ترغب بنشر مسار تعليمي؟ اضغط هنا

VStore: A Data Store for Analytics on Large Videos

100   0   0.0 ( 0 )
 نشر من قبل Tiantu Xu
 تاريخ النشر 2018
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

We present VStore, a data store for supporting fast, resource-efficient analytics over large archival videos. VStore manages video ingestion, storage, retrieval, and consumption. It controls video formats along the video data path. It is challenged by i) the huge combinatorial space of video format knobs; ii) the complex impacts of these knobs and their high profiling cost; iii) optimizing for multiple resource types. It explores an idea called backward derivation of configuration: in the opposite direction along the video data path, VStore passes the video quantity and quality expected by analytics backward to retrieval, to storage, and to ingestion. In this process, VStore derives an optimal set of video formats, optimizing for different resources in a progressive manner. VStore automatically derives large, complex configurations consisting of more than one hundred knobs over tens of video formats. In response to queries, VStore selects video formats catering to the executed operators and the target accuracy. It streams video data from disks through decoder to operators. It runs queries as fast as 362x of video realtime.



قيم البحث

اقرأ أيضاً

124 - Pengfei Liu 2021
With new emerging technologies, such as satellites and drones, archaeologists collect data over large areas. However, it becomes difficult to process such data in time. Archaeological data also have many different formats (images, texts, sensor data) and can be structured, semi-structured and unstructured. Such variety makes data difficult to collect, store, manage, search and analyze effectively. A few approaches have been proposed, but none of them covers the full data lifecycle nor provides an efficient data management system. Hence, we propose the use of a data lake to provide centralized data stores to host heterogeneous data, as well as tools for data quality checking, cleaning, transformation, and analysis. In this paper, we propose a generic, flexible and complete data lake architecture. Our metadata management system exploits goldMEDAL, which is the most complete metadata model currently available. Finally, we detail the concrete implementation of this architecture dedicated to an archaeological project.
Next Generation Sequencing (NGS) technology has resulted in massive amounts of proteomics and genomics data. This data is of no use if it is not properly analyzed. ETL (Extraction, Transformation, Loading) is an important step in designing data analy tics applications. ETL requires proper understanding of features of data. Data format plays a key role in understanding of data, representation of data, space required to store data, data I/O during processing of data, intermediate results of processing, in-memory analysis of data and overall time required to process data. Different data mining and machine learning algorithms require input data in specific types and formats. This paper explores the data formats used by different tools and algorithms and also presents modern data formats that are used on Big Data Platform. It will help researchers and developers in choosing appropriate data format to be used for a particular tool or algorithm.
Smart meters are increasingly used worldwide. Smart meters are the advanced meters capable of measuring energy consumption at a fine-grained time interval, e.g., every 15 minutes. Smart meter data are typically bundled with social economic data in an alytics, such as meter geographic locations, weather conditions and user information, which makes the data sets very sizable and the analytics complex. Data mining and emerging cloud computing technologies make collecting, processing, and analyzing the so-called big data possible. This paper proposes an innovative ICT-solution to streamline smart meter data analytics. The proposed solution offers an information integration pipeline for ingesting data from smart meters, a scalable platform for processing and mining big data sets, and a web portal for visualizing analytics results. The implemented system has a hybrid architecture of using Spark or Hive for big data processing, and using the machine learning toolkit, MADlib, for doing in-database data analytics in PostgreSQL database. This paper evaluates the key technologies of the proposed ICT-solution, and the results show the effectiveness and efficiency of using the system for both batch and online analytics.
In recent years, there has been a substantial amount of work on large-scale data analytics using Hadoop-based platforms running on large clusters of commodity machines. A less-explored topic is how those data, dominated by application logs, are colle cted and structured to begin with. In this paper, we present Twitters production logging infrastructure and its evolution from application-specific logging to a unified client events log format, where messages are captured in common, well-formatted, flexible Thrift messages. Since most analytics tasks consider the user session as the basic unit of analysis, we pre-materialize session sequences, which are compact summaries that can answer a large class of common queries quickly. The development of this infrastructure has streamlined log collection and data analysis, thereby improving our ability to rapidly experiment and iterate on various aspects of the service.
Scientific discoveries are increasingly driven by analyzing large volumes of image data. Many new libraries and specialized database management systems (DBMSs) have emerged to support such tasks. It is unclear, however, how well these systems support real-world image analysis use cases, and how performant are the image analytics tasks implemented on top of such systems. In this paper, we present the first comprehensive evaluation of large-scale image analysis systems using two real-world scientific image data processing use cases. We evaluate five representative systems (SciDB, Myria, Spark, Dask, and TensorFlow) and find that each of them has shortcomings that complicate implementation or hurt performance. Such shortcomings lead to new research opportunities in making large-scale image analysis both efficient and easy to use.
التعليقات
جاري جلب التعليقات جاري جلب التعليقات
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا