A Personalised Thermal Comfort Model Using a Bayesian Network

Authors: Frederik Auffenberg, Sebastian Stein, Alex Rogers

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Through an empirical evaluation based on the ASHRAE RP-884 data set, we show that our model is consistently 17.523.5% more accurate than current models, regardless of environmental conditions and the type of heating system used.
Researcher Affiliation Academia Frederik Auffenberg, Sebastian Stein and Alex Rogers Agents, Interaction and Complexity Research Group Electronics and Computer Science University of Southampton, UK {fa1c12,ss2,acr}@ecs.soton.ac.uk
Pseudocode No The paper describes the model using factor graphs (Figure 1, Figure 2) but does not include any pseudocode or algorithm blocks.
Open Source Code No The paper states 'We implement the model using the free library Infer.NET', and provides a URL for Infer.NET (http://research.microsoft.com/ en-us/um/cambridge/projects/infernet/), but does not provide a link or statement about the availability of the authors' own source code for their proposed methodology.
Open Datasets Yes To show the validity of our model and emphasize the need for more personalised models, we empirically evaluate it using existing longitudinal studies from the ASHRAE RP-884 project. The main parameters for each data set are shown in Table 3.
Dataset Splits No The paper states 'For those subsets, cross validation was performed using each single data point as an inference observation in separate evaluation runs, using random data points from the remaining data as training observations.' While it describes a cross-validation approach for training and testing, it does not specify explicit percentages or sample counts for a separate validation dataset split.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running the experiments.
Software Dependencies No The paper states 'We implement the model using the free library Infer.NET', but it does not specify a version number for Infer.NET or any other software dependencies.
Experiment Setup Yes For data sets with a lot of data points per individual (Pakistan and Athens), the amount of training observations was increased in steps of 2 for values between 2 and 30. For San Francisco, the amount was increased in steps of 1 between 1 and the maximum possible observation count (number of observations 1). ... The priors for the mean have a Gaussian distribution, the priors for the precision a gamma distribution. ... model parameters are fully relearned with every new training observation.