Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss Predictions

This paper analyzes the use of artificial neural networks (ANNs) for predicting the received power/path loss in both outdoor and indoor links. The approach followed has been a combined use of ANNs and ray-tracing, the latter allowing the identification and parameterization of the so-called dominant path. A complete description of the process for creating and training an ANN-based model is presented with special emphasis on the training process. More specifically, we will be discussing various techniques to arrive at valid predictions focusing on an optimum selection of the training set. A quantitative analysis based on results from two narrowband measurement campaigns, one outdoors and the other indoors, is also presented.

Cooperative artificial propagation programs for salmon and steelhead, 1995-1996

Fifteen cooperative fish rearing and planting programs for salmon and steelhead were active from July 1, 1995 through June 30, 1996. For all programs, 134,213 steelhead trout,(Oncorhynchus mykiss), 7,742,577 chinook salmon,(~ tshawytscha),and 25,075 coho salmon(~ kisutch) were planted. (PDF contains 26 pages.)

Cooperative artificial propagation programs for salmon and steelhead, 1996-1997

Fourteen cooperative fish rearing and planting programs for salmon and steelhead were active from July 1, 1996 through June 30, 1997. For all programs, 208,922 steelhead trout, (Oncorhynchus mykiss), 10,334,457 chinook salmon,(O. tshawytscha),and 60,681 coho salmon(O. kisutch) were planted. (PDF contains 24 pages.)