The Fusion of Temporal Sequence with Scene Priori Information in Deep Learning Object Recognition

For some important object recognition applications such as intelligent robots and unmanned driving, images are collected on a consecutive basis and associated among themselves, besides, the scenes have steady prior features. Yet existing technologies do not take full advantage of this information. In order to take object recognition further than existing algorithms in the above application, an object recognition method that fuses temporal sequence with scene priori information is proposed. This method first employs YOLOv3 as the basic algorithm to recognize objects in single-frame images, then the DeepSort algorithm to establish association among potential objects recognized in images of different moments, and finally the confidence fusion method and temporal boundary processing method designed herein to fuse, at the decision level, temporal sequence information with scene priori information. Experiments using public datasets and self-built industrial scene datasets show that due to the expansion of information sources, the quality of single-frame images has less impact on the recognition results, whereby the object recognition is greatly improved. It is presented herein as a widely applicable framework for the fusion of information under multiple classes. All the object recognition algorithms that output object class, location information and recognition confidence at the same time can be integrated into this information fusion framework to improve performance.

Exploration of Innovation Strategy in the Deep Integration of Information Technology and Education and Teaching

The rapid development of information technology provides a new opportunity and impetus for the reform of education and teaching.Deep integration of information technology and education and teaching is the only way to promote the modernization of education.Starting from the connotation of the deep integration of information technology and education and teaching,this paper analyzes the existing problems in the current integration process,and puts forward innovative strategies from the aspects of concept,resources,model,and evaluation.Through measures such as building a smart teaching environment,enriching high-quality teaching resources,innovating teaching organization models,and establishing multiple evaluation systems,we will realize the deep integration of information technology and teaching,promote the reform of teaching and learning methods,improve the quality of personnel training,and provide strong support for the modernization of education.

An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy

For a single-structure deep learning fault diagnosis model,its disadvantages are an insufficient feature extraction and weak fault classification capability.This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy.First,a normal autoencoder,denoising autoencoder,sparse autoencoder,and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure.A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features.Finally,the advantage of the deep belief network probability model is used as the fault classifier to identify the faults.The effectiveness of the proposed method was verified by a gearbox test-bed.Experimental results show that,compared with traditional and existing intelligent fault diagnosis methods,the proposed method can obtain representative information and features from the raw data with higher classification accuracy.

Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning

The development of precision agriculture demands high accuracy and efficiency of cultivated land information extraction. As a new means of monitoring the ground in recent years, unmanned aerial vehicle （UAV） low-height remote sensing technique, which is flexible, efficient with low cost and with high resolution, is widely applied to investing various resources. Based on this, a novel extraction method for cultivated land information based on Deep Convolutional Neural Network and Transfer Learning （DTCLE） was proposed. First, linear features （roads and ridges etc.） were excluded based on Deep Convolutional Neural Network （DCNN）. Next, feature extraction method learned from DCNN was used to cultivated land information extraction by introducing transfer learning mechanism. Last, cultivated land information extraction results were completed by the DTCLE and eCognifion for cultivated land information extraction （ECLE）. The location of the Pengzhou County and Guanghan County, Sichuan Province were selected for the experimental purpose. The experimental results showed that the overall precision for the experimental image 1, 2 and 3 （of extracting cultivated land） with the DTCLE method was 91.7%, 88.1% and 88.2% respectively, and the overall precision of ECLE is 9o.7%, 90.5% and 87.0%, respectively. Accuracy of DTCLE was equivalent to that of ECLE, and also outperformed ECLE in terms of integrity and continuity.

Weighted Forwarding in Graph Convolution Networks for Recommendation Information Systems

Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.

Semantic Information Extraction from Multi-Corpora Using Deep Learning

Information extraction plays a vital role in natural language processing,to extract named entities and events from unstructured data.Due to the exponential data growth in the agricultural sector,extracting significant information has become a challenging task.Though existing deep learningbased techniques have been applied in smart agriculture for crop cultivation,crop disease detection,weed removal,and yield production,still it is difficult to find the semantics between extracted information due to unswerving effects of weather,soil,pest,and fertilizer data.This paper consists of two parts.An initial phase,which proposes a data preprocessing technique for removal of ambiguity in input corpora,and the second phase proposes a novel deep learning-based long short-term memory with rectification in Adam optimizer andmultilayer perceptron to find agricultural-based named entity recognition,events,and relations between them.The proposed algorithm has been trained and tested on four input corpora i.e.,agriculture,weather,soil,and pest&fertilizers.The experimental results have been compared with existing techniques and itwas observed that the proposed algorithm outperformsWeighted-SOM,LSTM+RAO,PLR-DBN,KNN,and Na飗e Bayes on standard parameters like accuracy,sensitivity,and specificity.

