Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,l...Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,labeled data is very scarce due to patient privacy concerns.For researchers,obtaining high-quality labeled images is exceedingly challenging because it involves manual annotation and clinical understanding.In addition,skin datasets are highly suitable for medical image classification studies due to the inter-class relationships and the inter-class similarities of skin lesions.In this paper,we propose a model called Coalition Sample Relation Consistency(CSRC),a consistency-based method that leverages Canonical Correlation Analysis(CCA)to capture the intrinsic relationships between samples.Considering that traditional consistency-based models only focus on the consistency of prediction,we additionally explore the similarity between features by using CCA.We enforce feature relation consistency based on traditional models,encouraging the model to learn more meaningful information from unlabeled data.Finally,considering that cross-entropy loss is not as suitable as the supervised loss when studying with imbalanced datasets(i.e.,ISIC 2017 and ISIC 2018),we improve the supervised loss to achieve better classification accuracy.Our study shows that this model performs better than many semi-supervised methods.展开更多
Structure features need complicated pre-processing, and are probably domain-dependent. To reduce time cost of pre-processing, we propose a novel neural network architecture which is a bi-directional long-short-term-me...Structure features need complicated pre-processing, and are probably domain-dependent. To reduce time cost of pre-processing, we propose a novel neural network architecture which is a bi-directional long-short-term-memory recurrent-neural-network（Bi-LSTM-RNN） model based on low-cost sequence features such as words and part-of-speech（POS） tags, to classify the relation of two entities. First, this model performs bi-directional recurrent computation along the tokens of sentences. Then, the sequence is divided into five parts and standard pooling functions are applied over the token representations of each part. Finally, the token representations are concatenated and fed into a softmax layer for relation classification. We evaluate our model on two standard benchmark datasets in different domains, namely Sem Eval-2010 Task 8 and Bio NLP-ST 2016 Task BB3. In Sem Eval-2010 Task 8, the performance of our model matches those of the state-of-the-art models, achieving 83.0% in F1. In Bio NLP-ST 2016 Task BB3, our model obtains F1 51.3% which is comparable with that of the best system. Moreover, we find that the context between two target entities plays an important role in relation classification and it can be a replacement of the shortest dependency path.展开更多
Text classification,by automatically categorizing texts,is one of the foundational elements of natural language processing applications.This study investigates how text classification performance can be improved throu...Text classification,by automatically categorizing texts,is one of the foundational elements of natural language processing applications.This study investigates how text classification performance can be improved through the integration of entity-relation information obtained from the Wikidata(Wikipedia database)database and BERTbased pre-trained Named Entity Recognition(NER)models.Focusing on a significant challenge in the field of natural language processing(NLP),the research evaluates the potential of using entity and relational information to extract deeper meaning from texts.The adopted methodology encompasses a comprehensive approach that includes text preprocessing,entity detection,and the integration of relational information.Experiments conducted on text datasets in both Turkish and English assess the performance of various classification algorithms,such as Support Vector Machine,Logistic Regression,Deep Neural Network,and Convolutional Neural Network.The results indicate that the integration of entity-relation information can significantly enhance algorithmperformance in text classification tasks and offer new perspectives for information extraction and semantic analysis in NLP applications.Contributions of this work include the utilization of distant supervised entity-relation information in Turkish text classification,the development of a Turkish relational text classification approach,and the creation of a relational database.By demonstrating potential performance improvements through the integration of distant supervised entity-relation information into Turkish text classification,this research aims to support the effectiveness of text-based artificial intelligence(AI)tools.Additionally,it makes significant contributions to the development ofmultilingual text classification systems by adding deeper meaning to text content,thereby providing a valuable addition to current NLP studies and setting an important reference point for future research.展开更多
Given the scarcity of Satellite Frequency and Orbit(SFO)resources,it holds paramount importance to establish a comprehensive knowledge graph of SFO field(SFO-KG)and employ knowledge reasoning technology to automatical...Given the scarcity of Satellite Frequency and Orbit(SFO)resources,it holds paramount importance to establish a comprehensive knowledge graph of SFO field(SFO-KG)and employ knowledge reasoning technology to automatically mine available SFO resources.An essential aspect of constructing SFO-KG is the extraction of Chinese entity relations.Unfortunately,there is currently no publicly available Chinese SFO entity Relation Extraction(RE)dataset.Moreover,publicly available SFO text data contain numerous NA(representing for“No Answer”)relation category sentences that resemble other relation sentences and pose challenges in accurate classification,resulting in low recall and precision for the NA relation category in entity RE.Consequently,this issue adversely affects both the accuracy of constructing the knowledge graph and the efficiency of RE processes.To address these challenges,this paper proposes a method for extracting Chinese SFO text entity relations based on dynamic integrated learning.This method includes the construction of a manually annotated Chinese SFO entity RE dataset and a classifier combining features of SFO resource data.The proposed approach combines integrated learning and pre-training models,specifically utilizing Bidirectional Encoder Representation from Transformers(BERT).In addition,it incorporates one-class classification,attention mechanisms,and dynamic feedback mechanisms to improve the performance of the RE model.Experimental results show that the proposed method outperforms the traditional methods in terms of F1 value when extracting entity relations from both balanced and long-tailed datasets.展开更多
