Daytime Sleepiness Level Prediction Using Respiratory Information

Authors: Kazuhiko Shinoda, Masahiko Yoshii, Hayato Yamaguchi, Hirotaka Kaji

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the performance of our models through a comprehensive experiment.
Researcher Affiliation Industry Kazuhiko Shinoda , Masahiko Yoshii , Hayato Yamaguchi and Hirotaka Kaji Frontier Research Center, Toyota Motor Corporation {kazuhiko shinoda, masahiko yoshii, hayato yamaguchi aa, hirotaka kaji}@mail.toyota.co.jp
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements or links indicating the release of open-source code for the described methodology.
Open Datasets No The paper describes a custom dataset collected by the authors ("we collected a set of respiration and acceleration data..."), but provides no information or links for public access to this dataset.
Dataset Splits Yes We used the leave-one-subject-out cross validation (LOSO-CV) [Bao and Intille, 2004] to ensure the evaluation under more practical conditions. In our LOSO-CV, the samples of 17 subjects were used for training the model and the remaining one subject s samples were used as the test set.
Hardware Specification No The paper mentions devices used for data collection (e.g., 'Android tablet', 'wearable respiration sensor'), but does not specify the hardware used to run the computational experiments (e.g., GPU/CPU models, memory).
Software Dependencies No The paper lists machine learning methods (e.g., SVM, RF, NN) and models (HMM) used, but does not provide specific software library names with version numbers required for reproducibility.
Experiment Setup Yes The hidden layer of NN consisted of four nodes with the sigmoid function. and We set the lower bound of the passband frequency to 0.05 Hz... The upper bound frequency was chosen so that the filtered waveforms reflect important features of raw waveforms. We found from the preliminary experiment that 2.5 Hz was the optimal frequency for balancing noise reduction and the preservation of the original waveform features. and All the extracted features were normalized to have zero mean and unit standard deviation... and The candidate features were ranked based on the importance and we included the best four features in our experimental models.