Model Metric Co-Learning for Time Series Classification

Authors: Huanhuan Chen, Fengzhen Tang, Peter Tino, Anthony G. Cohn, Xin Yao

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on synthetic and benchmark data sets con firm the effectiveness of the algorithm compared to a variety of alternative methods.
Researcher Affiliation Academia Huanhuan Chen School of Computer Science, Univ. of Sci. & Tech. of China Hefei, Anhui, China hchen@ustc.edu.cn Fengzhen Tang, Peter Tino School of Computer Science University of Birmingham Birmingham, B15 2TT, UK fxt126,pxt@cs.bham.ac.uk Anthony G Cohn School of Computing University of Leeds Leeds, LS2 9JT, UK A.G.Cohn@leeds.ac.uk Xin Yao School of Computer Science University of Birmingham Birmingham, B15 2TT, UK X.Yao@cs.bham.ac.uk
Pseudocode No The paper describes the methodology using mathematical equations and prose but does not provide pseudocode or a clearly labeled algorithm block.
Open Source Code No The paper mentions external code for comparison methods but does not provide concrete access to the source code for the MMCL methodology described.
Open Datasets Yes We used 7 data sets from the UCR Time Series Repository [Keogh et al., 2011].
Dataset Splits Yes All (hyper) parameters, such as the MMCL trade-off parameter λ, order p in the AR kernel, number of hidden states in the HMM based Fisher kernel, regularization parameter η for ridge regression etc. have been set by 5-fold cross-validation on the training set.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions LIBSVM but does not provide specific version numbers for software dependencies needed to replicate the experiment.
Experiment Setup Yes In MMCL, the number of nodes was fixed to N = 50 and 10 jumps (making the jump length 5). All (hyper) parameters, such as the MMCL trade-off parameter λ, order p in the AR kernel, number of hidden states in the HMM based Fisher kernel, regularization parameter η for ridge regression etc. have been set by 5-fold cross-validation on the training set. The SVM parameters, kernel width γ in eq. (13) and C, were tuned in the following ranges: γ {10 6, 10 5, , 101}, C {10 3, 10 2, , 103}. We also tested our MMCL method using a k-NN classi fier where k {1, 2, , 10}.