SCCAM: Supervised Contrastive Convolutional Attention Mechanism for Ante-Hoc Interpretable Fault Diagnosis With Limited Fault Samples.

In real industrial processes, fault diagnosis methods are required to learn from limited fault samples since the procedures are mainly under normal conditions and the faults rarely occur. Although attention mechanisms have become increasingly popular for the task of fault diagnosis, the existing attention-based methods are still unsatisfying for the above practical applications. First, pure attention-based architectures like transformers need a substantial quantity of fault samples to offset the lack of inductive biases thus performing poorly under limited fault samples. Moreover, the poor fault classification dilemma further leads to the failure of the existing attention-based methods to identify the root causes. To develop a solution to the aforementioned problems, we innovatively propose a supervised contrastive convolutional attention mechanism (SCCAM) with ante-hoc interpretability, which solves the root cause analysis problem under limited fault samples for the first time. First, accurate classification results are obtained under limited fault samples. More specifically, we integrate the convolutional neural network (CNN) with attention mechanisms to provide strong intrinsic inductive biases of locality and spatial invariance, thereby strengthening the representational power under limited fault samples. In addition, we ulteriorly enhance the classification capability of the SCCAM method under limited fault samples by employing the supervised contrastive learning (SCL) loss. Second, a novel ante-hoc interpretable attention-based architecture is designed to directly obtain the root causes without expert knowledge. The convolutional block attention module (CBAM) is utilized to directly provide feature contributions behind each prediction thus achieving feature-level explanations. The proposed SCCAM method is testified on a continuous stirred tank heater (CSTH) and the Tennessee Eastman (TE) industrial process benchmark. Three common fault diagnosis scenarios are covered, including a balanced scenario for additional verification and two scenarios with limited fault samples (i.e., imbalanced scenario and long-tail scenario). The effectiveness of the presented SCCAM method is evidenced by the comprehensive results that show our method outperforms the state-of-the-art methods in terms of fault classification and root cause analysis.

Toward Energy-Efficient Routing of Multiple AGVs with Multi-Agent Reinforcement Learning.

This paper presents a multi-agent reinforcement learning (MARL) algorithm to address the scheduling and routing problems of multiple automated guided vehicles (AGVs), with the goal of minimizing overall energy consumption. The proposed algorithm is developed based on the multi-agent deep deterministic policy gradient (MADDPG) algorithm, with modifications made to the action and state space to fit the setting of AGV activities. While previous studies overlooked the energy efficiency of AGVs, this paper develops a well-designed reward function that helps to optimize the overall energy consumption required to fulfill all tasks. Moreover, we incorporate the e-greedy exploration strategy into the proposed algorithm to balance exploration and exploitation during training, which helps it converge faster and achieve better performance. The proposed MARL algorithm is equipped with carefully selected parameters that aid in avoiding obstacles, speeding up path planning, and achieving minimal energy consumption. To demonstrate the effectiveness of the proposed algorithm, three types of numerical experiments including the ϵ-greedy MADDPG, MADDPG, and Q-Learning methods were conducted. The results show that the proposed algorithm can effectively solve the multi-AGV task assignment and path planning problems, and the energy consumption results show that the planned routes can effectively improve energy efficiency.

A Hybrid Evolutionary Algorithm Using Two Solution Representations for Hybrid Flow-Shop Scheduling Problem.

As an extension of the classical flow-shop scheduling problem, the hybrid flow-shop scheduling problem (HFSP) widely exists in large-scale industrial production systems and has been considered to be challenging for its complexity and flexibility. Evolutionary algorithms based on encoding and heuristic decoding approaches are shown effective in solving the HFSP. However, frequently used encoding and decoding strategies can only search a limited area of the solution space, thus leading to unsatisfactory performance during the later period. In this article, a hybrid evolutionary algorithm (HEA) using two solution representations is proposed to solve the HFSP for makespan minimization. First, the proposed HEA searches the solution space by a permutation-based encoding representation and two heuristic decoding methods to find some promising areas. Afterward, a Tabu search (TS) procedure based on a disjunctive graph representation is introduced to expand the searching space for further optimization. Two classical neighborhood structures focusing on critical paths are extended to the problem-specific backward schedules to generate candidate solutions for the TS. The proposed HEA is tested on three public HFSP benchmark sets from the existing literature, including 567 instances in total, and is compared with some state-of-the-art algorithms. Extensive experimental results indicate that the proposed HEA performs much better than the other algorithms. Moreover, the proposed method finds new best solutions for 285 hard instances.

