To see the other types of publications on this topic, follow the link: Temporal Graph Processing.
Journal articles on the topic 'Temporal Graph Processing'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Temporal Graph Processing.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Christensen, Andrew J., Ananya Sen Gupta, and Ivars Kirsteins. "Sonar target feature representation using temporal graph networks." Journal of the Acoustical Society of America 151, no. 4 (April 2022): A102. http://dx.doi.org/10.1121/10.0010791.
Full textAbstract:
Autonomous sonar target recognition suffers from uncertainty caused by waveguide distortions to signal, unknown target geometry, and morphing target features. Typical “black-box” neural networks do not produce physically interpretable features and, therefore, are not effective in meeting these challenges. The primary objective of our work is to harness signal processing with machine learning to extract braided features that allow such physical interpretation by a domain expert. In this work, we introduce a feature extraction method using graph neural networks (GNNs) that seeks to discover braid manifolds from sonar magnitude spectra data. The approach involves representing the sonar magnitude spectra as sparse, dynamic graphs. These dynamic graphs can then be fed into a GNN as sequences of timed events to produce feature dictionaries that are resilient to environmental uncertainty and agnostic to ping direction. The ability of GNNs to learn complex systems of interactions makes them a great choice for braid-like feature discovery. To handle the evolving dynamic features of the sonar spectra graphs, a variation of a GNN, called temporal graph networks (TGNs), is used. TGNs utilize memory modules and graph-based operators to outperform previous GNN-based approaches when handling dynamic graphs. We use TGNs to model the evolution of the sonar spectra graphs and ultimately perform graph-based classification. Preliminary results performed on the Malta Plateau field experiment are presented.
2
Choi, Jeongwhan, Hwangyong Choi, Jeehyun Hwang, and Noseong Park. "Graph Neural Controlled Differential Equations for Traffic Forecasting." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 6 (June 28, 2022): 6367–74. http://dx.doi.org/10.1609/aaai.v36i6.20587.
Full textAbstract:
Traffic forecasting is one of the most popular spatio-temporal tasks in the field of machine learning. A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing. There has been fierce competition and many novel methods have been proposed. In this paper, we present the method of spatio-temporal graph neural controlled differential equation (STG-NCDE). Neural controlled differential equations (NCDEs) are a breakthrough concept for processing sequential data. We extend the concept and design two NCDEs: one for the temporal processing and the other for the spatial processing. After that, we combine them into a single framework. We conduct experiments with 6 benchmark datasets and 20 baselines. STG-NCDE shows the best accuracy in all cases, outperforming all those 20 baselines by non-trivial margins.
3
Zhao, Xiaojuan, Aiping Li, Rong Jiang, Kai Chen, and Zhichao Peng. "Householder Transformation-Based Temporal Knowledge Graph Reasoning." Electronics 12, no. 9 (April 26, 2023): 2001. http://dx.doi.org/10.3390/electronics12092001.
Full textAbstract:
Knowledge graphs’ reasoning is of great significance for the further development of artificial intelligence and information retrieval, especially for reasoning over temporal knowledge graphs. The rotation-based method has been shown to be effective at modeling entities and relations on a knowledge graph. However, due to the lack of temporal information representation capability, existing approaches can only model partial relational patterns and they cannot handle temporal combination reasoning. In this regard, we propose HTTR: Householder Transformation-based Temporal knowledge graph Reasoning, which focuses on the characteristics of relations that evolve over time. HTTR first fuses the relation and temporal information in the knowledge graph, then uses the Householder transformation to obtain an orthogonal matrix about the fused information, and finally defines the orthogonal matrix as the rotation of the head-entity to the tail-entity and calculates the similarity between the rotated vector and the vector representation of the tail entity. In addition, we compare three methods for fusing relational and temporal information. We allow other fusion methods to replace the current one as long as the dimensionality satisfies the requirements. We show that HTTR is able to outperform state-of-the-art methods in temporal knowledge graph reasoning tasks and has the ability to learn and infer all of the four relational patterns over time: symmetric reasoning, antisymmetric reasoning, inversion reasoning, and temporal combination reasoning.
4
Liu, Jun. "Motion Action Analysis at Basketball Sports Scene Based on Image Processing." Scientific Programming 2022 (March 7, 2022): 1–11. http://dx.doi.org/10.1155/2022/7349548.
Full textAbstract:
To solve the problems of low accuracy and high time cost in manual recording and statistics of basketball data, an automatic analysis method of motion action under the basketball sports scene based on the spatial temporal graph convolutional neural network is proposed. By using the graph structure in the data structure to model the joints and limbs of the human body, and using the spatial temporal graph structure to model the posture action, the extraction and estimation of human body posture in basketball sports scenes are realized. Then, training combined with transfer learning, the recognition of motion fuzzy posture is realized through the classification and application of a label subset. Finally, using the self-made OpenCV to collect and calibrate NBA basketball videos, the effectiveness of the proposed method is verified by analyzing the motion action. The results show that the proposed method based on the spatial temporal graph convolutional neural network can recognize all kinds of movements in different basketball scenes. The average recognition accuracy is more than 75%. It can be seen that the method has certain practical application value. Compared with the common motion analysis method feature descriptors, the motion action analysis method based on the spatial temporal graph convolution neural network has higher identification accuracy and can be used for motion action analysis in the actual basketball sports scenes.
5
Li, Jing, Wenyue Guo, Haiyan Liu, Xin Chen, Anzhu Yu, and Jia Li. "Predicting User Activity Intensity Using Geographic Interactions Based on Social Media Check-In Data." ISPRS International Journal of Geo-Information 10, no. 8 (August 17, 2021): 555. http://dx.doi.org/10.3390/ijgi10080555.
Full textAbstract:
Predicting user activity intensity is crucial for various applications. However, existing studies have two main problems. First, as user activity intensity is nonstationary and nonlinear, traditional methods can hardly fit the nonlinear spatio-temporal relationships that characterize user mobility. Second, user movements between different areas are valuable, but have not been utilized for the construction of spatial relationships. Therefore, we propose a deep learning model, the geographical interactions-weighted graph convolutional network-gated recurrent unit (GGCN-GRU), which is good at fitting nonlinear spatio-temporal relationships and incorporates users’ geographic interactions to construct spatial relationships in the form of graphs as the input. The model consists of a graph convolutional network (GCN) and a gated recurrent unit (GRU). The GCN, which is efficient at processing graphs, extracts spatial features. These features are then input into the GRU, which extracts their temporal features. Finally, the GRU output is passed through a fully connected layer to obtain the predictions. We validated this model using a social media check-in dataset and found that the geographical interactions graph construction method performs better than the baselines. This indicates that our model is appropriate for fitting the complex nonlinear spatio-temporal relationships that characterize user mobility and helps improve prediction accuracy when considering geographic flows.
6
Ke, Xiangyu, Arijit Khan, and Francesco Bonchi. "Multi-relation Graph Summarization." ACM Transactions on Knowledge Discovery from Data 16, no. 5 (October 31, 2022): 1–30. http://dx.doi.org/10.1145/3494561.