The classification method of relative permeability curves is rarely reported, when relative permeability curves are applied;if the multiple relative permeability curves are normalized directly, but not classified, the...The classification method of relative permeability curves is rarely reported, when relative permeability curves are applied;if the multiple relative permeability curves are normalized directly, but not classified, the calculated result maybe cause a large error. For example, the relationship curve between oil displacement efficiency and water cut, which derived from the relative permeability curve in LD oilfield is uncertain in the shape of low water cut stage. If being directly normalized, the result of the interpretation of the water flooded zone is very high. In this study, two problems were solved: 1) The mathematical equation of the relationship between oil displacement efficiency and water cut was deduced, and repaired the lost data of oil displacement efficiency and water cut curve, which solve the problem of uncertain curve shape. After analysis, the reason why the curve is not available is that relative permeability curves are not classified and optimized;2) Two kinds of classification and evaluation methods of relative permeability curve were put forward, the direct evaluation method and the analogy method;it can get the typical relative permeability curve by identifying abnormal curve.展开更多
The Cheng index distinguishes indica andjaponica rice based on six taxonomic traits.This index has been widely used for classifi- cation of indica and japonica varieties in China.In this study,a double haploid(DH)popu...The Cheng index distinguishes indica andjaponica rice based on six taxonomic traits.This index has been widely used for classifi- cation of indica and japonica varieties in China.In this study,a double haploid(DH)popula-tion derived from anther culture of ZYQ8/JX17 F,a typical inter-subspecies hybrid,was used to investigate the six taxonomictraits,i.e.leaf hairiness(LH),color of hullwhen heading(CHH),hairiness of hull(HH),length of the first and second panicle internode(LPI),length/width of grain(L/W),andphenol reaction(PH).The morphological in- dex(MI)was also calculated.Based on themolecular linkage map constructed from this展开更多
Moisture induced disintegration of soft rock in Red Beds is common all over the world. The slake durability index test is most useful to quantify durability of the soft rocks. Based on a series of slaking test, this a...Moisture induced disintegration of soft rock in Red Beds is common all over the world. The slake durability index test is most useful to quantify durability of the soft rocks. Based on a series of slaking test, this article aims to develop a durability classification involving particle size and slaking procedure. To describe the slaking procedure in detail,the Relative Slake Durability Index(Id_i) is proposed. The Id_i is the percentage ratio of the i^(th) weight of oven-dry retained portion to the(i-1)^(th) weight of ovendry retained portion. Results show that the Id_i of samples have a large difference in certain slaking procedure, whereas the traditional Durability Slake Index(Id) is almost constant. Considering this limitation of Id in durability classification, an advanced classification by applying the Id_i and disintegration ratio(DR) is further established in this article. Compared to the durability classification based on Slake Durability Index(Id), the new classification accounts for the particle size of the slaked material and the slaking procedure, so it provides a better measure of the degree of slaking. The classification recommended in this article divide the slake durability into three classes(i.e., low, medium and high class). Furthermore, it divides both the low class and the medium class into 3 subclasses.展开更多
Learning comprehensive spatiotemporal features is crucial for human action recognition. Existing methods tend to model the spatiotemporal feature blocks in an integrate-separate-integrate form, such as appearance-and-...Learning comprehensive spatiotemporal features is crucial for human action recognition. Existing methods tend to model the spatiotemporal feature blocks in an integrate-separate-integrate form, such as appearance-and-relation network(ARTNet) and spatiotemporal and motion network(STM). However, with blocks stacking up, the rear part of the network has poor interpretability. To avoid this problem, we propose a novel architecture called spatial temporal relation network(STRNet), which can learn explicit information of appearance, motion and especially the temporal relation information. Specifically, our STRNet is constructed by three branches,which separates the features into 1) appearance pathway, to obtain spatial semantics, 2) motion pathway, to reinforce the spatiotemporal feature representation, and 3) relation pathway, to focus on capturing temporal relation details of successive frames and to explore long-term representation dependency. In addition, our STRNet does not just simply merge the multi-branch information, but we apply a flexible and effective strategy to fuse the complementary information from multiple pathways. We evaluate our network on four major action recognition benchmarks: Kinetics-400, UCF-101, HMDB-51, and Something-Something v1, demonstrating that the performance of our STRNet achieves the state-of-the-art result on the UCF-101 and HMDB-51 datasets, as well as a comparable accuracy with the state-of-the-art method on Something-Something v1 and Kinetics-400.展开更多
Inland freshwater lake wetlands play an important role in regional ecological balance. Hongze Lake is the fourth biggest freshwater lake in China. In the past three decades, there has been significant loss of freshwat...Inland freshwater lake wetlands play an important role in regional ecological balance. Hongze Lake is the fourth biggest freshwater lake in China. In the past three decades, there has been significant loss of freshwater wet- lands within the lake and at the mouths of neighboring rivers, due to disturbance, primarily from human activities. The main purpose of this paper was to explore a practical technology for differentiating wetlands effectively from upland types in close proximity to them. In the paper, an integrated method, which combined per-pixel and per-field classifi- cation, was used for mapping wetlands of Hongze Lake and their neighboring upland types. Firstly, Landsat ETM＋ imagery was segmented and classified by using spectral and textural features. Secondly, ETM＋ spectral bands, textural features derived from ETM＋ Pan imagery, relative relations between neighboring classes, shape fea^xes, and elevation were used in a decision tree classification. Thirdly, per-pixel classification results from the decision tree classifier were improved by using classification results from object-oriented classification as a context. The results show that the technology has not only overcome the salt-and-pepper effect commonly observed in the past studies, but also has im- proved the accuracy of identification by nearly 5%.展开更多
