deletions | additions       diff --git a/_.tex b/_.tex  deleted file mode 100644  index 5b417c5..0000000  --- a/_.tex  +++ /dev/null 
...
}%  }  \begin{frontmatter}  \title{  Automated daily pattern filtering of measured building performance data   }  % \author{Clayton Miller}  \author{Clayton Miller\corref{cor1}}  \ead{[email protected]}  \cortext[cor1]{Corresponding author: Phone: +1-402-403-0090}  \author{Zolt\'an Nagy}  \author{Arno Schlueter}  \address{ETH Z\"urich, Institute of Technology in Architecture (ITA), Architecture and Sustainable Building Technologies (SuAT)}  \address{*Corresponding author: Phone: +1-402-403-0090, [email protected]}  \begin{abstract}  The amount of sensor data generated by modern building systems is growing rapidly. Automatically discovering the structure of diurnal patterns in this data supports implementation of building commissioning, fault detection and retrofit analysis techniques. Additionally, these data are crucial to informing design professionals about the efficacy of their assumptions and strategies used in performance prediction simulation models. In this paper, we introduce \emph{DayFilter}, an day-typing process that uses symbolic aggregate approximation (SAX), motif and discord extraction and clustering to detect the underlying structure of building performance data. Discords, or infrequent daily patterns, are filtered and tagged for deeper, detailed analysis of potential energy savings opportunities. Motifs, or the most frequent patterns, are detected and further aggregated using k-means clustering. This procedure is designed for application on whole building and sub-system metrics from hierarchical building and energy management systems (BMS/EMS). The process transforms quantitative raw data into qualitative subgroups based on daily performance similarity and visualizes them using expressive techniques. We apply \emph{DayFilter} on 474 days of example data from an international school campus in a tropical climate and 407 days of data from an office building from a temperate European climate. Discords were filtered resulting in 17 and 22 patterns were found. Selected discords were investigated and many correlated with specific failures and energy savings detected by the on-site operations staff. Six and ten motif candidates were detected in the two case studies. These motifs were then further aggregated to five and six performance clusters that reflect the typical operational behavior of those projects. Finally, we discuss the influence of the parameter choices and provide initial parameter settings for the \emph{DayFilter} process.\\  % We present the results of this implementation including an investigation of the discord days that were filtered and presentation of the basic performance modes.\\  % in a web-based interface  %Results of various validation experiments on the case studies shows that despite by only setting 2 screening model parameters we were able  %Partitioning clustering techniques are tested in the ability to appropriately capture the data structure. exposing trends of the time series data  \end{abstract}  \begin{keyword}  %% keywords here, in the form: keyword \sep keyword  Building efficiency \sep Building performance analysis \sep Knowledge discovery \sep Clustering \sep Temporal data mining \sep Occupancy patterns \sep Diversity factors  \end{keyword}  \end{frontmatter}  diff --git a/layout.md b/layout.md  index 4056d76..cda1eac 100644  --- a/layout.md  +++ b/layout.md 
...
abstract.tex  _.tex  sectionIntroduction_.tex  figures/D3_Combined_V3/default_figure.png  In_addition_to_the.tex