Zeitschriftenartikel: „Hierarchical Pooling“

1

Fernando, Basura, und Stephen Gould. „Discriminatively Learned Hierarchical Rank Pooling Networks“. International Journal of Computer Vision 124, Nr. 3 (24.06.2017): 335–55. http://dx.doi.org/10.1007/s11263-017-1030-x.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

2

Ranjan, Ekagra, Soumya Sanyal und Partha Talukdar. „ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations“. Proceedings of the AAAI Conference on Artificial Intelligence 34, Nr. 04 (03.04.2020): 5470–77. http://dx.doi.org/10.1609/aaai.v34i04.5997.

Der volle Inhalt der Quelle

Annotation:

Graph Neural Networks (GNN) have been shown to work effectively for modeling graph structured data to solve tasks such as node classification, link prediction and graph classification. There has been some recent progress in defining the notion of pooling in graphs whereby the model tries to generate a graph level representation by downsampling and summarizing the information present in the nodes. Existing pooling methods either fail to effectively capture the graph substructure or do not easily scale to large graphs. In this work, we propose ASAP (Adaptive Structure Aware Pooling), a sparse and differentiable pooling method that addresses the limitations of previous graph pooling architectures. ASAP utilizes a novel self-attention network along with a modified GNN formulation to capture the importance of each node in a given graph. It also learns a sparse soft cluster assignment for nodes at each layer to effectively pool the subgraphs to form the pooled graph. Through extensive experiments on multiple datasets and theoretical analysis, we motivate our choice of the components used in ASAP. Our experimental results show that combining existing GNN architectures with ASAP leads to state-of-the-art results on multiple graph classification benchmarks. ASAP has an average improvement of 4%, compared to current sparse hierarchical state-of-the-art method. We make the source code of ASAP available to encourage reproducible research 1.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

3

Chen, Jiawang, und Zhenqiang Wu. „Learning Embedding for Signed Network in Social Media with Hierarchical Graph Pooling“. Applied Sciences 12, Nr. 19 (28.09.2022): 9795. http://dx.doi.org/10.3390/app12199795.

Der volle Inhalt der Quelle

Annotation:

Signed network embedding concentrates on learning fixed-length representations for nodes in signed networks with positive and negative links, which contributes to many downstream tasks in social media, such as link prediction. However, most signed network embedding approaches neglect hierarchical graph pooling in the networks, limiting the capacity to learn genuine signed graph topology. To overcome this limitation, this paper presents a unique deep learning-based Signed network embedding model with Hierarchical Graph Pooling (SHGP). To be more explicit, a hierarchical pooling mechanism has been developed to encode the high-level features of the networks. Moreover, a graph convolution layer is introduced to aggregate both positive and negative information from neighbor nodes, and the concatenation of two parts generates the final embedding of the nodes. Extensive experiments on three large real-world signed network datasets demonstrate the effectiveness and excellence of the proposed method.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

4

Grumitt, R. D. P., Luke R. P. Jew und C. Dickinson. „Hierarchical Bayesian CMB component separation with the No-U-Turn Sampler“. Monthly Notices of the Royal Astronomical Society 496, Nr. 4 (26.06.2020): 4383–401. http://dx.doi.org/10.1093/mnras/staa1857.

Der volle Inhalt der Quelle

Annotation:

ABSTRACT In this paper, we present a novel implementation of Bayesian cosmic microwave background (CMB) component separation. We sample from the full posterior distribution using the No-U-Turn Sampler (NUTS), a gradient-based sampling algorithm. Alongside this, we introduce new foreground modelling approaches. We use the mean shift algorithm to define regions on the sky, clustering according to naively estimated foreground spectral parameters. Over these regions we adopt a complete pooling model, where we assume constant spectral parameters, and a hierarchical model, where we model individual pixel spectral parameters as being drawn from underlying hyperdistributions. We validate the algorithm against simulations of the LiteBIRD and C-Band All-Sky Survey (C-BASS) experiments, with an input tensor-to-scalar ratio of r = 5 × 10−3. Considering multipoles 30 ≤ ℓ < 180, we are able to recover estimates for r. With LiteBIRD-only observations, and using the complete pooling model, we recover r = (12.9 ± 1.4) × 10−3. For C-BASS and LiteBIRD observations we find r = (9.0 ± 1.1) × 10−3 using the complete pooling model, and r = (5.2 ± 1.0) × 10−3 using the hierarchical model. Unlike the complete pooling model, the hierarchical model captures pixel-scale spatial variations in the foreground spectral parameters, and therefore produces cosmological parameter estimates with reduced bias, without inflating their uncertainties. Measured by the rate of effective sample generation, NUTS offers performance improvements of ∼103 over using Metropolis–Hastings to fit the complete pooling model. The efficiency of NUTS allows us to fit the more sophisticated hierarchical foreground model that would likely be intractable with non-gradient-based sampling algorithms.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

5

Devineni, Naresh, Upmanu Lall, Neil Pederson und Edward Cook. „A Tree-Ring-Based Reconstruction of Delaware River Basin Streamflow Using Hierarchical Bayesian Regression“. Journal of Climate 26, Nr. 12 (15.06.2013): 4357–74. http://dx.doi.org/10.1175/jcli-d-11-00675.1.

Der volle Inhalt der Quelle

Annotation:

Abstract A hierarchical Bayesian regression model is presented for reconstructing the average summer streamflow at five gauges in the Delaware River basin using eight regional tree-ring chronologies. The model provides estimates of the posterior probability distribution of each reconstructed streamflow series considering parameter uncertainty. The vectors of regression coefficients are modeled as draws from a common multivariate normal distribution with unknown parameters estimated as part of the analysis. This leads to a multilevel structure. The covariance structure of the streamflow residuals across sites is explicitly modeled. The resulting partial pooling of information across multiple stations leads to a reduction in parameter uncertainty. The effect of no pooling and full pooling of station information, as end points of the method, is explored. The no-pooling model considers independent estimation of the regression coefficients for each streamflow gauge with respect to each tree-ring chronology. The full-pooling model considers that the same regression coefficients apply across all streamflow sites for a particular tree-ring chronology. The cross-site correlation of residuals is modeled in all cases. Performance on metrics typically used by tree-ring reconstruction experts, such as reduction of error, coefficient of efficiency, and coverage rates under credible intervals is comparable to, or better, for the partial-pooling model relative to the no-pooling model, and streamflow estimation uncertainty is reduced. Long record simulations from reconstructions are used to develop estimates of the probability of duration and severity of droughts in the region. Analysis of monotonic trends in the reconstructed drought events do not reject the null hypothesis of no trend at the 90% significance over 1754–2000.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

6

Chen, Junying, und Ying Chen. „Saliency Enhanced Hierarchical Bilinear Pooling for Fine-Grained Classification“. Journal of Computer-Aided Design & Computer Graphics 33, Nr. 2 (01.02.2021): 241–49. http://dx.doi.org/10.3724/sp.j.1089.2021.18399.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

7

Sanchez-Giraldo, Luis G., Md Nasir Uddin Laskar und Odelia Schwartz. „Normalization and pooling in hierarchical models of natural images“. Current Opinion in Neurobiology 55 (April 2019): 65–72. http://dx.doi.org/10.1016/j.conb.2019.01.008.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

8

Tan, Min, Fu Yuan, Jun Yu, Guijun Wang und Xiaoling Gu. „Fine-grained Image Classification via Multi-scale Selective Hierarchical Biquadratic Pooling“. ACM Transactions on Multimedia Computing, Communications, and Applications 18, Nr. 1s (28.02.2022): 1–23. http://dx.doi.org/10.1145/3492221.