This study is to explore a suitable method to classify landform, in order to support the decision making for community siting in mountainous areas.It first proposes the landform classification for community siting(LCC...This study is to explore a suitable method to classify landform, in order to support the decision making for community siting in mountainous areas.It first proposes the landform classification for community siting(LCCS) method with detailed discussions on its rationality and the chosen parameters.This method is then tested and verified in Quxian county.The LCCS method entails twograde parameters, which uses relative relief as the first grading parameter, slope as the second, followed by a synthesis process to form a suitable landform classification system.By applying the LCCS method in Quxian county, the result shows that its use of watershed to identify geomorphometric units, and its use of the altitude datum concept, can effectively classify landform according to the local cultural traditions, and the economic and environmental conditions.The verification result shows that comparing to the conventional methods, the LCCS method respects to people's daily experience due to its bottom-up approach.It not only help to minimize the disturbance to the nature when choosing locations for community development, but also helps to prepare more precise land management policies,which maximizes agricultural production and minimizes terrain transformation.展开更多
As the popularity of digital images is rapidly increasing on the Internet, research on technologies for semantic image classification has become an important research topic. However, the well-known content-based image...As the popularity of digital images is rapidly increasing on the Internet, research on technologies for semantic image classification has become an important research topic. However, the well-known content-based image classification methods do not overcome the so-called semantic gap problem in which low-level visual features cannot represent the high-level semantic content of images. Image classification using visual and textual information often performs poorly since the extracted textual features are often too limited to accurately represent the images. In this paper, we propose a semantic image classification ap- proach using multi-context analysis. For a given image, we model the relevant textual information as its multi-modal context, and regard the related images connected by hyperlinks as its link context. Two kinds of context analysis models, i.e., cross-modal correlation analysis and link-based correlation model, are used to capture the correlation among different modals of features and the topical dependency among images induced by the link structure. We propose a new collective classification model called relational support vector classifier (RSVC) based on the well-known Support Vector Machines (SVMs) and the link-based cor- relation model. Experiments showed that the proposed approach significantly improved classification accuracy over that of SVM classifiers using visual and/or textual features.展开更多
This paper investigates the approach of presenting groups by generators and relations from an original angle. It starts by interpreting this familiar concept with the novel notion of “formal words” created by juxtap...This paper investigates the approach of presenting groups by generators and relations from an original angle. It starts by interpreting this familiar concept with the novel notion of “formal words” created by juxtaposing letters in a set. Taking that as basis, several fundamental results related to free groups, such as Dyck’s Theorem, are proven. Then, the paper highlights three creative applications of the concept in classifying finite groups of a fixed order, representing all dihedral groups geometrically, and analyzing knots topologically. All three applications are of considerable significance in their respective topic areas and serve to illustrate the advantages and certain limitations of the approach flexibly and comprehensively.展开更多
Experiments of electrical responses of waterflooded layers were carried out on porous,fractured,porous-fractured and composite cores taken from carbonate reservoirs in the Zananor Oilfield,Kazakhstan to find out the e...Experiments of electrical responses of waterflooded layers were carried out on porous,fractured,porous-fractured and composite cores taken from carbonate reservoirs in the Zananor Oilfield,Kazakhstan to find out the effects of injected water salinity on electrical responses of carbonate reservoirs.On the basis of the experimental results and the mathematical model of calculating oil-water relative permeability of porous reservoirs by resistivity and the relative permeability model of two-phase flow in fractured reservoirs,the classification standards of water-flooded layers suitable for carbonate reservoirs with complex pore structure were established.The results show that the salinity of injected water is the main factor affecting the resistivity of carbonate reservoir.When low salinity water(fresh water)is injected,the relationship curve between resistivity and water saturation is U-shaped.When high salinity water(salt water)is injected,the curve is L-shaped.The classification criteria of water-flooded layers for carbonate reservoirs are as follows:(1)In porous reservoirs,the water cut(fw)is less than or equal to 5%in oil layers,5%–20%in weak water-flooded layers,20%–50%in moderately water-flooded layers,and greater than 50%in strong water-flooded layers.(2)For fractured,porous-fractured and composite reservoirs,the oil layers,weakly water-flooded layers,moderately water-flooded layers,and severely water-flooded layers have a water content of less than or equal to 5%,5%and 10%,10%to 50%,and larger than 50%respectively.展开更多
