Accurate Household Occupant Behavior Modeling Based on Data Mining Techniques

Authors: Márcia Baptista, Anjie Fang, Helmut Prendinger, Rui Prada, Yohei Yamaguchi

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Using real data from four households in Japan we are able to show that our model outperforms the traditional Markov chain model with respect to occupant coordination and generalization of behavior patterns. (...) Next, we compare the performance of traditional Markov chains to our model using real data of household occupant behavior.
Researcher Affiliation Academia Marcia Baptista, Anjie Fang, Helmut Prendinger National Institute of Informatics 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430, Japan (...) Rui Prada INESC-ID and Instituto Superior Tecnico, Universidade de Lisboa Av. Prof. Cavaco Silva, Taguspark Porto Salvo, Portugal (...) Yohei Yamaguchi Sustainable Energy and Environmental Engineering Graduate School of Engineering, Osaka University 2-1 Yamada-oka, Suita, Osaka 565-0871, Japan
Pseudocode Yes Algorithm 1 Calculating distance of activities
Open Source Code No The paper does not provide an explicit statement or link for open-source code for the described methodology.
Open Datasets No The data used in our experiment was collected from four households in the region of Osaka, Japan, in late 2011 and beginning of 2012. The paper does not provide concrete access information (link, DOI, repository, or citation) for this dataset, as it was collected by the authors and is not indicated as publicly available.
Dataset Splits No The paper describes a validation methodology, but it does not provide specific details on how the dataset itself was split into training, validation, and testing subsets for model development and evaluation. It mentions assessing accuracy by comparing output with original data.
Hardware Specification No The paper does not provide specific details about the hardware used to run the experiments, such as CPU or GPU models, or memory specifications.
Software Dependencies No The paper mentions the Apriori algorithm but does not specify any software dependencies with version numbers for implementation (e.g., Python 3.x, scikit-learn x.x, or specific library versions).
Experiment Setup Yes Each of the four households is simulated using the MC model and the NN model (σ2 = 0.002). In each simulation of a household, the daily activities of the occupants are reproduced for a period of 500 days.