Unsupervised Machine Condition Monitoring Using Segmental Hidden Markov Models
Authors: Chao Yuan
IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We propose an unsupervised approach based on segmental hidden Markov models. Our method has a unifying observation model integrating three pieces of information that are complementary to each other. ... The advantages of the proposed model are demonstrated by tests on gas turbine, truck and honeybee datasets. ... We present test results in Sect.4 and conclude this paper in Sect.5. ... A variety of tests are conducted to show the effectiveness of the proposed model. |
| Researcher Affiliation | Industry | Chao Yuan Siemens Corporation, Corporate Technology, Princeton, NJ 08540 yuanchao@yahoo.com |
| Pseudocode | No | The paper describes the training process using mathematical equations and narrative text but does not include a dedicated pseudocode block or algorithm. |
| Open Source Code | No | The paper does not provide any links to source code or explicitly state that the code is publicly available. |
| Open Datasets | Yes | For the honeybee data set, the paper cites '[Oh et al., 2008] S. M. Oh, J. M. Rehg, T. Balch, and F. Dellaert. Learning and inferring motion patterns using parametric segmental switching linear dynamic systems. International Journal of Computer Vision, 77:103 124, 2008.', indicating the use of a dataset from a published and citable source. |
| Dataset Splits | No | The paper describes using an EM algorithm for training and a leave-one-out strategy for some tests (which implies training and testing), but it does not specify a separate 'validation' dataset split for hyperparameter tuning or model selection. |
| Hardware Specification | No | The paper does not provide any specific details regarding the hardware (e.g., GPU, CPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper states 'All above models are implemented in matlab.' but does not specify a version number for Matlab or any other software libraries. |
| Experiment Setup | Yes | For all tests conducted, we set the order of the polynomial function R = 1 and order of the autoregressive component Q = 1. The initial number of states is set to M = 10. |