Dentistry is a profession with a high prevalence of work-related musculoskeletal disorders(WMSDs),with symptoms often appearing very early in one’s career[1].WMSDs are conditions affecting the muscles,bones,and nervo...Dentistry is a profession with a high prevalence of work-related musculoskeletal disorders(WMSDs),with symptoms often appearing very early in one’s career[1].WMSDs are conditions affecting the muscles,bones,and nervous system due to occupational factors.In 2002,the International Labor Organization included musculoskeletal diseases in the International List of Occupational Diseases.China’s recently updated Classification and Catalog of Occupational Diseases has introduced two new categories of occupational illnesses,including occupational musculoskeletal disorders.WMSDs significantly impact the health and work of dentists,reducing their quality of life and causing economic losses.These disorders are multifactorial in nature,influenced by personal,psychosocial,biomechanical,and environmental factors.Dentists frequently maintain static or awkward postures during procedures,which leads to musculoskeletal strain and discomfort;additionally,long working hours contribute to psychological stress,further increasing the risk of WMSDs[2].展开更多
This paper proposes a tree kernel method of semantic relation detection and classification （RDC） between named entities. It resolves two critical problems in previous tree kernel methods of RDC. First, a new tree ke...This paper proposes a tree kernel method of semantic relation detection and classification （RDC） between named entities. It resolves two critical problems in previous tree kernel methods of RDC. First, a new tree kernel is presented to better capture the inherent structural information in a parse tree by enabling the standard convolution tree kernel with context-sensitiveness and approximate matching of sub-trees. Second, an enriched parse tree structure is proposed to well derive necessary structural information, e.g., proper latent annotations, from a parse tree. Evaluation on the ACE RDC corpora shows that both the new tree kernel and the enriched parse tree structure contribute significantly to RDC and our tree kernel method much outperforms the state-of-the-art ones.展开更多
Relation classification is a crucial component in many Natural Language Processing(NLP) systems. In this paper, we propose a novel bidirectional recurrent neural network architecture(using Long Short-Term Memory,LSTM,...Relation classification is a crucial component in many Natural Language Processing(NLP) systems. In this paper, we propose a novel bidirectional recurrent neural network architecture(using Long Short-Term Memory,LSTM, cells) for relation classification, with an attention layer for organizing the context information on the word level and a tensor layer for detecting complex connections between two entities. The above two feature extraction operations are based on the LSTM networks and use their outputs. Our model allows end-to-end learning from the raw sentences in the dataset, without trimming or reconstructing them. Experiments on the SemEval-2010 Task 8dataset show that our model outperforms most state-of-the-art methods.展开更多
Entity relation classification aims to classify the semantic relationship between two marked entities in a given sentence,and plays a vital role in various natural language processing applications.However,existing stu...Entity relation classification aims to classify the semantic relationship between two marked entities in a given sentence,and plays a vital role in various natural language processing applications.However,existing studies focus on exploiting mono-lingual data in English,due to the lack of labeled data in other languages.How to effectively benefit from a richly-labeled language to help a poorly-labeled language is still an open problem.In this paper,we come up with a language adaptation framework for cross-lingual entity relation classification.The basic idea is to employ adversarial neural networks(AdvNN)to transfer feature representations from one language to another.Especially,such a language adaptation framework enables feature imitation via the competition between a sentence encoder and a rival language discriminator to generate effective representations.To verify the effectiveness of AdvNN,we introduce two kinds of adversarial structures,dual-channel AdvNN and single-channel AdvNN.Experimental results on the ACE 2005 multilingual training corpus show that our single-channel AdvNN achieves the best performance on both unsupervised and semi-supervised scenarios,yielding an improvement of 6.61%and 2.98%over the state-of-the-art,respectively.Compared with baselines which directly adopt a machine translation module,we find that both dual-channel and single-channel AdvNN significantly improve the performances(F1)of cross-lingual entity relation classification.Moreover,extensive analysis and discussion demonstrate the appropriateness and effectiveness of different parameter settings in our language adaptation framework.展开更多
In this study, we propose an incremental learning approach based on a machine-machine interaction via relative attribute feedbacks that exploit comparative relationships among top level image categories. One machine a...In this study, we propose an incremental learning approach based on a machine-machine interaction via relative attribute feedbacks that exploit comparative relationships among top level image categories. One machine acts as ＇Student （S）＇ with initially limited information and it endeavors to capture the task domain gradually by questioning its mentor on a pool of unlabeled data. The other machine is ＇Teacher （T）＇ with the implicit knowledge for helping S on learning the class models. T initiates relative attributes as a communication channel by randomly sorting the classes on attribute space in an unsupervised manner. S starts modeling the categories in this intermediate level by using only a limited number of labeled data. Thereafter, it first selects an entropy-based sample from the pool of unlabeled data and triggers the conversation by propagating the selected image with its belief class in a query. Since T already knows the ground truth labels, it not only decides whether the belief is true or false, but it also provides an attribute-based feedback to S in each case without revealing the true label of the query sample if the belief is false. So the number of training data is increased virtually by dropping the falsely predicted sample back into the unlabeled pool. Next, S updates the attribute space which, in fact, has an impact on T＇s future responses, and then the category models are updated concurrently for the next run. We experience the weakly supervised algorithm on the real world datasets of faces and natural scenes in comparison with direct attribute prediction and semi-supervised learning approaches, and a noteworthy performance increase is achieved.展开更多
基金sponsored by the National Natural Science Foundation of China Grant No.62271302the Shanghai Municipal Natural Science Foundation Grant 20ZR1423500.
