Real-time Retrieval Research Articles

Storage System for Supporting More Video Streams in Video Server

Video server needs a storage system with large bandwidth in order to provide concurrently more users with the real time retrieval requests for video streams. So, the storage system generally has the structure of disk array, which consists of multiple disks. When the storage system serves multiple video stream requests, it's bottlenecks come from the seeking delay caused by the random movement of disk head and from unbalanced disk access due to disk load unbalance among multiple disks. This paper presents a novel placement and retrieval policy. The new policy retrieves the requested data through sequential movement of disk heads and maintaining disk load balance so that it can diminish the bottlenecks on retrieving and can provide the concurrent real time retrieval services for more users simultaneously. In addition, the novel policy reduces the startup latency for the requests. The correctness of the novel placement and retrieval policy is analyzed with theoretical views. Performance analysis of the novel placement and retrieval policy is provided with simulations.

Mapping of temperature and line-of-sight errors in constituent retrievals for MIPAS/ENVISAT measurements

An optimized code for the near real-time retrieval of line of sight, temperature and volume-mixing ratio profiles of five key species (O 3, H 2O, HNO 3, CH 4 and N 2O) from infrared limb spectra recorded by the Michelson Interferometer for Passive Atmospheric Sounding (MIPAS) experiment on board the ENVISAT-1 satellite was developed as part of an ESA-supported study. In this code line of sight and temperature are retrieved simultaneously among themselves, but sequentially with respect to the volume-mixing ratio of the five key species. The sequential retrieval leaves unaccounted the mapping of line of sight and temperature errors in the retrieved volume-mixing ratio of the constituents. This paper illustrates an algorithm that provides the a-posteriori evaluation of temperature and line-of-sight-induced error on the retrieved volume-mixing ratio of the MIPAS key species. It is shown that in most cases temperature and line-of-sight-induced error provides a significant contribution to the total volume-mixing ratio error. The variability of this error as a function of latitude, season and atmospheric model is also analyzed.

A scalable storage supporting multistream real-time data retrieval

This paper presents a new data placement scheme for continuous-media playback via a scalable storage system. Multimedia contents are segmented into data blocks for the purpose of being stored, retrieved, and manipulated. If these data blocks belong to some continuous media, then they must be handled in a timely manner, for example, being retrieved before some deadline. One of the main challenges in implementing the above system is the simultaneous retrieval of a great number of different media streams from a very large storage system. The proposed scheme efficiently reduces the seeking delay by a very simple placement method and a retrieval scheduler. Thus, both the storage capacity and the number of concurrent accesses to the storage are scalable. The performance of the proposed scheme is evaluated through a simple analytical model and a practical prototype implementation.

A Variational Method for Real-Time Retrieval of Three-Dimensional Wind Field from Multiple-Doppler Bistatic Radar Network Data

Abstract A variational method for the retrieval of the 3D wind field from bistatic multiple-Doppler radar network data is developed, and its performance is evaluated. This bistatic network consists of one S-band weather radar and two passive low-gain receivers at remote sites. To allow for measurement error, the method uses the Doppler velocities of the three receivers as weak constraints and uses the continuity equation as a strong constraint in a cost function in which the two horizontal wind components are the control variables. Improvements are brought to the classical upward integration of the continuity equation, using a weighted combination of upward and downward integrations and its adjoint. A unique characteristic of a bistatic network is that all Doppler velocity measurements from individual resolution volumes are collected simultaneously, which minimizes the errors on the vertical wind component arising from the local evolution of the airflow. However, the time required to sample a complete wea...

Data Extraction and Ad Hoc Query of an Entity--Attribute--Value Database

Entity--attribute--value (EAV) tables form the major component of several mainstream electronic patient record systems (EPRSs). Such systems have been optimized for real-time retrieval of individual patient data. Data warehousing, on the other hand, involves cross-patient data retrieval based on values of patient attributes, with a focus on ad hoc query. Attribute-centric query is inherently more difficult when data are stored in EAV form than when they are stored conventionally. The authors illustrate their approach to the attribute-centric query problem with ACT/DB, a database for managing clinical trials data. This approach is based on metadata supporting a query front end that essentially hides the EAV/non-EAV nature of individual attributes from the user. The authors' work does not close the query problem, and they identify several complex subproblems that are still to be solved.

