With the rapid expanding of big data in all domains, data-driven and deep learning-based fault diagnosis methods in chemical industry have become a major research topic in recent years. In addition to a deep neural network, deep forest also provides a new idea for deep representation learning and overcomes the shortcomings of a deep neural network such as strong parameter dependence and large training cost. However, the ability of each base classifier is not taken into account in the standard cascade forest, which may lead to its indistinct discrimination. In this paper, a multigrained scanning-based weighted cascade forest (WCForest) is proposed and has been applied to fault diagnosis in chemical processes. In view of the high-dimensional nonlinear data in the process of chemical industry, WCForest first designs a set of relatively suitable windows for the multigrained scan strategy to learn its data representation. Next, considering the fitting quality of each forest classifier, a weighting strategy is proposed to calculate the weight of each forest in the cascade structure without additional calculation cost, so as to improve the overall performance of the model. In order to prove the effectiveness of WCForest, its application has been carried out in the benchmark Tennessee Eastman (TE) process. Experiments demonstrate that WCForest achieves better results than other related approaches across various evaluation metrics.

In order to cope with data with an irregular shape and uneven density, this paper proposes a two-phase clustering algorithm based on detecting the peaks of dimensional density and the degree of interaction between clusters (CPDD-ID). In the partitioning phase, the local densities of the data in all dimensions are calculated using kernel density estimation, the density curves are constructed based on the densities of all the data, and the peaks of the density curves are used as the benchmark to construct a Kd-Tree to search for the data points that are closest to each peak to partition the initial sub-clusters. Then, the intersection of the results of the initial sub-clusters obtained from all the dimensions is taken to obtain the final sub-clusters. The proposed partitioning strategy is able to accurately identify clusters with density differences and has significant effects in dealing with data with irregular shapes as well as uneven densities in this category. In addition, a new similarity measure based on the interaction degree between clusters is proposed in the merging stage. This method iteratively merges subclusters with maximum similarity by calculating the interaction degree of shared k-nearest neighbors between neighboring subclusters. The proposed similarity measure is effective in dealing with the problems of high overlap between clusters and ambiguous boundaries. The proposed algorithm is tested in detail on 10 synthetic datasets and 10 UCI real datasets and compared with existing state-of-the-art algorithms. The experimental results show that the CPDD-ID algorithm accurately identifies potential cluster structures and exhibits excellent performance in terms of both clustering accuracy.

Clustering analysis has been widely applied in various fields, and boundary detection based clustering algorithms have shown effective performance. In this work, we propose a clustering algorithm by boundary detection based on entropy of KNN (CBDEK). A border point contains only the nearest neighbors within a specific directional range. Thus, we define entropy of KNN (EK) to accurately identify the boundary of the cluster. Since entropy has the property of measuring uncertainty, it can be used to quantify the possibility that a point is a border point. A lower EK indicates an uneven neighbor distribution, increasing the possibility of the point being a border point. Then, the border points are clustered based on the directional similarity of their nearest neighbors. Specifically, if a border point is a neighbor of another border point and most of their nearest neighbors show directional similarity, they are considered to belong to the same cluster. Furthermore, we assign the label of a border point to the interior points located within the maximum nearest neighbor sub-block of this border point to facilitate an efficient allocation for the remaining points (interior points). In addition, our algorithm incorporates noise mitigation techniques using average distance and box plot analysis. The effectiveness of CBDEK is proven by a comparative evaluation of nine algorithms on 24 datasets.

Frequent Itemset Mining (FIM) from large-scale databases has emerged as an important problem in the data mining and knowledge discovery research community. However, FIM suffers from three important limitations with the rapidly expanding of big data in all domains. First, it assumes that all items have the same importance. Second, it ignores the fact that data collected in a real-life environment is often inaccurate. Third, it is also a data-intensive and computation-intensive process which makes the FIM algorithm very time-consuming over large datasets. To address these issues, we propose a Parallel uncertain frequent itemset mining algorithm with spark (Pufim). Pufim firstly expresses item uncertainty by considering both the probability and weight, and calculates the maximum probability weight value of 1-items. Next, a distributed Pufim-tree structure is designed inspiring by FP-Tree for reducing the times of scanning the databases. Each node of Pufim-tree stores an item and its maximum probability weight value. Finally, experiments on publicly available UCI datasets demonstrate that Pufim achieves more prominent results than other related approaches across various metrics. In addition, the empirical study also shows Pufim has a good scalability