文摘Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,labeled data is very scarce due to patient privacy concerns.For researchers,obtaining high-quality labeled images is exceedingly challenging because it involves manual annotation and clinical understanding.In addition,skin datasets are highly suitable for medical image classification studies due to the inter-class relationships and the inter-class similarities of skin lesions.In this paper,we propose a model called Coalition Sample Relation Consistency(CSRC),a consistency-based method that leverages Canonical Correlation Analysis(CCA)to capture the intrinsic relationships between samples.Considering that traditional consistency-based models only focus on the consistency of prediction,we additionally explore the similarity between features by using CCA.We enforce feature relation consistency based on traditional models,encouraging the model to learn more meaningful information from unlabeled data.Finally,considering that cross-entropy loss is not as suitable as the supervised loss when studying with imbalanced datasets(i.e.,ISIC 2017 and ISIC 2018),we improve the supervised loss to achieve better classification accuracy.Our study shows that this model performs better than many semi-supervised methods.
基金Supported by the China Postdoctoral Science Foundation(2014T70722)the Humanities and Social Science Foundation of Ministry of Education of China(16YJCZH004)
文摘Structure features need complicated pre-processing, and are probably domain-dependent. To reduce time cost of pre-processing, we propose a novel neural network architecture which is a bi-directional long-short-term-memory recurrent-neural-network（Bi-LSTM-RNN） model based on low-cost sequence features such as words and part-of-speech（POS） tags, to classify the relation of two entities. First, this model performs bi-directional recurrent computation along the tokens of sentences. Then, the sequence is divided into five parts and standard pooling functions are applied over the token representations of each part. Finally, the token representations are concatenated and fed into a softmax layer for relation classification. We evaluate our model on two standard benchmark datasets in different domains, namely Sem Eval-2010 Task 8 and Bio NLP-ST 2016 Task BB3. In Sem Eval-2010 Task 8, the performance of our model matches those of the state-of-the-art models, achieving 83.0% in F1. In Bio NLP-ST 2016 Task BB3, our model obtains F1 51.3% which is comparable with that of the best system. Moreover, we find that the context between two target entities plays an important role in relation classification and it can be a replacement of the shortest dependency path.
文摘Text classification,by automatically categorizing texts,is one of the foundational elements of natural language processing applications.This study investigates how text classification performance can be improved through the integration of entity-relation information obtained from the Wikidata(Wikipedia database)database and BERTbased pre-trained Named Entity Recognition(NER)models.Focusing on a significant challenge in the field of natural language processing(NLP),the research evaluates the potential of using entity and relational information to extract deeper meaning from texts.The adopted methodology encompasses a comprehensive approach that includes text preprocessing,entity detection,and the integration of relational information.Experiments conducted on text datasets in both Turkish and English assess the performance of various classification algorithms,such as Support Vector Machine,Logistic Regression,Deep Neural Network,and Convolutional Neural Network.The results indicate that the integration of entity-relation information can significantly enhance algorithmperformance in text classification tasks and offer new perspectives for information extraction and semantic analysis in NLP applications.Contributions of this work include the utilization of distant supervised entity-relation information in Turkish text classification,the development of a Turkish relational text classification approach,and the creation of a relational database.By demonstrating potential performance improvements through the integration of distant supervised entity-relation information into Turkish text classification,this research aims to support the effectiveness of text-based artificial intelligence(AI)tools.Additionally,it makes significant contributions to the development ofmultilingual text classification systems by adding deeper meaning to text content,thereby providing a valuable addition to current NLP studies and setting an important reference point for future research.
文摘Given the scarcity of Satellite Frequency and Orbit(SFO)resources,it holds paramount importance to establish a comprehensive knowledge graph of SFO field(SFO-KG)and employ knowledge reasoning technology to automatically mine available SFO resources.An essential aspect of constructing SFO-KG is the extraction of Chinese entity relations.Unfortunately,there is currently no publicly available Chinese SFO entity Relation Extraction(RE)dataset.Moreover,publicly available SFO text data contain numerous NA(representing for“No Answer”)relation category sentences that resemble other relation sentences and pose challenges in accurate classification,resulting in low recall and precision for the NA relation category in entity RE.Consequently,this issue adversely affects both the accuracy of constructing the knowledge graph and the efficiency of RE processes.To address these challenges,this paper proposes a method for extracting Chinese SFO text entity relations based on dynamic integrated learning.This method includes the construction of a manually annotated Chinese SFO entity RE dataset and a classifier combining features of SFO resource data.The proposed approach combines integrated learning and pre-training models,specifically utilizing Bidirectional Encoder Representation from Transformers(BERT).In addition,it incorporates one-class classification,attention mechanisms,and dynamic feedback mechanisms to improve the performance of the RE model.Experimental results show that the proposed method outperforms the traditional methods in terms of F1 value when extracting entity relations from both balanced and long-tailed datasets.
