Search

Dysfunction of the vascular angiocrine system is critically involved in regenerative defects and fibrosis of injured organs. Previous studies have identified various angiocrine factors and found that risk factors such as aging and metabolic disorders can disturb the vascular angiocrine system in fibrotic organs. One existing key gap is what sense the fibrotic risk to modulate the vascular angiocrine system in organ fibrosis. Here, using human and mouse data, we discovered that the metabolic pathway hydrogen sulfide (H2S)-AMP-activated protein kinase (AMPK) is a sensor of fibrotic stress and serves as a key mechanism upregulating the angiocrine factor plasminogen activator inhibitor-1 (PAI-1) in endothelial cells to participate in lung fibrosis. Activation of the metabolic sensor AMPK was inhibited in endothelial cells of fibrotic lungs, and AMPK inactivation was correlated with enriched fibrotic signature and reduced lung functions in humans. The inactivation of endothelial AMPK accelerated lung fibrosis in mice, while the activation of endothelial AMPK with metformin alleviated lung fibrosis. In fibrotic lungs, endothelial AMPK inactivation led to YAP activation and overexpression of the angiocrine factor PAI-1, which was positively correlated with the fibrotic signature in human fibrotic lungs and inhibition of PAI-1 with Tiplaxtinin mitigated lung fibrosis. Further study identified that the deficiency of the antioxidative gas metabolite H2S accounted for the inactivation of AMPK and activation of YAP-PAI-1 signaling in endothelial cells of fibrotic lungs. H2S deficiency was involved in human lung fibrosis and H2S supplement reversed mouse lung fibrosis in an endothelial AMPK-dependent manner. These findings provide new insight into the mechanism underlying the deregulation of the vascular angiocrine system in fibrotic organs.

Object detection via remote sensing encounters significant challenges due to factors such as small target sizes, uneven target distribution, and complex backgrounds. This paper introduces the K-CBST YOLO algorithm, which is designed to address these challenges. It features a novel architecture that integrates the Convolutional Block Attention Module (CBAM) and Swin-Transformer to enhance global semantic understanding of feature maps and maximize the utilization of contextual information. Such integration significantly improves the accuracy with which small targets are detected against complex backgrounds. Additionally, we propose an improved detection network that combines the improved K-Means algorithm with a smooth Non-Maximum Suppression (NMS) algorithm. This network employs an adaptive dynamic K-Means clustering algorithm to pinpoint target areas of concentration in remote sensing images that feature varied distributions and uses a smooth NMS algorithm to suppress the confidence of overlapping candidate boxes, thereby minimizing their interference with subsequent detection results. The enhanced algorithm substantially bolsters the model’s robustness in handling multi-scale target distributions, preserves more potentially valid information, and diminishes the likelihood of missed detections. This study involved experiments performed on the publicly available DIOR remote sensing image dataset and the DOTA aerial image dataset. Our experimental results demonstrate that, compared with other advanced detection algorithms, K-CBST YOLO outperforms all its counterparts in handling both datasets. It achieved a 68.3% mean Average Precision (mAP) on the DIOR dataset and a 78.4% mAP on the DOTA dataset.

The accuracy and reliability of unmanned aerial vehicle (UAV) visual positioning systems are dependent on the performance of multi-source image matching algorithms. Despite many advancements, targeted performance evaluation frameworks and datasets for UAV positioning are still lacking. Moreover, existing consistency verification methods such as Random Sample Consensus (RANSAC) often fail to entirely eliminate mismatches, affecting the precision and stability of the matching process. The contributions of this research include the following: (1) the development of a benchmarking framework accompanied by a large evaluation dataset for assessing the efficacy of multi-source image matching algorithms; (2) the results of this benchmarking framework indicate that combinations of multiple algorithms significantly enhance the Match Success Rate (MSR); (3) the introduction of a novel Geographic Geometric Consistency (GGC) method that effectively identifies mismatches within RANSAC results and accommodates rotational and scale variations; and (4) the implementation of a distance threshold iteration (DTI) method that, according to experimental results, achieves an 87.29% MSR with a Root Mean Square Error (RMSE) of 1.11 m (2.22 pixels) while maintaining runtime at only 1.52 times that of a single execution, thus optimizing the trade-off between MSR, accuracy, and efficiency. Furthermore, when compared with existing studies on UAV positioning, the multi-source image matching algorithms demonstrated a sub-meter positioning error, significantly outperforming the comparative method. These advancements are poised to enhance the application of advanced multi-source image matching technologies in UAV visual positioning.

