Performance evaluation of complex system (CS) is critical for ensuring their operational efficiency. Under limited monitoring data, incorporating expert knowledge becomes essential to achieve reliable evaluation results. However, the multiple uncertainties from the interfering monitoring data, subjectivity of expert judgments, and difficulty of quantifying critical performance states pose challenges to developing models integrating data with knowledge. To address these challenges, this article proposes a multiexpert inference model based on belief rule base (BRB-ME) for CS performance evaluation under uncertainty. In the proposed framework, multiple belief rule bases are embedded within a mixture-of-experts architecture to fuse multisource monitoring data, mitigating data uncertainty and avoiding rule explosion. Expert cognitive strength and prior knowledge are encoded into the beta distribution's shape parameters to obtain the reference values, enabling the probabilistic modeling of expert knowledge uncertainty. Moreover, single-proposition outputs are extended to the power set to explicitly represent both partial and complete ignorance, enhancing uncertainty characterization. An alternating iteration optimization strategy is further designed to optimize parameters across all BRB-ME components. Finally, by the case study on rocket structure performance inference, the BRB-ME model achieves an average root mean square error of 0.0065, validating the effectiveness of the BRB-ME evaluation results.

Artificial electric field algorithm (AEFA) is a metaheuristic optimization algorithm proposed in recent years, which has been successfully applied to address various optimization problems. However, it is likely to converge prematurely or fall into local optima when solving complex problems. To overcome these disadvantages, a multi-strategy artificial electric field algorithm (MAEFA) is proposed in this paper. For the MAEFA algorithm, the global optimal solution information is utilized to improve the diversity of population and global search ability. Then, the adaptive Coulomb’s constant is configured to balance the global exploration and local search. Also, a restart strategy is designed to further alleviate the premature convergence. To validate the effectiveness of MAEFA, it is compared with three AEFA algorithms and several other evolutionary algorithms on 14 test problems presented in CEC 2005 and 13 basic benchmark functions. Furthermore, a wind power prediction model based on MAEFA algorithm and back-propagation (BP) neural network is established to investigate its application ability. Experiments show that MAEFA is significantly superior to other algorithms in tackling these benchmark functions with different dimensions. Furthermore, in terms of wind power prediction, the BP neural network model optimized by MAEFA algorithm also provides higher prediction accuracy.

With excellent interpretability, the fuzzy rule-based method stands as a formidable instrument for knowledge representation and learning. Nowadays, the knowledge representation problem with multidimensional input information is widespread, leading to a large rule base and making it difficult to embed expert knowledge. In addition, human knowledge is not entirely reliable, causing inaccurate reasoning results. In this article, a novel large-scale linguistic Z-number belief rule base (LSLZ-BRB) method is proposed for the above multidimensional and unreliable knowledge representation and learning. Specifically, a multidimensional knowledge mapping representation method under the probabilistic framework is proposed to generate an LSLZ-BRB. It allows experts to embed knowledge via conditional probability and prior probability. To reduce the modeling error caused by uncertainty of knowledge, an online interactive learning mechanism of uncertain knowledge is developed. This mechanism ensures that LSLZ-BRB has high real-time performance and improves the accuracy of knowledge representation. A performance evaluation case for the laser inertial measurement unit (LIMU) and experiments on some public datasets illustrate the implementation process of the proposed method and further verify its effectiveness.

This paper develops a new online fault diagnosis and tolerant control framework for sensor failures based on belief rule base (BRB) expert system to solve three problems in engineering practice: lack of data in system failure state, expert knowledge uncertainty and complex environment interference. First of all, the new framework incorporates both quantitative information and qualitative knowledge, aimming to handle the influence of the lack of high-value failure data and uncertainty of expert knowledge. Secondly, this paper proposes a new BRB model considering dynamic attribute reliability (BRB-DR) by contemplating the impact of complex environments on multi-source information. In addition, the BRB-DR based online fault diagnosis and fault tolerant control (OFTC) framework is developed for handling sensor failures, where the model structure and parameters are both adjusted adaptively. Thirdly, a sensitivity analysis of the dynamic attribute reliability to OFTC framework output is performed based on the iterative BRB-DR model, that can also provide decision making support for system improvement design. A case study based on wireless sensor network (WSN) in rocket has been conducted to demonstrate the validity of the new framework.