Der volle Inhalt der Quelle

Annotation:

How to extract distinctive features greatly challenges the fine-grained image classification tasks. In previous models, bilinear pooling has been frequently adopted to address this problem. However, most bilinear pooling models neglect either intra or inter layer feature interaction. This insufficient interaction brings in the loss of discriminative information. In this article, we devise a novel fine-grained image classification approach named M ulti-scale S elective H ierarchical bi Q uadratic P ooling (MSHQP). The proposed biquadratic pooling simultaneously models intra and inter layer feature interactions and enhances part response by integrating multi-layer features. The subsequent coarse-to-fine multi-scale interaction structure captures the complementary information within features. Finally, the active interaction selection module adaptively learns the optimal interaction subset for a specific dataset. Consequently, we obtain a robust image representation with coarse-to-fine semantics. We conduct experiments on five benchmark datasets. The experimental results demonstrate that MSHQP achieves competitive or even match the state-of-the-art methods in terms of both accuracy and computational efficiency, with 89.0%, 94.9%, 93.4%, 90.4%, and 91.5% top-1 classification accuracy on CUB-200-2011, Stanford-Cars, FGVC-Aircraft, Stanford-Dog, and VegFru, respectively.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

9

Ko, Sung Moon, Sungjun Cho, Dae-Woong Jeong, Sehui Han, Moontae Lee und Honglak Lee. „Grouping Matrix Based Graph Pooling with Adaptive Number of Clusters“. Proceedings of the AAAI Conference on Artificial Intelligence 37, Nr. 7 (26.06.2023): 8334–42. http://dx.doi.org/10.1609/aaai.v37i7.26005.

Der volle Inhalt der Quelle

Annotation:

Graph pooling is a crucial operation for encoding hierarchical structures within graphs. Most existing graph pooling approaches formulate the problem as a node clustering task which effectively captures the graph topology. Conventional methods ask users to specify an appropriate number of clusters as a hyperparameter, then assuming that all input graphs share the same number of clusters. In inductive settings where the number of clusters could vary, however, the model should be able to represent this variation in its pooling layers in order to learn suitable clusters. Thus we propose GMPool, a novel differentiable graph pooling architecture that automatically determines the appropriate number of clusters based on the input data. The main intuition involves a grouping matrix defined as a quadratic form of the pooling operator, which induces use of binary classification probabilities of pairwise combinations of nodes. GMPool obtains the pooling operator by first computing the grouping matrix, then decomposing it. Extensive evaluations on molecular property prediction tasks demonstrate that our method outperforms conventional methods.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

10

Li, Keqin. „Hierarchical Pooling Strategy Optimization for Accelerating Asymptomatic COVID-19 Screening“. IEEE Open Journal of the Computer Society 1 (2020): 276–84. http://dx.doi.org/10.1109/ojcs.2020.3036581.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

11

Lian, Xuhang, Yanwei Pang, Jungong Han und Jing Pan. „Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation“. Pattern Recognition 110 (Februar 2021): 107622. http://dx.doi.org/10.1016/j.patcog.2020.107622.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

12

Nguyen, Xuan Son, Abdel-Illah Mouaddib und Thanh Phuong Nguyen. „Hierarchical Gaussian descriptor based on local pooling for action recognition“. Machine Vision and Applications 30, Nr. 2 (12.11.2018): 321–43. http://dx.doi.org/10.1007/s00138-018-0989-9.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

13

Li, Weifu, Paul Franzon, Sumon Dey und Joshua Schabel. „Hardware Implementation of Hierarchical Temporal Memory Algorithm“. ACM Journal on Emerging Technologies in Computing Systems 18, Nr. 1 (31.01.2022): 1–23. http://dx.doi.org/10.1145/3479430.

Der volle Inhalt der Quelle

Annotation:

Hierarchical temporal memory (HTM) is an un-supervised machine learning algorithm that can learn both spatial and temporal information of input. It has been successfully applied to multiple areas. In this paper, we propose a multi-level hierarchical ASIC implementation of HTM, referred to as processor core, to support both spatial and temporal pooling. To improve the unbalanced workload in HTM, the proposed design provides different mapping methods for the spatial and temporal pooling, respectively. In the proposed design, we implement a distributed memory system by assigning one dedicated memory bank to each level of hierarchy to improve the memory bandwidth utilization efficiency. Finally, the hot-spot operations are optimized using a series of customized units. Regarding scalability, we propose a ring-based network consisting of multiple processor cores to support a larger HTM network. To evaluate the performance of our proposed design, we map an HTM network that includes 2,048 columns and 65,536 cells on both the proposed design and NVIDIA Tesla K40c GPU using the KTH database as input. The latency and power of the proposed design is 6.04 ms and 4.1 W using GP 65 nm technology. Compared to the equivalent GPU implementation, the latency and power is improved 12.45× and 57.32×, respectively.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

14

ALSAIDI, RAMADHAN ABDO MUSLEH, HONG LI, YANTAO WEI, ROKAN KHAJI und YUAN YAN TANG. „HIERARCHICAL SPARSE METHOD WITH APPLICATIONS IN VISION AND SPEECH RECOGNITION“. International Journal of Wavelets, Multiresolution and Information Processing 11, Nr. 02 (März 2013): 1350016. http://dx.doi.org/10.1142/s0219691313500161.

Der volle Inhalt der Quelle

Annotation:

A new approach for feature extraction using neural response has been developed in this paper through combining the hierarchical architectures with the sparse coding technique. As far as proposed layered model, at each layer of hierarchy, it concerned two components that were used are sparse coding and pooling operation. While the sparse coding was used to solve increasingly complex sparse feature representations, the pooling operation by comparing sparse outputs was used to measure the match between a stored prototype and the input sub-image. It is recommended that value of the best matching should be kept and discarding the others. The proposed model is implemented and tested taking into account two ranges of recognition tasks i.e. image recognition and speech recognition (on isolated word vocabulary). Experimental results with various parameters demonstrate that proposed scheme leads to extract more efficient features than other methods.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

15

Wang, Yu, Liang Hu, Yang Wu und Wanfu Gao. „Graph Multihead Attention Pooling with Self-Supervised Learning“. Entropy 24, Nr. 12 (29.11.2022): 1745. http://dx.doi.org/10.3390/e24121745.

