Search

Fault diagnosis, as an important approach to ensure the safety and stability of industrial processes, has been widely studied in recent years. During the running process, it is noted that the normal data are always much more than the fault data, which demonstrates imbalanced characteristics and leads to a negative effect on the overall accuracy of fault diagnosis. Targeting the problem, a novel imbalanced fault diagnosis method integrated kernel local Fisher discriminant analysis (KLFDA) with improved adaptive near‐Bayesian support vector machine (ANBSVM) is proposed in this paper. First, KLFDA is used to extract the non‐linear features while maintaining the local spatial structure of the data by introducing flow pattern learning. Second, considering the imbalance characteristics of the data, the data set is divided into a majority class (normal data) and a minority class (fault data). The density distributions of the two classes in their overlapping region are characterized by the proportional function of variance. Third, by minimizing the Bayesian error under the proportion function, the weight factors are adaptively obtained and then introduced into the objective function of the support vector machine (SVM). Namely, a cost sensitivity‐based ANBSVM classifier for fault diagnosis is constructed. Finally, by the simulation experiment on the Tennessee Eastman (TE) process, the comparison results show that the proposed ANBSVM‐based fault diagnosis method makes progress in the performance of fault diagnosis with higher diagnostic accuracy and F1 score. [ABSTRACT FROM AUTHOR]

Recently, zebrafish has received more and more attention due to its wide range of applications such as regeneration promoting therapeutics and drug discovery. Therefore, vision‐based trackers are utilized to record the swimming trajectory of zebrafish. In this paper, a re‐association method is introduced in the 3D reconstruction process to generate missed targets caused by occlusion. Since the variation of the overall tracking targets has the property of continuity and stability, a topology association model (TAM) is proposed by point group similarity into the tracking framework. TAM describes the movement of zebrafish from the macroscopic level and utilizes the changes of the point group structure for tracking. Experimental results show that the tracking framework enhances the overall performance and promotes the trajectory integrity. On the latest 3D‐ZeF20 benchmark, state‐of‐the‐art results are achieved. In addition, TAM tracking framework is applied to 2D general tracking to prove that the method is useful and have great advantage in other scenarios with relatively stable amount of targets as well. [ABSTRACT FROM AUTHOR]

Multi‐object tracking is an important branch of computer vision, which is mostly used for behavior recognition and event analysis. At present, most of the research focuses on the accuracy of tracking. However, the real‐time performance is also urgently desired but there is lack of research. As a result, Deepsort, proposed 5 years ago, is still the most widely used tracker in real applications. In this paper, a Bilateral Association Tracking (BAT) framework is proposed. It uses tracklet as the basic node instead of discrete detection for tracking. Meanwhile, a Parzen density based Hierarchical Agglomerative Clustering (P‐HAC) algorithm is introduced to describe the density distribution of targets and generate tracklets with high confidence. In addition, Dual Appearance Features (DAF) is proposed which considers both spatial and temporal features of tracklets and promotes the accuracy of tracklet association. Experiments are conducted on popular benchmarks such as MOT2017, Visdrone and KITTI. BAT outperforms Deepsort on both association accuracy and trajectory integrity without obvious efficiency decline. Compared with other state‐of‐the‐art trackers, BAT shows significant advantage on computational cost while performing competitive tracking accuracy as well. It is hoped that the research can promote the applications on real‐time tracking in the near future. [ABSTRACT FROM AUTHOR]

Material scheduling is significant in the ethylene production process. However, factors such as the production scale and the technology also affect the choice of material scheduling solutions. Therefore, this paper proposes a novel P‐graph methodology integrated data envelopment analysis (DEA) for the solutions selection of material scheduling. First, based on the basic procedure, a scheduling superstructure model expanding from the time dimension is built. With the cost as the objective function, the optimal and partially feasible scheduling solutions are generated based on the P‐graph, and the results are analyzed in detail with reference to ISA‐95. Then the DEA is used to analyze the indicators of material consumption and product yields to give a selection strategy from the input‐output perspective. The optimal solution and suboptimal solution sets are evaluated and analyzed, and decision making units (DMUs) with the highest score are calculated. Based on the scheduling solution with the highest score and relatively low cost, the potential adjustment of other solution is also given. Finally, a complete base of material scheduling solution has been implemented, which provides more references for decision makers. This paper considers the lowest cost as the goal and gives a more suitable alternative from the perspective of input‐output efficiency in combination with the actual production conditions, which is a good extension of the P‐graph. [ABSTRACT FROM AUTHOR]