Plaster: an integration, benchmark, and development framework for metadata normalization methods

Plaster: an integration, benchmark, and development framework for metadata normalization methods
复制标题

Plaster:元数据标准化方法的集成、基准测试和开发框架

DOI:
10.1145/3276774.3276794
复制
发表时间:
2018
期刊:
Proceedings of the 5th Conference on Systems for Built Environments
影响因子:
--
通讯作者:
Agarwal, Yuvraj
Agarwal, Yuvraj
中科院分区:
--
文献类型:
--
作者:
Koh, Jason;Hong, Dezhi;Gupta, Rajesh;Whitehouse, Kamin;Wang, Hongning;Agarwal, Yuvraj

文献摘要

参考文献

被引文献

相似文献

元数据规范化自动化的最新进展和统一模式Brick的发明减轻了跨建筑物部署便携式应用程序的元数据规范化挑战。然而,现有的元数据规范化方法之间缺乏兼容性,排除了比较和组合它们的可能性。虽然通用机器学习(ML)框架,如MLML和OpenML,为标准ML问题提供了通用接口,但由于推理范围的异质性,输入所需的数据类型,评估指标以及建筑特定的人在环学习过程,它们无法轻松适应建筑物的元数据规范化任务。这是一个开放的模块化框架,它结合了构建元数据标准化方面的现有进展。它为元数据规范化的各种学习方法提供了统一的编程接口,并定义了用于构建元数据和时间序列数据的标准化数据模型。因此,它可以通过工作流集成不同的方法,通过统一的接口对不同的方法进行基准测试,并快速原型化新算法。使用Plaster,我们1)展示了三个工作流集成的示例,提供了比单个算法更好的性能,2)在五个常见建筑物上对五个算法进行基准测试/分析,以及3)验证了开发涉及时间序列特征的新算法的过程。我们相信Plaster将促进新算法的开发,并加快采用标准元数据模式,如Brick,以便在未来实现无缝的智能建筑应用。
The recent advances in the automation of metadata normalization and the invention of a unified schema --- Brick --- alleviate the metadata normalization challenge for deploying portable applications across buildings. Yet, the lack of compatibility between existing metadata normalization methods precludes the possibility of comparing and combining them. While generic machine learning (ML) frameworks, such as MLJAR and OpenML, provide versatile interfaces for standard ML problems, they cannot easily accommodate the metadata normalization tasks for buildings due to the heterogeneity in the inference scope, type of data required as input, evaluation metric, and the building-specific human-in-the-loop learning procedure.We propose Plaster, an open and modular framework that incorporates existing advances in building metadata normalization. It provides unified programming interfaces for various types of learning methods for metadata normalization and defines standardized data models for building metadata and timeseries data. Thus, it enables the integration of different methods via a workflow, benchmarking of different methods via unified interfaces, and rapid prototyping of new algorithms. With Plaster, we 1) show three examples of the workflow integration, delivering better performance than individual algorithms, 2) benchmark/analyze five algorithms over five common buildings, and 3) exemplify the process of developing a new algorithm involving time series features. We believe Plaster will facilitate the development of new algorithms and expedite the adoption of standard metadata schema such as Brick, in order to enable seamless smart building applications in the future.
DOI: 10.1016/j.neucom.2018.03.067
发表时间: 2018-09-13
期刊: NEUROCOMPUTING
影响因子: 6
作者:
Christ, Maximilian;Braun, Nils;Kempa-Liehr, Andreas W.
通讯作者: Kempa-Liehr, Andreas W.
DOI: 10.1145/3159652.3159681
发表时间: 2018-02
期刊: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining
影响因子: --
作者:
Longqi Yang;Eugene Bagdasaryan;Joshua Gruenstein;C. Hsieh;D. Estrin
通讯作者: Longqi Yang;Eugene Bagdasaryan;Joshua Gruenstein;C. Hsieh;D. Estrin
对空气处理机组传感器的自动元数据推理方法的大规模评估
DOI: 10.1016/j.aei.2018.04.010
发表时间: 2018
期刊: Adv. Eng. Informatics
影响因子: --
作者:
Jingkun Gao;M. Berges
通讯作者: M. Berges
使用异构数据模型和楼宇自动化系统的 HVAC 系统集成性能分析框架
DOI: --
发表时间: 2012
期刊: BuildSys@SenSys
影响因子: --
作者:
Xuesong Liu;B. Akinci;M. Berges;J. Garrett
通讯作者: J. Garrett
Genie:比较办公楼物理恒温器和软件恒温器的纵向研究
DOI: --
发表时间: 2016
期刊: Ubiquitous Computing
影响因子: --
作者:
Bharathan Balaji;Jason Koh;Nadir Weibel;Yuvraj Agarwal
通讯作者: Yuvraj Agarwal