文摘The classification method of relative permeability curves is rarely reported, when relative permeability curves are applied;if the multiple relative permeability curves are normalized directly, but not classified, the calculated result maybe cause a large error. For example, the relationship curve between oil displacement efficiency and water cut, which derived from the relative permeability curve in LD oilfield is uncertain in the shape of low water cut stage. If being directly normalized, the result of the interpretation of the water flooded zone is very high. In this study, two problems were solved: 1) The mathematical equation of the relationship between oil displacement efficiency and water cut was deduced, and repaired the lost data of oil displacement efficiency and water cut curve, which solve the problem of uncertain curve shape. After analysis, the reason why the curve is not available is that relative permeability curves are not classified and optimized;2) Two kinds of classification and evaluation methods of relative permeability curve were put forward, the direct evaluation method and the analogy method;it can get the typical relative permeability curve by identifying abnormal curve.
文摘The Cheng index distinguishes indica andjaponica rice based on six taxonomic traits.This index has been widely used for classifi- cation of indica and japonica varieties in China.In this study,a double haploid(DH)popula-tion derived from anther culture of ZYQ8/JX17 F,a typical inter-subspecies hybrid,was used to investigate the six taxonomictraits,i.e.leaf hairiness(LH),color of hullwhen heading(CHH),hairiness of hull(HH),length of the first and second panicle internode(LPI),length/width of grain(L/W),andphenol reaction(PH).The morphological in- dex(MI)was also calculated.Based on themolecular linkage map constructed from this
基金financially supported by the National Natural Science Foundation of China (Grant No. 41272332)
文摘Moisture induced disintegration of soft rock in Red Beds is common all over the world. The slake durability index test is most useful to quantify durability of the soft rocks. Based on a series of slaking test, this article aims to develop a durability classification involving particle size and slaking procedure. To describe the slaking procedure in detail,the Relative Slake Durability Index(Id_i) is proposed. The Id_i is the percentage ratio of the i^(th) weight of oven-dry retained portion to the(i-1)^(th) weight of ovendry retained portion. Results show that the Id_i of samples have a large difference in certain slaking procedure, whereas the traditional Durability Slake Index(Id) is almost constant. Considering this limitation of Id in durability classification, an advanced classification by applying the Id_i and disintegration ratio(DR) is further established in this article. Compared to the durability classification based on Slake Durability Index(Id), the new classification accounts for the particle size of the slaked material and the slaking procedure, so it provides a better measure of the degree of slaking. The classification recommended in this article divide the slake durability into three classes(i.e., low, medium and high class). Furthermore, it divides both the low class and the medium class into 3 subclasses.
基金supported by National Natural Science Foundation of China(Nos.U1836218,62020106012,61672265 and 61902153)the 111 Project of Ministry of Education of China(No.B12018)+1 种基金the EPSRC Programme FACER2VM(No.EP/N007743/1)the EPSRC/MURI/Dstl Project under(No.EP/R013616/1.)。
文摘Learning comprehensive spatiotemporal features is crucial for human action recognition. Existing methods tend to model the spatiotemporal feature blocks in an integrate-separate-integrate form, such as appearance-and-relation network(ARTNet) and spatiotemporal and motion network(STM). However, with blocks stacking up, the rear part of the network has poor interpretability. To avoid this problem, we propose a novel architecture called spatial temporal relation network(STRNet), which can learn explicit information of appearance, motion and especially the temporal relation information. Specifically, our STRNet is constructed by three branches,which separates the features into 1) appearance pathway, to obtain spatial semantics, 2) motion pathway, to reinforce the spatiotemporal feature representation, and 3) relation pathway, to focus on capturing temporal relation details of successive frames and to explore long-term representation dependency. In addition, our STRNet does not just simply merge the multi-branch information, but we apply a flexible and effective strategy to fuse the complementary information from multiple pathways. We evaluate our network on four major action recognition benchmarks: Kinetics-400, UCF-101, HMDB-51, and Something-Something v1, demonstrating that the performance of our STRNet achieves the state-of-the-art result on the UCF-101 and HMDB-51 datasets, as well as a comparable accuracy with the state-of-the-art method on Something-Something v1 and Kinetics-400.
基金Under the auspices of Natural Science Foundation of Jiangsu Province (No. BK2008360)Foundamental Research Funds for the Central Universities (No. 2009B12714,2009B11714)
文摘Inland freshwater lake wetlands play an important role in regional ecological balance. Hongze Lake is the fourth biggest freshwater lake in China. In the past three decades, there has been significant loss of freshwater wet- lands within the lake and at the mouths of neighboring rivers, due to disturbance, primarily from human activities. The main purpose of this paper was to explore a practical technology for differentiating wetlands effectively from upland types in close proximity to them. In the paper, an integrated method, which combined per-pixel and per-field classifi- cation, was used for mapping wetlands of Hongze Lake and their neighboring upland types. Firstly, Landsat ETM＋ imagery was segmented and classified by using spectral and textural features. Secondly, ETM＋ spectral bands, textural features derived from ETM＋ Pan imagery, relative relations between neighboring classes, shape fea^xes, and elevation were used in a decision tree classification. Thirdly, per-pixel classification results from the decision tree classifier were improved by using classification results from object-oriented classification as a context. The results show that the technology has not only overcome the salt-and-pepper effect commonly observed in the past studies, but also has im- proved the accuracy of identification by nearly 5%.
