WiFi-Based Human Identification via Convex Tensor Shapelet Learning

Authors: Han Zou, Yuxun Zhou, Jianfei Yang, Weixi Gu, Lihua Xie, Costas Spanos

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments are conducted in multiple real-world indoor environments, showing that Auto ID achieves an average human identification accuracy of 91% from a group of 20 people.
Researcher Affiliation Academia Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore Tsinghua-Berkeley Shenzhen Institute, Tsinghua University, China
Pseudocode No The paper describes the optimization method mathematically and textually but does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not include an unambiguous statement about releasing the source code for the methodology described in the paper, nor does it provide a direct link to a code repository.
Open Datasets No The paper describes a custom-collected dataset involving 20 human subjects walking in various indoor environments ('all the 20 subjects walked at arbitrary pace through the LOS of TX-RX pair for 10 times on one day (T1)...'), but it does not provide concrete access information (link, DOI, repository, or formal citation) for public availability of this dataset.
Dataset Splits Yes In all the above experiments we have used an optimal value obtained from 10-folds cross validation (CV).
Hardware Specification No The paper specifies the Wi-Fi routers used for data collection ('two TPLINK N750 routers'), but it does not provide specific hardware details (like GPU/CPU models, processor types, or memory) used for training or evaluating the models.
Software Dependencies No The paper mentions 'Open Wrt' as the OS and refers to upgrading the 'Atheros CSI Tool', but it does not provide specific version numbers for these or any other software components used for implementing the models or running experiments.
Experiment Setup No The paper states that 'The choice of the four hyperparameters, λ, ρ1, ρ2, ρ3, in the objective equation 3 are crucial for the performance of C3SL' and that 'an optimal value obtained from 10-folds cross validation (CV)' was used. However, it does not explicitly state these optimal hyperparameter values or other computational training details like learning rates or batch sizes.