摘要：Higher requirements for the accuracy of relevant models are put throughout the transformation and upgrade of the iron and steel sector to intelligent *** has been difficult to meet the needs of the field with the usual prediction model of mechanical properties of hotrolled *** data and difficult parameter adjustment limit deep learning models based on multi-layer networks in practical applications;besides,the limited discrete process parameters used make it impossible to effectively depict the actual strip processing *** order to solve these problems,this research proposed a new sampling approach for mechanical characteristics input data of hot-rolled strip based on the multi-grained cascade forest(gcForest)*** to the characteristics of complex process flow and abnormal sensitivity of process path and parameters to product quality in the hot-rolled strip production,a three-dimensional continuous time series process data sampling method based on time-temperature-deformation was *** basic information of strip steel(chemical composition and typical process parameters)is fused with the local process information collected by multi-grained scanning,so that the next link’s input has both local and global ***,in the multi-grained scanning structure,a sub sampling scheme with a variable window was designed,so that input data with different dimensions can get output characteristics of the same dimension after passing through the multi-grained scanning structure,allowing the cascade forest structure to be trained ***,actual production data of three steel grades was used to conduct the experimental *** results revealed that the gcForest-based mechanical property prediction model outperforms the competition in terms of comprehensive performance,ease of parameter adjustment,and ability to sustain high prediction accuracy with fewer samples.

摘要：Named entity disambiguation （NED） is the task of linking mentions of ambiguous entities to their referenced entities in a knowledge base such as Wikipedia. We propose an approach to effectively disentangle the discriminative features in the manner of collaborative utilization of collective wisdom （via human-labeled crowd labels） and deep learning （via human-generated data） for the NED task. In particular, we devise a crowd model to elicit the underlying features （crowd features） from crowd labels that indicate a matching candidate for each mention, and then use the crowd features to fine-tune a dynamic convolutional neural network （DCNN）. The learned DCNN is employed to obtain deep crowd features to enhance traditional hand-crafted features for the NED task. The proposed method substantially benefits from the utilization of crowd knowledge （via crowd labels） into a generic deep learning for the NED task. Experimental analysis demonstrates that the proposed approach is superior to the traditional hand-crafted features when enough crowd labels are gathered.

摘要：Objective To observe the value of deep learning (DL) models for automatic classification of echocardiographic views. Methods Totally 100 patients after heart transplantation were retrospectively enrolled and divided into training set, validation set and test set at a ratio of 7 ∶ 2 ∶ 1. ResNet18, ResNet34, Swin Transformer and Swin Transformer V2 models were established based on 2D apical two chamber view, 2D apical three chamber view, 2D apical four chamber view, 2D subcostal view, parasternal long-axis view of left ventricle, short-axis view of great arteries, short-axis view of apex of left ventricle, short-axis view of papillary muscle of left ventricle, short-axis view of mitral valve of left ventricle, also 3D and CDFI views of echocardiography. The accuracy, precision, recall, F1 score and confusion matrix were used to evaluate the performance of each model for automatically classifying echocardiographic views. The interactive interface was designed based on Qt Designer software and deployed on the desktop. Results The performance of models for automatically classifying echocardiographic views in test set were all good, with relatively poor performance for 2D short-axis view of left ventricle and superior performance for 3D and CDFI views. Swin Transformer V2 was the optimal model for automatically classifying echocardiographic views, with high accuracy, precision, recall and F1 score was 92.56%, 89.01%, 89.97% and 89.31%, respectively, which also had the highest diagonal value in confusion matrix and showed the best classification effect on various views in t-SNE figure. Conclusion DL model had good performance for automatically classifying echocardiographic views, especially Swin Transformer V2 model had the best performance. Using interactive classification interface could improve the interpretability of prediction results to some extent.

摘要：The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R&D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning (downstream task adaptation), and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36% and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasible .

摘要：In order to improve the accuracy and stability of terminal traffic flow prediction in convective weather,a multi-input deep learning(MICL)model is *** the basis of previous studies,this paper expands the set of weather characteristics affecting the traffic flow in the terminal area,including weather forecast data and Meteorological Report of Aerodrome Conditions(METAR)*** terminal airspace is divided into smaller areas based on function and the weather severity index(WSI)characteristics extracted from weather forecast data are established to better quantify the impact of *** model preserves the advantages of the convolution neural network(CNN)and the long short-term memory(LSTM)model,and adopts two channels to input WSI and METAR information,respectively,which can fully reflect the temporal and spatial distribution characteristics of weather in the terminal ***-scene experiments are designed based on the real historical data of Guangzhou Terminal Area operating in typical convective *** results show that the MICL model has excellent performance in mean squared error(MSE),root MSE(RMSE),mean absolute error(MAE)and other performance indicators compared with the existing machine learning models or deep learning models,such as Knearest neighbor(KNN),support vector regression(SVR),CNN and *** the forecast period ranging from 30 min to 6 h,the MICL model has the best prediction accuracy and stability.

