• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.182-185
• /
• 2003

This paper presents a new design algorithm for the combination with the fuzzy classifier and the Bayesian classifier. Only few attempts have so far been made at providing an effective design algorithm combining the advantages and removing the disadvantages of two classifiers. Specifically, the suggested algorithms are composed of three steps: the combining, the fuzzy-set-based pruning, and the fuzzy set tuning. In the combining, the multi-inputs and multi-outputs (MIMO) fuzzy model is used to combine two classifiers. In the fuzzy-set-based pruning, to effectively decrease the complexity of the fuzzy-Bayesian classifier and the risk of the overfitting, the analysis method of the fuzzy set and the recursive pruning method are proposesd. In the fuzzy set tuning for the misclassified feature vectors, the premise parameters are adjusted by using the gradient decent algorithm. Finally, to show the feasibility and the validity of the proposed algorithm, a computer simulation is provided.

• Journal of Internet Computing and Services
• /
• v.4 no.5
• /
• pp.69-76
• /
• 2003

In this paper we show a new learning algorithm for pattern classification. This algorithm considered a scheme to find a solution to a problem of incremental learning algorithm when the structure becomes too complex by noise patterns included in learning data set. Our approach for this problem uses a pruning method which terminates the learning process with a predefined criterion. In this process, an iterative model with 3 layer feedforward structure is derived from the incremental model by an appropriate manipulations. Notice that this network structure is not full-connected between upper and lower layers. To verify the effectiveness of pruning method, this network is retrained by EBP. From this results, we can find out that the proposed algorithm is effective, as an aspect of a system performence and the node number included in network structure.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.7-21
• /
• 2024

There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.663-667
• /
• 2004

This paper presents new pruning and learning methods for the fuzzy rule-based classifier. The structure of the proposed classifier is framed from the fuzzy sets in the premise part of the rule and the Bayesian classifier in the consequent part. For the simplicity of the model structure, the unnecessary features for each fuzzy rule are eliminated through the iterative pruning algorithm. The quality of the feature is measured by the proposed correctness method, which is defined as the ratio of the fuzzy values for a set of the feature values on the decision region to one for all feature values. For the improvement of the classification performance, the parameters of the proposed classifier are finely adjusted by using the gradient descent method so that the misclassified feature vectors are correctly re-categorized. The cost function is determined as the squared-error between the classifier output for the correct class and the sum of the maximum output for the rest and a positive scalar. Then, the learning rules are derived from forming the gradient. Finally, the fuzzy rule-based classifier is tested on two data sets and is found to demonstrate an excellent performance.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.6 no.2
• /
• pp.163-169
• /
• 2003

Studies were conducted on the effect of pruning time, host age, conidial dispersal and weather parameters on the incidence and severity of mulberry leaf spot (Myrothecium roridum). The disease severity (%) increased with increase in shoot age irrespective of pruning date. Maximum disease severity was observed in plants pruned during first week of April and minimum disease severity in plants pruned during first week of March. Significant (P ＜ 0.01) influence of date of pruning, shoot age and their interaction was observed on severity of the disease. Apparent infection rate (r) was significantly higher during the plant growth period from day 48 to day 55. Average apparent yale was higher in plants pruned during first week of April and least in plants pruned during first week of July. The disease infection was negatively correlated to distance from the inoculum source. Leaf spot severity (%) was influenced by weather parameters. Multiple regression analysis revealed contribution of various combinations of weather parameters on the disease severity. Linear prediction model $(Y ＝ －81.803＋1.176x_2＋0.765x_3) with significant $R^2$ was developed for prediction of the disease under natural epiphytotic condition.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.22 no.1
• /
• pp.11-15
• /
• 2011

