Decomposing Activities of Daily Living to Discover Routine Clusters
Authors: Onur Yürüten, Jiyong Zhang, Pearl Pu
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We validate our approach using two real-life ADL datasets and a well-known artificial dataset. Based on average silhouette width scores, our approach can capture strong structures in the underlying data. Furthermore, results show that our approach improves on the accuracy of the baseline algorithms by 12% with a statistical significance (p <0.05) using the Wilcoxon signed-rank comparison test. |
| Researcher Affiliation | Academia | 1Human Computer Interaction Group,2Artificial Intelligence Laboratory Ecole Polytechnique F ed erale de Lausanne (EPFL), Station 14 Lausanne, Switzerland CH 1015 {onur.yuruten,jiyong,zhang,pearl.pu}@epfl.ch |
| Pseudocode | No | No structured pseudocode or algorithm blocks (clearly labeled algorithm sections or code-like formatted procedures) were found. |
| Open Source Code | No | No explicit statement about releasing source code or providing a link to a code repository for the described methodology was found. |
| Open Datasets | Yes | CBF Dataset. This artificial dataset (Keogh and Kasetty 2003) contains time series objects that belong to one of three distinct shape characteristics (i.e., Cylinder c(t), Bell b(t) and Funnel f(t), see Figure 2). |
| Dataset Splits | Yes | Since CBF dataset contains labels, we also evaluated CBF dataset s output clusters with external evaluation indices (accuracy, F-1 score, normalized mutual information and Jaccard index) with 10-fold cross validation. |
| Hardware Specification | No | No specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments were found. |
| Software Dependencies | No | No specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, CPLEX 12.4) needed to replicate the experiment were found. |
| Experiment Setup | Yes | The representatives for each cluster (...), and the selected values for the parameters λ and γ are shown in Figure 4. The clusters for the E-Walk dataset (λ = 100 and γ = 0.065). The clusters for the Healthy Together dataset (λ = 100 and γ = 0.026). |