| Abstract |
Pattern Recognition and Classification present a comprehensive introduction to the core concepts involved in automated pattern recognition and classification. There are four best-known approaches for pattern recognition such as template matching, statistical classification, syntactic or structural matching, and neural networks. The main characteristics of neural networks are that they have the ability to learn complex nonlinear input-output relationships, use sequential training procedures, and adapt themselves to the data. Artificial neural networks are computational models that presented as systems of interconnected "neurons" that can compute values from inputs by feeding information through the network. An artificial neural network is configured for a specific application, such as pattern recognition or data classification, through a learning process. Like other machine learning methods, neural networks have been used to solve a wide variety of tasks that are hard to solve using ordinary rule-based programming. In geothermal operation, such application has been utilized for determining (predicting) a geothermal power plant performance under broad range of operating conditions. Other than that, the application of artificial neural networks can also be utilized for predicting Bit condition in geothermal drilling, as an accurate determination of drill bit condition can effectively decrease drilling cost of a geothermal well. An artificial neural network can also be used for estimation of static formation temperatures in geothermal wells, and even for optimization of re-injection in low-temperature geothermal reservoirs. |