Search

Case-based reasoning (CBR) is one of the main forecasting methods in business forecasting, which performs well in prediction and holds the ability of giving explanations for the results. In business failure prediction (BFP), the number of failed enterprises is relatively small, compared with the number of non-failed ones. However, the loss is huge when an enterprise fails. Therefore, it is necessary to develop methods (trained on imbalanced samples) which forecast well for this small proportion of failed enterprises and performs accurately on total accuracy meanwhile. Commonly used methods constructed on the assumption of balanced samples do not perform well in predicting minority samples on imbalanced samples consisting of the minority/failed enterprises and the majority/non-failed ones. This article develops a new method called clustering-based CBR (CBCBR), which integrates clustering analysis, an unsupervised process, with CBR, a supervised process, to enhance the efficiency of retrieving information from both minority and majority in CBR. In CBCBR, various case classes are firstly generated through hierarchical clustering inside stored experienced cases, and class centres are calculated out by integrating cases information in the same clustered class. When predicting the label of a target case, its nearest clustered case class is firstly retrieved by ranking similarities between the target case and each clustered case class centre. Then, nearest neighbours of the target case in the determined clustered case class are retrieved. Finally, labels of the nearest experienced cases are used in prediction. In the empirical experiment with two imbalanced samples from China, the performance of CBCBR was compared with the classical CBR, a support vector machine, a logistic regression and a multi-variant discriminate analysis. The results show that compared with the other four methods, CBCBR performed significantly better in terms of sensitivity for identifying the minority samples and generated high total accuracy meanwhile. The proposed approach makes CBR useful in imbalanced forecasting. [ABSTRACT FROM AUTHOR]

Objective: To observe the effect of heat-tonifying needling on Keap1-Nrf2/ARE/HO-1 signal transduction pathway in knee synovium in rabbits with cold syndrome type rheumatoid arthritis (RA), so as to explore its mechanisms underl-ying improvement of RA., Methods: New Zealand rabbits were randomly divided into normal control, RA model, uniform reinforcing-reducing acupuncture, twisting reinforcing acupuncture and heat-tonifying acupuncture groups, with 6 rabbits in each group. The cold syndrome type RA model was established by subcutaneous injection of mixture fluid of ovalbumin and Freund's complete adjuvant at the shoulder-back as well as injection of mixture of ovalbumin and normal saline into knee-joint cavity combined with ice-compress freezing. Acupuncture stimulation (uniform reinforcing-reducing, or twisting reinforcing or heat-tonifying) was applied to bilateral "Zusanli"(ST36) for 1 min with the needle retained for 30 min, once a day for 7 consecutive days. The general conditions of rabbits in each group were recorded, the thermal pain threshold (TPT) and perimeter of knee joints was measured. Conditions of the synovium in the knee cavity, hydrops, blood flow signal, articular surface, and related muscles were observed by using a color Doppler ultrasonic diagnostic apparatus, and the blood flow signals inside the synovium (image scores) were divided into 0 (no signals), I (1 or 2 dot-like signal), II (less than half) ad III (more than half). After H.E. staining, the pathological changes (0-3 points) were assessed according to the state of inflammatory cell infiltration, and hyperplasia of synovial matrix and coating cells. The expression levels of Keap1, Nrf2, HO-1 and GSH-PX1 mRNAs in the knee synovium were detected by quantitative real-time PCR, and the expression of knee synovial HO-1 protein was measured by Western blot., Results: In comparison with the normal control group, the model group had a significant increase in the perimeter, pathological score, expression of Nrf2, HO-1 mRNAs and HO-1 protein ( P <0.05), and an obvious decrease in the TPT, expression levels of Keap1 and GSH-PX1 mRNAs ( P <0.05). Relevant to the model group, all the three acupuncture maneuvers reversed modeling-induced increase of perimeter and pathological score ( P <0.05), decrease of TPT and expression of GSH-PX1 mRNA( P <0.05), further down-regulated expression of Keap1 mRNA ( P <0.05), further up-regulated the expression of Nrf2, HO-1 mRNAs and HO-1 protein ( P <0.05). The heat-reinforcing manipulation was significantly superior to uniform reinforcing-reducing and twirling reinforcing manipulations in up-regulating TPT, and expression of Nrf2 mRNA, GSH-PX1 mRNA, HO-1 mRNA and protein ( P <0.05), and in down-regulating pathological score and Keap1 mRNA expression ( P <0.05)., Conclusion: Heat-tonifying, uniform reinforcing-reducing and twirling reinforcing needling manipulations may relieve pain and improve pathological state in RA rabbits, which may be associated with their functions in raising the ability of anti-oxidative stress by regulating Keap1-Nrf2/ARE/ HO-1 signaling pathway, the therapeutic effect of heat-tonifying needling is superior to that of uniform reinforcing-reducing and twirling reinforcing needling.