Rule - Extraction from trained neural networks : Di erent techniques for the determination ofherbicides for the plant protection
نویسندگان
چکیده
The Department of Computer Science in Agriculture at the University of Mnster (DCSA-UMG) has developed and implemented the plant protection advisory system PRO PLANT in cooperation with the Department for Plant Protection, Seed testing and Agriculture Research (DPSAR) (a government and farmer aided institution in Westfalia). The system was nancially supported by the Ministry for Environment, Regional Planing and Agriculture of North Rhine Westfalia. The system runs ooine on a PC under Windows 3.x. It is a knowledge-based system which supports fungicide and growth-regulator consultations for cereal and sugar beet production. In addition it provides consultations on insecticide usage in rape, and herbicide usage in corn (Visser et al 1994). The system incorporates a multilayer-feedforward Artiicial Neural Network (ANN). However a recognised limitation of ANNs is their inability to explain in a human-comprehensible form, how a given decision has been reached. In this article we investigate the application of a set of techniques (RuleNeg, RULEX (Andrews et al 1995), LAP (Hayward et al 1996)) for extracting the knowledge embedded in the trained ANN as a set of symbolic rules. The results are compared with those produced by applying a symbolic induction algorithm OSL (Orlowski 1993) directly to the data.
منابع مشابه
Knowledge Extraction from the Neural ‘Black Box’ in Ecological Monitoring
Phytoplankton biomass within the Saginaw Bay ecosystem (Lake Huron, Michigan, USA) was characterized as a function of select physical/chemical indicators. The complexity and variability of ecological systems typically make it difficult to model the influences of anthropogenic stressors and/or natural disturbances. Here, Artificial Neural Networks (ANNs) were developed to model chlorophyll a con...
متن کاملOptimization of Oleuropein Extraction from Olive Leaves using Artificial Neural Network
In this work, the artificial neural networks (ANN) technology was applied to the simulation of oleuropein extraction process. For this technology, a 3-layer network structure is applied, and the operation factors such as amount of flow intensity ratio, temperature, residence time, and pH are used as input variables of the network, whereas the extraction yield is considere...
متن کاملClassification of Data to Extract Knowledge from Neural Networks
A major drawback of artificial neural networks is their black-box character. Therefore, the rule extraction algorithm is becoming more and more important in explaining the extracted rules from the neural networks. In this paper, we use a method that can be used for symbolic knowledge extraction from neural networks, once they have been trained with desired function. The basis of this method is ...
متن کاملThe Extraction of Re ned Rules from Knowledge - Based Neural Networks
Neural networks, despite their empirically-proven abilities, have been little used for the renement of existing knowledge because this task requires a three-step process. First, knowledge in some form must be inserted into a neural network. Second, the network must be re ned. Third, knowledge must be extracted from the network. We have previously described a method for the rst step of this proc...
متن کاملComparative analysis of different approaches to target differentiation and localization with sonar
This study compares the performances of di erent methods for the di erentiation and localization of commonly encountered features in indoor environments. Di erentiation of such features is of interest for intelligent systems in a variety of applications such as system control based on acoustic signal detection and identi/cation, map building, navigation, obstacle avoidance, and target tracking....
متن کامل