical data %K History %K incremental computations %K Information retrieval %K partitioned storage models %K queries %K relational data model %K Relational databases %K stored views %K Transaction databases %K transaction time %K view materialization %X An implementation model for the standard relational data model extended with transaction time is presented. The implementation model integrates techniques of view materialization, differential computation, and deferred update into a coherent whole. It is capable of storing any view (reflecting past or present states) and subsequently using stored views as outsets for incremental and decremental computations of requested views, making it more flexible than previously proposed partitioned storage models. The working and the expressiveness of the model are demonstrated by sample queries that show how historical data are retrieved %B IEEE Transactions on Knowledge and Data Engineering %V 3 %P 461 - 473 %8 1991/12// %@ 1041-4347 %G eng %N 4 %R 10.1109/69.109107 %0 Conference Paper %B IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1989. Proceedings CVPR '89 %D 1989 %T 3D object recognition via simulated particles diffusion %A Yacoob,Yaser %A Gold,Y. I %K 3D object recognition %K alignment strategy %K Computational modeling %K Computer science %K data mining %K Gold %K Layout %K Noise shaping %K Object detection %K Object recognition %K parallel projection %K pattern recognition %K point features %K radio access networks %K scene acquisition %K shape characterisation %K Shape measurement %K simulated particles diffusion %K transformation detection %X A novel approach for 3D object recognition is presented. This approach is model-based, and assumes either 3D or 21/2 D scene acquisition. Transformation detection is accomplished along with an object identification (six degrees of freedom, three rotational and three translational, are assumed). The diffusion-like simulation recently introduced as a means for characterization of shape is used in the extraction of point features. The point features represent regions on the object's surface that are extreme in curvature (i.e. concavities and convexities). Object matching is carried out by examining the correspondence between the object's set of point features and the model's set of point features, using an alignment strategy. Triangles are constructed between all possible triples of object's point features, and then are aligned to candidate corresponding triangles of the model's point features. 21/2 range images are transformed into a volumetric representation through a parallel projection onto the 3-D space. The resultant volume is suitable for processing by the diffusion-like simulation %B IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1989. Proceedings CVPR '89 %I IEEE %P 442 - 449 %8 1989/06// %@ 0-8186-1952-x %G eng %R 10.1109/CVPR.1989.37886 %0 Conference Paper %B 1987 IEEE International Conference on Robotics and Automation. Proceedings %D 1987 %T Determining three dimensional transformation parameters from images: Theory %A Ito, E. %A Aloimonos, J. %K Automation %K Computational modeling %K Educational institutions %K Image motion analysis %K Indium tin oxide %K Linear systems %K Motion estimation %K Optical computing %K Robots %K Simulated annealing %X We present a theory for the determination of the three dimensional transformation parameters of an object, from its images. The input to this process is the image intensity function and its temporal derivative. In particular, our results are: 1) If the structure of the transforming object in view is known, then the transformation parameters are determined from the solution of a linear system. Rigid motion is a special ease of our theory. 2)If the structure of the object in view is not known, then both the structure and transformation parameters may be computed through a hill climbing or simulated annealing algorithm. %B 1987 IEEE International Conference on Robotics and Automation. Proceedings %I IEEE %V 4 %P 57 - 61 %8 1987/03// %G eng %R 10.1109/ROBOT.1987.1088011