Identifying the optimal maintenance timing (OMT) of complex industrial equipment (CIE) is a highly effective way to maintain its stable operation and reduce unreasonable maintenance costs. Currently, determination of OMT for CIE involves the following two main issues: an accurate mathematical model is hard to establish and difficulty in guaranteeing the validity of OMT determination. Hence, in this article, a new OMT model considering cohesion factor has been developed based on the evidential reasoning rule (ER-rule), where dynamic boundaries are set for model parameters to determine the optimal solution more accurate and faster in the optimization process (CERr-DB). In CERr-DB, cohesion factor is introduced to represent the fusion of weight and reliability of evidence in the original ER-rule method to make it more interpretable. What is more, CERr-DB adopts a new output feedback mechanism to provide a dynamic boundary solution space for the optimization process of parameters, which effectively improves the search accuracy and rate. In an effort to quantitatively assess the effect of cohesion factors and dynamic boundaries on the properties of CIE, a sensitivity analysis based on the transparency and traceability of the CERr-DB methodology has been performed. A case study of the electric servo mechanism is carried out to validate the effectiveness of the new OMT model.

Deep neural networks now have become the de-facto standard for sequential recommendation. In the existing techniques, an embedding vector is assigned for each item, encoding all the characteristics of the latter in latent space. Then, the recommendation is transferred to devising a similarity metric to recommend user's next behavior. Here, we consider each dimension of an embedding vector as a (latent) feature. Though effective, it is unknown which feature carries what semantics toward the item. Actually, in reality, this merit is highly preferable since a specific group of features could induce a particular relation among the items while the others are in vain. Unfortunately, the previous treatment overlooks the feature semantic learning at such a fine-grained level. When each item contains multiple latent aspects, which however is prevalent in real-world, the relations between items are very complex. The existing solutions are easy to fail on better recommendation performance. It is necessary to disentangle the item embeddings and extract credible features in a context-aware manner.

Histopathology image segmentation is the gold standard for diagnosing cancer, and can indicate cancer prognosis. However, histopathology image segmentation requires high-quality masks, so many studies now use image-level labels to achieve pixel-level segmentation to reduce the need for fine-grained annotation. To solve this problem, we propose an attention-based cross-view feature consistency end-to-end pseudo-mask generation framework named CVFC based on the attention mechanism. Specifically, CVFC is a three-branch joint framework composed of two Resnet38 and one Resnet50, and the independent branch multi-scale integrated feature map to generate a class activation map (CAM); in each branch, through down-sampling and The expansion method adjusts the size of the CAM; the middle branch projects the feature matrix to the query and key feature spaces, and generates a feature space perception matrix through the connection layer and inner product to adjust and refine the CAM of each branch; finally, through the feature consistency loss and feature cross loss to optimize the parameters of CVFC in co-training mode. After a large number of experiments, An IoU of 0.7122 and a fwIoU of 0.7018 are obtained on the WSSS4LUAD dataset, which outperforms HistoSegNet, SEAM, C-CAM, WSSS-Tissue, and OEEM, respectively.

Recommender systems play a pivotal role in navigating users through vast reservoirs of information. However, data sparseness can compromise recommendation accuracy, making it challenging to improve recommendation performance. To address this issue, researchers have explored incorporating multiple data types. Yet, this approach can introduce noise that impairs the recommendations' accuracy. Therefore, it is crucial to denoise the data to enhance recommendation quality. This tutorial highlights the importance of data denoising metrics for improving the accuracy and quality of recommendations. Four groups of data denoising metrics are introduced: feature, item, pattern, and modality level. For each group, various denoising methods are presented. The tutorial emphasizes the significance of selecting the right data denoising methods to enhance recommendation quality. It provides valuable guidance for practitioners and researchers implementing reliable data denoising metrics in recommender systems. Finally, the tutorial proposes open research questions for future studies, making it a valuable resource for the research community.

The analysis and mining of user heterogeneous behavior are of paramount importance in recommendation systems. However, the conventional approach of incorporating various types of heterogeneous behavior into recommendation models leads to feature sparsity and knowledge fragmentation issues. To address this challenge, we propose a novel approach for personalized recommendation via Large Language Model (LLM), by extracting and fusing heterogeneous knowledge from user heterogeneous behavior information. In addition, by combining heterogeneous knowledge and recommendation tasks, instruction tuning is performed on LLM for personalized recommendations. The experimental results demonstrate that our method can effectively integrate user heterogeneous behavior and significantly improve recommendation performance.

Insufficient annotated data and minor lung lesions pose big challenges for computed tomography (CT)-aided automatic COVID-19 diagnosis at an early outbreak stage. To address this issue, we propose a Semi-Supervised Tri-Branch Network (SS-TBN). First, we develop a joint TBN model for dual-task application scenarios of image segmentation and classification such as CT-based COVID-19 diagnosis, in which pixel-level lesion segmentation and slice-level infection classification branches are simultaneously trained via lesion attention, and individual-level diagnosis branch aggregates slice-level outputs for COVID-19 screening. Second, we propose a novel hybrid semi-supervised learning method to make full use of unlabeled data, combining a new double-threshold pseudo labeling method specifically designed to the joint model and a new inter-slice consistency regularization method specifically tailored to CT images. Besides two publicly available external datasets, we collect internal and our own external datasets including 210,395 images (1,420 cases versus 498 controls) from ten hospitals. Experimental results show that the proposed method achieves state-of-the-art performance in COVID-19 classification with limited annotated data even if lesions are subtle, and that segmentation results promote interpretability for diagnosis, suggesting the potential of the SS-TBN in early screening in insufficient labeled data situations at the early stage of a pandemic outbreak like COVID-19.

