Neural network technologies are successfully used in solving problems from various areas of the economy - industry, agriculture, medicine. The problems of substantiating the choice of architecture and hyperparameters of artificial neural networks (ins) aimed at solving various classes of applied problems are caused by the need to improve the quality and speed of deep ins training. Various methods of optimizing ins hyperparameters are known, for example, using genetic algorithms, but this requires writing additional software. To optimize the process of selecting hyperparameters, Google research has developed the KerasTuner Toolkit, which is a user-friendly platform for automated search for optimal hyperparameter combinations. In the described Kerastuner Toolkit, you can use random search, Bayesian optimization, or Hyperband methods. In numerical experiments, 14 hyperparameters varied: the number of blocks of convolutional layers and their forming filters, the type of activation functions, the parameters of the «dropout» regulatory layers, and others. The studied tools demonstrated high optimization efficiency while simultaneously varying more than a dozen parameters of the convolutional network, while the calculation time on the Colaboratory platform for the studied INM architectures was several hours, even with the use of GPU graphics accelerators. For ins focused on processing and recognizing text information in natural language (NLP), the recognition quality has been improved to 83-92%.
The results of the analytical review of the use of unmanned aerial vehicles (UAVs) and artificial neural networks in agricultural production are presented. They can be used as aerial robots that perform the function of aerial photography, transportation of technological components, such as plant protection products and perform other similar functions. On the aircraft, some other functional equipment can be installed: thermal imagers, multispectral and IR cameras, etc. With the help of the data obtained from the UAV, it is possible to create an orthophotoplan or 3D model of the terrain, create a map of heights, determine the state of the field, crops and determine their vegetation indices NDVI. The multi-level classification of areas of application of UAVs in agricultural production is proposed. Classification involves the ordering of areas of application of UAV in agriculture depending on the composition in use. A conceptual model of a software package designed to obtain and process remote sensing data using UAVs in different parts of the spectrum has been developed. The software package is designed to obtain and process the results of monitoring and subsequent analysis of the totality of the calculated vegetation indices. The main research tasks solved by the developed software, which determine its structure, are formulated. To predict the yield of different crops, a method of applying the results of aerial photography in conjunction with experimental data on the biological development of crops has been developed. For the practical use of the developed methodology, a database for each culture is formed. The obtained results are used to construct regression and matrix mathematical models of the relationship of optical-spectral characteristics with the productivity of crops.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.