Crowdsourcing is a cheap and popular method to solve problems that are difficult for computers to handle. Due to the differences in ability among workers on crowdsourcing platforms, existing research use aggregation s...
详细信息
ISBN:
(纸本)9781665438599
Crowdsourcing is a cheap and popular method to solve problems that are difficult for computers to handle. Due to the differences in ability among workers on crowdsourcing platforms, existing research use aggregation strategies to deal with the labels of different workers to improve the utility of crowdsourcing data. However, most of these studies are based on probabilistic graphical models, which have problems such as difficulty in setting initial parameters. This paper proposes a novel crowdsourcing method Truth Inference based on Graph Embedding (TIGE) for single-choice questions, the method draws on the idea of graph autoencoder, constructs feature vectors for each crowdsourcing task, embeds the relationship between crowdsourcing tasks and workers in graphs, then uses graph neural networks to convert crowdsourcing problems into graph node prediction problems. The feature vectors are continuously optimized in the convolutional layer to obtain the final result. Compared with the six state-of-the-art algorithms on real-world datasets, our method has significant advantages in accuracy and F1-score.
Ontology revision aims to seamlessly incorporate a new ontology into an existing ontology and plays a crucial role in tasks such as ontology evolution, ontology maintenance, and ontology alignment. Similar to repair s...
详细信息
Ontology revision aims to seamlessly incorporate a new ontology into an existing ontology and plays a crucial role in tasks such as ontology evolution, ontology maintenance, and ontology alignment. Similar to repair single ontologies, resolving logical incoherence in the task of ontology revision is also important and meaningful, because incoherence is a main potential factor to cause inconsistency and reasoning with an inconsistent ontology will obtain meaningless answers. To deal with this problem, various ontology revision approaches have been proposed to define revision operators and design ranking strategies for axioms in an ontology. However, they rarely consider axiom semantics which provides important information to differentiate axioms. In addition, pre-trained models can be utilized to encode axiom semantics, and have been widely applied in many natural language processing tasks and ontology-related ones in recent years. Therefore, in this paper, we study how to apply pre-trained models to revise ontologies. We first define four scoring functions to rank axioms based on a pre-trained model by considering various information from an ontology. Based on the functions, an ontology revision algorithm is then proposed to deal with unsatisfiable concepts at once. To improve efficiency, an adapted revision algorithm is designed to deal with unsatisfiable concepts group by group. We conduct experiments over 19 ontology pairs and compare our algorithms and scoring functions with existing ones. According to the experiments, our algorithms could achieve promising performance. The adapted revision algorithm could improve the efficiency largely, and at most about 90% of the time could be saved for some ontology pairs. Some of our scoring functions like reliableOnt cos could help a revision algorithm obtain better results in many cases, especially for those challenging ontology pairs like OM8. We also provide discussion about the overall experimental results and guidelin
Few clustering methods show good performance on multivariate time series (MTS) data. Traditional methods rely too much on similarity measures and perform poorly on the MTS data with complex structures. This paper prop...
详细信息
ISBN:
(纸本)9781665438599
Few clustering methods show good performance on multivariate time series (MTS) data. Traditional methods rely too much on similarity measures and perform poorly on the MTS data with complex structures. This paper proposes an MTS clustering algorithm based on graph embedding called MTSC-GE to improve the performance of MTS clustering. MTSC-GE can map MTS samples to the feature representations in a low-dimensional space and then cluster them. While mining the information of the samples themselves, MTSC-GE builds the whole time series data into a graph, paying attention to the connections between samples from an overall perspective and discovering the local structural feature of MTS data. The proposed MTSC-G E consists of three stages. The first stage builds a graph using the original dataset, where each of the MTS samples is regarded as a node in the graph. The second stage uses the graph embedding technique to obtain a new representation of each node. Finally, MTSC-G E uses the K - Means algorithm to cluster based on the newly obtained representation. We compare MTSC-GE with six state-of-the-art benchmark methods on five public datasets, experimental results show that MTSC-GE has achieved good performance.
Background:As a systemic disease,pancreatic cancer(PC)can be treated systemically to raise the R0 resection rate and enhance patient *** best ways to assess the treatment response to systemic treatment of patients wit...