Surrogate-Assisted Multi-Objective Evolutionary Optimization With Pareto Front Model-Based Local Search Method.

Some local search methods have been incorporated into surrogate-assisted multi-objective evolutionary algorithms to accelerate the search toward the real Pareto front (PF). In this article, a PF model-based local search method is proposed to accelerate the exploration and exploitation of the PF. It first builds a predicted PF model with current nondominated solutions. Then, some sparse points in the predicted PF are selected to guide the search directions of the local search in order to promote the search of promising sparse areas. The approximation degree of the predicted and real PFs will influence the speed of the local search, while extreme points can significantly influence the shape of the PF. To accelerate the search progress, the optima of surrogate models are utilized to promote the progress of finding extreme points. The proposed local search method is incorporated into a surrogate-assisted multi-objective evolutionary algorithm. The proposed surrogate-assisted multi-objective evolutionary algorithm with the proposed local search method is tested with Zitzler-Deb-Thiele (ZDT), Deb-Thiele-Laummans-Zitzler (DTLZ), and MAF instances. The experimental results demonstrated the efficiency of the proposed local search method and the superiority of the proposed algorithm.

Hybrid Loss-Constrained Lightweight Convolutional Neural Networks for Cervical Cell Classification.

Artificial intelligence (AI) technologies have resulted in remarkable achievements and conferred massive benefits to computer-aided systems in medical imaging. However, the worldwide usage of AI-based automation-assisted cervical cancer screening systems is hindered by computational cost and resource limitations. Thus, a highly economical and efficient model with enhanced classification ability is much more desirable. This paper proposes a hybrid loss function with label smoothing to improve the distinguishing power of lightweight convolutional neural networks (CNNs) for cervical cell classification. The results strengthen our confidence in hybrid loss-constrained lightweight CNNs, which can achieve satisfactory accuracy with much lower computational cost for the SIPakMeD dataset. In particular, ShufflenetV2 obtained a comparable classification result (96.18% in accuracy, 96.30% in precision, 96.23% in recall, and 99.08% in specificity) with only one-seventh of the memory usage, one-sixth of the number of parameters, and one-fiftieth of total flops compared with Densenet-121 (96.79% in accuracy). GhostNet achieved an improved classification result (96.39% accuracy, 96.42% precision, 96.39% recall, and 99.09% specificity) with one-half of the memory usage, one-quarter of the number of parameters, and one-fiftieth of total flops compared with Densenet-121 (96.79% in accuracy). The proposed lightweight CNNs are likely to lead to an easily-applicable and cost-efficient automation-assisted system for cervical cancer diagnosis and prevention.

A balanced and weighted alignment network for partial transfer fault diagnosis.

Domain adaptation techniques have attracted great attention in mechanical fault diagnosis. However, most existing methods work under the assumption that the source and target domains share the identical label space. Such methods are unable to handle a practical issue where the target label space is a subset of the source label space. To tackle this challenge, a balanced and weighted alignment network is proposed for partial transfer fault diagnosis. The proposed method views this issue from a new angle by augmenting the target domain to make the classes of two domains balanced and shortening class-center distances to reduce conditional distribution shifts. Meanwhile, a weighted adversarial alignment is developed to filter out the irrelative source samples and minimize marginal distribution discrepancy. As such, negative transfer can be avoided, and positive transfer can be enhanced. Comprehensive experiments on two test rigs demonstrate that the proposed method achieves promising performance and outperforms state-of-the-art partial transfer methods.

Rocaglamide promotes the infiltration and antitumor immunity of NK cells by activating cGAS-STING signaling in non-small cell lung cancer.