Full textAbstract:
Graph summarization is beneficial in a wide range of applications, such as visualization, interactive and exploratory analysis, approximate query processing, reducing the on-disk storage footprint, and graph processing in modern hardware. However, the bulk of the literature on graph summarization surprisingly overlooks the possibility of having edges of different types. In this article, we study the novel problem of producing summaries of multi-relation networks, i.e., graphs where multiple edges of different types may exist between any pair of nodes. Multi-relation graphs are an expressive model of real-world activities, in which a relation can be a topic in social networks, an interaction type in genetic networks, or a snapshot in temporal graphs. The first approach that we consider for multi-relation graph summarization is a two-step method based on summarizing each relation in isolation, and then aggregating the resulting summaries in some clever way to produce a final unique summary. In doing this, as a side contribution, we provide the first polynomial-time approximation algorithm based on the k -Median clustering for the classic problem of lossless single-relation graph summarization. Then, we demonstrate the shortcomings of these two-step methods, and propose holistic approaches, both approximate and heuristic algorithms, to compute a summary directly for multi-relation graphs. In particular, we prove that the approximation bound of k -Median clustering for the single relation solution can be maintained in a multi-relation graph with proper aggregation operation over adjacency matrices corresponding to its multiple relations. Experimental results and case studies (on co-authorship networks and brain networks) validate the effectiveness and efficiency of the proposed algorithms.
7
Zhang, Guoxing, Haixiao Wang, and Yuanpu Yin. "Multi-type Parameter Prediction of Traffic Flow Based on Time-space Attention Graph Convolutional Network." International Journal of Circuits, Systems and Signal Processing 15 (August 11, 2021): 902–12. http://dx.doi.org/10.46300/9106.2021.15.97.
Full textAbstract:
Graph Convolutional Neural Networks are more and more widely used in traffic flow parameter prediction tasks by virtue of their excellent non-Euclidean spatial feature extraction capabilities. However, most graph convolutional neural networks are only used to predict one type of traffic flow parameter. This means that the proposed graph convolutional neural network may only be effective for specific parameters of specific travel modes. In order to improve the universality of graph convolutional neural networks. By embedding time feature and spatio-temporal attention layer, we propose a spatio-temporal attention graph convolutional neural network based on the attention mechanism of the neural network. Through experiments on passenger flow data and vehicle speed data of two different travel modes (Hangzhou Metro Data and California Highway Data), it is verified that the proposed spatio-temporal attention graph convolutional neural network can be used to predict passenger flow and vehicle speed simultaneously. Meanwhile, the error distribution range of the proposed model is minimum, and the overall level of prediction results is more accurate.
8
Zheng, Xiaolong, Dongdong Guan, Bangjie Li, Zhengsheng Chen, and Lefei Pan. "Global and Local Graph-Based Difference Image Enhancement for Change Detection." Remote Sensing 15, no. 5 (February 21, 2023): 1194. http://dx.doi.org/10.3390/rs15051194.
Full textAbstract:
Change detection (CD) is an important research topic in remote sensing, which has been applied in many fields. In the paper, we focus on the post-processing of difference images (DIs), i.e., how to further improve the quality of a DI after the initial DI is obtained. The importance of DIs for CD problems cannot be overstated, however few methods have been investigated so far for re-processing DIs after their acquisition. In order to improve the DI quality, we propose a global and local graph-based DI-enhancement method (GLGDE) specifically for CD problems; this is a plug-and-play method that can be applied to both homogeneous and heterogeneous CD. GLGDE first segments the multi-temporal images and DIs into superpixels with the same boundaries and then constructs two graphs for the DI with superpixels as vertices: one is the global feature graph that characterizes the association between the similarity relationships of connected vertices in the multi-temporal images and their changing states in a DI, the other is the local spatial graph that exploits the change information and contextual information of the DI. Based on these two graphs, a DI-enhancement model is built, which constrains the enhanced DI to be smooth on both graphs. Therefore, the proposed GLGDE can not only smooth the DI but also correct the it. By solving the minimization model, we can obtain an improved DI. The experimental results and comparisons on different CD tasks with six real datasets demonstrate the effectiveness of the proposed method.
9
Steinbauer, Matthias, and Gabriele Anderst Kotsis. "DynamoGraph: extending the Pregel paradigm for large-scale temporal graph processing." International Journal of Grid and Utility Computing 7, no. 2 (2016): 141. http://dx.doi.org/10.1504/ijguc.2016.077491.
Full text
10
Chen, Yaosen, Bing Guo, Yan Shen, Wei Wang, Weichen Lu, and Xinhua Suo. "Boundary graph convolutional network for temporal action detection." Image and Vision Computing 109 (May 2021): 104144. http://dx.doi.org/10.1016/j.imavis.2021.104144.
Full text
11
Sun, Linhui, Yifan Zhang, Jian Cheng, and Hanqing Lu. "Asynchronous Event Processing with Local-Shift Graph Convolutional Network." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 2 (June 26, 2023): 2402–10. http://dx.doi.org/10.1609/aaai.v37i2.25336.
Full textAbstract:
Event cameras are bio-inspired sensors that produce sparse and asynchronous event streams instead of frame-based images at a high-rate. Recent works utilizing graph convolutional networks (GCNs) have achieved remarkable performance in recognition tasks, which model event stream as spatio-temporal graph. However, the computational mechanism of graph convolution introduces redundant computation when aggregating neighbor features, which limits the low-latency nature of the events. And they perform a synchronous inference process, which can not achieve a fast response to the asynchronous event signals. This paper proposes a local-shift graph convolutional network (LSNet), which utilizes a novel local-shift operation equipped with a local spatio-temporal attention component to achieve efficient and adaptive aggregation of neighbor features. To improve the efficiency of pooling operation in feature extraction, we design a node-importance based parallel pooling method (NIPooling) for sparse and low-latency event data. Based on the calculated importance of each node, NIPooling can efficiently obtain uniform sampling results in parallel, which retains the diversity of event streams. Furthermore, for achieving a fast response to asynchronous event signals, an asynchronous event processing procedure is proposed to restrict the network nodes which need to recompute activations only to those affected by the new arrival event. Experimental results show that the computational cost can be reduced by nearly 9 times through using local-shift operation and the proposed asynchronous procedure can further improve the inference efficiency, while achieving state-of-the-art performance on gesture recognition and object recognition.
12
Zeng, Hui, Chaojie Jiang, Yuanchun Lan, Xiaohui Huang, Junyang Wang, and Xinhua Yuan. "Long Short-Term Fusion Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting." Electronics 12, no. 1 (January 3, 2023): 238. http://dx.doi.org/10.3390/electronics12010238.
Full textAbstract:
Traffic flow forecasting, as one of the important components of intelligent transport systems (ITS), plays an indispensable role in a wide range of applications such as traffic management and city planning. However, complex spatial dependencies and dynamic changes in temporal patterns exist between different routes, and obtaining as many spatial-temporal features and dependencies as possible from node data has been a challenging task in traffic flow prediction. Current approaches typically use independent modules to treat temporal and spatial correlations separately without synchronously capturing such spatial-temporal correlations, or focus only on local spatial-temporal dependencies, thereby ignoring the implied long-term spatial-temporal periodicity. With this in mind, this paper proposes a long-term spatial-temporal graph convolutional fusion network (LSTFGCN) for traffic flow prediction modeling. First, we designed a synchronous spatial-temporal feature capture module, which can fruitfully extract the complex local spatial-temporal dependence of nodes. Second, we designed an ordinary differential equation graph convolution (ODEGCN) to capture more long-term spatial-temporal dependence using the spatial-temporal graph convolution of ordinary differential equation. At the same time, by integrating in parallel the ODEGCN, the spatial-temporal graph convolution attention module (GCAM), and the gated convolution module, we can effectively make the model learn more long short-term spatial-temporal dependencies in the processing of spatial-temporal sequences.Our experimental results on multiple public traffic datasets show that our method consistently obtained the optimal performance compared to the other baselines.
13
GLAVAŠ, GORAN, and JAN ŠNAJDER. "Construction and evaluation of event graphs." Natural Language Engineering 21, no. 4 (May 1, 2014): 607–52. http://dx.doi.org/10.1017/s1351324914000060.