详细信息
Background:As a systemic disease,pancreatic cancer(PC)can be treated systemically to raise the R0 resection rate and enhance patient *** best ways to assess the treatment response to systemic treatment of patients with PC are still ***:A total of 122 PC patients were enrolled;25 of these patients were used as an independent testing *** to the pathologic response,PC patients were classified into the responder and nonresponder *** whole tumor,core,edge,and peritumoral were segmented from the enhanced computed tomography(CT)***-learning models were created by extracting the variations in radionics features before and after therapy(delta radiomics features).Finally,we compared the performance of models based on radiomics features,changes in tumor markers,and radiologic ***:The model based on the core(area under curve[AUC]=0.864)and edge features(AUC=0.853)showed better performance than that based on the whole tumor(AUC=0.847)or peritumoral area(AUC=0.846).Moreover,the tumor core_edge combination model(AUC=0.899)could better increase confidence in treatment response than using either of them *** accuracies of models based on changes in tumor markers and radiologic evaluation were relatively poorer than of the radiomics ***,Patients predicted to respond to therapy using the radiomics model showed a relatively longer overall survival(43 vs 27 months),although there were no significant differences(P=.063).Conclusions:The tumor core_edge combination delta radiomics model is an effective approach to evaluate pathologic response in PC patients with systemic treatment.
Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding. However, the existing SSL-based methods suffer fr...
详细信息
Image captioning is still a challenging task aiming at describing the contents of image by words. Current image caption methods usually assume the object relation to be important if the semantic and spatial geometric ...
详细信息
Image captioning is still a challenging task aiming at describing the contents of image by words. Current image caption methods usually assume the object relation to be important if the semantic and spatial geometric relationships between objects are close and large, but the relations meeting this assumption are not necessarily important to describe the contents of image in a fine-grained way. That is, the importance of fine-grained object relations is not properly taken into account. Besides, current Transformer based image caption models also fail to consider the importance of fine-grained objects, since they generate all the words of a sentence at one time, which cannot Figure out which objects are more important and vice versa. In this paper, we propose a novel Fine-grained Adaptive Object Transformer (FineFormer) network, which can jointly discover the importance of fine-grained objects and object relations for image captioning. Specifically, a new concept of adaptive soft-foreground attention is proposed to highlight the fine-grained objects dominating the descriptive contents. To characterize and calculate the important relations between fine-grained objects, we also propose an adaptive object relation attention to refine the object relation from the generation process of relation. As such, FineFormer can describe the contents of image more accurately, by reducing the interference of unimportant objects in the background. Extensive experiments on the highly-competitive MS-COCO dataset demonstrated the superiority of our FineFormer.
Class activation mapping (CAM), a visualization technique for interpreting deep learning models, is now commonly used for weakly supervised semantic segmentation (WSSS) and object localization (WSOL). It is the weight...
详细信息
Viewport prediction is a crucial aspect of tile-based 360◦ video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion be...
详细信息
This study investigates the effects of Fe on the oxygen-evolution reaction(OER)in the presence of *** distinct areas of OER were identified:the first associated with Fe sites at low overpotential(~330 mV),and the seco...
详细信息
This study investigates the effects of Fe on the oxygen-evolution reaction(OER)in the presence of *** distinct areas of OER were identified:the first associated with Fe sites at low overpotential(~330 mV),and the second with Au sites at high overpotential(~870 mV).Various factors such as surface Fe concentration,electrochemical method,scan rate,potential range,concentration,method of adding K_(2)Fe O_(4),nature of Fe,and temperature were varied to observe diverse behaviors during OER for Fe O_(x)H_(y)/*** amounts of Fe ions had a significant impact on OER,reaching a saturation point where the activity did not increase *** electronic interaction between Fe and Au ions was indicated by X-ray photoelectron spectroscopy(XPS)and electron paramagnetic resonance(EPR)*** situ visible spectroscopy confirmed the formation of Fe O_(4)^(2-)during *** situ Mossbauer and surfaceenhanced Raman spectroscopy(SERS)analyses suggest the involvement of Fe-based species as intermediates during the rate-determining step of OER.A lattice OER mechanism based on Fe O_(x)H_(y)was proposed for operation at low *** functional theory(DFT)calculations revealed that Fe oxide,Fe-oxide clusters,and Fe doping on the Au foil exhibited different activities and stabilities during *** study provides insights into the interplay between Fe and Au in OER,advancing the understanding of OER mechanisms and offering implications for the design of efficient electrocatalytic systems.
We propose a generalized framework for block-structured nonconvex optimization, which can be applied to structured subgraph detection in interdependent networks, such as multi-layer networks, temporal networks, networ...
详细信息
暂无评论