Background: Natural killer (NK) cell-based immunotherapy is clinically limited due to insufficient tumor infiltration in solid tumors. We have previously found that the natural product rocaglamide (RocA) can enhance NK cell-mediated killing of non-small cell lung cancer (NSCLC) cells by inhibiting autophagy, and autophagic inhibition has been shown to increase NK cell tumor infiltration in melanoma. Therefore, we hypothesized that RocA could increase NK cell infiltration in NSCLC by autophagy inhibition. Methods: Flow cytometry, RNA-sequencing, real-time PCR, Western blotting analysis, and xenograft tumor model were utilized to assess the infiltration of NK cells and the underlying mechanism. Results: RocA significantly increased the infiltration of NK cells and the expressions of CCL5 and CXCL10 in NSCLC cells, which could not be reversed by the inhibitions of autophagy/ULK1, JNK and NF-κB. However, such up-regulation could be suppressed by the inhibitions of TKB1 and STING. Furthermore, RocA dramatically activated the cGAS (cyclic GMP-AMP synthase)-STING (stimulator of interferon genes) signaling pathway, and the inhibition/depletion of STING ablated the up-regulation of CCL5 and CXCL10, NK cell infiltration, and tumor regression induced by RocA. Besides, RocA damaged mitochondrial DNA (mtDNA) and promoted the cytoplasmic release of mtDNA. The mPTP inhibitor cyclosporin A could reverse RocA-induced cytoplasmic release of mtDNA. Conclusions: RocA could promote NK cell infiltration by activating cGAS-STING signaling via targeting mtDNA, but not by inhibiting autophagy. Taken together, our current findings suggested that RocA was a potent cGAS-STING agonist and had a promising potential in cancer immunotherapy, especially in NK cell-based immunotherapy.

Resetting Weight Vectors in MOEA/D for Multiobjective Optimization Problems With Discontinuous Pareto Front.

When a multiobjective evolutionary algorithm based on decomposition (MOEA/D) is applied to solve problems with discontinuous Pareto front (PF), a set of evenly distributed weight vectors may lead to many solutions assembling in boundaries of the discontinuous PF. To overcome this limitation, this article proposes a mechanism of resetting weight vectors (RWVs) for MOEA/D. When the RWV mechanism is triggered, a classic data clustering algorithm DBSCAN is used to categorize current solutions into several parts. A classic statistical method called principal component analysis (PCA) is used to determine the ideal number of solutions in each part of PF. Thereafter, PCA is used again for each part of PF separately and virtual targeted solutions are generated by linear interpolation methods. Then, the new weight vectors are reset according to the interrelationship between the optimal solutions and the weight vectors under the Tchebycheff decomposition framework. Finally, taking advantage of the current obtained solutions, the new solutions in the decision space are updated via a linear interpolation method. Numerical experiments show that the proposed MOEA/D-RWV can achieve good results for bi-objective and tri-objective optimization problems with discontinuous PF. In addition, the test on a recently proposed MaF benchmark suite demonstrates that MOEA/D-RWV also works for some problems with other complicated characteristics.

Corrigendum to "Digital twins-based remote semi-physical commissioning of flow-type smart manufacturing systems". J. Clean. Prod. 306 (2021) 127278.

[This corrects the article DOI: 10.1016/j.jclepro.2021.127278.].

Grain-sized moxibustion promotes NK cell antitumour immunity by inhibiting adrenergic signalling in non-small cell lung cancer.

Lung cancer is the leading cause of cancer-related death worldwide, and non-small cell lung cancer (NSCLC) accounts for 85% of lung cancer diagnoses. As an ancient therapy, moxibustion has been used to treat cancer-related symptoms in clinical practice. However, its antitumour effect on NSCLC remains largely unexplored. In the present study, a Lewis lung cancer (LLC) xenograft tumour model was established, and grain-sized moxibustion (gMoxi) was performed at the acupoint of Zusanli (ST36). Flow cytometry and RNA sequencing (RNA-Seq) were used to access the immune cell phenotype, cytotoxicity and gene expression. PK136, propranolol and epinephrine were used for natural killer (NK) cell depletion, ß-adrenoceptor blockade and activation, respectively. Results showed that gMoxi significantly inhibited LLC tumour growth. Moreover, gMoxi significantly increased the proportion, infiltration and activation of NK cells, whereas it did not affect CD4+ and CD8+ T cells. NK cell depletion reversed gMoxi-mediated tumour regression. LLC tumour RNA-Seq indicated that these effects might be related to the inhibition of adrenergic signalling. Surely, ß-blocker propranolol clearly inhibited LLC tumour growth and promoted NK cells, and gMoxi no longer increased tumour regression and promoted NK cells after propranolol treatment. Epinephrine could inhibit NK cell activity, and gMoxi significantly inhibited tumour growth and promoted NK cells after epinephrine treatment. These results demonstrated that gMoxi could promote NK cell antitumour immunity by inhibiting adrenergic signalling, suggesting that gMoxi could be used as a promising therapeutic regimen for the treatment of NSCLC, and it had a great potential in NK cell-based cancer immunotherapy.