Rapid developments in automatic driving technology have given rise to new experiences for passengers. Safety is a main priority in automatic driving. A strong familiarity with road-surface conditions during the day and night is essential to ensuring driving safety. Existing models used for recognizing road-surface conditions lack the required robustness and generalization abilities. Most studies only validated the performance of these models on daylight images. To address this problem, we propose a novel multi-supervised bidirectional fusion network (MBFN) model to detect weather-induced road-surface conditions on the path of automatic vehicles at both daytime and nighttime. We employed ConvNeXt to extract the basic features, which were further processed using a new bidirectional fusion module to create a fused feature. Then, the basic and fused features were concatenated to generate a refined feature with greater discriminative and generalization abilities. Finally, we designed a multi-supervised loss function to train the MBFN model based on the extracted features. Experiments were conducted using two public datasets. The results clearly demonstrated that the MBFN model could classify diverse road-surface conditions, such as dry, wet, and snowy conditions, with a satisfactory accuracy and outperform state-of-the-art baseline models. Notably, the proposed model has multiple variants that could also achieve competitive performances under different road conditions. The code for the MBFN model is shared at https://zenodo.org/badge/latestdoi/607014079.

In order to study the influence of isolator arrangement on the vibration of the foundation in a marine gearbox，a gear system with single-stage isolation is taken as an example. The impedance model of gear pair，shaft，bearing，housing，isolator，and foundation is constituted considering the flexibility of subsystems，and the impedance synthesis approach is adopted to constitute the coupled impedance model. The influence of the span，non-symmetric arrangement，and number of isolator on the vibration isolation is studied. Results show that，slightly decrease the span of isolators is beneficial to vibration isolation，the symmetric arrangement of isolators is not the optimal scheme to reduce vibration，increasing the number of isolator does not always increase vibration，and the rib feature of housing and foundation cannot be ignored in the vibration isolation analysis.

The nonconstant concrete flow due to the alternating pumping of the twin cylinder of the hydraulic pump will cause vibration of concrete pump trucks. Furthermore, the discontinuous pumping of concrete caused by inadequate suction and air doping will exacerbate the vibration. In order to study the effect of nonconstant and discontinuous pumping of concrete on the dynamic response and vibrational stability of the whole vehicle, multi-fluid pumping models with concrete-lubrication gas for straight and elbow pipes are established, respectively, and the boundary conditions of periodic pumping speed are taken into account to compare the rheological characteristics of concrete and the exciting force on the pipe wall under nonconstant pumping, discontinuous pumping and nonconstant discontinuous pumping conditions. Results show that the pipe pressure and the exciting force vary periodically with the pumping speed under nonconstant pumping conditions, and the peak-to-peak value of the pipe pressure and excitation for discontinuous pumping depend on the volume fraction and distribution state of the gas in the pipe.

The FFT-DBN model based on fast Fourier transform and deep belief network， WT-CNN model based on wavelet transform and deep convolutional neural network and HHT-CNN model based on Hilbert Huang transform and deep convolutional neural network are established respectively. Through the integration of the three depth learning models， the comprehensive evaluation model of gear system fault diagnosis based on depth learning is further constructed. By setting up the vibration test bench of the power closed gear system， the test gear pairs with different failure modes are processed and their vibration acceleration signals are extracted as samples， the fault identification effect of the comprehensive evaluation model based on the depth learning is compared with other models， and the results show that the comprehensive evaluation model based on the depth learning can effectively identify a variety of gear faults. Comparing with other models， the fault recognition accuracy of the comprehensive evaluation model based on deep learning is higher.

