|Hughs, Sidney - Hughs Ed|
Submitted to: Midwest Symposium on Circuits and Systems
Publication Type: Proceedings
Publication Acceptance Date: 5/5/1999
Publication Date: N/A
Citation: N/A Interpretive Summary: Research at the Southwestern Cotton Ginning Research Laboratory (SWCGRL) has resulted in improving our ability to identify trash categories of bark1 (fibrous), bark2 (non-fibrous), leaf, and pepper in cotton. The correlation between computed trash content and AMS measures of 100 cotton samples are reported.
Technical Abstract: The paper discusses the use of soft computing techniques such as neural networks and Fuzzy Logic based approaches in the identification of various types of trash (non-lint material/foreign matter), and the computation of trash content in ginned cotton. Lint is the cotton fiber; non-lint or foreign matter is everything other than lint. Trash content is the percentage of sample surface covered by non-lint particles. The effectiveness of a hybrid neuro-fuzzy structure, namely the Adaptive Network-Based Fuzzy Inference System (ANFIS) to classify trash types is compared with other techniques.