The scientific knowledge, in many areas, is obtained from time series analysis, which is usually done in two phases, preprocessing and data analysis. Trend extraction (detrending) is one important step of preprocessing phase, where many detrending software using different statistical methods can be applied for the same time series to correct them. In this context, the knowledge about time series data is relevant to the researcher to choose appropriate statistical methods to be used. Also the knowledge about how and how often the time series were corrected is essential for choice of detrending methods that can be applied to getting better results. This knowledge is not always explicit and easy to interpret. Provenance using Web Ontology Language -OWL ontologies contributes for helping the researcher to get knowledge about data and processes executed. Provenance information allows knowing as data were detrended, improving the decision making and contributing for generation of scientific knowledge. The main contribution of this paper is presenting the modular development of ontologies combined with Open Provenance Model -OPM, which is extended to facilitate the understanding about as detrending processes were executed in time series data, enriching semantically the preprocessing phase of time series analysis.

Investiga a automatização dos processos para a publicação de dados abertos científicos na Web de Dados. Metodologicamente, o trabalho é baseado no ciclo de vida Linked Data Lifecycle e suas tecnologias. Como resultado, apresenta-se um workflow automatizado para compartilhar dados primários. Conclui-se que o workflow é importante na preservação de dados científicos primários, suportando tanto as pesquisas científicas quanto o reuso de recursos sob os princípios de Dados Abertos Conectados.

No abstract

Time series data are generated all the time with a volume without precedent, constituting themselves of a points sequence spread out over time, usually at time regular intervals. Time series analysis is different from data analysis, given its intrinsic nature, where observations are dependent and the observations order is important for analysis. The knowledge about the data which will be analyzed is relevant in an analysis process, but this knowledge is not always explicit and easy to interpret in many information resources. Time series can be semantically enriched where provenance information using ontologies allows to representing and inferring knowledge. The main contribution of this paper is to present a domain ontology developed by modular design for time series provenance, which adds semantic knowledge and contributes to the choice of appropriate statistical methods for an important step of time series analysis that is the trend extraction (detrending). Trend is a time series component that needs be extracted because it can hide other phenomena, as well as the most statistical methods are developed for stationary time series. With this work, is intended to contribute for semantically improving the decision making about trend extraction step, facilitating the preprocessing phase of time series analysis.