Abstract Background Blood cultures are often performed to detect patients who has a serious illness without infections and patients with bloodstream infections. Early positive blood culture prediction is important, as bloodstream infections may cause inflammation of the body, even organ failure or death. However, existing work mainly adopts statistical models with laboratory indicators, and fails to make full use of textual description information from EHRs. Methods We study the problem of positive blood culture prediction by using neural network model. Specifically, we first construct dataset from raw EHRs. Then we propose a hybrid neural network which incorporates attention based Bi-directional Long Short-Term Memory and Autoencoder networks to fully capture the information in EHRs. Results In order to evaluate the proposed method, we constructe a dataset which consists of totally 5963 patients who had one or more blood cultures tests during hospitalization. Experimental results show that the proposed neural model gets 91.23% F-measure for this task. Conclusions The comparison results of different models demonstrated the effectiveness of our model. The proposed model outperformed traditional statistical models.

Abstract Background Disease prediction based on Electronic Health Records (EHR) has become one hot research topic in biomedical community. Existing work mainly focuses on the prediction of one target disease, and little work is proposed for multiple associated diseases prediction. Meanwhile, a piece of EHR usually contains two main information: the textual description and physical indicators. However, existing work largely adopts statistical models with discrete features from numerical physical indicators in EHR, and fails to make full use of textual description information. Methods In this paper, we study the problem of kidney disease prediction in hypertension patients by using neural network model. Specifically, we first model the prediction problem as a binary classification task. Then we propose a hybrid neural network which incorporates Bidirectional Long Short-Term Memory (BiLSTM) and Autoencoder networks to fully capture the information in EHR. Results We construct a dataset based on a large number of raw EHR data. The dataset consists of totally 35,332 records from hypertension patients. Experimental results show that the proposed neural model achieves 89.7% accuracy for the task. Conclusions A hybrid neural network model was presented. Based on the constructed dataset, the comparison results of different models demonstrated the effectiveness of the proposed neural model. The proposed model outperformed traditional statistical models with discrete features and neural baseline systems.

With the development of e-commerce, more and more users begin to post reviews or comments about the quality of products on the internet. Meanwhile, people usually read previous reviews before purchasing online products. However, people are frequently deceived by deceptive opinion spam, which is usually used for promoting the products or damaging their reputations because of economic benefit. Deceptive opinion spam can mislead people's purchase behavior, so the techniques of detecting deceptive opinion spam have extensively been researched in past ten years. In particular, some work based on deep learning has been investigated in last three years for the task. However, there still lack a survey, which can systematically analyze and summarize the previous techniques. To address this issue, this paper first introduces the task of deceptive opinion spam detection. Then, we summarize the existing dataset resources and their construction methods. Third, existing methods are analyzed from two aspects: traditional statistical methods and neural network models. Finally, we give some future directions of the task.

Narrative reports in medical records contain abundant clinical information that may be converted into structured data for managing patient information and predicting trends in diseases. Though various rule-based and machine-learning methods are available in electronic medical records (EMRs), a few works have explored the hybrid methods in extracting information from the Chinese EMRs. In this paper, we developed a novel hybrid approach which integrates the rules and bidirectional long short-term memory with a conditional random field layer (BiLSTM-CRF) model to extract clinical entities and attributes. A corpus of 1509 electronic notes (discharge summaries and operation notes) was annotated. Annotation from three clinicians was reconciled to form a gold standard dataset. The performance of our method was assessed by calculating the precision, recall, and F-measure for two boundary matching strategies. The experimental results demonstrate the effectiveness of our method in clinical information extraction from the Chinese EMRs.

Sentiment analysis has attracted extensive attention in recent years. Existing work mainly focuses on sentiment classification task in which a text or sentence usually contains sentiment word to express subjective feeling. However, little research is proposed for identifying implicit polarity of a text. Here, implicit polarity of a text means that the text does not contain sentiment words but still express a positive or negative sentiment. To address this issue, we propose an attention-based neural network model to identify implicit polarity of events. In particular, the model first learns the sentence representation by recurrent neural network with gated recurrent unit. Then multiple hops attention mechanism is used for capturing multiple aspects closely related to sentiment polarity and the event type. Experimental results on SemEval 2015 dataset show the effectiveness of the proposed model, outperforming the previous systems and strong neural baselines.