Der volle Inhalt der Quelle

Annotation:

Graph neural networks (GNNs), which work with graph-structured data, have attracted considerable attention and achieved promising performance on graph-related tasks. While the majority of existing GNN methods focus on the convolutional operation for encoding the node representations, the graph pooling operation, which maps the set of nodes into a coarsened graph, is crucial for graph-level tasks. We argue that a well-defined graph pooling operation should avoid the information loss of the local node features and global graph structure. In this paper, we propose a hierarchical graph pooling method based on the multihead attention mechanism, namely GMAPS, which compresses both node features and graph structure into the coarsened graph. Specifically, a multihead attention mechanism is adopted to arrange nodes into a coarsened graph based on their features and structural dependencies between nodes. In addition, to enhance the expressiveness of the cluster representations, a self-supervised mechanism is introduced to maximize the mutual information between the cluster representations and the global representation of the hierarchical graph. Our experimental results show that the proposed GMAPS obtains significant and consistent performance improvements compared with state-of-the-art baselines on six benchmarks from the biological and social domains of graph classification and reconstruction tasks.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

16

Tang, Haoteng, Guixiang Ma, Lifang He, Heng Huang und Liang Zhan. „CommPOOL: An interpretable graph pooling framework for hierarchical graph representation learning“. Neural Networks 143 (November 2021): 669–77. http://dx.doi.org/10.1016/j.neunet.2021.07.028.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

17

Gelman, Andrew, und Iain Pardoe. „Bayesian Measures of Explained Variance and Pooling in Multilevel (Hierarchical) Models“. Technometrics 48, Nr. 2 (Mai 2006): 241–51. http://dx.doi.org/10.1198/004017005000000517.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

18

Tan, Min, Guijun Wang, Jian Zhou, Zhiyou Peng und Meilian Zheng. „Fine-Grained Classification via Hierarchical Bilinear Pooling With Aggregated Slack Mask“. IEEE Access 7 (2019): 117944–53. http://dx.doi.org/10.1109/access.2019.2936118.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

19

Warasi, Md S., Joshua M. Tebbs, Christopher S. McMahan und Christopher R. Bilder. „Estimating the prevalence of multiple diseases from two-stage hierarchical pooling“. Statistics in Medicine 35, Nr. 21 (18.04.2016): 3851–64. http://dx.doi.org/10.1002/sim.6964.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

20

Wersing, Heiko, und Edgar Körner. „Learning Optimized Features for Hierarchical Models of Invariant Object Recognition“. Neural Computation 15, Nr. 7 (01.07.2003): 1559–88. http://dx.doi.org/10.1162/089976603321891800.

Der volle Inhalt der Quelle

Annotation:

There is an ongoing debate over the capabilities of hierarchical neural feedforward architectures for performing real-world invariant object recognition. Although a variety of hierarchical models exists, appropriate supervised and unsupervised learning methods are still an issue of intense research. We propose a feedforward model for recognition that shares components like weight sharing, pooling stages, and competitive nonlinearities with earlier approaches but focuses on new methods for learning optimal feature-detecting cells in intermediate stages of the hierarchical network. We show that principles of sparse coding, which were previously mostly applied to the initial feature detection stages, can also be employed to obtain optimized intermediate complex features. We suggest a new approach to optimize the learning of sparse features under the constraints of a weight-sharing or convolutional architecture that uses pooling operations to achieve gradual invariance in the feature hierarchy. The approach explicitly enforces symmetry constraints like translation invariance on the feature set. This leads to a dimension reduction in the search space of optimal features and allows determining more efficiently the basis representatives, which achieve a sparse decomposition of the input. We analyze the quality of the learned feature representation by investigating the recognition performance of the resulting hierarchical network on object and face databases. We show that a hierarchy with features learned on a single object data set can also be applied to face recognition without parameter changes and is competitive with other recent machine learning recognition approaches. To investigate the effect of the interplay between sparse coding and processing nonlinearities, we also consider alternative feedforward pooling nonlinearities such as presynaptic maximum selection and sum-of-squares integration. The comparison shows that a combination of strong competitive nonlinearities with sparse coding offers the best recognition performance in the difficult scenario of segmentation-free recognition in cluttered surround. We demonstrate that for both learning and recognition, a precise segmentation of the objects is not necessary.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

21

Liang, Qi, Qiang Li, Lihu Zhang, Haixiao Mi, Weizhi Nie und Xuanya Li. „MHFP: Multi-view based hierarchical fusion pooling method for 3D shape recognition“. Pattern Recognition Letters 150 (Oktober 2021): 214–20. http://dx.doi.org/10.1016/j.patrec.2021.07.010.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

22

Wang, Hongbin, Minghui Hou, Fan Li und Yafei Zhang. „Chinese Implicit Sentiment Analysis Based on Hierarchical Knowledge Enhancement and Multi-Pooling“. IEEE Access 8 (2020): 126051–65. http://dx.doi.org/10.1109/access.2020.3008874.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

23

Anders, R., Z. Oravecz und F. X. Alario. „Improved information pooling for hierarchical cognitive models through multiple and covaried regression“. Behavior Research Methods 50, Nr. 3 (11.07.2017): 989–1010. http://dx.doi.org/10.3758/s13428-017-0921-7.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

24

Odani, Motoi, Satoru Fukimbara und Tosiya Sato. „A Bayesian meta-analytic approach for safety signal detection in randomized clinical trials“. Clinical Trials 14, Nr. 2 (06.01.2017): 192–200. http://dx.doi.org/10.1177/1740774516683920.

Der volle Inhalt der Quelle

Annotation:

