Tea plant cultivar identification is normally achieved manually or by spectroscopic, chromatographic, and other methods that are time-consuming often inaccurate. In this paper, a method for the of three tea cultivars with similar leaf morphology proposed using transfer learning five pre-trained models: EfficientNet-B0, MobileNetV2, MobileNetV3, MobileViT-S, ShuffleNetV2. The results showed best...

Failure of joints can lead to structural collapse. It is vital monitor joint stiffness during operation prevent such failures. This paper proposes a novel method for the quality assessment using coaxial correlation in 6D space. Coaxially placed sensors on either side implemented by 3D accelerometers and gyroscopes with wide frequency range, automatic synchronisation between input signal receive...

The article is devoted to the issue of improving coordinate registration information in means automated non-destructive testing. Existing systems non-contact spatial position sensors testing are mostly focused on use signal fields different physical nature, for example, acoustic or optical, which created around these and amplitude methods processing. These do not provide necessary accuracy dete...