Gray blight disease is one of the most destructive diseases of tea plants and occurs widely in the tea-growing areas of the world. It is caused by several fungal phytopathogens, of which Pseudopestalotiopsis camelliae-sinensis is the main pathogen in China. The environmentally friendly antimicrobial, phenazine-1-carboxylic acid (PCA), a metabolite of the natural soil-borne bacteria Pseudomonas spp., can inhibit a range of fungal crop diseases. In this study, we determined that PCA was active against Ps. camelliae-sinensis in vitro. We studied the mode of action of PCA on hyphae using a microscopic investigation, transcriptomics, biochemical methods, and molecular docking. The results of scanning and transmission electron microscopy indicated that PCA caused developmental deformity of mycelia and organelle damage, and it significantly decreased the accumulation of exopolysaccharides on the hyphal surface. The transcriptome revealed that 1705 and 1683 differentially expressed genes of Ps. camelliae-sinensis treated with PCA were up-regulated or down-regulated, respectively, with genes associated with ribosome biogenesis, oxidative phosphorylation, and encoding various proteins of N-glycan biosynthesis being significantly up-regulated. Up-regulation of nine genes related to N-glycan biosynthesis of Ps. camelliae-sinensis in response to PCA treatment was confirmed by reverse transcription qPCR. The enzymatic activity of catalase and superoxide dismutase of hyphae was significantly decreased by PCA treatment. Our results indicated that exposure to PCA resulted in expression changes in oxidoreductase genes, accumulation of reactive oxygen species, and decreased activity of catalase, with concomitant damage to the fungal cell membrane and cell wall.

Many keywords in a sentence that represents the semantic propensity of the sentence. These words can exist anywhere in the sentence, which poses a great challenge to sentence semantic classification. The current sentence semantic classification methods usually tackle this problem by the use of attention mechanism, and most of them utilize softmax function to calculate each word’s weight. According to the observation that a word with higher score carries more valuable information in sentence modeling, this paper presents a novel low-complexity model termed as CNN-BiGRU by integrating both convolution neural network (CNN) and bidirectional gated recurrent unit (BiGRU). Both the contextual representations and the semantic distribution are obtained through BiGRU, and the latter is constrained to a Gaussian distribution. In addition, the proposed model utilizes a shallow word-level CNN to obtain intermediate representations, and the score of each word is denoted as the Euclidean distance between the intermediate representations and the semantic distribution. Then, the final representations are obtained by the combination of the contextual representations and the score of each word, and thus, the model learns a compact code for sentence sentiment classification and can be trained end-to-end with limited hyper-parameters. In conclusion, the proposed model is able to focus both the keywords and the underlying semantics of the words. Comprehensive experiments are conducted on seven benchmarks. Compared with the state-of-the-art models, our model has excellent performance.

Abstract Background Biomedical named entity recognition(BNER) is a crucial initial step of information extraction in biomedical domain. The task is typically modeled as a sequence labeling problem. Various machine learning algorithms, such as Conditional Random Fields (CRFs), have been successfully used for this task. However, these state-of-the-art BNER systems largely depend on hand-crafted features. Results We present a recurrent neural network (RNN) framework based on word embeddings and character representation. On top of the neural network architecture, we use a CRF layer to jointly decode labels for the whole sentence. In our approach, contextual information from both directions and long-range dependencies in the sequence, which is useful for this task, can be well modeled by bidirectional variation and long short-term memory (LSTM) unit, respectively. Although our models use word embeddings and character embeddings as the only features, the bidirectional LSTM-RNN (BLSTM-RNN) model achieves state-of-the-art performance — 86.55% F1 on BioCreative II gene mention (GM) corpus and 73.79% F1 on JNLPBA 2004 corpus. Conclusions Our neural network architecture can be successfully used for BNER without any manual feature engineering. Experimental results show that domain-specific pre-trained word embeddings and character-level representation can improve the performance of the LSTM-RNN models. On the GM corpus, we achieve comparable performance compared with other systems using complex hand-crafted features. Considering the JNLPBA corpus, our model achieves the best results, outperforming the previously top performing systems. The source code of our method is freely available under GPL at https://github.com/lvchen1989/BNER .