Disk-based storage for scalable video

We consider the placement of scalable video data on single and multiple disks for storage and real-time retrieval. For the single-disk case, we extend the principle of constant frame grouping from constant bit rate (CBR) to variable bit rate (VBR) scalable video data. When the number of admitted users exceeds the server capacity, the rate of data sent to each user is reduced to relieve the disk system overload, offering a graceful degradation in comparison with nonscalable data. We examine the qualities of video reconstructions obtained from a real disk video server and find the scalable video more visually appealing. In the VBR case, scalability is also used to improve interactivity by reducing the delay associated with using interactive functions in a predictive admission control environment. Finally, we consider the multiple disk scenario and prove that periodic interleaving results in lower system delay than striping in a video server using round-robin scheduling. We verify the results through detailed simulation of a four-disk array.

Presto—A System Environment for Mission-CriticalMultimedia Applications

Summarized in this report is a multiphased R and D program, presto, conducted for developing a multimedia system environment to support a variety of mission-critical applications. The concepts, software design, and system prototype developed during the first phase of the program are presented. In particular, the work on real-time scheduling, multimedia storage and retrieval, and application programming model is described. The major results of the presto Phase I program are a set of new techniques and system software for QoS- and criticality-based, adaptive multiresource management, raw-I/O-based continuous multimedia file management, and data flow-oriented programming with integrated real-time scheduling support.

Cost analyses for VBR video servers

Comparing techniques for storage and real time retrieval of variable bit rate video data for multiple simultaneous users, we conclude that constant time length and hybrid techniques can greatly reduce the total system cost. Of three admission control techniques, data limit admission control offers a moderate gain for a moderate increase in implementation complexity. We also applied our data placement and admission control strategies to an interleaved disk array.

Allocation strategies of multimedia data on disk arrays

Recent technological advances will make it feasible to integrate multimedia data with computing. The data intensive nature of media types such as digital video and audio imposes two stringent requirements on the storage technology: (1) large storage capacity, and (2) a data transfer bandwidth that is sufficient to support the real-time retrieval of multi-media data. A disk array is one approach to improve the I/O performance by using multiple disks as a storage system. There are various ways in which to configure disk arrays, and various data allocation strategies also exist. Each gives a different performance from the others, depending on the type of workload. In this paper, we propose various allocation strategies of multimedia data on disk arrays, and evaluate their performance by simulation. Results show that the strategy of storing media blocks so they are synchronized contiguously has the best performance. Unfortunately, it is almost impossible to carry out the strategy when a number of users are involved. The second best strategy is the case where media of the same type take disk modules exclusively. Furthermore, the results lead us to conclude that, for most multimedia applications, it is better to pursue concurrency than parallelism in disk array organization.

Supporting random access on real-time retrieval of digital continuous media

In addition to the large data size requirement and real-time constraint in continuous media, future video applications such as video editing demand a random access capability at the video-frame level. This paper introduces our study on effective buffering control for the real-time retrieval of jitter-free digital video medium. We adopt a video-frame level approach to maintaining the flexibility on placement and analysing the efficiency of the buffering schemes. An integrated solution which offers efficient buffering schemes and flexible storage placement to support random access is our goal. We present two buffering schemes: the two-buffer scheme and the k-buffer compensation scheme. The two-buffer scheme requires that all the frames in a block are stored consecutively, while providing random access between blocks. However, this intuitive buffering scheme potentially requires a large block size and buffer space. The k-buffer compensation scheme is proposed to resolve this large buffer space requirement, by using more than two buffers and requiring a minimal number of blocks randomly placed in each cylinder. This scheme differs from the contiguous placement scheme because individual blocks can be stored anywhere in each cylinder. Compared to the two-buffer scheme, the k-buffer compensation scheme requires less buffer space, has higher disk utilization and finer granularity on disk data transfer. The placement requirements are more flexible and implementable than the contiguous and storage pattern placement schemes. Experimental measurement results reveal the significant improvements on the buffer-size reduction and placement flexibility by using the k-buffer compensation scheme. Extensions of the k-buffer compensation scheme to support multiple streams are also addressed.