Full textAbstract:
AbstractEvents play an important role in natural language processing and information retrieval due to numerous event-oriented texts and information needs. Many natural language processing and information retrieval applications could benefit from a structured event-oriented document representation. In this paper, we proposeevent graphsas a novel way of structuring event-based information from text. Nodes in event graphs represent the individual mentions of events, whereas edges represent the temporal and coreference relations between mentions. Contrary to previous natural language processing research, which has mainly focused on individual event extraction tasks, we describe a complete end-to-end system for event graph extraction from text. Our system is a three-stage pipeline that performs anchor extraction, argument extraction, and relation extraction (temporal relation extraction and event coreference resolution), each at a performance level comparable with the state of the art. We presentEvExtra, a large newspaper corpus annotated with event mentions and event graphs, on which we train and evaluate our models. To measure the overall quality of the constructed event graphs, we propose two metrics based on the tensor product between automatically and manually constructed graphs. Finally, we evaluate the overall quality of event graphs with the proposed evaluation metrics and perform a headroom analysis of the system.
14
Fang, Junhua, Jiafeng Ding, Pengpeng Zhao, Jiajie Xu, An Liu, and Zhixu Li. "Distributed and parallel processing for real-time and dynamic spatio-temporal graph." World Wide Web 23, no. 2 (November 18, 2019): 905–26. http://dx.doi.org/10.1007/s11280-019-00741-6.
Full text
15
Körner, Christof, Margit Höfler, Barbara Tröbinger, and Iain D. Gilchrist. "Eye Movements Indicate the Temporal Organisation of Information Processing in Graph Comprehension." Applied Cognitive Psychology 28, no. 3 (February 12, 2014): 360–73. http://dx.doi.org/10.1002/acp.3006.
Full text
16
Wang, Xiaojuan, Ziliang Gan, Lei Jin, Yabo Xiao, and Mingshu He. "Adaptive Multi-Scale Difference Graph Convolution Network for Skeleton-Based Action Recognition." Electronics 12, no. 13 (June 28, 2023): 2852. http://dx.doi.org/10.3390/electronics12132852.
Full textAbstract:
Graph convolutional networks (GCNs) have obtained remarkable performance in skeleton-based action recognition. However, previous approaches fail to capture the implicit correlations between joints and handle actions across varying time intervals. To address these problems, we propose an adaptive multi-scale difference graph convolution Network (AMD-GCN), which comprises an adaptive spatial graph convolution module (ASGC) and a multi-scale temporal difference convolution module (MTDC). The first module is capable of acquiring data-dependent and channel-wise graphs that are adaptable to both samples and channels. The second module employs the multi-scale approach to model temporal information across a range of time scales. Additionally, the MTDC incorporates an attention-enhanced module and difference convolution to accentuate significant channels and enhance temporal features, respectively. Finally, we propose a multi-stream framework for integrating diverse skeletal modalities to achieve superior performance. Our AMD-GCN approach was extensively tested and proven to outperform the current state-of-the-art methods on three widely recognized benchmarks: the NTU-RGB+D, NTU-RGB+D 120, and Kinetics Skeleton datasets.
17
Kerracher, Natalie, Jessie Kennedy, and Kevin Chalmers. "A Task Taxonomy for Temporal Graph Visualisation." IEEE Transactions on Visualization and Computer Graphics 21, no. 10 (October 1, 2015): 1160–72. http://dx.doi.org/10.1109/tvcg.2015.2424889.
Full text
18
El rai, Marwa Chendeb, Muna Darweesh, and Mina Al-Saad. "Semi-Supervised Segmentation of Echocardiography Videos Using Graph Signal Processing." Electronics 11, no. 21 (October 26, 2022): 3462. http://dx.doi.org/10.3390/electronics11213462.
Full textAbstract:
Machine learning and computer vision algorithms can provide a precise and automated interpretation of medical videos. The segmentation of the left ventricle of echocardiography videos plays an essential role in cardiology for carrying out clinical cardiac diagnosis and monitoring the patient’s condition. Most of the developed deep learning algorithms for video segmentation require an enormous amount of labeled data to generate accurate results. Thus, there is a need to develop new semi-supervised segmentation methods due to the scarcity and costly labeled data. In recent research, semi-supervised learning approaches based on graph signal processing emerged in computer vision due to their ability to avail the geometrical structure of data. Video object segmentation can be considered as a node classification problem. In this paper, we propose a new approach called GraphECV based on the use of graph signal processing for semi-supervised learning of video object segmentation applied for the segmentation of the left ventricle in echordiography videos. GraphECV includes instance segmentation, extraction of temporal, texture and statistical features to represent the nodes, construction of a graph using K-nearest neighbors, graph sampling to embed the graph with small amount of labeled nodes or graph signals, and finally a semi-supervised learning approach based on the minimization of the Sobolov norm of graph signals. The new algorithm is evaluated using two publicly available echocardiography videos, EchoNet-Dynamic and CAMUS datasets. The proposed approach outperforms other state-of-the-art methods under challenging background conditions.
19
Xue, Jizhong, Zaohui Kang, Chun Sing Lai, Yu Wang, Fangyuan Xu, and Haoliang Yuan. "Distributed Generation Forecasting Based on Rolling Graph Neural Network (ROLL-GNN)." Energies 16, no. 11 (May 31, 2023): 4436. http://dx.doi.org/10.3390/en16114436.
Full textAbstract:
The future power grid will have more distributed energy sources, and the widespread access of distributed energy sources has the potential to improve the energy efficiency, resilience, and sustainability of the system. However, distributed energy, mainly wind power generation and photovoltaic power generation, has the characteristics of intermittency and strong randomness, which will bring challenges to the safe operation of the power grid. Accurate prediction of solar power generation with high spatial and temporal resolution is very important for the normal operation of the power grid. In order to improve the accuracy of distributed photovoltaic power generation prediction, this paper proposes a new distributed photovoltaic power generation prediction model: ROLL-GNN, which is defined as a prediction model based on rolling prediction of the graph neural network. The ROLL-GNN uses the perspective of graph signal processing to model distributed generation production timeseries data as signals on graphs. In the model, the similarity of data is used to capture their spatio-temporal dependencies to achieve improved prediction accuracy.
20
Liu, Zhi, Jixin Bian, Deju Zhang, Yang Chen, Guojiang Shen, and Xiangjie Kong. "Dynamic Multi-View Coupled Graph Convolution Network for Urban Travel Demand Forecasting." Electronics 11, no. 16 (August 21, 2022): 2620. http://dx.doi.org/10.3390/electronics11162620.
Full textAbstract:
Accurate urban travel demand forecasting can help organize traffic flow, improve traffic utilization, reduce passenger waiting time, etc. It plays an important role in intelligent transportation systems. Most of the existing research methods construct static graphs from a single perspective or two perspectives, without considering the dynamic impact of time changes and various factors on traffic demand. Moreover, travel demand is also affected by regional functions such as weather, etc. To address these issues, we propose an urban travel demand prediction framework based on dynamic multi-view coupled graph convolution (DMV-GCN). Specifically, we dynamically construct demand similarity graphs based on node features to model the dynamic correlation of demand. Then we combine it with the predefined geographic similarity graph, functional similarity graph, and road similarity graph. We use coupled graph convolution network and gated recurrent units (GRU), to model the spatio-temporal correlation in traffic. We conduct extensive experiments over two large real-world datasets. The results verify the superior performance of our proposed approach for the urban travel demand forecasting task.
21
Li, Tingwei, Ruiwen Zhang, and Qing Li. "A Novel Graph Representation for Skeleton-based Action Recognition." Signal & Image Processing : An International Journal 11, no. 6 (December 30, 2020): 65–73. http://dx.doi.org/10.5121/sipij.2020.11605.