Background/Aim: Meta-analyses are frequently performed on adverse event data and are primarily used for improving statistical power to detect safety signals. However, in the evaluation of drug safety for New Drug Applications, simple pooling of adverse event data from multiple clinical trials is still commonly used. We sought to propose a new Bayesian hierarchical meta-analytic approach based on consideration of a hierarchical structure of reported individual adverse event data from multiple randomized clinical trials. Methods: To develop our meta-analysis model, we extended an existing three-stage Bayesian hierarchical model by including an additional stage of the clinical trial level in the hierarchical model; this generated a four-stage Bayesian hierarchical model. We applied the proposed Bayesian meta-analysis models to published adverse event data from three premarketing randomized clinical trials of tadalafil and to a simulation study motivated by the case example to evaluate the characteristics of three alternative models. Results: Comparison of the results from the Bayesian meta-analysis model with those from Fisher’s exact test after simple pooling showed that 6 out of 10 adverse events were the same within a top 10 ranking of individual adverse events with regard to association with treatment. However, more individual adverse events were detected in the Bayesian meta-analysis model than in Fisher’s exact test under the body system “Musculoskeletal and connective tissue disorders.” Moreover, comparison of the overall trend of estimates between the Bayesian model and the standard approach (odds ratios after simple pooling methods) revealed that the posterior median odds ratios for the Bayesian model for most adverse events shrank toward values for no association. Based on the simulation results, the Bayesian meta-analysis model could balance the false detection rate and power to a better extent than Fisher’s exact test. For example, when the threshold value of the posterior probability for signal detection was set to 0.8, the false detection rate was 41% and power was 88% in the Bayesian meta-analysis model, whereas the false detection rate was 56% and power was 86% in Fisher’s exact test. Limitations: Adverse events under the same body system were not necessarily positively related when we used “system organ class” and “preferred term” in the Medical Dictionary for Regulatory Activities as a hierarchical structure of adverse events. For the Bayesian meta-analysis models to be effective, the validity of the hierarchical structure of adverse events and the grouping of adverse events are critical. Conclusion: Our proposed meta-analysis models considered trial effects to avoid confounding by trial and borrowed strength from both within and across body systems to obtain reasonable and stable estimates of an effect measure by considering a hierarchical structure of adverse events.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

25

Liao, Dongliang, Jin Xu, Gongfu Li und Yiru Wang. „Hierarchical Coherence Modeling for Document Quality Assessment“. Proceedings of the AAAI Conference on Artificial Intelligence 35, Nr. 15 (18.05.2021): 13353–61. http://dx.doi.org/10.1609/aaai.v35i15.17576.

Der volle Inhalt der Quelle

Annotation:

Text coherence plays a key role in document quality assessment. Most existing text coherence methods only focus on similarity of adjacent sentences. However, local coherence exists in sentences with broader contexts and diverse rhetoric relations, rather than just adjacent sentences similarity. Besides, the highlevel text coherence is also an important aspect of document quality. To this end, we propose a hierarchical coherence model for document quality assessment. In our model, we implement a local attention mechanism to capture the location semantics, bilinear tensor layer for measure coherence and max-coherence pooling for acquiring high-level coherence. We evaluate the proposed method on two realistic tasks: news quality judgement and automated essay scoring. Experimental results demonstrate the validity and superiority of our work.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

26

Ji, Xiujuan, Lei Liu und Jingwen Zhu. „Code Clone Detection with Hierarchical Attentive Graph Embedding“. International Journal of Software Engineering and Knowledge Engineering 31, Nr. 06 (Juni 2021): 837–61. http://dx.doi.org/10.1142/s021819402150025x.

Der volle Inhalt der Quelle

Annotation:

Code clone serves as a typical programming manner that reuses the existing code to solve similar programming problems, which greatly facilitates software development but recurs program bugs and maintenance costs. Recently, deep learning-based detection approaches gradually present their effectiveness on feature representation and detection performance. Among them, deep learning approaches based on abstract syntax tree (AST) construct models relying on the node embedding technique. In AST, the semantic of nodes is obviously hierarchical, and the importance of nodes is quite different to determine whether the two code fragments are cloned or not. However, some approaches do not fully consider the hierarchical structure information of source code. Some approaches ignore the different importance of nodes when generating the features of source code. Thirdly, when the tree is very large and deep, many approaches are vulnerable to the gradient vanishing problem during training. In order to properly address these challenges, we propose a hierarchical attentive graph neural network embedding model-HAG for the code clone detection. Firstly, the attention mechanism is applied on nodes in AST to distinguish the importance of different nodes during the model training. In addition, the HAG adopts graph convolutional network (GCN) to propagate the code message on AST graph and then exploits a hierarchical differential pooling GCN to sufficiently capture the code semantics at different structure level. To evaluate the effectiveness of HAG, we conducted extensive experiments on public clone dataset and compared it with seven state-of-the-art clone detection models. The experimental results demonstrate that the HAG achieves superior detection performance compared with baseline models. Especially, in the detection of moderately Type-3 or Type-4 clones, the HAG particularly outperforms baselines, indicating the strong detection capability of HAG for semantic clones. Apart from that, the impacts of the hierarchical pooling, attention mechanism and critical model parameters are systematically discussed.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

27

Pham, Hai Van, Dat Hoang Thanh und Philip Moore. „Hierarchical Pooling in Graph Neural Networks to Enhance Classification Performance in Large Datasets“. Sensors 21, Nr. 18 (10.09.2021): 6070. http://dx.doi.org/10.3390/s21186070.

Der volle Inhalt der Quelle

Annotation:

Deep learning methods predicated on convolutional neural networks and graph neural networks have enabled significant improvement in node classification and prediction when applied to graph representation with learning node embedding to effectively represent the hierarchical properties of graphs. An interesting approach (DiffPool) utilises a differentiable graph pooling technique which learns ‘differentiable soft cluster assignment’ for nodes at each layer of a deep graph neural network with nodes mapped on sets of clusters. However, effective control of the learning process is difficult given the inherent complexity in an ‘end-to-end’ model with the potential for a large number parameters (including the potential for redundant parameters). In this paper, we propose an approach termed FPool, which is a development of the basic method adopted in DiffPool (where pooling is applied directly to node representations). Techniques designed to enhance data classification have been created and evaluated using a number of popular and publicly available sensor datasets. Experimental results for FPool demonstrate improved classification and prediction performance when compared to alternative methods considered. Moreover, FPool shows a significant reduction in the training time over the basic DiffPool framework.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

28

Xu, Ziang. „Grasp Detection Based on Light-Weight Hierarchical Fusion Convolutional Neural Network“. Journal of Physics: Conference Series 2083, Nr. 4 (01.11.2021): 042030. http://dx.doi.org/10.1088/1742-6596/2083/4/042030.

Der volle Inhalt der Quelle

Annotation:

Abstract This paper presents a light-weight Hierarchical Fusion Convolutional Neural Network (HF-CNN) which can be used for grasping detection. The network mainly employs residual structures, atrous spatial pyramid pooling (ASPP) and coding-decoding based feature fusion. Compared with the usual grasping detection, the network in this paper greatly improves the robustness and generalizability on detecting tasks by extensively extracting feature information of the images. In our test with the Cornell University dataset, we achieve 85% accuracy when detecting the unknown objects.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

29

Wang, Di, Ronghao Yang, Hanhu Liu, Haiqing He, Junxiang Tan, Shaoda Li, Yichun Qiao, Kangqi Tang und Xiao Wang. „HFENet: Hierarchical Feature Extraction Network for Accurate Landcover Classification“. Remote Sensing 14, Nr. 17 (28.08.2022): 4244. http://dx.doi.org/10.3390/rs14174244.

