Search

To alleviate the problem of under-utilization features of sentence-level relation extraction, which leads to insufficient performance of the pre-trained language model and underutilization of the feature vector, a sentence-level relation extraction method based on adding prompt information and feature reuse is proposed. At first, in addition to the pair of nominals and sentence information, a piece of prompt information is added, and the overall feature information consists of sentence information, entity pair information, and prompt information, and then the features are encoded by the pre-trained language model ROBERTA. Moreover, in the pre-trained language model, BIGRU is also introduced in the composition of the neural network to extract information, and the feature information is passed through the neural network to form several sets of feature vectors. After that, these feature vectors are reused in different combinations to form multiple outputs, and the outputs are aggregated using ensemble-learning soft voting to perform relation classification. In addition to this, the sum of cross-entropy, KL divergence, and negative log-likelihood loss is used as the final loss function in this paper. In the comparison experiments, the model based on adding prompt information and feature reuse achieved higher results of the SemEval-2010 task 8 relational dataset.

Viologen-based MOFs were developed to show highly efficient electrocatalytic CO2 reduction reaction with a high CO faradaic efficiency of 93.8% at 2.3 V and large CO partial current density of 111.1 mA cm−2 at 2.9 V.

A highly efficient atomic nickel catalyst Ni-SAC-800 with high porosity and conductivity has been developed to show excellent performance for CO2 electroreduction in acidic conditions.

Inferential modeling has been of significance for modern manufacturing in estimating the quality-related process variables. As an effective inferential model, probabilistic slow feature analysis (PSFA) has gained attention in regression tasks to interpret dynamic properties with a slowness preference. However, PSFA is often challenged by the nonlinear sequential data due to its linear state-space structure. In this study, a new nonlinear extension of PSFA is proposed under the deep learning framework to enhance the dynamic feature extraction with limited labels, incorporating variational inference and Monte Carlo inference to derive the objective function. The proposed model considers the relevance of inputs with outputs as the input weights to upgrade prediction performance. The proposed model is verified through an industrial hydrocracking process to predict diesel yield with missing labels ranged from 0% to 50%, and the root mean squared error is reduced by at least 8.78% compared to PSFA.

Deep-learning-based soft sensors have been extensively developed for predicting key quality or performance variables in industrial processes. However, most approaches assume that data are uniformly sampled while the multiple variables are often acquired at different rates in practical processes. This article designed a progressive transfer strategy, based on which a variational progressive-transfer network (VPTN) method is proposed for the soft sensor development of industrial multirate processes. In VPTN, the multirate data are first separated into multiple data chunks where the variables within each chunk are acquired at a uniform rate. Then, a variational multichunk data modeling framework is developed to model the multiple chunks in a unified fashion through deep variational structures. The base models, including the unsupervised ones with only partial process variables and the supervised soft sensor model share a similar network structure, such that the subsequent transfer strategy can be readily implemented. Finally, a progressive transfer learning strategy is designed to transfer the model parameters from the fastest sampled data chunk to the slowest one in a progressive manner. Thus, the knowledge from various data chunks can be sequentially explored and transferred to enhance the performance of the terminal soft sensor model. Case studies on both a debutanizer column dataset and a real coal mill dataset in a thermal power plant validate the performance of the proposed method.

Objectives This study aimed to establish time-resolved fluorescence immunoassays to quantitatively detect the autoantibodies targeting different epitopes of M-type phospholipase A2 receptor (PLA2R) and evaluate its clinical application in primary membranous nephropathy (PMN). Methods PLA2R and its reactive epitope-specific IgG/IgG4 time-resolved fluorescence immunoassays (TRFIAs) were established using europium-labeled anti-human IgG/IgG4 antibodies, recombinant proteins, and patient serum. The levels of IgG/IgG4 targeting PLA2R and its epitopes in PMN patient serum were detected, and the relationship between epitope spreading of PLA2R and the severity of patients with PMN was evaluated. Results The TRFIAs established in this study could quantitatively detect PLA2R and its epitope-specific IgG and IgG4. Sera from 59 patients with PMN were subjected to detection using anti-PLA2R IgG and anti-PLA2R IgG4. Among them, 46 and 54 patients were found positive for PLA2R antibodies, respectively. Moreover, the levels of PLA2R antibodies were strongly correlated with the severity of patients with PMN. Patients who were detected to have two or more epitopes had more serious renal injury. Conclusions PLA2R domain-specific IgG/IgG4 TRFIAs were established in this study, and detection with anti-PLA2R IgG4 could more sensitively screen the reactivity of patients to the PLA2R domain. Moreover, detection epitope spreading of PLA2R was confirmed which is related to the severity of patients with PMN.