Full textAbstract:
Graph convolutional networks (GCNs) have been proven to be effective for processing structured data, so that it can effectively capture the features of related nodes and improve the performance of model. More attention is paid to employing GCN in Skeleton-Based action recognition. But there are some challenges with the existing methods based on GCNs. First, the consistency of temporal and spatial features is ignored due to extracting features node by node and frame by frame. We design a generic representation of skeleton sequences for action recognition and propose a novel model called Temporal Graph Networks (TGN), which can obtain spatiotemporal features simultaneously. Secondly, the adjacency matrix of graph describing the relation of joints are mostly depended on the physical connection between joints. We propose a multi-scale graph strategy to appropriately describe the relations between joints in skeleton graph, which adopts a full-scale graph, part-scale graph and core-scale graph to capture the local features of each joint and the contour features of important joints. Extensive experiments are conducted on two large datasets including NTU RGB+D and Kinetics Skeleton. And the experiments results show that TGN with our graph strategy outperforms other state-of-the-art methods.
22
Li, Chaoyue, Lian Zou, Cien Fan, Hao Jiang, and Yifeng Liu. "Multi-Stage Attention-Enhanced Sparse Graph Convolutional Network for Skeleton-Based Action Recognition." Electronics 10, no. 18 (September 8, 2021): 2198. http://dx.doi.org/10.3390/electronics10182198.
Full textAbstract:
Graph convolutional networks (GCNs), which model human actions as a series of spatial-temporal graphs, have recently achieved superior performance in skeleton-based action recognition. However, the existing methods mostly use the physical connections of joints to construct a spatial graph, resulting in limited topological information of the human skeleton. In addition, the action features in the time domain have not been fully explored. To better extract spatial-temporal features, we propose a multi-stage attention-enhanced sparse graph convolutional network (MS-ASGCN) for skeleton-based action recognition. To capture more abundant joint dependencies, we propose a new strategy for constructing skeleton graphs. This simulates bidirectional information flows between neighboring joints and pays greater attention to the information transmission between sparse joints. In addition, a part attention mechanism is proposed to learn the weight of each part and enhance the part-level feature learning. We introduce multiple streams of different stages and merge them in specific layers of the network to further improve the performance of the model. Our model is finally verified on two large-scale datasets, namely NTU-RGB+D and Skeleton-Kinetics. Experiments demonstrate that the proposed MS-ASGCN outperformed the previous state-of-the-art methods on both datasets.
23
Binsfeld Gonçalves, Laurent, Ivan Nesic, Marko Obradovic, Bram Stieltjes, Thomas Weikert, and Jens Bremerich. "Natural Language Processing and Graph Theory: Making Sense of Imaging Records in a Novel Representation Frame." JMIR Medical Informatics 10, no. 12 (December 21, 2022): e40534. http://dx.doi.org/10.2196/40534.
Full textAbstract:
Background A concise visualization framework of related reports would increase readability and improve patient management. To this end, temporal referrals to prior comparative exams are an essential connection to previous exams in written reports. Due to unstructured narrative texts' variable structure and content, their extraction is hampered by poor computer readability. Natural language processing (NLP) permits the extraction of structured information from unstructured texts automatically and can serve as an essential input for such a novel visualization framework. Objective This study proposes and evaluates an NLP-based algorithm capable of extracting the temporal referrals in written radiology reports, applies it to all the radiology reports generated for 10 years, introduces a graphical representation of imaging reports, and investigates its benefits for clinical and research purposes. Methods In this single-center, university hospital, retrospective study, we developed a convolutional neural network capable of extracting the date of referrals from imaging reports. The model's performance was assessed by calculating precision, recall, and F1-score using an independent test set of 149 reports. Next, the algorithm was applied to our department's radiology reports generated from 2011 to 2021. Finally, the reports and their metadata were represented in a modulable graph. Results For extracting the date of referrals, the named-entity recognition (NER) model had a high precision of 0.93, a recall of 0.95, and an F1-score of 0.94. A total of 1,684,635 reports were included in the analysis. Temporal reference was mentioned in 53.3% (656,852/1,684,635), explicitly stated as not available in 21.0% (258,386/1,684,635), and omitted in 25.7% (317,059/1,684,635) of the reports. Imaging records can be visualized in a directed and modulable graph, in which the referring links represent the connecting arrows. Conclusions Automatically extracting the date of referrals from unstructured radiology reports using deep learning NLP algorithms is feasible. Graphs refined the selection of distinct pathology pathways, facilitated the revelation of missing comparisons, and enabled the query of specific referring exam sequences. Further work is needed to evaluate its benefits in clinics, research, and resource planning.
24
Tomei, Matteo, Lorenzo Baraldi, Simone Calderara, Simone Bronzin, and Rita Cucchiara. "Video action detection by learning graph-based spatio-temporal interactions." Computer Vision and Image Understanding 206 (May 2021): 103187. http://dx.doi.org/10.1016/j.cviu.2021.103187.
Full text
25
Wang, Daocheng, Chao Chen, Chong Di, and Minglei Shu. "Exploring Behavior Patterns for Next-POI Recommendation via Graph Self-Supervised Learning." Electronics 12, no. 8 (April 20, 2023): 1939. http://dx.doi.org/10.3390/electronics12081939.
Full textAbstract:
Next-point-of-interest (POI) recommendation is a crucial part of location-based social applications. Existing works have attempted to learn behavior representation through a sequence model combined with spatial-temporal-interval context. However, these approaches ignore the impact of implicit behavior patterns contained in the visit trajectory on user decision making. In this paper, we propose a novel graph self-supervised behavior pattern learning model (GSBPL) for the next-POI recommendation. GSBPL applies two graph data augmentation operations to generate augmented trajectory graphs to model implicit behavior patterns. At the same time, a graph preference representation encoder (GPRE) based on geographical and social context is proposed to learn the high-order representations of trajectory graphs, and then capture implicit behavior patterns through contrastive learning. In addition, we propose a self-attention based on multi-feature embedding to learn users’ short-term dynamic preferences, and finally combine trajectory graph representation to predict the next location. The experimental results on three real-world datasets demonstrate that GSBPL outperforms the supervised learning baseline in terms of performance under the same conditions.
26
Li, Huiyong, Xiaofeng Wu, and Yanhong Wang. "Dynamic Performance Analysis of STEP System in Internet of Vehicles Based on Queuing Theory." Computational Intelligence and Neuroscience 2022 (April 10, 2022): 1–13. http://dx.doi.org/10.1155/2022/8322029.
Full textAbstract:
The Internet of vehicles (IoV) is an important research area of the intelligent transportation systems using Internet of things theory. The complex event processing technology is a basic issue for processing the data stream in IoV. In recent years, many researchers process the temporal and spatial data flow by complex event processing technology. Spatial Temporal Event Processing (STEP) is a complex event query language focusing on the temporal and spatial data flow in Internet of vehicles. There are four processing models of the event stream processing system based on the complex event query language: finite automata model, matching tree model, directed acyclic graph model, and Petri net model. In addition, the worst-case response time of the event stream processing system is an important indicator of evaluating the performance of the system. Firstly, this paper proposed a core algorithm of the temporal and spatial event stream processing program based on STEP by Petri net model. Secondly, we proposed a novel method to estimate the worst-case response time of the event stream processing system, which is based on stochastic Petri net and queuing theory. Finally, through the simulation experiment based on queuing theory, this paper proves that the data stream processing system based on STEP has good dynamic performance in processing the spatiotemporal data stream in Internet of vehicles.
27
Karuza, Elisabeth A., Ari E. Kahn, and Danielle S. Bassett. "Human Sensitivity to Community Structure Is Robust to Topological Variation." Complexity 2019 (February 11, 2019): 1–8. http://dx.doi.org/10.1155/2019/8379321.