A Surrogate-Assisted Multiswarm Optimization Algorithm for High-Dimensional Computationally Expensive Problems.

This article presents a surrogate-assisted multiswarm optimization (SAMSO) algorithm for high-dimensional computationally expensive problems. The proposed algorithm includes two swarms: the first one uses the learner phase of teaching-learning-based optimization (TLBO) to enhance exploration and the second one uses the particle swarm optimization (PSO) for faster convergence. These two swarms can learn from each other. A dynamic swarm size adjustment scheme is proposed to control the evolutionary progress. Two coordinate systems are used to generate promising positions for the PSO in order to further enhance its search efficiency on different function landscapes. Moreover, a novel prescreening criterion is proposed to select promising individuals for exact function evaluations. Several commonly used benchmark functions with their dimensions varying from 30 to 200 are adopted to evaluate the proposed algorithm. The experimental results demonstrate the superiority of the proposed algorithm over three state-of-the-art algorithms.

Digital twins-based remote semi-physical commissioning of flow-type smart manufacturing systems.

The COVID-19 has become a global pandemic that dramatically impacted human lives and economic activities. Due to the high risk of getting affected in high-density population areas and the implementation of national emergency measures under the COVID-19 pandemic, both travel and transportation among cities become difficult for engineers and equipment. Consequently, the costly physical commissioning of a new manufacturing system is greatly hindered. As an emerging technology, digital twins can achieve semi-physical simulation to avoid the vast cost of physical commissioning of the manufacturing system. Therefore, this paper proposes a digital twins-based remote semi-physical commissioning (DT-RSPC) approach for open architecture flow-type smart manufacturing systems. A digital twin system is developed to enable the remote semi-physical commissioning. The proposed approach is validated through a case study of digital twins-based remote semi-physical commissioning of a smartphone assembly line. The results showed that combining the open architecture design paradigm with the proposed digital twins-based approach makes the commissioning of a new flow-type smart manufacturing system more sustainable.

Exosomes derived from mesenchymal stem cells inhibit neointimal hyperplasia by activating the Erk1/2 signalling pathway in rats.