Deep original information preservation by applying in-situ film formation technology during coring

Accurately obtaining the original information of an in-situ rock via coring is a significant guiding step for exploring and developing deep oil and gas resources.It is difficult for traditional coring technology and equipment to preserve the original information in deep rocks.This study develops a technology for insitu substance-preserved(ISP),moisture-preserved(IMP),and light-preserved(ILP)coring.This technology stores the original information in real time by forming a solid sealing film on the in-situ sample during coring.This study designed the ISP-IMP-ILP-Coring process and tool.In addition,an ISP-IMP-ILPCoring process simulation system was developed.The effects of temperature,pressure,and film thickness on the quality of the in-situ film were investigated by performing in-situ film-forming simulation experiments.A solid sealing film with a thickness of 2-3 mm can be formed;it completely covers the core sample and has uniform thickness.The film maintains good ISP-IMP-ILP properties and can protect the core sample in the in-situ environment steadily.This study verifies the feasibility of“film formation during coring”technology and provides strong support for the engineering application of ISP-IMP-ILPCoring technology.

Research on Heterogeneous Information Network Link Prediction Based on Representation Learning

A heterogeneous information network,which is composed of various types of nodes and edges,has a complex structure and rich information content,and is widely used in social networks,academic networks,e-commerce,and other fields.Link prediction,as a key task to reveal the unobserved relationships in the network,is of great significance in heterogeneous information networks.This paper reviews the application of presentation-based learning methods in link prediction of heterogeneous information networks.This paper introduces the basic concepts of heterogeneous information networks,and the theoretical basis of representation learning,and discusses the specific application of the deep learning model in node embedding learning and link prediction in detail.The effectiveness and superiority of these methods on multiple real data sets are demonstrated by experimental verification.

Deep learning in extracting tropical cyclone intensity and wind radius information from satellite infrared images—A review

热带气旋(TC)严重危害人类生命和财产安全,TC的实时监测一直是研究热点,随着空间和传感器技术的发展,卫星遥感已成为监测TC的主要手段.此外,深度学习具有卓越的数据挖掘能力,在地球科学中的表现优于基于物理或统计的算法,越来越多的深度学习算法被开发和应用于TC信息的提取,本文系统地回顾了深度学习在TC信息提取中的应用,并给出了深度学习模型在TC强度和风圈半径提取中的应用.此外,本文还展望了深度学习在TC信息提取中的应用前景.

A Survey of Image Information Hiding Algorithms Based on Deep Learning

With the development of data science and technology,information security has been further concerned.In order to solve privacy problems such as personal privacy being peeped and copyright being infringed,information hiding algorithms has been developed.Image information hiding is to make use of the redundancy of the cover image to hide secret information in it.Ensuring that the stego image cannot be distinguished from the cover image,and sending secret information to receiver through the transmission of the stego image.At present,the model based on deep learning is also widely applied to the field of information hiding.This paper makes an overall conclusion on image information hiding based on deep learning.It is divided into four parts of steganography algorithms,watermarking embedding algorithms,coverless information hiding algorithms and steganalysis algorithms based on deep learning.From these four aspects,the state-of-the-art information hiding technologies based on deep learning are illustrated and analyzed.

Aortic Dissection Diagnosis Based on Sequence Information and Deep Learning

Aortic dissection(AD)is one of the most serious diseases with high mortality,and its diagnosis mainly depends on computed tomography(CT)results.Most existing automatic diagnosis methods of AD are only suitable for AD recognition,which usually require preselection of CT images and cannot be further classified to different types.In this work,we constructed a dataset of 105 cases with a total of 49021 slices,including 31043 slices expertlevel annotation and proposed a two-stage AD diagnosis structure based on sequence information and deep learning.The proposed region of interest(RoI)extraction algorithm based on sequence information(RESI)can realize high-precision for RoI identification in the first stage.Then DenseNet-121 is applied for further diagnosis.Specially,the proposed method can judge the type of AD without preselection of CT images.The experimental results show that the accuracy of Stanford typing classification of AD is 89.19%,and the accuracy at the slice-level reaches 97.41%,which outperform the state-ofart methods.It can provide important decision-making information for the determination of further surgical treatment plan for patients.