Full textAbstract:
Despite mounting evidence that human learners are sensitive to community structure underpinning temporal sequences, this phenomenon has been studied using an extremely narrow set of network ensembles. The extent to which behavioral signatures of learning are robust to changes in community size and number is the focus of the present work. Here we present adult participants with a continuous stream of novel objects generated by a random walk along graphs of 1, 2, 3, 4, or 6 communities comprised of N = 24, 12, 8, 6, and 4 nodes, respectively. Nodes of the graph correspond to a unique object and edges correspond to their immediate succession in the stream. In short, we find that previously observed processing costs associated with community boundaries persist across an array of graph architectures. These results indicate that statistical learning mechanisms can flexibly accommodate variation in community structure during visual event segmentation.
28
Bayram, Ulya, Runia Roy, Aqil Assalil, and Lamia BenHiba. "The unknown knowns: a graph-based approach for temporal COVID-19 literature mining." Online Information Review 45, no. 4 (March 23, 2021): 687–708. http://dx.doi.org/10.1108/oir-12-2020-0562.
Full textAbstract:
PurposeThe COVID-19 pandemic has sparked a remarkable volume of research literature, and scientists are increasingly in need of intelligent tools to cut through the noise and uncover relevant research directions. As a response, the authors propose a novel framework. In this framework, the authors develop a novel weighted semantic graph model to compress the research studies efficiently. Also, the authors present two analyses on this graph to propose alternative ways to uncover additional aspects of COVID-19 research.Design/methodology/approachThe authors construct the semantic graph using state-of-the-art natural language processing (NLP) techniques on COVID-19 publication texts (>100,000 texts). Next, the authors conduct an evolutionary analysis to capture the changes in COVID-19 research across time. Finally, the authors apply a link prediction study to detect novel COVID-19 research directions that are so far undiscovered.FindingsFindings reveal the success of the semantic graph in capturing scientific knowledge and its evolution. Meanwhile, the prediction experiments provide 79% accuracy on returning intelligible links, showing the reliability of the methods for predicting novel connections that could help scientists discover potential new directions.Originality/valueTo the authors’ knowledge, this is the first study to propose a holistic framework that includes encoding the scientific knowledge in a semantic graph, demonstrates an evolutionary examination of past and ongoing research and offers scientists with tools to generate new hypotheses and research directions through predictive modeling and deep machine learning techniques.
29
Carrillo, Rafael E., Martin Leblanc, Baptiste Schubnel, Renaud Langou, Cyril Topfel, and Pierre-Jean Alet. "High-Resolution PV Forecasting from Imperfect Data: A Graph-Based Solution." Energies 13, no. 21 (November 3, 2020): 5763. http://dx.doi.org/10.3390/en13215763.
Full textAbstract:
Operating power systems with large amounts of renewables requires predicting future photovoltaic (PV) production with fine temporal and spatial resolution. State-of-the-art techniques combine numerical weather predictions with statistical post-processing, but their resolution is too coarse for applications such as local congestion management. In this paper we introduce computing methods for multi-site PV forecasting, which exploit the intuition that PV systems provide a dense network of simple weather stations. These methods rely entirely on production data and address the real-life challenges that come with them, such as noise and gaps. Our approach builds on graph signal processing for signal reconstruction and for forecasting with a linear, spatio-temporal autoregressive (ST-AR) model. It also introduces a data-driven clear-sky production estimation for normalization. The proposed framework was evaluated over one year on both 303 real PV systems under commercial monitoring across Switzerland, and 1000 simulated ones based on high-resolution weather data. The results demonstrate the performance and robustness of the approach: with gaps of four hours on average in the input data, the average daytime NRMSE over a six-hour forecasting horizon (in 15 min steps) and over all systems is 13.8% and 9% for the real and synthetic data sets, respectively.
30
Aqil, Marco, Selen Atasoy, Morten L. Kringelbach, and Rikkert Hindriks. "Graph neural fields: A framework for spatiotemporal dynamical models on the human connectome." PLOS Computational Biology 17, no. 1 (January 28, 2021): e1008310. http://dx.doi.org/10.1371/journal.pcbi.1008310.
Full textAbstract:
Tools from the field of graph signal processing, in particular the graph Laplacian operator, have recently been successfully applied to the investigation of structure-function relationships in the human brain. The eigenvectors of the human connectome graph Laplacian, dubbed “connectome harmonics”, have been shown to relate to the functionally relevant resting-state networks. Whole-brain modelling of brain activity combines structural connectivity with local dynamical models to provide insight into the large-scale functional organization of the human brain. In this study, we employ the graph Laplacian and its properties to define and implement a large class of neural activity models directly on the human connectome. These models, consisting of systems of stochastic integrodifferential equations on graphs, are dubbed graph neural fields, in analogy with the well-established continuous neural fields. We obtain analytic predictions for harmonic and temporal power spectra, as well as functional connectivity and coherence matrices, of graph neural fields, with a technique dubbed CHAOSS (shorthand for Connectome-Harmonic Analysis Of Spatiotemporal Spectra). Combining graph neural fields with appropriate observation models allows for estimating model parameters from experimental data as obtained from electroencephalography (EEG), magnetoencephalography (MEG), or functional magnetic resonance imaging (fMRI). As an example application, we study a stochastic Wilson-Cowan graph neural field model on a high-resolution connectome graph constructed from diffusion tensor imaging (DTI) and structural MRI data. We show that the model equilibrium fluctuations can reproduce the empirically observed harmonic power spectrum of resting-state fMRI data, and predict its functional connectivity, with a high level of detail. Graph neural fields natively allow the inclusion of important features of cortical anatomy and fast computations of observable quantities for comparison with multimodal empirical data. They thus appear particularly suitable for modelling whole-brain activity at mesoscopic scales, and opening new potential avenues for connectome-graph-based investigations of structure-function relationships.
31
Guda, Vanitha, and SureshKumar Sanampudi. "Event Time Relationship in Natural Language Text." International Journal of Recent Contributions from Engineering, Science & IT (iJES) 7, no. 3 (September 25, 2019): 4. http://dx.doi.org/10.3991/ijes.v7i3.10985.
Full textAbstract:
<p>Due to the numerous information needs, retrieval of events from a given natural language text is inevitable. In natural language processing (NLP) perspective, "Events" are situations, occurrences, real-world entities or facts. Extraction of events and arranging them on a timeline is helpful in various NLP application like building the summary of news articles, processing health records, and Question Answering System (QA) systems. This paper presents a framework for identifying the events and times from a given document and representing them using a graph data structure. As a result, a graph is derived to show event-time relationships in the given text. Events form the nodes in a graph, and edges represent the temporal relations among the nodes. Time of an event occurrence exists in two forms namely qualitative (like before, after, duringetc) and quantitative (exact time points/periods). To build the event-time-event structure quantitative time is normalized to qualitative form. Thus obtained temporal information is used to label the edges among the events. Data set released in the shared task EvTExtract of (Forum for Information Retrieval Extraction) FIRE 2018 conference is identified to evaluate the framework. Precision and recall are used as evaluation metrics to access the performance of the proposed framework with other methods mentioned in state of the art with 85% of accuracy and 90% of precision.</p>
32
Huang, Xiaohui, Yuanchun Lan, Yuming Ye, Junyang Wang, and Yuan Jiang. "Traffic Flow Prediction Based on Multi-Mode Spatial-Temporal Convolution of Mixed Hop Diffuse ODE." Electronics 11, no. 19 (September 22, 2022): 3012. http://dx.doi.org/10.3390/electronics11193012.