Der volle Inhalt der Quelle

Annotation:

Landcover classification is an important application in remote sensing, but it is always a challenge to distinguish different features with similar characteristics or large-scale differences. Some deep learning networks, such as UperNet, PSPNet, and DANet, use pyramid pooling and attention mechanisms to improve their abilities in multi-scale features extraction. However, due to the neglect of low-level features contained in the underlying network and the information differences between feature maps, it is difficult to identify small-scale objects. Thus, we propose a novel image segmentation network, named HFENet, for mining multi-level semantic information. Like the UperNet, HFENet adopts a top-down horizontal connection architecture while includes two improved modules, the HFE and the MFF. According to the characteristics of different levels of semantic information, HFE module reconstructs the feature extraction part by introducing an attention mechanism and pyramid pooling module to fully mine semantic information. With the help of a channel attention mechanism, MFF module up-samples and re-weights the feature maps to fuse them and enhance the expression ability of multi-scale features. Ablation studies and comparative experiments between HFENet and seven state-of-the-art models (U-Net, DeepLabv3+, PSPNet, FCN, UperNet, DANet and SegNet) are conducted with a self-labeled GF-2 remote sensing image dataset (MZData) and two open datasets landcover.ai and WHU building dataset. The results show that HFENet on three datasets with six evaluation metrics (mIoU, FWIoU, PA, mP, mRecall and mF1) are better than the other models and the mIoU is improved 7.41–10.60% on MZData, 1.17–11.57% on WHU building dataset and 0.93–4.31% on landcover.ai. HFENet can perform better in the task of refining the semantic segmentation of remote sensing images.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

30

Lai, Jun-Yao, Shi-Lin Wang, Alan Wee-Chung Liew und Xing-Jian Shi. „Visual speaker identification and authentication by joint spatiotemporal sparse coding and hierarchical pooling“. Information Sciences 373 (Dezember 2016): 219–32. http://dx.doi.org/10.1016/j.ins.2016.09.015.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

31

Nisar, Muhammad Adeel, Kimiaki Shirahama, Frédéric Li, Xinyu Huang und Marcin Grzegorzek. „Rank Pooling Approach for Wearable Sensor-Based ADLs Recognition“. Sensors 20, Nr. 12 (19.06.2020): 3463. http://dx.doi.org/10.3390/s20123463.

Der volle Inhalt der Quelle

Annotation:

This paper addresses wearable-based recognition of Activities of Daily Living (ADLs) which are composed of several repetitive and concurrent short movements having temporal dependencies. It is improbable to directly use sensor data to recognize these long-term composite activities because two examples (data sequences) of the same ADL result in largely diverse sensory data. However, they may be similar in terms of more semantic and meaningful short-term atomic actions. Therefore, we propose a two-level hierarchical model for recognition of ADLs. Firstly, atomic activities are detected and their probabilistic scores are generated at the lower level. Secondly, we deal with the temporal transitions of atomic activities using a temporal pooling method, rank pooling. This enables us to encode the ordering of probabilistic scores for atomic activities at the higher level of our model. Rank pooling leads to a 5–13% improvement in results as compared to the other popularly used techniques. We also produce a large dataset of 61 atomic and 7 composite activities for our experiments.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

32

Ji, Xiaoyu, Wanyang Hu und Yanyan Liang. „Hierarchical and Bidirectional Joint Multi-Task Classifiers for Natural Language Understanding“. Mathematics 11, Nr. 24 (07.12.2023): 4895. http://dx.doi.org/10.3390/math11244895.

Der volle Inhalt der Quelle

Annotation:

The MASSIVE dataset is a spoken-language comprehension resource package for slot filling, intent classification, and virtual assistant evaluation tasks. It contains multi-language utterances from human beings communicating with a virtual assistant. In this paper, we exploited the relationship between intent classification and slot filling to improve the exact match accuracy by proposing five models with hierarchical and bidirectional architectures. There are two variants for hierarchical architectures and three variants for bidirectional architectures. These are the hierarchical concatenation model, the hierarchical attention-based model, the bidirectional max-pooling model, the bidirectional LSTM model, and the bidirectional attention-based model. The results of our models showed a significant improvement in the averaged exact match accuracy. The hierarchical attention-based model improved the accuracy by 1.01 points for the full training dataset. As for the zero-shot setup, we observed that the exact match accuracy increased from 53.43 to 53.91. In this study, we observed that, for multi-task problems, utilizing the relevance between different tasks can help in improving the model’s overall performance.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

33

Wu, Hanbo, Xin Ma und Yibin Li. „Hierarchical dynamic depth projected difference images–based action recognition in videos with convolutional neural networks“. International Journal of Advanced Robotic Systems 16, Nr. 1 (01.01.2019): 172988141882509. http://dx.doi.org/10.1177/1729881418825093.

Der volle Inhalt der Quelle

Annotation:

Temporal information plays a significant role in video-based human action recognition. How to effectively extract the spatial–temporal characteristics of actions in videos has always been a challenging problem. Most existing methods acquire spatial and temporal cues in videos individually. In this article, we propose a new effective representation for depth video sequences, called hierarchical dynamic depth projected difference images that can aggregate the action spatial and temporal information simultaneously at different temporal scales. We firstly project depth video sequences onto three orthogonal Cartesian views to capture the 3D shape and motion information of human actions. Hierarchical dynamic depth projected difference images are constructed with the rank pooling in each projected view to hierarchically encode the spatial–temporal motion dynamics in depth videos. Convolutional neural networks can automatically learn discriminative features from images and have been extended to video classification because of their superior performance. To verify the effectiveness of hierarchical dynamic depth projected difference images representation, we construct a hierarchical dynamic depth projected difference images–based action recognition framework where hierarchical dynamic depth projected difference images in three views are fed into three identical pretrained convolutional neural networks independently for finely retuning. We design three classification schemes in the framework and different schemes utilize different convolutional neural network layers to compare their effects on action recognition. Three views are combined to describe the actions more comprehensively in each classification scheme. The proposed framework is evaluated on three challenging public human action data sets. Experiments indicate that our method has better performance and can provide discriminative spatial–temporal information for human action recognition in depth videos.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

34

Syed, Abbas Shah, Daniel Sierra-Sosa, Anup Kumar und Adel Elmaghraby. „A Hierarchical Approach to Activity Recognition and Fall Detection Using Wavelets and Adaptive Pooling“. Sensors 21, Nr. 19 (07.10.2021): 6653. http://dx.doi.org/10.3390/s21196653.

