检索结果-南通市图书馆

A novel lightweight computerized ECG interpretation approach based on clinical 12-lead data

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第2期67卷 449-463页

作者： liu YunQing QIN ChengJin liu JinLei JIN YanRui LI ZhiYuan ZHAO LiQun liu chengliang School of Mechanical Engineering Shanghai Jiao Tong UniversityShanghai 200240China Key Labof Artificial Intelligence(Ministryof Education) AI InstituteShanghai Jiao Tong UniversityShanghai 200240China Department of Cardiology Shanghai First Peoples Hospital Affiliated to Shanghai Jiao Tong UniversityShanghai 200080China

Although 12-lead electrocardiograms(ECGs)provide a wide range of spatiotemporal characteristics,interpreting them for arrhythmia detection is difficult due to a lack of reliable large-scale clinical datasets.Herein,we proposed an innovative lightweight computerized ECG interpretation approach based on 12-lead data.Our model was trained,validated,and tested on 53845 standard 12-lead ECG records collected at Shanghai First People’s Hospital in affiliation with Shanghai Jiao Tong University.The experiments revealed that our approach had a classification accuracy of 94.41%in the classification task of seven types of rhythms,which was markedly superior to related single-lead and 12-lead ECG classification methods.Moreover,the average receiver operating characteristic area under the curve reached a value of 0.940,and the precision values for sinus tachycardia and sinus bradycardia were 0.945 and 0.91,respectively,with specificity values of 0.996 and 0.994.By employing our boosting method,we were able to improve the accuracy to 94.85%.To investigate the performance degradation of the proposed neural network in some classes,an ECG cardiologist was enlisted to review questionable ECGs;this process provides a promising direction for network performance improvement.Therefore,the proposed computerized ECG interpretation approach has practical significance because it could help professional physicians analyze patients’heart conditions based on real-time 12-lead ECG or grade their disease severity in advance.

关键词： computerized ECG interpretation large-scale 12-lead clinical ECG database lightweight neural network

A residual denoising and multiscale attention-based weighted domain adaptation network for tunnel boring machine main bearing fault diagnosis

在线全文

学校读者我要写书评

暂无评论

Science China Technological Sciences 2024年

作者： ZHONG Tao QIN ChengJin SHI Gang ZHANG ZhiNan TAO JianFeng liu chengliang State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University

As a critical component of a tunnel boring machine (TBM), the precise condition monitoring and fault analysis of the main bearing is essential to guarantee the safety and efficiency of the TBM cutter drive. Currently, under conditions of strong noise and complex working environments, traditional signal decomposition and machine learning methods struggle to extract weak fault features and achieve high fault classification accuracy. To address these issues, we propose a novel residual denoising and multiscale attention-based weighted domain adaptation network (RDMA-WDAN) for TBM main bearing fault diagnosis. Our approach skillfully designs a deep feature extractor incorporating residual denoising and multiscale attention modules, achieving better domain adaptation despite significant domain interference. The residual denoising component utilizes a convolutional block to extract noise features, removing them via residual connections. Meanwhile, the multiscale attention module uses a 4-branch convolution and 3 pooling strategy-based channel–spatial attention mechanism to extract multiscale features, concentrating on deep fault features. During training, a weighting mechanism is introduced to prioritize domain samples with clear fault features. This optimizes the deep feature extractor to obtain common features, enhancing domain adaptation. A low-speed and heavy-loaded bearing testbed was built, and fault data sets were established to validate the proposed method. Comparative experiments show that in noise domain adaptation tasks, proposed the RDMA–WDAN significantly improves target domain classification accuracy by 42.544%, 23.088%, 43.133%, 16.344%, 5.022%, and 9.233%over dense connection network(DenseNet), squeeze–excitation residual network (SE-ResNet), antinoise multiscale convolutional neural network(ANMSCNN), multiscale attention module-based convolutional neural network (MSAMCNN), domain adaptation network, and hybrid weighted domain adaptation (HWDA). In combined noise and working condition domain adaptation

关键词：

Combinatorial knowledge dynamics,innovative performance,and transition studies

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Geographical Sciences 2023年第4期33卷 705-718页

作者： XUE Shuaijun liu chengliang Department of Geography Kiel UniversityKiel 24118Germany School of Urban and Regional Sciences East China Normal UniversityShanghai 200241China Institute for Global Innovation and Development East China Normal UniversityShanghai 200062China Center of World Geography and Geo-strategical Studies East China Normal UniversityShanghai 200062China

Cross-domain research and development has prevailed in regional transformation and disruptive innovation in the last 15 years.Recently,a new concept,termed combinatorial knowledge bases(CKBs),offers insights into combining knowledge dynamics and is considered a good approach to explore recombinant innovative activities.Here,we review the literature on CKBs in Western economic geography,and we introduce a research agenda for CKBs in China’s economic geography.Concerning the latter,four aspects are elaborated:the co-evolution of the innovation chain and industrial chain,the geography of innovative activiinnovative entrepreneurship and new path development,and innovation system reconfiguration.This paper contributes to theoretical studies of China’s geography by linking CKBs to Chinese-specific phenomena.