Full textAbstract:
In recent years, traffic flow forecasting has attracted the great attention of many researchers with increasing traffic congestion in metropolises. As a hot topic in the field of intelligent city computing, traffic flow forecasting plays a vital role, since predicting the changes in traffic flow can timely alleviate traffic congestion and reduce the occurrence of accidents by vehicle scheduling. The most difficult challenges of traffic flow prediction are the temporal feature extraction and the spatial correlation extraction of nodes. At the same time, graph neural networks (GNNs) show an excellent ability in dealing with spatial dependence. Existing works typically make use of graph neural networks (GNNs) and temporal convolutional networks (TCNs) to model spatial and temporal dependencies respectively. However, how to extract as much valid information as possible from nodes is a challenge for GNNs. Therefore, we propose a multi-mode spatial-temporal convolution of mixed hop diffuse ODE (MHODE) for modeling traffic flow prediction. First, we design an adaptive spatial-temporal convolution module that combines Gate TCN and graph convolution to capture more short-term spatial-temporal dependencies and features. Secondly, we design a mixed hop diffuse ordinary differential equation(ODE) spatial-temporal convolution module to capture long-term spatial-temporal dependencies using the receptive field of the mixed hop diffuse ODE. Finally, we design a multi spatial-temporal fusion module to integrate the different spatial-temporal dependencies extracted from two different spatial-temporal convolutions. To capture more spatial-temporal features of traffic flow, we use the multi-mode spatial-temporal fusion module to get more abundant traffic features by considering short-term and long-term two different features. The experimental results on two public traffic datasets (METR-LA and PEMS-BAY) demonstrate that our proposed algorithm performs better than the existing methods in most of cases.
33
Ghosh, Dipon Kumar, Amitabha Chakrabarty, Hyeonjoon Moon, and M. Jalil Piran. "A Spatio-Temporal Graph Convolutional Network Model for Internet of Medical Things (IoMT)." Sensors 22, no. 21 (November 2, 2022): 8438. http://dx.doi.org/10.3390/s22218438.
Full textAbstract:
In order to provide intelligent and efficient healthcare services in the Internet of Medical Things (IoMT), human action recognition (HAR) can play a crucial role. As a result of their stringent requirements, such as high computational complexity and memory efficiency, classical HAR techniques are not applicable to modern and intelligent healthcare services, e.g., IoMT. To address these issues, we present in this paper a novel HAR technique for healthcare services in IoMT. This model, referred to as the spatio-temporal graph convolutional network (STGCN), primarily aims at skeleton-based human–machine interfaces. By independently extracting spatial and temporal features, STGCN significantly reduces information loss. Spatio-temporal information is extracted independently of the exact spatial and temporal point, ensuring the extraction of useful features for HAR. Using only joint data and fewer parameters, we demonstrate that our proposed STGCN achieved 92.2% accuracy on the skeleton dataset. Unlike multi-channel methods, which use a combination of joint and bone data and have a large number of parameters, multi-channel methods use both joint and bone data. As a result, STGCN offers a good balance between accuracy, memory consumption, and processing time, making it suitable for detecting medical conditions.
34
He, Jiatong, Jia Cui, Gaobo Zhang, Mingrui Xue, Dengyu Chu, and Yanna Zhao. "Spatial–temporal seizure detection with graph attention network and bi-directional LSTM architecture." Biomedical Signal Processing and Control 78 (September 2022): 103908. http://dx.doi.org/10.1016/j.bspc.2022.103908.
Full text
35
Zhao, Mengyao, Zhengping Hu, Shufang Li, Shuai Bi, and Zhe Sun. "Two-stream graph convolutional neural network fusion for weakly supervised temporal action detection." Signal, Image and Video Processing 16, no. 4 (October 11, 2021): 947–54. http://dx.doi.org/10.1007/s11760-021-02039-5.
Full text
36
Shuai, Wenjing, Fenlong Jiang, Hanhong Zheng, and Jianzhao Li. "MSGATN: A Superpixel-Based Multi-Scale Siamese Graph Attention Network for Change Detection in Remote Sensing Images." Applied Sciences 12, no. 10 (May 20, 2022): 5158. http://dx.doi.org/10.3390/app12105158.
Full textAbstract:
With the rapid development of Earth observation technology, how to effectively and efficiently detect changes in multi-temporal images has become an important but challenging problem. Relying on the advantages of high performance and robustness, object-based change detection (CD) has become increasingly popular. By analyzing the similarity of local pixels, object-based CD aggregates similar pixels into one object and takes it as the basic processing unit. However, object-based approaches often have difficulty capturing discriminative features, as irregular objects make processing difficult. To address this problem, in this paper, we propose a novel superpixel-based multi-scale Siamese graph attention network (MSGATN) which can process unstructured data natively and extract valuable features. First, a difference image (DI) is generated by Euclidean distance between bitemporal images. Second, superpixel segmentation is employed based on DI to divide each image into many homogeneous regions. Then, these superpixels are used to model the problem by graph theory to construct a series of nodes with the adjacency between them. Subsequently, the multi-scale neighborhood features of the nodes are extracted through applying a graph convolutional network and concatenated by an attention mechanism. Finally, the binary change map can be obtained by classifying each node by some fully connected layers. The novel features of MSGATN can be summarized as follows: (1) Training in multi-scale constructed graphs improves the recognition over changed land cover of varied sizes and shapes. (2) Spectral and spatial self-attention mechanisms are exploited for a better change detection performance. The experimental results on several real datasets show the effectiveness and superiority of the proposed method. In addition, compared to other recent methods, the proposed can demonstrate very high processing efficiency and greatly reduce the dependence on labeled training samples in a semisupervised training fashion.
37
Wu, Lei, Yong Tang, Pei Zhang, and Ying Zhou. "Spatio-Temporal Heterogeneous Graph Neural Networks for Estimating Time of Travel." Electronics 12, no. 6 (March 8, 2023): 1293. http://dx.doi.org/10.3390/electronics12061293.
Full textAbstract:
Estimating Time of Travel (ETT) is a crucial element of intelligent transportation systems. In most previous studies, time of travel is estimated by identifying the spatio-temporal features of road segments or intersections independently. However, due to continuous changes in road segments and intersections in a path, dynamic features should be coupled and interactive. Therefore, employing only road segment or intersection features is inadequate for improving the accuracy of ETT. To address this issue, we proposed a novel deep learning framework for ETT based on a spatio-temporal heterogeneous graph neural network (STHGNN). Specifically, a heterogeneous traffic graph was first created based on intersections and road segments, which implies an adjacency correlation. Next, a learning approach for spatio-temporal heterogeneous convolutional attention networks was proposed to obtain the spatio-temporal correlations of joint intersections and road segments. This approach integrates temporal and spatial features. Finally, a fusion prediction approach was employed to estimate the travel time of a given path. Experiments were conducted on real-world path datasets to evaluate our proposed model. The results showed that STHGNN significantly outperformed the baselines.
38
Cao, Yibo, Lu Liu, and Yuhan Dong. "Convolutional Long Short-Term Memory Two-Dimensional Bidirectional Graph Convolutional Network for Taxi Demand Prediction." Sustainability 15, no. 10 (May 11, 2023): 7903. http://dx.doi.org/10.3390/su15107903.
