The imbalanced issue among data is common in many machine-learning applications, where samples from one or more classes are rare. To address this issue, many imbalanced machine-learning methods have been proposed. Most of these methods rely on cost-sensitive learning. However, we note that it is infeasible to determine the precise cost values even with great domain knowledge for those cost-sensitive machine-learning methods. So in this method, due to the superiority of F-measure on evaluating the performance of imbalanced data classification, we employ F-measure to calculate the cost information and propose a cost-sensitive hypergraph learning method with F-measure optimization to solve the imbalanced issue. In this method, we employ the hypergraph structure to explore the high-order relationships among the imbalanced data. Based on the constructed hypergraph structure, we optimize the cost value with F-measure and further conduct cost-sensitive hypergraph learning with the optimized cost information. The comprehensive experiments validate the effectiveness of the proposed method.

Anomaly detection aims to find the outlier noise data, which has attracted much attention in recent years. However, in most industrial cases, we can only obtain very few labeled anomalous data with abundant unlabeled data, which makes anomaly detection intractable. To tackle this issue, we propose a vertex-weighted hypergraph structure (VWHL) and a learning algorithm on it for anomaly detection. In this method, the correlation among data is formulated in a hypergraph structure, where each vertex denotes one sample, and the connections (hyperedges) on the hypergraph represent the relation among samples in feature space. We introduce vertex weights to investigate the importance of different samples, where each vertex is initialized with a weight corresponding to its similarity score and isolation score. Then, we learn the label projection matrix for anomaly detection and optimize vertex weights simultaneously. In this way, the vertices with high weights, which indicate data likely to be anomalies, play an important role during the learning process. We have evaluated our method on Industry Anomaly Detection dataset, Outlier Detection dataset (ODDS) and Software Defect Prediction (SDP) dataset, and experimental results show that our method achieves better performance when compared with other state-of-the-art methods.

Background: With the rapid development of high-throughput sequencing technologies, many datasets on the same biological subject are generated. A meta-analysis is an approach that combines results from different studies on the same topic. The random-effects model in a meta-analysis enables the modeling of differences between studies by incorporating the between-study variance. Results: This paper proposes a moments estimator of the between-study variance that represents the across-study variation. A new random-effects method (DSLD2), which involves two-step estimation starting with the DSL estimate and the $D_{g}^{2}$Dg2 in the second step, is presented. The DSLD2 method is compared with 6 other meta-analysis methods based on effect sizes across 8 aspects under three hypothesis settings. The results show that DSLD2 is a suitable method for identifying differentially expressed genes under the first hypothesis. The DSLD2 method is also applied to Alzheimer’s microarray datasets. The differentially expressed genes detected by the DSLD2 method are significantly enriched in neurological diseases. Conclusions: The results from both simulationes and an application show that DSLD2 is a suitable method for detecting differentially expressed genes under the first hypothesis.