DeepSchema: Automatic Schema Acquisition from Wearable Sensor Data in Restaurant Situations
Authors: Eun-Sol Kim, Kyoung-Woon On, Byoung-Tak Zhang
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | For the experiments, we collected sensory data using multiple wearable devices in restaurant situations. The experimental results demonstrate the real hierarchical schemas, which are probabilistic scripts and action primitives, constructed from the methods. |
| Researcher Affiliation | Academia | Eun-Sol Kim, Kyoung-Woon On and Byoung-Tak Zhang Department of Computer Science and Engineering Cognitive Robotics Artiļ¬cial Intelligence Center (CRAIC) Seoul National University Seoul 151-744, Korea |
| Pseudocode | No | The paper describes learning methods with equations but does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement about making its source code available, nor does it include any links to a code repository. |
| Open Datasets | No | The paper describes collecting a multi-modal sensory dataset ('7 datasets are collected and each dataset is composed of approximately 4000 seconds of 5 heterogeneous stream data'), but it does not provide any specific link, DOI, repository name, or formal citation for public access to this dataset. |
| Dataset Splits | No | The paper states, 'Due to the huge size of the data set, we did not used cross validation but instead randomly divided and assigned the data set into training or test set,' but it does not provide specific percentages or counts for a validation split. |
| Hardware Specification | No | The paper mentions 'multiple wearable devices' used for data collection (e.g., 'eye tracker', 'watch-type wearable sensor') but provides no specific details about the hardware used to run the experiments or train the models (e.g., GPU/CPU models, memory). |
| Software Dependencies | Yes | The suggested model is implemented with Theano framework [Bastien et al., 2012]. |
| Experiment Setup | No | The paper describes the model and data preprocessing, but it does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size, number of epochs) or optimizer settings. |