Full textAbstract:
With the rise of the online ride-hailing market, taxi demand prediction has received more and more research interest in intelligent transportation. However, most traditional research methods mainly focused on the demand based on the original point and ignored the intention of the passenger’s destination. At the same time, many forecasting methods need sufficient investigation and data processing, which undoubtedly increases the complexity and operability of forecasting problems. Therefore, we regard the current taxi demand prediction as an origin–destination problem in order to provide more accurate predictions for the taxi demand problem. By combining a spatial network based on graph convolutional network (GCN) and a temporal network of convolutional long short-term memory (Conv-LSTM), we propose a new spatial-temporal model of Conv-LSTM two-dimensional bidirectional GCN (CTBGCN) to uncover the potential correlation between origin and destination. We utilize the temporal network for effective temporal information and the spatial network of multi-layers to get the implicit origin–destination correlation. Numerical results suggest that the proposed method outperforms the state-of-the-art baseline and other traditional methods.
39
Huang, Wanrong, Xiaodong Yi, Yichun Sun, Yingwen Liu, Shuai Ye, and Hengzhu Liu. "Scalable Parallel Distributed Coprocessor System for Graph Searching Problems with Massive Data." Scientific Programming 2017 (2017): 1–9. http://dx.doi.org/10.1155/2017/1496104.
Full textAbstract:
The Internet applications, such as network searching, electronic commerce, and modern medical applications, produce and process massive data. Considerable data parallelism exists in computation processes of data-intensive applications. A traversal algorithm, breadth-first search (BFS), is fundamental in many graph processing applications and metrics when a graph grows in scale. A variety of scientific programming methods have been proposed for accelerating and parallelizing BFS because of the poor temporal and spatial locality caused by inherent irregular memory access patterns. However, new parallel hardware could provide better improvement for scientific methods. To address small-world graph problems, we propose a scalable and novel field-programmable gate array-based heterogeneous multicore system for scientific programming. The core is multithread for streaming processing. And the communication network InfiniBand is adopted for scalability. We design a binary search algorithm to address mapping to unify all processor addresses. Within the limits permitted by the Graph500 test bench after 1D parallel hybrid BFS algorithm testing, our 8-core and 8-thread-per-core system achieved superior performance and efficiency compared with the prior work under the same degree of parallelism. Our system is efficient not as a special acceleration unit but as a processor platform that deals with graph searching applications.
40
Rozhdestvenskaya, К. N. "Temporal analysis of a control system in a data processing network." Information and Control Systems, no. 1 (February 19, 2019): 32–39. http://dx.doi.org/10.31799/1684-8853-2019-1-32-39.
Full textAbstract:
Introduction:A control system for a data processing network interacts with the network by sending commands and receiving responses. Such a control system is responsible for the network viability, and therefore should be analyzed, in particular, in terms of behavior over time, without exhaustive search for possible control options.Purpose:Studying and analyzing the behavior of a control system in a data processing network using mathematical modeling based on finite automata theory, and performing computer simulation of the obtained theoretical positions.Results:A finite state machine is constructed, presented in the form of a transition graph, reflecting the temporal behavior of a part of a specific control system in the data processing network by Plug-and-Play manager. Rules of conduct are specified, and the problem of the manager FSM analysis is defined. As a result, the control vector types have been obtained which lead the PnP manager to the correct temporal behavior. Computer simulation was performed using a script program in MatLab mathematical package. The simulation results are presented as time diagrams of finite state machine transitions. Its behavior varies depending on the incoming signals and the starting state of the machine. On the time diagrams, you can trace the behavior and transitions between states, estimate the frequency of getting into a particular state, or bypass the machine states.Practical relevance:The control vector types found for the PnP manager without an exhaustive search do not lead to incorrect situations in network data processing.
41
Pang, Shiyan, Xiangyun Hu, Mi Zhang, Zhongliang Cai, and Fengzhu Liu. "Co-Segmentation and Superpixel-Based Graph Cuts for Building Change Detection from Bi-Temporal Digital Surface Models and Aerial Images." Remote Sensing 11, no. 6 (March 26, 2019): 729. http://dx.doi.org/10.3390/rs11060729.
Full textAbstract:
Thanks to the recent development of laser scanner hardware and the technology of dense image matching (DIM), the acquisition of three-dimensional (3D) point cloud data has become increasingly convenient. However, how to effectively combine 3D point cloud data and images to realize accurate building change detection is still a hotspot in the field of photogrammetry and remote sensing. Therefore, with the bi-temporal aerial images and point cloud data obtained by airborne laser scanner (ALS) or DIM as the data source, a novel building change detection method combining co-segmentation and superpixel-based graph cuts is proposed in this paper. In this method, the bi-temporal point cloud data are firstly combined to achieve a co-segmentation to obtain bi-temporal superpixels with the simple linear iterative clustering (SLIC) algorithm. Secondly, for each period of aerial images, semantic segmentation based on a deep convolutional neural network is used to extract building areas, and this is the basis for subsequent superpixel feature extraction. Again, with the bi-temporal superpixel as the processing unit, a graph-cuts-based building change detection algorithm is proposed to extract the changed buildings. In this step, the building change detection problem is modeled as two binary classifications, and acquisition of each period’s changed buildings is a binary classification, in which the changed building is regarded as foreground and the other area as background. Then, the graph cuts algorithm is used to obtain the optimal solution. Next, by combining the bi-temporal changed buildings and digital surface models (DSMs), these changed buildings are further classified as “newly built,” “taller,” “demolished”, and “lower”. Finally, two typical datasets composed of bi-temporal aerial images and point cloud data obtained by ALS or DIM are used to validate the proposed method, and the experiments demonstrate the effectiveness and generality of the proposed algorithm.
42
Do, M., and S. Kambhampati. "SAPA: A Multi-objective Metric Temporal Planner." Journal of Artificial Intelligence Research 20 (December 1, 2003): 155–94. http://dx.doi.org/10.1613/jair.1156.
Full textAbstract:
SAPA is a domain-independent heuristic forward chaining planner that can handle durative actions, metric resource constraints, and deadline goals. It is designed to be capable of handling the multi-objective nature of metric temporal planning. Our technical contributions include (i) planning-graph based methods for deriving heuristics that are sensitive to both cost and makespan (ii) techniques for adjusting the heuristic estimates to take action interactions and metric resource limitations into account and (iii) a linear time greedy post-processing technique to improve execution flexibility of the solution plans. An implementation of SAPA using many of the techniques presented in this paper was one of the best domain independent planners for domains with metric and temporal constraints in the third International Planning Competition, held at AIPS-02. We describe the technical details of extracting the heuristics and present an empirical evaluation of the current implementation of SAPA.
43
Sighencea, Bogdan Ilie, Ion Rareș Stanciu, and Cătălin Daniel Căleanu. "D-STGCN: Dynamic Pedestrian Trajectory Prediction Using Spatio-Temporal Graph Convolutional Networks." Electronics 12, no. 3 (January 26, 2023): 611. http://dx.doi.org/10.3390/electronics12030611.
Full textAbstract:
Predicting pedestrian trajectories in urban scenarios is a challenging task that has a wide range of applications, from video surveillance to autonomous driving. The task is difficult since pedestrian behavior is affected by both their individual path’s history, their interactions with others, and with the environment. For predicting pedestrian trajectories, an attention-based interaction-aware spatio-temporal graph neural network is introduced. This paper introduces an approach based on two components: a spatial graph neural network (SGNN) for interaction-modeling and a temporal graph neural network (TGNN) for motion feature extraction. The SGNN uses an attention method to periodically collect spatial interactions between all pedestrians. The TGNN employs an attention method as well, this time to collect each pedestrian’s temporal motion pattern. Finally, in the graph’s temporal dimension characteristics, a time-extrapolator convolutional neural network (CNN) is employed to predict the trajectories. Using a lower variable size (data and model) and a better accuracy, the proposed method is compact, efficient, and better than the one represented by the social-STGCNN. Moreover, using three video surveillance datasets (ETH, UCY, and SDD), D-STGCN achieves better experimental results considering the average displacement error (ADE) and final displacement error (FDE) metrics, in addition to predicting more social trajectories.