Impact of pruning date, shoot age and weather parameters on the severity and development of grey leaf spot (Pseudocercospora mori) of mulberry was studied. The disease severity (%) increased with increase in shoot age irrespective of pruning date. Maximum disease severity was observed in plants pruned during second week of October and minimum in plants pruned during last week of December. Significant (P<0.05) influence of date of pruning, shoot age and their interaction was observed on the severity of the disease. Apparent infection rate (r) was significantly higher during plant growth period from day-48 to day-55. Average apparent rate was higher in plants pruned during first week of September and least in plants pruned during third and fourth week of December. Multiple regression analysis revealed contribution of various combinations of weather parameters on the disease severity. A linear prediction model [$Y=66.05+(-1.39)x_1+(-0.219)x_4$] with significant $R^2$ was developed for prediction of the disease under natural epiphytotic condition.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.326-338
• /
• 2003

The objective of a neural network design and model selection is to construct an optimal network with a good generalization performance. However, training data include noises, and the number of training data is not sufficient, which results in the difference between the true probability distribution and the empirical one. The difference makes the teaming parameters to over-fit only to training data and to deviate from the true distribution of data, which is called the overfitting phenomenon. The overfilled neural network shows good approximations for the training data, but gives bad predictions to untrained new data. As the complexity of the neural network increases, this overfitting phenomenon also becomes more severe. In this paper, by taking statistical viewpoint, we proposed an integrative process for neural network design and model selection method in order to improve generalization performance. At first, by using the natural gradient learning with adaptive regularization, we try to obtain optimal parameters that are not overfilled to training data with fast convergence. By adopting the natural pruning to the obtained optimal parameters, we generate several candidates of network model with different sizes. Finally, we select an optimal model among candidate models based on the Bayesian Information Criteria. Through the computer simulation on benchmark problems, we confirm the generalization and structure optimization performance of the proposed integrative process of teaming and model selection.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.6
• /
• pp.457-462
• /
• 2003

In this paper, we propose a speaker pruning method for real-time processing and improving performance of speaker identification system based on GMM(Gaussian Mixture Model). Conventional speaker identification methods, such as ML (Maximum Likelihood), WMR(weighting Model Rank), and MWMR(Modified WMR) we that frame likelihoods are calculated using the whole frames of each input speech and all of the speaker models and then a speaker having the biggest accumulated likelihood is selected. However, in these methods, calculation cost and processing time become larger as the increase of the number of input frames and speakers. To solve this problem in the proposed method, only a part of speaker models that have higher likelihood are selected using only a part of input frames, and identified speaker is decided from evaluating the selected speaker models. In this method, fm can be applied for improving the identification performance in speaker identification even the number of speakers is changed. In several experiments, the proposed method showed a reduction of 65% on calculation cost and an increase of 2% on identification rate than conventional methods. These results means that the proposed method can be applied effectively for a real-time processing and for improvement of performance in speaker identification.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.6
• /
• pp.543-551
• /
• 2002

In this paper, we present an efficient decoding method that performs in real time for 20k word continuous speech recognition task. Basic search method is a one-pass Viterbi decoder on the search space constructed from the novel language model network. With the consistent search space representation derived from various language models by the LM network, we incorporate basic pruning strategies, from which tokens alive constitute a dynamic search space. To facilitate post-processing, it produces a word graph and a N-best list subsequently. The decoder is tested on the database of 20k words and evaluated with respect to accuracy and RTF.

• Journal of KIISE:Software and Applications
• /
• v.30 no.7_8
• /
• pp.649-658
• /
• 2003

We propose a hierarchical architecture of ART2 Network for performance improvement and fast pattern classification model using fitness selection. This hierarchical network creates coarse clusters as first ART2 network layer by unsupervised learning, then creates fine clusters of the each first layer as second network layer by supervised learning. First, it compares input pattern with each clusters of first layer and select candidate clusters by fitness measure. We design a optimized fitness function for pruning clusters by measuring relative distance ratio between a input pattern and clusters. This makes it possible to improve speed and accuracy. Next, it compares input pattern with each clusters connected with selected clusters and finds winner cluster. Finally it classifies the pattern by a label of the winner cluster. Results of our experiments show that the proposed method is more accurate and fast than other approaches.