BACKGROUND: Restenosis is a serious problem in patients who have undergone percutaneous transluminal angioplasty. Endothelial injury resulting from surgery can lead to endothelial dysfunction and neointimal formation by inducing aberrant proliferation and migration of vascular smooth muscle cells. Exosomes secreted by mesenchymal stem cells have been a hot topic in cardioprotective research. However, to date, exosomes derived from mesenchymal stem cells (MSC-Exo) have rarely been reported in association with restenosis after artery injury. The aim of this study was to investigate whether MSC-Exo inhibit neointimal hyperplasia in a rat model of carotid artery balloon-induced injury and, if so, to explore the underlying mechanisms. METHODS: Characterization of MSC-Exo immunophenotypes was performed by electron microscopy, nanoparticle tracking analysis and western blot assays. To investigate whether MSC-Exo inhibited neointimal hyperplasia, rats were intravenously injected with normal saline or MSC-Exo after carotid artery balloon-induced injury. Haematoxylin-eosin staining was performed to examine the intimal and media areas. Evans blue dye staining was performed to examine re-endothelialization. Moreover, immunohistochemistry and immunofluorescence were performed to examine the expression of CD31, vWF and α-SMA. To further investigate the involvement of MSC-Exo-induced re-endothelialization, the underlying mechanisms were studied by cell counting kit-8, cell scratch, immunofluorescence and western blot assays. RESULTS: Our data showed that MSC-Exo were ingested by endothelial cells and that systemic injection of MSC-Exo suppressed neointimal hyperplasia after artery injury. The Evans blue staining results showed that MSC-Exo could accelerate re-endothelialization compared to the saline group. The immunofluorescence and immunohistochemistry results showed that MSC-Exo upregulated the expression of CD31 and vWF but downregulated the expression of α-SMA. Furthermore, MSC-Exo mechanistically facilitated proliferation and migration by activating the Erk1/2 signalling pathway. The western blot results showed that MSC-Exo upregulated the expression of PCNA, Cyclin D1, Vimentin, MMP2 and MMP9 compared to that in the control group. Interestingly, an Erk1/2 inhibitor reversed the expression of the above proteins. CONCLUSION: Our data suggest that MSC-Exo can inhibit neointimal hyperplasia after carotid artery injury by accelerating re-endothelialization, which is accompanied by activation of the Erk1/2 signalling pathway. Importantly, our study provides a novel cell-free approach for the treatment of restenosis diseases after intervention.

A Novel Point Cloud Encoding Method Based on Local Information for 3D Classification and Segmentation.

Deep learning is robust to the perturbation of a point cloud, which is an important data form in the Internet of Things. However, it cannot effectively capture the local information of the point cloud and recognize the fine-grained features of an object. Different levels of features in the deep learning network are integrated to obtain local information, but this strategy increases network complexity. This paper proposes an effective point cloud encoding method that facilitates the deep learning network to utilize the local information. An axis-aligned cube is used to search for a local region that represents the local information. All of the points in the local region are available to construct the feature representation of each point. These feature representations are then input to a deep learning network. Two well-known datasets, ModelNet40 shape classification benchmark and Stanford 3D Indoor Semantics Dataset, are used to test the performance of the proposed method. Compared with other methods with complicated structures, the proposed method with only a simple deep learning network, can achieve a higher accuracy in 3D object classification and semantic segmentation.

A Two-Level WiFi Fingerprint-Based Indoor Localization Method for Dangerous Area Monitoring.

Localization technologies play an important role in disaster management and emergence response. In areas where the environment does not change much after an accident or in the case of dangerous areas monitoring, indoor fingerprint-based localization can be used. In such scenarios, a positioning system needs to have both a high accuracy and a rapid response. However, these two requirements are usually conflicting since a fingerprint-based indoor localization system with high accuracy usually has complex algorithms and needs to process a large amount of data, and therefore has a slow response. This problem becomes even worse when both the size of monitoring area and the number of reference nodes increase. To address this challenging problem, this paper proposes a two-level positioning algorithm in order to improve both the accuracy and the response time. In the off-line stage, a fingerprint database is divided into several sub databases by using an affinity propagation clustering (APC) algorithm based on Shepard similarity. The online stage has two steps: (1) a coarse positioning algorithm is adopted to find the most similar sub database by matching the cluster center with the fingerprint of the node tested, which will narrow the search space and consequently save time; (2) in the sub database area, a support vector regression (SVR) algorithm with its parameters being optimized by particle swarm optimization (PSO) is used for fine positioning, thus improving the online positioning accuracy. Both experiment results and actual implementations proved that the proposed two-level localization method is more suitable than other methods in term of algorithm complexity, storage requirements and localization accuracy in dangerous area monitoring.

IL-25 promotes cisplatin resistance of lung cancer cells by activating NF-κB signaling pathway to increase of major vault protein.