Data-driven methods have been extensively utilized in establishing predictive models from historical data for process monitoring and prediction of quality variables. However, most data-driven approaches assume that training data and testing data come from steady-state operating regions and follow the same distribution, which may not be the case when it comes to complex industrial processes. To avoid these restrictive assumptions and account for practical implementation, a novel online transfer learning technique is proposed to dynamically learn cross-domain features based on the variational Bayesian inference in this work. Stemming from the probabilistic slow feature analysis, a transfer slow feature analysis (TSFA) technique is presented to transfer dynamic models learned from different source processes to enhance prediction performance in the target process. In particular, two weighting functions associated with transition and emission equations are introduced and updated dynamically to quantify the transferability from source domains to the target domain at each time instant. Instead of point estimation, a variational Bayesian inference scheme is designed to learn the parameters under probability distributions accounting for corresponding uncertainties. The effectiveness of the proposed technique with applications to soft sensor modelling is demonstrated by a simulation example, a public dataset and an industrial case study.

Hyperspectral techniques are promising alternatives to traditional methods of investigating potentially toxic metal(loid) contamination. In this study, hyperspectral technology combined with partial least squares regression (PLSR) and extreme learning machine (ELM) established estimation models to predict the contents of copper (Cu), zinc (Zn), arsenic (As), cadmium (Cd), lead (Pb) and tin (Sn) in multi-media environments (mine tailings, soils and sediments) surrounding abandoned mineral processing plants in a typical tin-polymetallic mineral agglomeration in Guangxi Autonomous Region. Four spectral preprocessing methods, Savitzky-Golay (SG) smoothing, continuum removal (CR), first derivative (FD) and continuous wavelet transform (CWT), were used to eliminate noise and highlight spectral features. The optimum combinations of spectral preprocessing and machine learning algorithms were explored, then the estimation models with best accuracy were obtained. CWT and CR were excellent spectral pretreatments for the hyperspectral data regardless of the applied algorithms. The coefficients of determination (R

With the aid of neural networks, this article develops two data-driven designs of fault detection (FD) for dynamic systems. The first neural network is constructed for generating residual signals in the so-called finite impulse response (FIR) filter-based form, and the second one is designed for recursively generating residual signals. By theoretical analysis, we show that two proposed neural networks via self-organizing learning can find their optimal architectures, respectively, corresponding to FIR filter and recursive observer for FD purposes. Additional contributions of this study lie in that we establish bridges that link model- and neural-network-based methods for detecting faults in dynamic systems. An experiment on a three-tank system is adopted to illustrate the effectiveness of two proposed neural network-aided FD algorithms.

Background. Cutaneous squamous cell carcinoma (cSCC) is the leading cause of death in patients with nonmelanoma skin cancers (NMSC). However, the unclear pathogenesis of cSCC limits the application of molecular targeted therapy. Methods. Three microarray datasets (GSE2503, GSE45164, and GSE66359) were downloaded from the Gene Expression Omnibus (GEO). After identifying the differentially expressed genes (DEGs) in tumor and nontumor tissues, five kinds of analyses, namely, functional annotation, protein-protein interaction (PPI) network, hub gene selection, TF-miRNA-mRNA regulatory network analysis, and ferroptosis mechanism, were performed. Results. A total of 146 DEGs were identified with significant differences, including 113 upregulated genes and 33 downregulated genes. The enriched functions and pathways of the DEGs included microtubule-based movement, ATP binding, cell cycle, P53 signaling pathway, oocyte meiosis, and PLK1 signaling events. Nine hub genes were identified (CDK1, AURKA, RRM2, CENPE, CCNB1, KIAA0101, ZWINT, TOP2A, and ASPM). Finally, RRM2, AURKA, and SAT1 were identified as significant ferroptosis-related genes in cSCC. The differential expression of these genes has been verified in two other independent datasets. Conclusions. By integrated bioinformatic analysis, the hub genes identified in this study elucidated the molecular mechanism of the pathogenesis and progression of cSCC and are expected to become future biomarkers or therapeutic targets.

Although hydroxyapatite (HAP) can prominently lower Cd uptake by celery from Cd-polluted soil, its high application rates in reality may lead to high cost and potential environmental risk. Therefore, we aimed to clarify whether combined amendments of HAP and another low-cost material (hydrated lime, corn straw-derived biochar, or zeolite) with reduced application rate of each single amendment could significantly decrease Cd transfer in soil-celery-human system without side effect on celery growth through a pot experiment. Results revealed that adding biochar, HAP, zeolite, or combined amendments had no obvious side effect on celery growth, while adding 0.3% hydrated lime significantly decreased fresh edible celery yield by 69.0%. Conversely, adding 0.5% HAP + 0.05% hydrated lime increased fresh edible celery yield by 39.8%. Additionally, adding HAP, zeolite, or hydrated lime rather than adding biochar effectively decreased total and bioaccessible Cd in edible celery. Similarly, HAP + hydrated lime and HAP + zeolite were much more efficient than HAP + biochar in lowering Cd transfer in soil-celery-human system. The total and bioaccessible Cd in edible celery were even reduced by over 50.0% after adding HAP + hydrated lime or HAP + zeolite at low rates. Considering the effects on celery growth and Cd transfer, HAP + hydrated lime and HAP + zeolite have the potential in remediating soil Cd contamination.

