1. This paper proposes a garden landscape design system based on deep neural network and multimodal intelligent computing.
2. The system uses pooling and convolution operations on garden landscape images to improve model accuracy.
3. The proposed method uses feature series fusion, maximum value fusion, and multiplicative fusion in the score layer to achieve a high accuracy rate of 77.1%.
The article is generally reliable and trustworthy as it provides evidence for its claims through experiments and simulations. The authors have used MATLAB software to extract spatiotemporal features from dynamic garden landscape images, which is an effective way of improving model accuracy. Furthermore, the authors have used feature series fusion, maximum value fusion, and multiplicative fusion in the score layer to achieve a high accuracy rate of 77.1%, which further supports their claims.
However, there are some points that could be improved upon in the article. For example, the authors do not provide any information about possible risks associated with their proposed system or any counterarguments that could be raised against it. Additionally, they do not present both sides of the argument equally; instead they focus solely on the advantages of their proposed system without exploring any potential drawbacks or limitations. Furthermore, there is no mention of any promotional content or partiality in the article which could lead to bias in its reporting.
In conclusion, while this article is generally reliable and trustworthy due to its evidence-based approach, there are some areas where it could be improved upon such as providing more information about possible risks associated with their proposed system or exploring counterarguments against it more thoroughly.