Der volle Inhalt der Quelle

Annotation:

Human activity recognition has been a key study topic in the development of cyber physical systems and assisted living applications. In particular, inertial sensor based systems have become increasingly popular because they do not restrict users’ movement and are also relatively simple to implement compared to other approaches. In this paper, we present a hierarchical classification framework based on wavelets and adaptive pooling for activity recognition and fall detection predicting fall direction and severity. To accomplish this, windowed segments were extracted from each recording of inertial measurements from the SisFall dataset. A combination of wavelet based feature extraction and adaptive pooling was used before a classification framework was applied to determine the output class. Furthermore, tests were performed to determine the best observation window size and the sensor modality to use. Based on the experiments the best window size was found to be 3 s and the best sensor modality was found to be a combination of accelerometer and gyroscope measurements. These were used to perform activity recognition and fall detection with a resulting weighted F1 score of 94.67%. This framework is novel in terms of the approach to the human activity recognition and fall detection problem as it provides a scheme that is computationally less intensive while providing promising results and therefore can contribute to edge deployment of such systems.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

35

Wang, Dongfang, Jun Wang, Zhuang Ren und Wenrui Li. „DHBP: A dual-stream hierarchical bilinear pooling model for plant disease multi-task classification“. Computers and Electronics in Agriculture 195 (April 2022): 106788. http://dx.doi.org/10.1016/j.compag.2022.106788.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

36

Dong, Zehao, Heming Zhang, Yixin Chen, Philip R. O. Payne und Fuhai Li. „Interpreting the Mechanism of Synergism for Drug Combinations Using Attention-Based Hierarchical Graph Pooling“. Cancers 15, Nr. 17 (22.08.2023): 4210. http://dx.doi.org/10.3390/cancers15174210.

Der volle Inhalt der Quelle

Annotation:

Synergistic drug combinations provide huge potentials to enhance therapeutic efficacy and to reduce adverse reactions. However, effective and synergistic drug combination prediction remains an open question because of the unknown causal disease signaling pathways. Though various deep learning (AI) models have been proposed to quantitatively predict the synergism of drug combinations, the major limitation of existing deep learning methods is that they are inherently not interpretable, which makes the conclusions of AI models untransparent to human experts, henceforth limiting the robustness of the model conclusion and the implementation ability of these models in real-world human–AI healthcare. In this paper, we develop an interpretable graph neural network (GNN) that reveals the underlying essential therapeutic targets and the mechanism of the synergy (MoS) by mining the sub-molecular network of great importance. The key point of the interpretable GNN prediction model is a novel graph pooling layer, a self-attention-based node and edge pool (henceforth SANEpool), that can compute the attention score (importance) of genes and connections based on the genomic features and topology. As such, the proposed GNN model provides a systematic way to predict and interpret the drug combination synergism based on the detected crucial sub-molecular network. Experiments on various well-adopted drug-synergy-prediction datasets demonstrate that (1) the SANEpool model has superior predictive ability to generate accurate synergy score prediction, and (2) the sub-molecular networks detected by the SANEpool are self-explainable and salient for identifying synergistic drug combinations.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

37

Rahill-Marier, Bianca, Naresh Devineni und Upmanu Lall. „Technical note: Modeling spatial fields of extreme precipitation – a hierarchical Bayesian approach“. Hydrology and Earth System Sciences 26, Nr. 21 (11.11.2022): 5685–95. http://dx.doi.org/10.5194/hess-26-5685-2022.

Der volle Inhalt der Quelle

Annotation:

Abstract. We introduce a hierarchical Bayesian model for the spatial distribution of rainfall corresponding to an extreme event of a specified duration that could be used with regional hydrologic models to perform a regional hydrologic risk analysis. An extreme event is defined if any gaging site in the watershed experiences an annual maximum rainfall event and the spatial field of rainfall at all sites corresponding to that occurrence is modeled. Applications to data from New York City demonstrate the effectiveness of the model for providing spatial scenarios that could be used for simulating loadings into the urban drainage system. Insights as to the homogeneity in spatial rainfall and its implications for modeling are provided by considering partial pooling in the hierarchical Bayesian framework.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

38

Liu, Qiuhua, Min Fu, Hao Jiang und Xinqi Gong. „Densely Dilated Spatial Pooling Convolutional Network Using Benign Loss Functions for Imbalanced Volumetric Prostate Segmentation“. Current Bioinformatics 15, Nr. 7 (15.12.2020): 788–99. http://dx.doi.org/10.2174/1574893615666200127124145.

Der volle Inhalt der Quelle

Annotation:

Background: The high incidence rate of prostate disease poses a requirement of accurate early detection. Magnetic Resonance Imaging (MRI) is one of the main imaging methods used for prostate cancer detection so far, but it has problems of imbalance and variation in appearance, therefore, automated prostate segmentation is still challenging. Objective: Aiming to accurately segment the prostate from MRI, the focus was on designing a unique network with benign loss functions. Methods: A novel Densely Dilated Spatial Pooling Convolutional Network (DDSP ConNet) in an encoderdecoder structure, with a unique DDSP block was proposed. By densely combining dilated convolution and global pooling layers, the DDSP block supplies coarse segmentation results and preserves hierarchical contextual information. Meanwhile, the DSC and Jaccard loss were adopted to train the DDSP ConNet. And it was proved theoretically that they have benign properties, including symmetry, continuity, and differentiability on the parameters of the network. Results: Extensive experiments have been conducted to corroborate the effectiveness of the DDSP ConNet with DSC and Jaccard loss on the MICCAI PROMISE12 challenge dataset. In the test dataset, the DDSP ConNet achieved a score of 85.78. Conclusion: In the conducted experiments, DDSP network with DSC and Jaccard loss outperformed most of the other competitors on the PROMISE12 dataset. Therefore, it has a better ability to extract hierarchical features and solve the imbalanced medical image problem.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

39

Viegas, Franklin Robert. „Handwritten Digit Recognition of MNIST dataset using Deep Learning Convolutional Neural Network (CNN)“. INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, Nr. 05 (16.05.2024): 1–5. http://dx.doi.org/10.55041/ijsrem34043.

Der volle Inhalt der Quelle

Annotation:

With applications ranging from postal services to digitized document processing, handwritten digit identification is a key problem in the fields of machine learning and computer vision. By utilizing their capacity to automatically extract hierarchical characteristics from unprocessed pixel data, Convolutional Neural Networks (CNNs) have become effective instruments for addressing this job. This study presents a thorough investigation of a CNN-based method that uses the MNIST dataset to recognize handwritten numbers. We explore the design, implementation, and performance assessment of the CNN model, demonstrating its ability to achieve high accuracy on tasks involving the recognition of numbers. We also go over the significance of our results for the larger picture of image categorization and suggest directions for further investigation and advancement. Key Words: CNN, MNIST, Convolutional Layer, Pooling layer, Max Pooling, Neural Networks, Preprocessing, Dropout Layer, Activation layer, Rectified Linear Unit (ReLU), Epochs, MNIST dataset

APA, Harvard, Vancouver, ISO und andere Zitierweisen

40

Aluvalu, RajaniKanth, Vanraj Kamliya und Lakshmi Muddana. „HASBE access control model with Secure Key Distribution and Efficient Domain Hierarchy for cloud computing“. International Journal of Electrical and Computer Engineering (IJECE) 6, Nr. 2 (01.04.2016): 770. http://dx.doi.org/10.11591/ijece.v6i2.8919.