An Analysis Model of Learners’ Online Learning Status Based on Deep Neural Network and Multi-Dimensional Information Fusion

The learning status of learners directly affects the quality of learning.Compared with offline teachers,it is difficult for online teachers to capture the learning status of students in the whole class,and it is even more difficult to continue to pay attention to studentswhile teaching.Therefore,this paper proposes an online learning state analysis model based on a convolutional neural network and multi-dimensional information fusion.Specifically,a facial expression recognition model and an eye state recognition model are constructed to detect students’emotions and fatigue,respectively.By integrating the detected data with the homework test score data after online learning,an analysis model of students’online learning status is constructed.According to the PAD model,the learning state is expressed as three dimensions of students’understanding,engagement and interest,and then analyzed from multiple perspectives.Finally,the proposed model is applied to actual teaching,and procedural analysis of 5 different types of online classroom learners is carried out,and the validity of the model is verified by comparing with the results of the manual analysis.

Power Information System Database Cache Model Based on Deep Machine Learning

At present,the database cache model of power information system has problems such as slow running speed and low database hit rate.To this end,this paper proposes a database cache model for power information systems based on deep machine learning.The caching model includes program caching,Structured Query Language(SQL)preprocessing,and core caching modules.Among them,the method to improve the efficiency of the statement is to adjust operations such as multi-table joins and replacement keywords in the SQL optimizer.Build predictive models using boosted regression trees in the core caching module.Generate a series of regression tree models using machine learning algorithms.Analyze the resource occupancy rate in the power information system to dynamically adjust the voting selection of the regression tree.At the same time,the voting threshold of the prediction model is dynamically adjusted.By analogy,the cache model is re-initialized.The experimental results show that the model has a good cache hit rate and cache efficiency,and can improve the data cache performance of the power information system.It has a high hit rate and short delay time,and always maintains a good hit rate even under different computer memory;at the same time,it only occupies less space and less CPU during actual operation,which is beneficial to power The information system operates efficiently and quickly.

Deep convolutional adversarial graph autoencoder using positive pointwise mutual information for graph embedding

Graph embedding aims to map the high-dimensional nodes to a low-dimensional space and learns the graph relationship from its latent representations.Most existing graph embedding methods focus on the topological structure of graph data,but ignore the semantic information of graph data,which results in the unsatisfied performance in practical applications.To overcome the problem,this paper proposes a novel deep convolutional adversarial graph autoencoder(GAE)model.To embed the semantic information between nodes in the graph data,the random walk strategy is first used to construct the positive pointwise mutual information(PPMI)matrix,then,graph convolutional net-work(GCN)is employed to encode the PPMI matrix and node content into the latent representation.Finally,the learned latent representation is used to reconstruct the topological structure of the graph data by decoder.Furthermore,the deep convolutional adversarial training algorithm is introduced to make the learned latent representation conform to the prior distribution better.The state-of-the-art experimental results on the graph data validate the effectiveness of the proposed model in the link prediction,node clustering and graph visualization tasks for three standard datasets,Cora,Citeseer and Pubmed.

Double Pruning Structure Design for Deep Stochastic Configuration Networks Based on Mutual Information and Relevance

Deep stochastic configuration networks(DSCNs)produce redundant hidden nodes and connections during training,which complicates their model structures.Aiming at the above problems,this paper proposes a double pruning structure design algorithm for DSCNs based on mutual information and relevance.During the training process,the mutual information algorithm is used to calculate and sort the importance scores of the nodes in each hidden layer in a layer-by-layer manner,the node pruning rate of each layer is set according to the depth of the DSCN at the current time,the nodes that contribute little to the model are deleted,and the network-related parameters are updated.When the model completes the configuration procedure,the correlation evaluation strategy is used to sort the global connection weights and delete insignificance connections;then,the network parameters are updated after pruning is completed.The experimental results show that the proposed structure design method can effectively compress the scale of a DSCN model and improve its modeling speed;the model accuracy loss is small,and fine-tuning for accuracy restoration is not needed.The obtained DSCN model has certain application value in the field of regression analysis.