The running state of a geared transmission system affects the stability and reliability of the whole mechanical system. It will greatly reduce the maintenance cost of a mechanical system to identify the faulty state of the geared transmission system. Based on the measured gear fault vibration signals and the deep learning theory, four fault diagnosis neural network models including fast Fourier transform–deep belief network model, wavelet transform–convolutional neural network model, Hilbert-Huang transform–convolutional neural network model, and comprehensive deep neural network model are developed and trained respectively. The results show that the gear fault diagnosis method based on deep learning theory can effectively identify various gear faults under real test conditions. The comprehensive deep neural network model is the most effective one in gear fault recognition.

The marine gearbox is usually installed on a vibration isolation system in order to reduce oscillation transmitted to the ship foundation. However, researches on vibration transmission in the gear-housing system and isolation system are currently independent. With the increasing requirement of lower vibration, a coupled model needs to be built to control the vibration propagation from a view of the whole system. Considering the mesh transmission error excitation of a gear pair, a flexible gear-housing-foundation coupled impedance model is constructed in this paper, and the vibratory power flow of the whole system is calculated. Power transmissions between three different gearbox installation configurations, that is, rigid installation, single-stage isolation, and double-stage isolation, are compared. Taking the single-stage isolation configuration as an example, parameter influences on the vibration of the foundation are studied. Results show that double-stage isolation can achieve lower vibration than single-stage isolation; decrease in bearing stiffness or Young’s modulus of isolator will yield better vibration isolation performance; housing damping and isolator damping are beneficial to vibration reduction.

The severity of gear noise response depends on the sensitivity of geared rotor system dynamics to the transmission error. As gearbox design trending towards lighter weight and lower noise, the influence of housing compliance on system dynamic characteristics cannot be ignored. In this study, a gear-shaft-bearing-housing coupled impedance model is proposed to account for the effect of housing compliance on the vibration of geared transmission system. This proposed dynamic model offers convenient modeling, efficient computing, and ability to combine computed parameters with experimental ones. The numerical simulations on system dynamic characteristics are performed for both a rigid housing configuration and a flexible one. Natural frequencies, dynamic mesh forces, and dynamic bearing reaction loads are computed, and the housing compliance contribution on system dynamic characteristics is analyzed. Results show that increasing housing compliance will decrease the system natural frequencies and will affect the dynamic bearing reaction loads significantly but have very little influence on the dynamic mesh force. Also, the analysis shows that bearing stiffness has significant influence on the degree of housing contribution on system dynamic characteristics.

Active magnetic bearing system is a typical geometric constraint system which is combined with each part by certain assembly constraint relations. Graph theory is used to build the assembly model in the progress of assembly design. Trough the graph to express this system, it is not only clear and intuitive, and the algorithm is stable and high efficiency. Modeling active magnetic bearing assembly system is achieved by hierarchical model of data structure, which leads to accelerate the assessment of system configuration program and save a lot of time for designers.

Recurrent neural network (RNN) is one of the most popular architectures for addressing variable sequence text, and it shows outstanding results in many natural language processing (NLP) tasks and remarkable performance in capturing long-term dependencies. Many models have achieved excellent results based on RNN. However, most of these models overlook the locations of the keywords in a sentence and the semantic connections in different directions. As a consequence, these methods do not make full use of the available information. Considering that different words in a sequence usually have different importance, in this paper, we propose bidirectional gated recurrent units (BGRUs) which integrates a novel attention pooling mechanism with max-pooling operation to force the model to pay attention to the keywords in a sentence and maintain the most meaningful information of the text automatically. The presented model allows to encode longer sequences. Thus, it not only prevents important information from being discarded but also can be used to filter noises. To avoid full exposure of content without any control, we add an output gate to the GRU, which is named as text unit. The proposed model was evaluated on multiple tasks, including sentimental classification, movie review data, and a subjective classification dataset. Experimental results show that our model can achieve excellent performance on these tasks.