No abstract

The extended belief-rule-based (EBRB) system has become a widely recognized and effective rule-based system in decision-making. The system uses a data-driven method to generate the rule base by transforming each training sample into a rule. Hence, when an EBRB system is applied in an imbalanced classification dataset, the imbalance of training dataset will retain in the generated rule base. More specifically, the number of rules transformed from majority classes will be far greater than the rules transformed from minority classes. This issue usually leads to a sharp decrease in the accuracies of minority classes. This study analyses how the imbalance of training dataset exists in the generated EBRB and then proposes a Balance Adjusting (BA) approach to eliminate the influence of imbalance in the rule base. The BA approach adjusts rule activation weights of all activated rules, and further enhances the competitiveness of rules with higher activation weight during the rule aggregation process of the EBRB system. Several case studies in imbalanced benchmark classification datasets from UCI demonstrate how the use of the BA approach improves the performance of the EBRB system. This study also conducts a series of experiments to validate the improvement of the proposed approach compared with some conventional and recent existing works. The comparison results illustrate that the BA approach is feasible, effective and robust, and it performs well especially in large scale datasets. Moreover, the BA approach can also combine with various rule activation weight calculation methods, which means it might worth to be applied as a generic process before the rule aggregation process of the EBRB system. INDEX TERMS Extended belief-rule-based system, rule activation weight, imbalanced classification problem.

Extended belief rule-based (EBRB) system has a better ability to model complex problems than belief rule-based (BRB) system. However, the storage of rules in EBRB system is out of order, which leads to the low efficiency of rule retrieval during the reasoning process. Therefore, to improve the efficiency of rule retrieval, this study introduces K-means clustering tree algorithm into the construction of rule base, then proposes a multi-layer weighted reasoning approach based on K-means clustering tree. The proposed approach seeks out a path on the tree during the rule retrieval process, and then figures out several reasoning results according to the nodes on the path. These results are weighted and aggregated to obtain the final conclusion of the system, thus ensure both the efficiency of reasoning and the sufficient utilization of information. In addition, the differential evolution (DE) algorithm is used to train the parameters of EBRB system in this study. Several experiments are conducted on commonly used classification datasets from UCI, and the results are compared with some existing works of EBRB system and conventional machine learning methods. The comparison results illustrate that the proposed method can make an obvious improvement in the performance of EBRB system.INDEX TERMS Extended belief rule-based system, K-means clustering tree, differential evolutionary.

Fabrics play a pivotal role in human life and production, and surface defects can directly affect the quality and value of fabrics. Many methods for fabric defect detection have been proposed, but tiny defects are still difficult to be detected effectively, and the accuracy of defect localization and classification is low. To address these issues, a modified YOLOX network called YOLOX-CATD is proposed, which was supplemented with a coordinate attention module (CAM) and tiny defect detection layer (TDDL) for fast and efficient detection of fabric defects, especially tiny defects. Firstly, the anchor-free network is used as the detection framework to avoid the influence of hyperparameters of the setting anchor. Secondly, a CAM is proposed to enhance the representation of the object of interest in the input feature map and suppress the background regions. Finally, a TDDL is added to introduce high-resolution features to improve the localization accuracy of tiny defects. The experimental results on the Aliyun Tianchi Fabric dataset and NEU-DET demonstrate the superiority and generalization of the modified model. The mean average precision (mAP) of YOLOX-CATD on the fabric defect dataset is improved by 5.67% compared to the original YOLOX, and the detection speed can reach 35-36 frames per second (FPS). This proves that YOLOX-CATD can obtain excellent fabric defect detection performance and meet the urgent need for real-time detection in industrial applications.