基于Informer融合模型的油田开发指标预测方法

为解决油田开发指标的预测问题,提出了一种基于物质平衡方程和Informer的融合模型。首先,通过物质平衡方程领域知识建立油田开发产量递减前后的机理模型;其次,将所建机理模型作为约束与Informer模型损失函数进行融合建立符合油田开发物理规律的指标预测模型;最后,采用油田实际生产数据进行实验分析,结果表明相比于纯数据驱动的几种循环结构预测模型,本融合模型在相同数据条件下的预测效果更优。该模型的机理约束部分能引导模型的训练过程,使其收敛速度更快,且波峰波谷处的预测更准确。该融合模型具有更好的预测能力和泛化能力和比较合理的物理可解释性。

SSD Real-Time Illegal Parking Detection Based on Contextual Information Transmission

With the improvement of the national economic level,the number of vehicles is still increasing year by year.According to the statistics of National Bureau of Statics,the number is approximately up to 327 million in China by the end of 2018,which makes urban traffic pressure continues to rise so that the negative impact of urban traffic order is growing.Illegal parking-the common problem in the field of transportation security is urgent to be solved and traditional methods to address it are mainly based on ground loop and manual supervision,which may miss detection and cost much manpower.Due to the rapidly developing deep learning sweeping the world in recent years,object detection methods relying on background segmentation cannot meet the requirements of complex and various scenes on speed and precision.Thus,an improved Single Shot MultiBox Detector(SSD)based on deep learning is proposed in our study,we introduce attention mechanism by spatial transformer module which gives neural networks the ability to actively spatially transform feature maps and add contextual information transmission in specified layer.Finally,we found out the best connection layer in the detection model by repeated experiments especially for small objects and increased the precision by 1.5%than the baseline SSD without extra training cost.Meanwhile,we designed an illegal parking vehicle detection method by the improved SSD,reaching a high precision up to 97.3%and achieving a speed of 40FPS,superior to most of vehicle detection methods,will make contributions to relieving the negative impact of illegal parking.

Multi-source information fused generative adversarial network model and data assimilation based history matching for reservoir with complex geologies

For reservoirs with complex non-Gaussian geological characteristics,such as carbonate reservoirs or reservoirs with sedimentary facies distribution,it is difficult to implement history matching directly,especially for the ensemble-based data assimilation methods.In this paper,we propose a multi-source information fused generative adversarial network(MSIGAN)model,which is used for parameterization of the complex geologies.In MSIGAN,various information such as facies distribution,microseismic,and inter-well connectivity,can be integrated to learn the geological features.And two major generative models in deep learning,variational autoencoder(VAE)and generative adversarial network(GAN)are combined in our model.Then the proposed MSIGAN model is integrated into the ensemble smoother with multiple data assimilation(ESMDA)method to conduct history matching.We tested the proposed method on two reservoir models with fluvial facies.The experimental results show that the proposed MSIGAN model can effectively learn the complex geological features,which can promote the accuracy of history matching.

Visual Relationship Detection with Contextual Information

Understanding an image goes beyond recognizing and locating the objects in it,the relationships between objects also very important in image understanding.Most previous methods have focused on recognizing local predictions of the relationships.But real-world image relationships often determined by the surrounding objects and other contextual information.In this work,we employ this insight to propose a novel framework to deal with the problem of visual relationship detection.The core of the framework is a relationship inference network,which is a recurrent structure designed for combining the global contextual information of the object to infer the relationship of the image.Experimental results on Stanford VRD and Visual Genome demonstrate that the proposed method achieves a good performance both in efficiency and accuracy.Finally,we demonstrate the value of visual relationship on two computer vision tasks:image retrieval and scene graph generation.

A Survey of Web Information System and Applications

The fourth international conference on Web information systems and applications （WISA 2007） has received 409 submissions and has accepted 37 papers for publication in this issue. The papers cover broad research areas, including Web mining and data warehouse, Deep Web and Web integration, P2P networks, text processing and information retrieval, as well as Web Services and Web infrastructure. After briefly introducing the WISA conference, the survey outlines the current activities and future trends concerning Web information systems and applications based on the papers accepted for publication.