摘要：In this study,we implement forward modeling and inversion based on deep-learning strategies using an optimal nearly analytic discrete(ONAD)*** forward-modeling method combines the ONAD method with recurrent neural network(RNN)for the fi rst *** is a type of neural network that is suitable for sequential data,which uses information from both previous and current times to obtain output *** express the ONAD method using an RNN framework to advance the time iteration of an acoustic *** process can simplify programming using RNN and convolution ***,we use deep learning based on the proposed forward-modeling method to study full waveform-inversion *** the main purpose of inversion is to minimize the error between real and synthetic data,inversion is essentially an optimization *** new optimizers are available in the framework of deep learning,such as the Adam and Nadam optimizers,which are used for optimizing velocity model in the inversion *** perform six numerical *** first two experiments demonstrate the forward-modeling results,which indicate that the forward-modeling method can effectively suppress numerical dispersion and improve computational effi *** other four experiments demonstrate the inversion results,which show that the method proposed in this paper can eff ectively realize inversion *** compare several optimizers used in deep learning and find that the Nadam optimizer has faster convergence and better effectiveness based on the ONAD method combined with RNN.

摘要：In the era of Big Data,we are faced with an inevitable and challenging problem of“overload information”.To alleviate this problem,it is important to use effective automatic text summarization techniques to obtain the key information quickly and efficiently from the huge amount of *** this paper,we propose a hybrid method of extractive text summarization based on deep learning and graph ranking algorithms(ETSDG).In this method,a pre-trained deep learning model is designed to yield useful sentence *** the association between sentences in raw documents,a traditional LexRank algorithm with fine-tuning is adopted fin *** order to improve the performance of the extractive text summarization method,we further integrate the traditional LexRank algorithm with deep *** results on the data set DUC2004 show that ETSDG has better performance in ROUGE metrics compared with certain benchmark methods.

摘要：Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art *** efforts have explored the incorporation of Transformers to augment network performance in ***,the high computational cost of Transformers makes them less suitable for deployment on lightweight ***,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel *** this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel ***,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these *** addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel *** results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.

摘要：In modern terminology,“organoids”refer to cells that grow in a specific three-dimensional(3D)environment in vitro,sharing similar structures with their source organs or *** themorphology or growth characteristics of organoids through a microscope is a commonly used method of organoid ***,it is difficult,time-consuming,and inaccurate to screen and analyze organoids only manually,a problem which cannot be easily solved with traditional *** intelligence(AI)technology has proven to be effective in many biological and medical research fields,especially in the analysis of single-cell or hematoxylin/eosin stained tissue *** used to analyze organoids,AI should also provide more efficient,quantitative,accurate,and fast *** this review,we will first briefly outline the application areas of organoids and then discuss the shortcomings of traditional organoid measurement and analysis ***,we will summarize the development from machine learning to deep learning and the advantages of the latter,and then describe how to utilize a convolutional neural network to solve the challenges in organoid observation and ***,we will discuss the limitations of current AI used in organoid research,as well as opportunities and future research directions.

摘要：Thanks to the fast improvement of the computing power and the rapid development of the computational chemistry and biology,the computer-aided drug design techniques have been successfully applied in almost every stage of the drug discovery and development pipeline to speed up the process of research and reduce the cost and risk related to preclinical and clinical *** to the development of machine learning theory and the accumulation of pharmacological data, the artificial intelligence(AI) technology, as a powerful data mining tool, has cut a figure in various fields of the drug design, such as virtual screening,activity scoring, quantitative structure-activity relationship(QSAR) analysis, de novo drug design, and in silico evaluation of absorption, distribution, metabolism, excretion and toxicity(ADME/T) properties. Although it is still challenging to provide a physical explanation of the AI-based models, it indeed has been acting as a great power to help manipulating the drug discovery through the versatile frameworks. Recently, due to the strong generalization ability and powerful feature extraction capability,deep learning methods have been employed in predicting the molecular properties as well as generating the desired molecules,which will further promote the application of AI technologies in the field of drug design.