As an inflammatory factor, IL-25 has been studied in variouscancers, but it is rarely reported in cancer chemotherapy resistance. Major vault protein (MVP), as a gene associated with lung multidrug resistance, is associated with multiple chemotherapy resistances of lung cancer. However, the relationship between IL-25 and MVP in lung cancer cells has not been studied. In this study, we found that both IL-25 and MVP were elevated expressed in cisplatin-resistant lung adenocarcinoma cell line (A549/CDDP). Silencing of IL-25 resulted in down-regulation of MVP expression and reduced cisplatin tolerance of A549/CDDP cells. Overexpression of IL-25 resulted in increase of MVP expression and the cisplatin tolerance in A549 cells. In addition, we found that the extracellular IL-25 could stimulate the expression of MVP and activate the NF-κB signaling pathway. Further, animal models also confirmed that IL-25 reduced the sensitivity of xenografts to chemotherapy. Taken together, we believe that the up-regulation of IL-25 induces MVP expression contributing to chemotherapy resistances of lung cancer cells. Our findings suggest that interference the expression of IL-25 might be potential treatment strategies for the clinical reversing the chemotherapy resistance.

Internet of Things in Marine Environment Monitoring: A Review.

Marine environment monitoring has attracted more and more attention due to the growing concern about climate change. During the past couple of decades, advanced information and communication technologies have been applied to the development of various marine environment monitoring systems. Among others, the Internet of Things (IoT) has been playing an important role in this area. This paper presents a review of the application of the Internet of Things in the field of marine environment monitoring. New technologies including advanced Big Data analytics and their applications in this area are briefly reviewed. It also discusses key research challenges and opportunities in this area, including the potential application of IoT and Big Data in marine environment protection.

Bearing Fault Diagnosis Method Based on Deep Convolutional Neural Network and Random Forest Ensemble Learning.

Recently, research on data-driven bearing fault diagnosis methods has attracted increasing attention due to the availability of massive condition monitoring data. However, most existing methods still have difficulties in learning representative features from the raw data. In addition, they assume that the feature distribution of training data in source domain is the same as that of testing data in target domain, which is invalid in many real-world bearing fault diagnosis problems. Since deep learning has the automatic feature extraction ability and ensemble learning can improve the accuracy and generalization performance of classifiers, this paper proposes a novel bearing fault diagnosis method based on deep convolutional neural network (CNN) and random forest (RF) ensemble learning. Firstly, time domain vibration signals are converted into two dimensional (2D) gray-scale images containing abundant fault information by continuous wavelet transform (CWT). Secondly, a CNN model based on LeNet-5 is built to automatically extract multi-level features that are sensitive to the detection of faults from the images. Finally, the multi-level features containing both local and global information are utilized to diagnose bearing faults by the ensemble of multiple RF classifiers. In particular, low-level features containing local characteristics and accurate details in the hidden layers are combined to improve the diagnostic performance. The effectiveness of the proposed method is validated by two sets of bearing data collected from reliance electric motor and rolling mill, respectively. The experimental results indicate that the proposed method achieves high accuracy in bearing fault diagnosis under complex operational conditions and is superior to traditional methods and standard deep learning methods.

Multishelled Transition Metal-Based Microspheres: Synthesis and Applications for Batteries and Supercapacitors.

With the rapid growth of material innovations, multishelled hollow nanostructures are of tremendous interest due to their unique structural features and attractive physicochemical properties. Continued effort has been made in the geometric manipulation, composition complexity, and construction diversity of this material, expanding its applications. Energy storage technology has benefited from the large surface area, short transport path, and excellent buffering ability of the nanostructures. In this work, the general synthesis of multishelled hollow structures, especially with architecture versatility, is summarized. A wealth of attractive properties is also discussed for a wide area of potential applications based on energy storage systems, including Li-ion/Na-ion batteries, supercapacitors, and Li-S batteries. Finally, the emerging challenges and outlook for multishelled hollow structures are mentioned.

[The development and recent status of the craniomaxillofacial surgery in China during past three decades].

The authors made a profound review on the development and the recent status of craniomaxillofacial surgery in China during past three decades. The emphases were placed on the following aspects: the modifications of the reconstructive procedure and minimal invasive mode, the researches on molecular genetic characteristics of the congenital craniofacial malformations, the clinical applications of three-dimensional digital computer-aided techniques (including three-dimensional printing and prefabricated template for precious osteotomies), the craniomaxillofacial defects reconstructing by using the distraction osteogenesis and osseous integrated titanium implant and prothesis, etc. Finally, the authors outlooked prospectively the future trends of the craniomaxillofacial surgery.