基金supported by the National Natural Science Foundation of China(Grant Nos.51478056 and 51208202)
文摘This study is to explore a suitable method to classify landform, in order to support the decision making for community siting in mountainous areas.It first proposes the landform classification for community siting(LCCS) method with detailed discussions on its rationality and the chosen parameters.This method is then tested and verified in Quxian county.The LCCS method entails twograde parameters, which uses relative relief as the first grading parameter, slope as the second, followed by a synthesis process to form a suitable landform classification system.By applying the LCCS method in Quxian county, the result shows that its use of watershed to identify geomorphometric units, and its use of the altitude datum concept, can effectively classify landform according to the local cultural traditions, and the economic and environmental conditions.The verification result shows that comparing to the conventional methods, the LCCS method respects to people's daily experience due to its bottom-up approach.It not only help to minimize the disturbance to the nature when choosing locations for community development, but also helps to prepare more precise land management policies,which maximizes agricultural production and minimizes terrain transformation.
基金Project supported by the Hi-Tech Research and Development Pro-gram (863) of China (No. 2003AA119010), and China-American Digital Academic Library (CADAL) Project (No. CADAL2004002)
文摘As the popularity of digital images is rapidly increasing on the Internet, research on technologies for semantic image classification has become an important research topic. However, the well-known content-based image classification methods do not overcome the so-called semantic gap problem in which low-level visual features cannot represent the high-level semantic content of images. Image classification using visual and textual information often performs poorly since the extracted textual features are often too limited to accurately represent the images. In this paper, we propose a semantic image classification ap- proach using multi-context analysis. For a given image, we model the relevant textual information as its multi-modal context, and regard the related images connected by hyperlinks as its link context. Two kinds of context analysis models, i.e., cross-modal correlation analysis and link-based correlation model, are used to capture the correlation among different modals of features and the topical dependency among images induced by the link structure. We propose a new collective classification model called relational support vector classifier (RSVC) based on the well-known Support Vector Machines (SVMs) and the link-based cor- relation model. Experiments showed that the proposed approach significantly improved classification accuracy over that of SVM classifiers using visual and/or textual features.
文摘This paper investigates the approach of presenting groups by generators and relations from an original angle. It starts by interpreting this familiar concept with the novel notion of “formal words” created by juxtaposing letters in a set. Taking that as basis, several fundamental results related to free groups, such as Dyck’s Theorem, are proven. Then, the paper highlights three creative applications of the concept in classifying finite groups of a fixed order, representing all dihedral groups geometrically, and analyzing knots topologically. All three applications are of considerable significance in their respective topic areas and serve to illustrate the advantages and certain limitations of the approach flexibly and comprehensively.
基金Supported by the China National Major Science and Technology Project(2017ZX05030-002)the Natural Science Basic Research Plan in Shaanxi Province of China(2020JQ-747)the Fundamental Research Funds for the Central Universities(300102260107)
文摘Experiments of electrical responses of waterflooded layers were carried out on porous,fractured,porous-fractured and composite cores taken from carbonate reservoirs in the Zananor Oilfield,Kazakhstan to find out the effects of injected water salinity on electrical responses of carbonate reservoirs.On the basis of the experimental results and the mathematical model of calculating oil-water relative permeability of porous reservoirs by resistivity and the relative permeability model of two-phase flow in fractured reservoirs,the classification standards of water-flooded layers suitable for carbonate reservoirs with complex pore structure were established.The results show that the salinity of injected water is the main factor affecting the resistivity of carbonate reservoir.When low salinity water(fresh water)is injected,the relationship curve between resistivity and water saturation is U-shaped.When high salinity water(salt water)is injected,the curve is L-shaped.The classification criteria of water-flooded layers for carbonate reservoirs are as follows:(1)In porous reservoirs,the water cut(fw)is less than or equal to 5%in oil layers,5%–20%in weak water-flooded layers,20%–50%in moderately water-flooded layers,and greater than 50%in strong water-flooded layers.(2)For fractured,porous-fractured and composite reservoirs,the oil layers,weakly water-flooded layers,moderately water-flooded layers,and severely water-flooded layers have a water content of less than or equal to 5%,5%and 10%,10%to 50%,and larger than 50%respectively.
基金supported by the 2021 Shandong Province Higher Education Institutions“Youth Innovation Talent Introduction and Cultivation Plan”(Public Health Safety Risk Assessment and Response Innovation Team)National Traditional Chinese Medicine Comprehensive Reform Demonstration Zone Science and Technology Co construction Project(No.GZYKJSSD-2024-106)Research Project of Shandong Educational Supervision Society(No.SDJYDDXH2023-2159).
