Classification of hypoglycemic episodes for Type 1 diabetes mellitus based on neural networks
Hypoglycemia is dangerous for Type 1 diabetes mellitus (T1DM) patients. Based on the physiological parameters, we have developed a classification unit with hybridizing the approaches of neural networks and genetic algorithm to identify the presences of hypoglycemic episodes for TIDM patients. The pr...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
IEEE
2010
|
| Online Access: | http://hdl.handle.net/20.500.11937/34068 |
| _version_ | 1848754121510748160 |
|---|---|
| author | Chan, Kit Yan Ling, S.H. Dillon, Tharam S. Nguyen, H. |
| author2 | Gary Fogel |
| author_facet | Gary Fogel Chan, Kit Yan Ling, S.H. Dillon, Tharam S. Nguyen, H. |
| author_sort | Chan, Kit Yan |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Hypoglycemia is dangerous for Type 1 diabetes mellitus (T1DM) patients. Based on the physiological parameters, we have developed a classification unit with hybridizing the approaches of neural networks and genetic algorithm to identify the presences of hypoglycemic episodes for TIDM patients. The proposed classification unit is built and is validated by using the real T1DM patients' data sets collected from Department of Health, Government of Western Australia. Experimental results show that the proposed neural network based classification unit can achieve more accurate results on both trained and unseen T1DM patients' data sets compared with those developed based on the commonly used classification methods for medical diagnosis including statistical regression, fuzzy regression and genetic programming. |
| first_indexed | 2025-11-14T08:35:22Z |
| format | Conference Paper |
| id | curtin-20.500.11937-34068 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:35:22Z |
| publishDate | 2010 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-340682017-09-13T15:52:03Z Classification of hypoglycemic episodes for Type 1 diabetes mellitus based on neural networks Chan, Kit Yan Ling, S.H. Dillon, Tharam S. Nguyen, H. Gary Fogel Hypoglycemia is dangerous for Type 1 diabetes mellitus (T1DM) patients. Based on the physiological parameters, we have developed a classification unit with hybridizing the approaches of neural networks and genetic algorithm to identify the presences of hypoglycemic episodes for TIDM patients. The proposed classification unit is built and is validated by using the real T1DM patients' data sets collected from Department of Health, Government of Western Australia. Experimental results show that the proposed neural network based classification unit can achieve more accurate results on both trained and unseen T1DM patients' data sets compared with those developed based on the commonly used classification methods for medical diagnosis including statistical regression, fuzzy regression and genetic programming. 2010 Conference Paper http://hdl.handle.net/20.500.11937/34068 10.1109/CEC.2010.5586320 IEEE fulltext |
| spellingShingle | Chan, Kit Yan Ling, S.H. Dillon, Tharam S. Nguyen, H. Classification of hypoglycemic episodes for Type 1 diabetes mellitus based on neural networks |
| title | Classification of hypoglycemic episodes for Type 1 diabetes mellitus based on neural networks |
| title_full | Classification of hypoglycemic episodes for Type 1 diabetes mellitus based on neural networks |
| title_fullStr | Classification of hypoglycemic episodes for Type 1 diabetes mellitus based on neural networks |
| title_full_unstemmed | Classification of hypoglycemic episodes for Type 1 diabetes mellitus based on neural networks |
| title_short | Classification of hypoglycemic episodes for Type 1 diabetes mellitus based on neural networks |
| title_sort | classification of hypoglycemic episodes for type 1 diabetes mellitus based on neural networks |
| url | http://hdl.handle.net/20.500.11937/34068 |