No abstract

No abstract

No abstract

This paper proposes a new technique to train neural network (NN); with the result, we can solve some real-world application problems such as microwave components modeling and optimization. Its major advance is achieved in avoiding the testing error falling into local minimum. After the generalization, the ability of three-layer and four-layer NN is also checked; our investigations show that four-layer NN trained by the proposed training method can map the electromagnetic simulation of microwave components better than its counterpart. Besides, the modeling of microwave circuits and slotted patch antennas is examined to demonstrate the validity of this technique.

The genus Orthobittacus was established by Willmann (1989) and is characterised by a long Sc vein and the unusually developed medial sector for the Bittacidae. Four Jurassic species have been described in this genus to date: O. abshiricus (Martynova, 1951) from Kirgizia; O.desacuminatus (Bode, 1953) from Braunschweig (Germany); O. polymitus Novokshonov, 1996 from Karatau (Kazakhstan); and O. maculosus Liu, Shih, Bashkuev & Ren, 2016 from the Jiulongshan Formation of Daohugou (China). The fifth congeneric and second species from China, O. suni sp. nov., is described herein. The importance of the genus Orthobittacus for the phylogeny of Bittacidae, as the most plesiomorphic genus, is discussed.