Der volle Inhalt der Quelle

Annotation:

Cloud computing refers to the application and service that run on a distributed system using virtualized resources and access by common internet protocol and networking standard. Cloud computing virtualizes system by pooling and sharing resources. System and resources can be monitored from central infrastructure as needed. It requires high security because now day’s companies are placing more essential and huge amount of data on cloud. Hence traditional access control models are not sufficient for cloud computing applications. So encryption based on Attribute (“ABE”-“Attribute based encryption”) has been offered for access control of subcontracted data in cloud computing with complex access control policies. Traditional HASBE provides Flexibility, scalability and fine-grained access control but does not support hierarchical domain structure. In this paper, we had enhanced “Hierarchical attribute-set-based encryption” (“HASBE”) access control with a hierarchical assembly of users, with flexible domain Hierarchy structure and Secure key distribution with predefined policy

APA, Harvard, Vancouver, ISO und andere Zitierweisen

41

Aluvalu, RajaniKanth, Vanraj Kamliya und Lakshmi Muddana. „HASBE access control model with Secure Key Distribution and Efficient Domain Hierarchy for cloud computing“. International Journal of Electrical and Computer Engineering (IJECE) 6, Nr. 2 (01.04.2016): 770. http://dx.doi.org/10.11591/ijece.v6i2.pp770-777.

Der volle Inhalt der Quelle

Annotation:

Cloud computing refers to the application and service that run on a distributed system using virtualized resources and access by common internet protocol and networking standard. Cloud computing virtualizes system by pooling and sharing resources. System and resources can be monitored from central infrastructure as needed. It requires high security because now day’s companies are placing more essential and huge amount of data on cloud. Hence traditional access control models are not sufficient for cloud computing applications. So encryption based on Attribute (“ABE”-“Attribute based encryption”) has been offered for access control of subcontracted data in cloud computing with complex access control policies. Traditional HASBE provides Flexibility, scalability and fine-grained access control but does not support hierarchical domain structure. In this paper, we had enhanced “Hierarchical attribute-set-based encryption” (“HASBE”) access control with a hierarchical assembly of users, with flexible domain Hierarchy structure and Secure key distribution with predefined policy

APA, Harvard, Vancouver, ISO und andere Zitierweisen

42

Németová, Zuzana, Silvia Kohnová und Romana Marková. „Comparison of two approaches for an estimation of the mean annual flood at ungauged sites in Slovakia“. Pollack Periodica 15, Nr. 2 (August 2020): 130–41. http://dx.doi.org/10.1556/606.2020.15.2.12.

Der volle Inhalt der Quelle

Annotation:

AbstractRegional flood frequency analysis is considered to be an important and popular method for estimating different hydrological variables at ungauged sites. The estimation of the index flood is the essential problem when this method is applied. The objective of the study is a comparison of the estimation of the mean annual flood (or index flood) by using two approaches based on the ‘so-called’ index flood method and top-kriging. The concept behind these methods permits estimating the mean annual flood at ungauged locations using information taken from gauged sites located within the same homogeneous pooling groups. The study area comprises 104 gauging stations on the whole territory of Slovakia. The observation period of the annual maximum discharges of the selected stations was from 1961-2010. The identification of the homogeneous pooling group was performed using a non-hierarchical k-means clustering algorithm. The optimal number of clusters is determined by the Silhouette method. As a result, eight homogeneous pooling group clusters were identified. Finally, the results of the estimated mean annual floods using the index flood method and top-kriging were compared with the observed data. Top-kriging provided better results than the classical index flood method for estimating the mean annual flood at ungauged sites.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

43

Johnson, Samuel D. N., und Sean P. Cox. „Evaluating the role of data quality when sharing information in hierarchical multistock assessment models, with an application to Dover sole“. Canadian Journal of Fisheries and Aquatic Sciences 76, Nr. 10 (Oktober 2019): 1819–35. http://dx.doi.org/10.1139/cjfas-2018-0048.

Der volle Inhalt der Quelle

Annotation:

An emerging approach to data-limited fisheries stock assessment uses hierarchical multistock assessment models to group stocks together, sharing information from data-rich to data-poor stocks. In this paper, we simulate data-rich and data-poor fishery and survey data scenarios for a complex of Dover sole (Microstomus pacificus) stocks. Simulated data for individual stocks were used to compare estimation performance for single-stock and hierarchical multistock versions of a Schaefer production model. The single-stock and best-performing multistock models were then used in stock assessments for the real Dover sole data. Multistock models often had lower estimation errors than single-stock models when assessment data had low statistical power. Relative errors for productivity and relative biomass parameters were lower for multistock assessment model configurations. In addition, multistock models that estimated hierarchical priors for survey catchability performed the best under data-poor scenarios. We conclude that hierarchical multistock assessment models are useful for data-limited stocks and could provide a more flexible alternative to data pooling and catch-only methods; however, these models are subject to nonlinear side effects of parameter shrinkage. Therefore, we recommend testing hierarchical multistock models in closed-loop simulations before application to real fishery management systems.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

44

Guo, Kan, Yongli Hu, Yanfeng Sun, Sean Qian, Junbin Gao und Baocai Yin. „Hierarchical Graph Convolution Network for Traffic Forecasting“. Proceedings of the AAAI Conference on Artificial Intelligence 35, Nr. 1 (18.05.2021): 151–59. http://dx.doi.org/10.1609/aaai.v35i1.16088.

Der volle Inhalt der Quelle

Annotation:

Traffic forecasting is attracting considerable interest due to its widespread application in intelligent transportation systems. Given the complex and dynamic traffic data, many methods focus on how to establish a spatial-temporal model to express the non-stationary traffic patterns. Recently, the latest Graph Convolution Network (GCN) has been introduced to learn spatial features while the time neural networks are used to learn temporal features. These GCN based methods obtain state-of-the-art performance. However, the current GCN based methods ignore the natural hierarchical structure of traffic systems which is composed of the micro layers of road networks and the macro layers of region networks, in which the nodes are obtained through pooling method and could include some hot traffic regions such as downtown and CBD etc., while the current GCN is only applied on the micro graph of road networks. In this paper, we propose a novel Hierarchical Graph Convolution Networks (HGCN) for traffic forecasting by operating on both the micro and macro traffic graphs. The proposed method is evaluated on two complex city traffic speed datasets. Compared to the latest GCN based methods like Graph WaveNet, the proposed HGCN gets higher traffic forecasting precision with lower computational cost.The website of the code is https://github.com/guokan987/HGCN.git.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

45

Zhou, Wujie, Chang Liu, Jingsheng Lei, Lu Yu und Ting Luo. „HFNet: Hierarchical feedback network with multilevel atrous spatial pyramid pooling for RGB-D saliency detection“. Neurocomputing 490 (Juni 2022): 347–57. http://dx.doi.org/10.1016/j.neucom.2021.11.100.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

46

Han, Hong, Qiqiang Han, Xiaojun Li und Jianyin Gu. „Hierarchical spatial pyramid max pooling based on SIFT features and sparse coding for image classification“. IET Computer Vision 7, Nr. 2 (April 2013): 144–50. http://dx.doi.org/10.1049/iet-cvi.2012.0145.

