A Novel Distribution-Embedded Neural Network for Sensor-Based Activity Recognition

Authors: Hangwei Qian, Sinno Jialin Pan, Bingshui Da, Chunyan Miao

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments are conducted on four datasets to demonstrate the effectiveness of our proposed method compared with state-of-the-art baselines.
Researcher Affiliation Academia 1School of Computer Science and Engineering 2Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly 3Interdisciplinary Graduate School Nanyang Technological University, Singapore
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Code of the proposed DDNN is available at https://github.com/Hangwei12358/IJCAI2019 DDNN.
Open Datasets Yes We conduct experiments on four sensor-based activity datasets... The Daphnet Gait dataset (DG) [B achlin et al., 2010]... The Opportunity dataset (OPPOR) [Chavarriaga et al., 2013]... The UCIHAR dataset [Anguita et al., 2012]... The PAMAP2 dataset [Reiss and Stricker, 2012]
Dataset Splits Yes We randomly split activities into training set {(Xi, yi)}n i=1, validation set {(Xj, yj)}m j=1 and test set {Xt}p t=1... run 2 from subject 1 as validation set, runs 4 and 5 from subject 2 and 3 as test set and the rest as training set.
Hardware Specification Yes All experiments are run on a Tesla V100 GPU.
Software Dependencies No The paper mentions the use of Adam optimizer and ReLU activation functions but does not specify any software or library versions (e.g., Python, PyTorch, TensorFlow, scikit-learn versions).
Experiment Setup Yes The batch size is set to 64, and the maximum training epoch is 100. Adam optimizer is used for training with learning rate 10 3 and weight decay 10 3. Both LSTMs in spatial and temporal module have l layers of LSTMs with h-dimensional hidden representations, where l {1, 2, 3} and h {32, 64, 128, 256, 512, 1024}. Four convolutional layers with filter size (1, 5) are utilized in the temporal module.