In recommender systems, top- N recommendation is an important task with implicit feedback data. Although the recent success of deep learning largely pushes forward the research on top- N recommendation, there are increasing concerns on appropriate evaluation of recommendation algorithms. It therefore is important to study how recommendation algorithms can be reliably evaluated and thoroughly verified. This work presents a large-scale, systematic study on six important factors from three aspects for evaluating recommender systems. We carefully select 12 top- N recommendation algorithms and eight recommendation datasets. Our experiments are carefully designed and extensively conducted with these algorithms and datasets. In particular, all the experiments in our work are implemented based on an open sourced recommendation library, Recbole [ 139 ], which ensures the reproducibility and reliability of our results. Based on the large-scale experiments and detailed analysis, we derive several key findings on the experimental settings for evaluating recommender systems. Our findings show that some settings can lead to substantial or significant differences in performance ranking of the compared algorithms. In response to recent evaluation concerns, we also provide several suggested settings that are specially important for performance comparison.

Colorectal cancer (CRC) is among the top three malignant tumor types in terms of morbidity and mortality. Histopathological images are the gold standard for diagnosing colon cancer. Cellular nuclei instance segmentation and classification, and nuclear component regression tasks can aid in the analysis of the tumor microenvironment in colon tissue. Traditional methods are still unable to handle both types of tasks end-to-end at the same time, and have poor prediction accuracy and high application costs. This paper proposes a new UNet model for handling nuclei based on the UNet framework, called MGTUNet, which uses Mish, Group normalization and transposed convolution layer to improve the segmentation model, and a ranger optimizer to adjust the SmoothL1Loss values. Secondly, it uses different channels to segment and classify different types of nucleus, ultimately completing the nuclei instance segmentation and classification task, and the nuclei component regression task simultaneously. Finally, we did extensive comparison experiments using eight segmentation models. By comparing the three evaluation metrics and the parameter sizes of the models, MGTUNet obtained 0.6254 on PQ, 0.6359 on mPQ, and 0.8695 on R2. Thus, the experiments demonstrated that MGTUNet is now a state-of-the-art method for quantifying histopathological images of colon cancer.

In recent years, there are a large number of recommendation algorithms proposed in the literature, from traditional collaborative filtering to deep learning algorithms. However, the concerns about how to standardize open source implementation of recommendation algorithms continually increase in the research community. In the light of this challenge, we propose a unified, comprehensive and efficient recommender system library called RecBole (pronounced as [rEk'[email protected]]), which provides a unified framework to develop and reproduce recommendation algorithms for research purpose. In this library, we implement 73 recommendation models on 28 benchmark datasets, covering the categories of general recommendation, sequential recommendation, context-aware recommendation and knowledge-based recommendation. We implement the RecBole library based on PyTorch, which is one of the most popular deep learning frameworks. Our library is featured in many aspects, including general and extensible data structures, comprehensive benchmark models and datasets, efficient GPU-accelerated execution, and extensive and standard evaluation protocols. We provide a series of auxiliary functions, tools, and scripts to facilitate the use of this library, such as automatic parameter tuning and break-point resume. Such a framework is useful to standardize the implementation and evaluation of recommender systems. The project and documents are released at https://recbole.io/.

In current studies of the belief rule base (BRB) model, the attributes are assumed to be fully reliable and the observation data are directly used as input. However, in engineering practice, the observation data may be affected by some disturbance factors, including the quality of the sensors and noise in the environment. Then, the reliability of observation data may be affected and the modeling accuracy of the BRB is therefore influenced. As such, a new BRB model with attribute reliability (BRB-r) is proposed in this paper. In particular, a calculation method of attribute reliability is given based on the statistical method. Moreover, to integrate the attribute reliability into the BRB-r, a new calculation method of matching degree is developed. The model's overall reliability denotes its ability to provide the correct result. When the attributes are unreliable, the overall reliability of the BRB-r is degraded. Thus, a calculation method for the overall reliability of the BRB-r is developed to support decision-making in engineering practice. A case study of the safety assessment of a diesel engine is conducted to demonstrate the efficiency of the proposed BRB-r model.