Designing a multiuser HDTV storage server

The authors present a quantitative study of designing a multiuser HDTV server, and they present efficient techniques for storing multiple HDTV videos on disk and servicing multiple subscriber requests simultaneously, both under the constraint of guaranteeing HDTV playback rates. They develop a model that relates disk and device characteristics to the HDTV playback rate and derive a storage pattern for HDTV video streams that guarantees their real-time retrieval. Given multiple HDTV streams, mechanisms for merging their individual storage patterns are developed. Merging algorithms that yield a large improvement in space utilization over storing each of the streams independently are proposed. Policies such as round robin and quality proportional for servicing multiple subscribers simultaneously are studied. These studies provide a quantitative demonstration of the technological feasibility and economic viability of HDTV-on-demand servers on metropolitan area networks (MANs). >

Feedback Techniques for Intra-Media Continuity and Inter-Media Synchronization in Distributed Multimedia Systems

Future advances in networking and storage will make it feasible to build multimedia on-demand servers that provide services similar to those of a neighbourhood videotape rental store over metropolitan area networks such as B-ISDN. Such multimedia servers can support real-time retrieval of multimedia objects by users onto their ISDN videophones and audiophones for playback. The design of techniques and protocols for providing continuous and synchronous access to multimedia services constitutes the subject matter of this paper

Visual evoked potential: enhancing its utility.

The VEP can be used to assess the contributions of specific neuronal populations to visual processing heretofore evaluable only by microelectrode or psychophysical techniques. The first approach is not feasible in humans. The second is exquisitely sensitive and reliable when trained observers are studied. Psychophysical methods are subjective, requiring subject cooperation and understanding of threshold detection. These studies are often prolonged, with results inconsistent among patients in the clinic. The VEP offers an objective assessment of visual performance and permits quantification of deficits in acuity, contrast, and adaptation (especially when real-time retrieval is used), when one measures more than the latency.

情報処理の立場から

情報処理の立場から

Quasi real-time microwave holography

The advantages of real-time microwave holography are reviewed. Real-time capabilities require real-time acquisition of the raw hologram data and real-time retrieval of images from the collected data. This paper examines in detail the acquisition of microwave hologram data by double circular scanning of a single reciever in the context of quasi real-time operation. The principle of the double circular scan is presented and the effect of this sampling format on the retrieved image analyzed. Optical bench simulation of hologram recording employing this sampling format is also presented. It is shown that such a scanning format has the attractive properties of economy, speed (≃1 holographic frame/sec) and excellent retrieved image quality. Finally, the compatibility of the double circular scan format with scanned transmitter-receiver holography is discussed in the context of practical low-cost systems.

Retrieval of Atmospheric Temperature Profiles from Satellite Measurements for Dynamical Forecasting

The method of real-time retrieval of atmospheric temperature profiles from Nimbus IV Satellite Infrared Spectrometer observations currently used in dynamical weather analysis-forecast operation is described. Each vertical temperature profile is determined by its deviation from a “guess” profile. The deviation is expressed as a linear combination of differences between the measured radiances and those computed from the guess profile. The coefficients are estimated, by matrix inversion, from the weighting functions (i.e., derivatives of atmospheric transmittance functions), which are regularized by the ratio of the expected variance of the measurement errors to the expected variance of the errors in the guess profile. The deviations are iterated until the variance of the radiance residuals is less than the expected variance of the measurement errors. For weather analysis-forecast operation the dynamical forecast is used as the first guess; therefore, the calculated profiles should differ from the forecast profiles only when the measurable error in the forecast exceeds the instrumental noise level. The retrieved profiles are those which deviate least from the forecast in order to satisfy all the radiance observations. This property is well suited to dynamical forecasting in that it does not tend to produce erroneous atmospheric waves.