Partial multi-label feature selection (PMFS) effectively addresses the high-dimensionality challenge in partial multi-label data, where each sample is associated with a candidate label set containing both ground-truth and false positive labels. Most existing methods that perform only a single disambiguation step tend to be insufficient. Moreover, they undervalue rare labels, resulting in the neglect of critical but infrequent information. Furthermore, they overlook the overlapping information within each label pair, resulting in redundant counting of shared information. In addition, they explore the relationship between a candidate feature and selected features under labels solely from the redundancy perspective, which is insufficient. To tackle these challenges, we propose a novel PMFS method, called PMFS-F2Deur. First, we propose fuzzy two-stage disambiguation method to sufficiently minimize the disturbance caused by false positive labels. Second, we propose label weight to measure the importance of each label. Third, we define two relationships between a label pair and a candidate feature, and then propose weighted pure relevance to reduce biased relevance estimation. Fourth, we define weighted feature individual contribution ratio from the perspective of individual contribution. Finally, we propose a PMFS method considering weighted pure relevance, weighted feature individual contribution ratio and redundancy information. Experimental results on artificial and practical partial multi-label datasets confirm that PMFS-F2Deur outperforms other representative methods.

Multi-label feature selection (MFS) has received much attention because it can effectively mitigate the impact of ‘dimensionality curse’. Ambiguity and unavoidable label noise in real life pose significant challenges to MFS. So far, there are relatively few studies on MFS considering label noise. Existing few studies do not consider that label sets of different samples are affected by noise to different degrees, and ignoring differences between samples may reduce robustness of MFS. Moreover, they explore the fuzzy relationship between samples and labels from a local perspective, which is not comprehensive. In addition, they lack a monotonic metric for measuring attribute importance, leading to the unreasonable selected feature subset. To solve these issues, we propose a noise-tolerant MFS method by monotonic noise-tolerant fuzzy confidence conditional entropy with sample reliability degree and fuzzy association confidence called SRDAC. Firstly, sample reliability degree is defined from the perspective of consistency to distinguish samples affected by different levels of label noise. Secondly, the idea of global similarity and the fuzzy association confidence between samples and labels are proposed, and corresponding noise-tolerant label enhancement for different types of samples is carried out to better explore the relationship between samples and labels. Thirdly, based on noise-tolerant label space, the noise-tolerant fuzzy confidence conditional entropy is proposed to more reasonably measure the relationship between attributes. Finally, a robust MFS method based on monotonic noise-tolerant fuzzy confidence conditional entropy is proposed. Extensive experiments show that the effectiveness and robustness of SRDAC is better than other representative methods.

The interpretability of prediction models is very important for decision management. The vast majority of existing prediction analysis models based on rough set theory lack a certain interpretability. To break through the existing framework, this article deeply integrates rough fuzzy sets and logistic regression to construct an interpretable prediction model for multiattribute information systems. First, the Jensen–Shannon divergence with statistical interpretability is used to capture the attribute information with strong correlation under on a level, and then an fresh attribute-oriented$\delta$-rough fuzzy set model is presented. The pessimistic and optimistic decision concepts of the proposed rough fuzzy set model are used to interpretability enhancement of data information. On this basis, an interpretable predictive analysis model is constructed by combining logistic regression model. The construction process of the prediction model is supported by sufficient interpretable information. The predicted result is a result of development trend with a certain interpretability. Finally, to assess the effectiveness and viability of the proposed prediction model, we conduct comparative experiments with other three prediction models accompanied with four prediction performance indexes. Experimental results display that the proposed prediction model has well-pleasing prediction performance and antinoise ability.

High-level synthesis (HLS) compiles a algorithmic description (C or C++) into a digital hardware implementation (VHDL or Verilog) through a sequence of transformations. However, the complex compiling process may introduce an error in the produced register-transfer level (RTL) implementation. Global common subexpression elimination (GCSE) as a commonly used code motion technique in the scheduling of HLS is an error-prone and complex process that need to be validated. In this paper, we propose an equivalence checking method to validate GCSE with non-common variables used in the rest code in the scheduling of HLS by enhancing the path equivalence criteria. The source and target programs are modeled using Finite State Machine with Datapath (FSMD) that is essentially a Control and Data Flow Graph (CDFG). The experimental results show that our method can indeed validate the GCSE with non-common variables used in the rest code in HLS which has not been solved in the existing papers.

SUMMARY: We present GWASpro, a high-performance web server for the analyses of large-scale genome-wide association studies (GWAS). GWASpro was developed to provide data analyses for large-scale molecular genetic data, coupled with complex replicated experimental designs such as found in plant science investigations and to overcome the steep learning curves of existing GWAS software tools. GWASpro supports building complex design matrices, by which complex experimental designs that may include replications, treatments, locations and times, can be accounted for in the linear mixed model. GWASpro is optimized to handle GWAS data that may consist of up to 10 million markers and 10 000 samples from replicable lines or hybrids. GWASpro provides an interface that significantly reduces the learning curve for new GWAS investigators. AVAILABILITY AND IMPLEMENTATION: GWASpro is freely available at https://bioinfo.noble.org/GWASPRO. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.