Fuzzy DIFACONN-miner: A novel approach for fuzzy rule extraction from neural networks
Introduction
Artificial neural network is a mathematical or computational model based on biological neural networks. In most cases, an ANN is an adaptive system that changes its structure based on internal and external information that flows through the network during the learning process. Even in the case of an element of the neural network failing, it has the ability to continue learning without any problem through their parallel structure. In addition, ANNs can tolerate incomplete or noisy inputs. These characteristics make ANNs a convenient tool for classification and prediction.
However, classification and function approximation concepts of ANNs are usually incomprehensible to the end user. This is because typical ANN solutions consist of a large number of interacting non-linear elements, characterized by large sets of real-valued parameters that are difficult to interpret. Distributed internal representations make it even more difficult to understand what exactly an ANN has learned and where it will fail to generate the correct answer (Kuttuyil, 2004). Because of this fact, many researchers tend to develop humanly understandable representations of ANNs. This can be achieved by extracting production rules from trained ANNs (Huang & Xing, 2002).
Algorithms for rule extraction from ANNs are grouped into three categories. The first category is the decompositional approach that involves rule extraction at the level of hidden and output units, which are mapped in a binary form (Hruschka & Ebecken, 2006). The second is the pedagogical approach which attempts to map inputs directly into outputs, and views ANNs as a black-box. Finally, the eclectic approach incorporates elements of both pedagogical and decomposition techniques.
Besides these approaches, researchers also extended the scope of rule extraction algorithms from ANNs so as to incorporate the fuzziness in rules (Huang and Xing, 2002, Muslimi et al., 2006, Quteishat and Lim, 2008). The motivation behind this theory is to integrate the advantages of ANNs such as learning, adaptation, fault-tolerance, parallelism and generalization, with fuzzy inference mechanisms under cognitive uncertainty. Extracting fuzzy rules from a trained ANN offers the advantage of being able to build a fuzzy system which is transparent to the user, even when domain expert knowledge is unavailable (Muslimi et al., 2006).
In this paper, a new approach, named the Fuzzy DIFACONN-miner, is proposed for extracting conjunctive normal form (CNF) fuzzy rules from feed-forward ANNs. Conjunction is used between the attributes of rule, and disjunction is used between the sub-attributes. The continuous valued attributes of the datasets are fuzzified using a triangular membership function. A fixed length binary encoding scheme is mapped to represent rules in the proposed approach. The performance of the algorithm is tested on six classification benchmark problems, and compared with a number of other FRBC algorithms available in the literature. Non-parametric statistical tests have been used to compare and analyze the accuracy of the experimental results. They show the superiority of the proposed algorithm over compared algorithms with regard to the accuracy of the results.
The paper is organized in the following way: In Section 2, the rule extraction problem is briefly described. Fuzzy DIFACONN-miner algorithm is comprehensibly explained in Section 3. The experimental study is presented in Section 4. Experimental results and their analysis are given in Section 5. Finally, in Section 6, concluding remarks are reported.
Section snippets
The rule extraction problem
The problem of rule extraction from ANNs was proposed by Craven and Shavlik (1994) as “Given a trained neural network and the examples used to train it, produce a concise and accurate symbolic description of the network.” Having extracted rules from trained ANNs, the end user can understand what the ANN has learned and how it works. In rule extraction, a rule generally represents the discovered knowledge in the form of IF-THEN rules. The main goal of the rule extraction is to discover hidden
Fuzzy DIFACONN-miner algorithm for rule extraction
In this study, a novel algorithm for generating fuzzy rules from feed-forward ANNs is proposed. In the present approach, the continuous valued attributes are fuzzified by using triangular membership function and categorical attributes are directly coded. Training and rule extraction phases of proposed algorithm are integrated within a multiple objective evaluation framework for generating fuzzy classification rules directly. The proposed algorithm employs differential evolution (DE) algorithm
The datasets
Six commonly used classification datasets from the UCI (University of California at Irvine) Machine Learning Repository (http://mlearn.ics.edu//MLRepository.html) are used to test the performance of the Fuzzy DIFACONN-miner algorithm. The main characteristics of these datasets are summarized in Table 3.
Bupa dataset: Bupa dataset is used to classify liver disorders and each instance constitutes the record of a single male individual. It consists of 345 instances, 2 classes and 6 attributes.
Experimental results and analysis
Ten-fold cross-validation results of thirty executions of the proposed algorithm for each of the datasets are shown in Table 5. Average predictive accuracies on the training and testing datasets, average number of rules and standard deviations are shown in this table.
As can be seen from the table, the proposed algorithm is able to generate accurate and concise fuzzy rules. The sample rule sets for the Pima (continuous attributes) and Cleveland (attributes 2, 3, 6, 7, 9, 11, 12, 13 are
Conclusion
In this paper, Fuzzy DIFACONN-miner, a novel algorithm for fuzzy rule extraction from ANNs, is proposed. The algorithm is simultaneously trained with fuzzified data by differential evolution algorithm, and generates CNF fuzzy rules by touring ant colony optimization algorithm. The best fuzzy rule set is then tested in fuzzy inference system. Fuzzy DIFACONN-miner algorithm can extract fuzzy rules from the datasets which have continuous, categorical or both of them. Experiments on five commonly
References (30)
- et al.
MEPAR-miner: multi-expression programming for classification rule mining
European Journal of Operational Research
(2007) - et al.
GP-COACH: Genetic Programming-based learning of COmpact and ACcurate fuzzy rule-based classification systems for high-dimensional problems
Information Sciences
(2010) - et al.
Extracting rules from multilayer perceptrons in classification problems: a clustering-based approach
Neurocomputing
(2006) - et al.
Extract intelligible and concise fuzzy rules from neural networks
Fuzzy Sets and Systems
(2002) Learning fuzzy rules and approximate reasoning in fuzzy neural networks and hybrid systems
Fuzzy Sets and Systems
(1996)- et al.
A search technique for rule extraction from trained neural networks
Pattern Recognition Letters
(1999) - et al.
An approach for on-line extraction of fuzzy rules using a self-organising fuzzy neural network
Fuzzy Sets and Systems
(2005) Fuzzy MLP based expert system for medical diagnosis
Fuzzy Sets and Systems
(1994)- et al.
A neuro-fuzzy method to learn fuzzy classification rules from data
Fuzzy Sets and Systems
(1997) - et al.
A soft computing-based approach for integrated training and rule extraction from artificial neural networks: DIFACONN-miner
Applied Soft Computing
(2010)