Der volle Inhalt der Quelle

APA, Harvard, Vancouver, ISO und andere Zitierweisen

47

Wang, Mengxi, Qingwang Liu, Liyong Fu, Guangxing Wang und Xiongqing Zhang. „Airborne LIDAR-Derived Aboveground Biomass Estimates Using a Hierarchical Bayesian Approach“. Remote Sensing 11, Nr. 9 (03.05.2019): 1050. http://dx.doi.org/10.3390/rs11091050.

Der volle Inhalt der Quelle

Annotation:

Conventional ground survey data are very accurate, but expensive. Airborne lidar data can reduce the costs and effort required to conduct large-scale forest surveys. It is critical to improve biomass estimation and evaluate carbon stock when we use lidar data. Bayesian methods integrate prior information about unknown parameters, reduce the parameter estimation uncertainty, and improve model performance. This study focused on predicting the independent tree aboveground biomass (AGB) with a hierarchical Bayesian model using airborne LIDAR data and comparing the hierarchical Bayesian model with classical methods (nonlinear mixed effect model, NLME). Firstly, we chose the best diameter at breast height (DBH) model from several widely used models through a hierarchical Bayesian method. Secondly, we used the DBH predictions together with the tree height (LH) and canopy projection area (CPA) derived by airborne lidar as independent variables to develop the AGB model through a hierarchical Bayesian method with parameter priors from the NLME method. We then compared the hierarchical Bayesian method with the NLME method. The results showed that the two methods performed similarly when pooling the data, while for small sample sizes, the Bayesian method was much better than the classical method. The results of this study imply that the Bayesian method has the potential to improve the estimations of both DBH and AGB using LIDAR data, which reduces costs compared with conventional measurements.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

48

Hou, Peijie, Joshua M. Tebbs, Dewei Wang, Christopher S. McMahan und Christopher R. Bilder. „Array testing for multiplex assays“. Biostatistics 21, Nr. 3 (26.10.2018): 417–31. http://dx.doi.org/10.1093/biostatistics/kxy058.

Der volle Inhalt der Quelle

Annotation:

Summary Group testing involves pooling individual specimens (e.g., blood, urine, swabs, etc.) and testing the pools for the presence of disease. When the proportion of diseased individuals is small, group testing can greatly reduce the number of tests needed to screen a population. Statistical research in group testing has traditionally focused on applications for a single disease. However, blood service organizations and large-scale disease surveillance programs are increasingly moving towards the use of multiplex assays, which measure multiple disease biomarkers at once. Tebbs and others (2013, Two-stage hierarchical group testing for multiple infections with application to the Infertility Prevention Project. Biometrics69, 1064–1073) and Hou and others (2017, Hierarchical group testing for multiple infections. Biometrics73, 656–665) were the first to examine hierarchical group testing case identification procedures for multiple diseases. In this article, we propose new non-hierarchical procedures which utilize two-dimensional arrays. We derive closed-form expressions for the expected number of tests per individual and classification accuracy probabilities and show that array testing can be more efficient than hierarchical procedures when screening individuals for multiple diseases at once. We illustrate the potential of using array testing in the detection of chlamydia and gonorrhea for a statewide screening program in Iowa. Finally, we describe an R/Shiny application that will help practitioners identify the best multiple-disease case identification algorithm.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

49

Zhao, Xueru, Furong Chang, Hehe Lv, Guobing Zou und Bofeng Zhang. „A Novel Deep Learning Method for Predicting RNA-Protein Binding Sites“. Applied Sciences 13, Nr. 5 (03.03.2023): 3247. http://dx.doi.org/10.3390/app13053247.

Der volle Inhalt der Quelle

Annotation:

The cell cycle and biological processes rely on RNA and RNA-binding protein (RBP) interactions. It is crucial to identify the binding sites on RNA. Various deep-learning methods have been used for RNA-binding site prediction. However, they cannot extract the hierarchical features of the RNA secondary structure. Therefore, this paper proposes HPNet, which can automatically identify RNA-binding sites and -binding preferences. HPNet performs feature learning from the two perspectives of the RNA sequence and the RNA secondary structure. A convolutional neural network (CNN), a deep-learning method, is used to learn RNA sequence features in HPNet. To capture the hierarchical information for RNA, we introduced DiffPool into HPNet, a differentiable pooling graph neural network (GNN). A CNN and DiffPool were combined to improve the binding site prediction accuracy by leveraging both RNA sequence features and hierarchical features of the RNA secondary structure. Binding preferences can be extracted based on model outputs and parameters. Overall, the experimental results showed that HPNet achieved a mean area under the curve (AUC) of 94.5% for the benchmark dataset, which was more accurate than the state-of-the-art methods. Moreover, these results demonstrate that the hierarchical features of RNA secondary structure play an essential role in selecting RNA-binding sites.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

50

Tong, Li, Zhang, Chen, Zhang, Yang und Zhang. „Point Set Multi-Level Aggregation Feature Extraction Based on Multi-Scale Max Pooling and LDA for Point Cloud Classification“. Remote Sensing 11, Nr. 23 (29.11.2019): 2846. http://dx.doi.org/10.3390/rs11232846.

Der volle Inhalt der Quelle

Annotation:

Accurate and effective classification of lidar point clouds with discriminative features expression is a challenging task for scene understanding. In order to improve the accuracy and the robustness of point cloud classification based on single point features, we propose a novel point set multi-level aggregation features extraction and fusion method based on multi-scale max pooling and latent Dirichlet allocation (LDA). To this end, in the hierarchical point set feature extraction, point sets of different levels and sizes are first adaptively generated through multi-level clustering. Then, more effective sparse representation is implemented by locality-constrained linear coding (LLC) based on single point features, which contributes to the extraction of discriminative individual point set features. Next, the local point set features are extracted by combining the max pooling method and the multi-scale pyramid structure constructed by the point’s coordinates within each point set. The global and the local features of the point sets are effectively expressed by the fusion of multi-scale max pooling features and global features constructed by the point set LLC-LDA model. The point clouds are classified by using the point set multi-level aggregation features. Our experiments on two scenes of airborne laser scanning (ALS) point clouds—a mobile laser scanning (MLS) scene point cloud and a terrestrial laser scanning (TLS) scene point cloud—demonstrate the effectiveness of the proposed point set multi-level aggregation features for point cloud classification, and the proposed method outperforms other related and compared algorithms.

APA, Harvard, Vancouver, ISO und andere Zitierweisen

Zeitschriftenartikel zum Thema „Hierarchical Pooling“

Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an