文摘Dentistry is a profession with a high prevalence of work-related musculoskeletal disorders(WMSDs),with symptoms often appearing very early in one’s career[1].WMSDs are conditions affecting the muscles,bones,and nervous system due to occupational factors.In 2002,the International Labor Organization included musculoskeletal diseases in the International List of Occupational Diseases.China’s recently updated Classification and Catalog of Occupational Diseases has introduced two new categories of occupational illnesses,including occupational musculoskeletal disorders.WMSDs significantly impact the health and work of dentists,reducing their quality of life and causing economic losses.These disorders are multifactorial in nature,influenced by personal,psychosocial,biomechanical,and environmental factors.Dentists frequently maintain static or awkward postures during procedures,which leads to musculoskeletal strain and discomfort;additionally,long working hours contribute to psychological stress,further increasing the risk of WMSDs[2].
基金Supported by the National Natural Science Foundation of China under Grant Nos.60873150,60970056 and 90920004
文摘This paper proposes a tree kernel method of semantic relation detection and classification （RDC） between named entities. It resolves two critical problems in previous tree kernel methods of RDC. First, a new tree kernel is presented to better capture the inherent structural information in a parse tree by enabling the standard convolution tree kernel with context-sensitiveness and approximate matching of sub-trees. Second, an enriched parse tree structure is proposed to well derive necessary structural information, e.g., proper latent annotations, from a parse tree. Evaluation on the ACE RDC corpora shows that both the new tree kernel and the enriched parse tree structure contribute significantly to RDC and our tree kernel method much outperforms the state-of-the-art ones.
基金supported by the National Natural Science Foundation of China (No. 61572505)ChanXueYan Prospective Project of Jiangsu Province (No. BY201502305)
文摘Relation classification is a crucial component in many Natural Language Processing(NLP) systems. In this paper, we propose a novel bidirectional recurrent neural network architecture(using Long Short-Term Memory,LSTM, cells) for relation classification, with an attention layer for organizing the context information on the word level and a tensor layer for detecting complex connections between two entities. The above two feature extraction operations are based on the LSTM networks and use their outputs. Our model allows end-to-end learning from the raw sentences in the dataset, without trimming or reconstructing them. Experiments on the SemEval-2010 Task 8dataset show that our model outperforms most state-of-the-art methods.
基金This work was supported by the National Natural Science Foundation of China under Grant Nos.61703293,61751206,and 61672368.
文摘Entity relation classification aims to classify the semantic relationship between two marked entities in a given sentence,and plays a vital role in various natural language processing applications.However,existing studies focus on exploiting mono-lingual data in English,due to the lack of labeled data in other languages.How to effectively benefit from a richly-labeled language to help a poorly-labeled language is still an open problem.In this paper,we come up with a language adaptation framework for cross-lingual entity relation classification.The basic idea is to employ adversarial neural networks(AdvNN)to transfer feature representations from one language to another.Especially,such a language adaptation framework enables feature imitation via the competition between a sentence encoder and a rival language discriminator to generate effective representations.To verify the effectiveness of AdvNN,we introduce two kinds of adversarial structures,dual-channel AdvNN and single-channel AdvNN.Experimental results on the ACE 2005 multilingual training corpus show that our single-channel AdvNN achieves the best performance on both unsupervised and semi-supervised scenarios,yielding an improvement of 6.61%and 2.98%over the state-of-the-art,respectively.Compared with baselines which directly adopt a machine translation module,we find that both dual-channel and single-channel AdvNN significantly improve the performances(F1)of cross-lingual entity relation classification.Moreover,extensive analysis and discussion demonstrate the appropriateness and effectiveness of different parameter settings in our language adaptation framework.
文摘In this study, we propose an incremental learning approach based on a machine-machine interaction via relative attribute feedbacks that exploit comparative relationships among top level image categories. One machine acts as ＇Student （S）＇ with initially limited information and it endeavors to capture the task domain gradually by questioning its mentor on a pool of unlabeled data. The other machine is ＇Teacher （T）＇ with the implicit knowledge for helping S on learning the class models. T initiates relative attributes as a communication channel by randomly sorting the classes on attribute space in an unsupervised manner. S starts modeling the categories in this intermediate level by using only a limited number of labeled data. Thereafter, it first selects an entropy-based sample from the pool of unlabeled data and triggers the conversation by propagating the selected image with its belief class in a query. Since T already knows the ground truth labels, it not only decides whether the belief is true or false, but it also provides an attribute-based feedback to S in each case without revealing the true label of the query sample if the belief is false. So the number of training data is increased virtually by dropping the falsely predicted sample back into the unlabeled pool. Next, S updates the attribute space which, in fact, has an impact on T＇s future responses, and then the category models are updated concurrently for the next run. We experience the weakly supervised algorithm on the real world datasets of faces and natural scenes in comparison with direct attribute prediction and semi-supervised learning approaches, and a noteworthy performance increase is achieved.