关键词： combinatorial knowledge bases innovation China's transformation

Augmentation-based discriminative meta-learning for cross-machine few-shot fault diagnosis

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2023年第6期66卷 1698-1716页

作者： XIA PengCheng HUANG YiXiang WANG YuXiang liu chengliang liu Jie State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong UniversityShanghai 200240China MoE Key Lab of Artificial Intelligence AI InstituteShanghai Jiao Tong UniversityShanghai 200240China Department of Mechanical and Aerospace Engineering Carleton UniversityOttawa ON K1S 5B6Canada

Deep learning methods have demonstrated promising performance in fault diagnosis tasks.Although the scarcity of data in industrial scenarios limits the practical application of such methods,transfer learning effectively tackles this issue through crossmachine knowledge transfer.Nevertheless,the cross-machine few-shot problem,which is a more general industrial scenario,has been rarely investigated.Existing studies have not considered the cross-machine domain shift problem,which results in poor testing performance.This paper proposes an augmentation-based discriminative meta-learning method to address this issue.In the meta-training process,signal transformation is proposed to increase the meta-task diversity for more robust feature learning,and multi-scale learning is combined for more adaptive feature embedding.In the meta-testing process,limited labeled fault information is used to promote model generalization in the target domain through quasi-meta-training based on data augmentation.Furthermore,a novel hyperbolic prototypical loss is proposed for more discriminative feature representation and separable category prototypes by designing a hyperbolic decision boundary.Cross-machine few-shot diagnosis experiments were conducted using three datasets from different machines,namely,the bearing,motor,and gear datasets.The effectiveness of the proposed method was verified through ablation and comparison studies.

关键词： fault diagnosis few-shot learning meta-learning data augmentation cross-machine discriminative loss

Multi-class 12-lead ECG automatic diagnosis based on a novel subdomain adaptive deep network

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2022年第11期65卷 2617-2630页

作者： JIN YanRui LI ZhiYuan liu YunQing liu JinLei QIN Chengjin ZHAO LiQun liu chengliang State Key Laboratory of Mechanical System and Vibration School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Department of Cardiology Shanghai First People's Hospital Afiliated to Shanghai Jiao Tong University Shanghai 200080China

Arrhythmia is a common type of cardiovascular disease,which has become the leading cause of global deaths.Recently,the automatic 12-lead ECG diagnosis system based on numerous labelled data has attracted increasing attention.However,labelling 12-lead ECG recordings is a complex and time-consuming task for clinicians.And then,the existence of data distribution differences limits the direct cross domain use of the trained model.Enlighted by subdomain adaptation methods,this paper designs a novel subdomain adaptative deep network(SADN)for excavating diagnosis knowledge from source domain datasets.Firstly,the convolutional layer,residual blocks and SE-Residual blocks are utilized for extracting meaningful deep features automatically.Additionally,the feature classifier uses these deep features for obtaining the final diagnosis predictions.Further,designing a novel loss function with local maximum mean discrepancy is utilized for restricting data distribution discrepancy from different datasets.Finally,the Clinical Outcomes in Digital ECG and 1st China Physiological Signal Challenge datasets are utilized for evaluating the superiority of SADN,which presents that SADN enhances algorithm performance on the unlabelled target domain dataset.Further,compared with the existing methods,the proposed network structure acquires better performance with a F1-macro of 89.43%and a F1-macro1 of 87.09%.Besides,among the 4 kinds of ECG abnormalities,the diagnostic effect of the SADN is better than that of cardiology residents.Thus,SADN has promising potential as an auxiliary diagnostic tool for the clinical environment.

关键词： arrhythmia detection subdomainadaptation deep network 12-lead ECG

A multi-scale convolutional neural network for bearing compound fault diagnosis under various noise conditions

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2022年第11期65卷 2551-2563页

作者： JIN YanRui QIN ChengJin ZHANG ZhiNan TAO JianFeng liu chengliang School of Mechanical Engineering Shanghai Jiao TongUniversityShanghai 200240China

Recently,with the urgent demand for data-driven approaches in practical industrial scenarios,the deep learning diagnosis model in noise environments has attracted increasing attention.However,the existing research has two limitations:(1)the complex and changeable environmental noise,which cannot ensure the high-performance diagnosis of the model in different noise domains and(2)the possibility of multiple faults occurring simultaneously,which brings challenges to the model diagnosis.This paper presents a novel anti-noise multi-scale convolutional neural network(AM-CNN)for solving the issue of compound fault diagnosis under different intensity noises.First,we propose a residual pre-processing block according to the principle of noise superposition to process the input information and present the residual loss to construct a new loss function.Additionally,considering the strong coupling of input information,we design a multi-scale convolution block to realize multi-scale feature extraction for enhancing the proposed model’s robustness and effectiveness.Finally,a multi-label classifier is utilized to simultaneously distinguish multiple bearing faults.The proposed AM-CNN is verified under our collected compound fault dataset.On average,AM-CNN improves 39.93%accuracy and 25.84%F1-macro under the no-noise working condition and 45.67%accuracy and 27.72%F1-macro under different intensity noise working conditions compared with the existing methods.Furthermore,the experimental results show that AM-CNN can achieve good cross-domain performance with 100%accuracy and 100%F1-macro.Thus,AM-CNN has the potential to be an accurate and stable fault diagnosis tool.