In this article, the optimal consensus problem at specified data points is considered for heterogeneous networked agents with iteration-switching topologies. A point-to-point linear data model (PTP-LDM) is proposed for heterogeneous agents to establish an iterative input-output relationship of the agents at the specified data points between two consecutive iterations. The proposed PTP-LDM is only used to facilitate the subsequent controller design and analysis. In the sequel, an iterative identification algorithm is presented to estimate the unknown parameters in the PTP-LDM. Next, an event-triggered point-to-point iterative learning control (ET-PTPILC) is proposed to achieve an optimal consensus of heterogeneous networked agents with switching topology. A Lyapunov function is designed to attain the event-triggering condition where only the control information at the specified data points is available. The controller is updated in a batch wise only when the event-triggering condition is satisfied, thus saving significant communication resources and reducing the number of the actuator updates. The convergence is proved mathematically. In addition, the results are also extended from linear discrete-time systems to nonlinear nonaffine discrete-time systems. The validity of the presented ET-PTPILC method is demonstrated through simulation studies.

Lately, variational autoencoder (VAE) has arisen as one of the most prevalent methods for unsupervised learning of intricate distributions. Despite being successful in deep feature extraction and uncertain data modelling, it still suffers from the instability and reconstruction error due to random sampling in the latent subspace representation of original input space. In this paper, to deal with those limitations, constrained VAE (CVAE) is proposed by utilizing input sample information. Enthused by parallel interaction mechanism between the ventral and dorsal stream of human brain in object recognition, parallel interaction spatial-temporal CVAE (PIST-CVAE) is proposed to extract spatial and temporal features from input samples. Lower dimensional nonlinear features extracted from PIST-CVAE are used to build the soft sensor. The effectiveness of CVAE and PIST-CVAE is demonstrated in an industrial case study, a polyester polymerization process.

Aiming to addressing the nonrepetitive uncertainties of multiagent systems, this work proposes a discrete-time-distributed adaptive iterative learning control (DDAILC) scheme for an output consensus problem, where two fundamental requirements in the traditional distributed iterative learning control (ILC) methods, i.e., the identical initial states and the repetitive desired trajectories, are removed. Furthermore, the algorithm design and analysis are directly aimed at discrete-time nonlinear multiagent systems, rather than continuous-time ones, to meet the needs of practical implementations. The iteration-varying trajectory of the virtual leader is included in the learning control protocol for a compensation. The adaptive parameter-updating law works along the iteration dimension by using a general consensus error that contains the output data of adjacent agents. To ensure the estimation of the control gain to be nonzero, a semisaturator is utilized in the parameter-updating law. The convergence of the output consensus is shown rigorously. Both numerical and practical examples are used to test the theoretical results. Moreover, the DDAILC efficiently improves performance of the building heating, ventilation, and air conditioning (HVAC) system by utilizing both the distributed topology and the repetitive dynamic characteristic.

Modern industrial plants generally consist of multiple manufacturing units, and the local correlation within each unit can be used to effectively alleviate the effect of spurious correlation and meticulously reflect the operation status of the process system. Therefore, the local correlation, which is called spatial information here, should also be taken into consideration when developing the monitoring model. In this study, a cascaded monitoring network (MoniNet) method is proposed to develop the monitoring model with concurrent analytics of temporal and spatial information. By implementing convolutional operation to each variable, the temporal information that reveals dynamic correlation of process data and spatial information that reflects local characteristics within individual operation unit can be extracted simultaneously. For each convolutional feature, a submodel is developed and then all the submodels are integrated to generate a final monitoring model. Based on the developed model, the operation status of the newly collected sample can be identified by comparing the calculated statistics with their corresponding control limits. Similar to the convolutional neural network (CNN), the MoniNet can also expand its receptive field and capture deeper information by adding more convolutional layers. Besides, the filter selection and submodel development in MoniNet can be replaced to generalize the proposed network to many existing monitoring strategies. The performance of the proposed method is validated using two real industrial processes. The illustration results show that the proposed method can effectively detect process anomalies by concurrent analytics of temporal and spatial information.