44
Weghenkel, Björn, and Laurenz Wiskott. "Slowness as a Proxy for Temporal Predictability: An Empirical Comparison." Neural Computation 30, no. 5 (May 2018): 1151–79. http://dx.doi.org/10.1162/neco_a_01070.
Full textAbstract:
The computational principles of slowness and predictability have been proposed to describe aspects of information processing in the visual system. From the perspective of slowness being a limited special case of predictability we investigate the relationship between these two principles empirically. On a collection of real-world data sets we compare the features extracted by slow feature analysis (SFA) to the features of three recently proposed methods for predictable feature extraction: forecastable component analysis, predictable feature analysis, and graph-based predictable feature analysis. Our experiments show that the predictability of the learned features is highly correlated, and, thus, SFA appears to effectively implement a method for extracting predictable features according to different measures of predictability.
45
Shi, Yong, Yang Xiao, Pei Quan, MingLong Lei, and Lingfeng Niu. "Document-level relation extraction via graph transformer networks and temporal convolutional networks." Pattern Recognition Letters 149 (September 2021): 150–56. http://dx.doi.org/10.1016/j.patrec.2021.06.012.
Full text
46
Pan, Chengsheng, Jiang Zhu, Zhixiang Kong, Huaifeng Shi, and Wensheng Yang. "DC-STGCN: Dual-Channel Based Graph Convolutional Networks for Network Traffic Forecasting." Electronics 10, no. 9 (April 24, 2021): 1014. http://dx.doi.org/10.3390/electronics10091014.
Full textAbstract:
Network traffic forecasting is essential for efficient network management and planning. Accurate long-term forecasting models are also essential for proactive control of upcoming congestion events. Due to the complex spatial-temporal dependencies between traffic flows, traditional time series forecasting models are often unable to fully extract the spatial-temporal characteristics between the traffic flows. To address this issue, we propose a novel dual-channel based graph convolutional network (DC-STGCN) model. The proposed model consists of two temporal components that characterize the daily and weekly correlation of the network traffic. Each of these two components contains a spatial-temporal characteristics extraction module consisting of a dual-channel graph convolutional network (DCGCN) and a gated recurrent unit (GRU). The DCGCN further consists of an adjacency feature extraction module (AGCN) and a correlation feature extraction module (PGCN) to capture the connectivity between nodes and the proximity correlation, respectively. The GRU further extracts the temporal characteristics of the traffic. The experimental results based on real network data sets show that the prediction accuracy of the DC-STGCN model overperforms the existing baseline and is capable of making long-term predictions.
47
Feng, Yongliang. "Air Quality Prediction Model Using Deep Learning in Internet of Things Environmental Monitoring System." Mobile Information Systems 2022 (September 29, 2022): 1–9. http://dx.doi.org/10.1155/2022/7221157.
Full textAbstract:
In order to realize the accurate prediction of spatial-temporal air quality index, this paper constructs a STAQI prediction model based on deep learning, including data processing, spatial feature acquisition, temporal feature acquisition, and STAQI prediction. Firstly, the spatial interpolation method is used to optimize the sample data set to provide reliable data; the improved graph convolutional network and the improved long short-term memory are used to effectively extract the spatial and temporal distribution characteristics of AQI data; and then, the extreme learning machine model is used to accurately predict and analyze AQI data. Simulation results show that the evaluation indexes RMSE and MAE of the constructed prediction model are 4.51 and 3.92, respectively, showing excellent curve fitting ability and AQI prediction ability.
48
Hu, Zhiqiu, Fengjing Shao, and Rencheng Sun. "A New Perspective on Traffic Flow Prediction: A Graph Spatial-Temporal Network with Complex Network Information." Electronics 11, no. 15 (August 4, 2022): 2432. http://dx.doi.org/10.3390/electronics11152432.
Full textAbstract:
Traffic flow prediction provides support for travel management, vehicle scheduling, and intelligent transportation system construction. In this work, a graph space–time network (GSTNCNI), incorporating complex network feature information, is proposed to predict future highway traffic flow time series. Firstly, a traffic complex network model using traffic big data is established, the topological features of traffic road networks are then analyzed using complex network theory, and finally, the topological features are combined with graph neural networks to explore the roles played by the topological features of 97 traffic network nodes. Consequently, six complex network properties are discussed, namely, degree centrality, clustering coefficient, closeness centrality, betweenness centrality, point intensity, and shortest average path length. This study improves the graph convolutional neural network based on the above six complex network properties and proposes a graph spatial–temporal network consisting of a combination of several complex network properties. By comparison with existing baselines containing graph convolutional neural networks, it is verified that GSTNCNI possesses high traffic flow prediction accuracy and robustness. In addition, ablation experiments are conducted for six different complex network features to verify the effect of different complex network features on the model’s prediction accuracy. Experimental analysis indicates that the model with combined multiple complex network features has a higher prediction accuracy, and its performance is improved by 31.46% on average, compared with the model containing only one complex network feature.
49
Zhu, Qilin, Hongmin Deng, and Kaixuan Wang. "Skeleton Action Recognition Based on Temporal Gated Unit and Adaptive Graph Convolution." Electronics 11, no. 18 (September 19, 2022): 2973. http://dx.doi.org/10.3390/electronics11182973.
Full textAbstract:
In recent years, great progress has been made in the recognition of skeletal behaviors based on graph convolutional networks (GCNs). In most existing methods, however, the fixed adjacency matrix and fixed graph structure are used for skeleton data feature extraction in the spatial dimension, which usually leads to weak spatial modeling ability, unsatisfactory generalization performance, and an excessive number of model parameters. Most of these methods follow the ST-GCN approach in the temporal dimension, which inevitably leads to a number of non-key frames, increasing the cost of feature extraction and causing the model to be slower in terms of feature extraction and the required computational burden. In this paper, a gated temporally and spatially adaptive graph convolutional network is proposed. On the one hand, a learnable parameter matrix which can adaptively learn the key information of the skeleton data in spatial dimension is added to the graph convolution layer, improving the feature extraction and generalizability of the model and reducing the number of parameters. On the other hand, a gated unit is added to the temporal feature extraction module to alleviate interference from non-critical frames and reduce computational complexity. A channel attention mechanism based on an SE module and a frame attention mechanism are used to enhance the model’s feature extraction ability. To prevent model degradation and ensure more stable training, residual links are added to each feature extraction module. The proposed approach was ultimately able to achieve 0.63% higher accuracy on the X-Sub benchmark with 4.46 M fewer parameters than GAT, one of the best SOTA methods. Inference speed of our model reaches as fast as 86.23 sequences/(second × GPU). Extensive experimental results further validate the effectiveness of our proposed approach on three large-scale datasets, namely, NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton.
50
Zhong, Yang Jun, and Qian Cai. "A Novel Registration Approach for Mammograms Based on SIFT and Graph Transformation." Applied Mechanics and Materials 157-158 (February 2012): 1313–19. http://dx.doi.org/10.4028/www.scientific.net/amm.157-158.1313.
Full textAbstract:
Mammogram registration is an important step in the processing of automatic detection of breast cancer. It provides aid to better visualization correspondence on temporal pairs of mammograms. This paper presents a novel algorithm based on SIFT feature and Graph Transformation methods for mammogram registration. First, features are extracted from the mammogram images by scale invariant feature transform (SIFT) method. Second, we use graph transformation matching (GTM) approach to obtain more accurate image information. At last, we registered a pair of mammograms using Thin-Plate spline (TPS) interpolation based on corresponding points on the two breasts, and acquire the mammogram registration image. Performance of the proposed algorithm is evaluated by three criterions. The experimental results show that our method is accurate and closely to the source images.