关键词： anti-noise residual pre-processing block bearing compound fault multi-label classifier multi-scale convolution feature extraction

A novel LSTM-autoencoder and enhanced transformer-based detection method for shield machine cutterhead clogging

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2023年第2期66卷 512-527页

作者： QIN ChengJin WU RuiHong HUANG GuoQiang TAO JianFeng liu chengliang State Key Laboratory of Mechanical System and Vibration School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai 200240China

Shield tunneling machines are paramount underground engineering equipment and play a key role in tunnel construction.During the shield construction process,the“mud cake”formed by the difficult-to-remove clay attached to the cutterhead severely affects the shield construction efficiency and is harmful to the healthy operation of a shield tunneling machine.In this study,we propose an enhanced transformer-based detection model for detecting the cutterhead clogging status of shield tunneling machines.First,the working state data of shield machines are selected from historical excavation data,and a long short-term memory-autoencoder neural network module is constructed to remove outliers.Next,variational mode decomposition and wavelet transform are employed to denoise the data.After the preprocessing,nonoverlapping rectangular windows are used to intercept the working state data to obtain the time slices used for analysis,and several time-domain features of these periods are extracted.Owing to the data imbalance in the original dataset,the k-means-synthetic minority oversampling technique algorithm is adopted to oversample the extracted time-domain features of the clogging data in the training set to balance the dataset and improve the model performance.Finally,an enhanced transformer-based neural network is constructed to extract essential implicit features and detect cutterhead clogging status.Data collected from actual tunnel construction projects are used to verify the proposed model.The results show that the proposed model achieves accurate detection of shield machine cutterhead clogging status,with 98.85%accuracy and a 0.9786 F1 score.Moreover,the proposed model significantly outperforms the comparison models.

关键词： shield tunneling machine cutterhead clogging fault diagnosis autoencoder multihead self-attention mechanism imbalanced data

Adaptive decision-level fusion strategy for the fault diagnosis of axial piston pumps using multiple channels of vibration signals

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2022年第2期65卷 470-480页

作者： CHAO Qun GAO HaoHan TAO JianFeng WANG YuanHang ZHOU Jian liu chengliang State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong UniversityShanghai 200240China MoE Key Lab of Artificial Intelligence AI InstituteShanghai Jiao Tong UniversityShanghai 200240China China Electronic Product Reliability and Environmental Testing Research Institute Guangzhou 510610China

An axial piston pump is a key component that plays the role of the "heart" in hydraulic systems. The pump failure will lead to an unexpected breakdown of the entire hydraulic system or even economic loss and catastrophic safety consequences. Several vibration-based machine learning methods have been developed to detect and diagnose faults of axial piston pumps. However,most of these intelligent diagnosis methods use single-sensor vibration data to monitor the pump health states. Additionally, the diagnostic accuracy is unacceptable in most situations due to the complex pump structure and limited sensor information.Therefore, this study proposes a multi-sensor fusion method to improve the fault diagnosis performance of axial piston pumps.The convolutional neural network receives three channels of vibration data and makes the final diagnosis through information fusion at the decision level. The proposed decision fusion method is evaluated on the classification task of leakage levels of an actual axial piston pump. The experimental results show that the proposed method improves the classification accuracy by adjusting the probability distribution of classification according to the learned weight matrix.

关键词： axial piston pump leakage fault diagnosis CNN decision-level fusion

Weighted Heterogeneous Graph-Based Incremental Automatic Disease Diagnosis Method

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2024年第1期29卷 120-130页

作者：田圆圆金衍瑞李志远刘金磊刘成良 State Key Laboratory of Mechanical System and Vibration School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai 200240China

The objective of this study is to construct a multi-department symptom-based automatic diagnosis model.However,it is dificult to establish a model to classify plenty of diseases and collect thousands of disease-symptom datasets simultaneously.Inspired by the thought of"knowledge graph is model",this study proposes to build an experience-infused knowledge model by continuously learning the experiential knowledge from data,and incrementally injecting it into the knowledge graph.Therefore,incremental learning and injection are used to solve the data collection problem,and the knowledge graph is modeled and containerized to solve the large-scale multi-classification problems.First,an entity linking method is designed and a heterogeneous knowledge graph is constructed by graph fusion.Then,an adaptive neural network model is constructed for each dataset,and the data is used for statistical initialization and model training.Finally,the weights and biases of the learned neural network model are updated to the knowledge graph.It is worth noting that for the incremental process,we consider both the data and class increments.We evaluate the diagnostic effectiveness of the model on the current dataset and the anti-forgetting ability on the historical dataset after class increment on three public datasets.Compared with the classical model,the proposed model improves the diagnostic accuracy of the three datasets by 5%,2%,and 15%on average,respectively.Meanwhile,the model under incremental learning has a better ability to resist forgetting.

关键词： knowledge graph disease diagnosis incremental learning adaptive neural network knowledge model