scholarly journals A Dynamic and Static Context-Aware Attention Network for Trajectory Prediction

2021 ◽  
Vol 10 (5) ◽  
pp. 336
Author(s):  
Jian Yu ◽  
Meng Zhou ◽  
Xin Wang ◽  
Guoliang Pu ◽  
Chengqi Cheng ◽  
...  
Keyword(s):  
Real World ◽  
Autonomous Driving ◽  
Attention Mechanism ◽  
Context Aware ◽  
Trajectory Prediction ◽  
Attention Network ◽  
Series Of Experiments ◽  
Real World Datasets ◽  
The Moment ◽  
Autonomous Driving System

Forecasting the motion of surrounding vehicles is necessary for an autonomous driving system applied in complex traffic. Trajectory prediction helps vehicles make more sensible decisions, which provides vehicles with foresight. However, traditional models consider the trajectory prediction as a simple sequence prediction task. The ignorance of inter-vehicle interaction and environment influence degrades these models in real-world datasets. To address this issue, we propose a novel Dynamic and Static Context-aware Attention Network named DSCAN in this paper. The DSCAN utilizes an attention mechanism to dynamically decide which surrounding vehicles are more important at the moment. We also equip the DSCAN with a constraint network to consider the static environment information. We conducted a series of experiments on a real-world dataset, and the experimental results demonstrated the effectiveness of our model. Moreover, the present study suggests that the attention mechanism and static constraints enhance the prediction results.

scholarly journals Which Attributes Matter the Most for Loan Origination? A Neural Attention Approach

2020 ◽  
Author(s):  
Antonios Alexos ◽  
Sotirios Chatzis
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Individual Case ◽  
Learning Model ◽  
Attention Mechanism ◽  
Novel Approach ◽  
Specific Individual ◽  
Real World Datasets ◽  
Deep Learning Model

In this paper we address the understanding of the problem, of why a deep learning model decides that an individual is eligible for a loan or not. Here we propose a novel approach for inferring, which attributes matter the most, for making a decision in each specific individual case. Specifically we leverage concepts from neural attention to devise a novel feature wise attention mechanism. As we show, using real world datasets, our approach offers unique insights into the importance of various features, by producing a decision explanation for each specific loan case. At the same time, we observe that our novel mechanism, generates decisions which are much closer to the decisions generated by human experts, compared to the existent competitors.

scholarly journals Extracting Entity Synonymous Relations via Context-Aware Permutation Invariance

2022 ◽  
Vol 17 (1) ◽  
pp. 1-17
Author(s):  
Nan Yan ◽  
Subin Huang ◽  
Chao Kong
Keyword(s):  
Real World ◽  
Relation Extraction ◽  
The Other ◽  
Context Aware ◽  
Important Work ◽  
Relational Context ◽  
Permutation Invariance ◽  
Level Statistics ◽  
Real World Datasets ◽  
Better Than

Discovering entity synonymous relations is an important work for many entity-based applications. Existing entity synonymous relation extraction approaches are mainly based on lexical patterns or distributional corpus-level statistics, ignoring the context semantics between entities. For example, the contexts around ''apple'' determine whether ''apple'' is a kind of fruit or Apple Inc. In this paper, an entity synonymous relation extraction approach is proposed using context-aware permutation invariance. Specifically, a triplet network is used to obtain the permutation invariance between the entities to learn whether two given entities possess synonymous relation. To track more synonymous features, the relational context semantics and entity representations are integrated into the triplet network, which can improve the performance of extracting entity synonymous relations. The proposed approach is implemented on three real-world datasets. Experimental results demonstrate that the approach performs better than the other compared approaches on entity synonymous relation extraction task.

scholarly journals User Monitoring in Autonomous Driving System Using Gamified Task: A Case for vr/AR in-Car Gaming

2021 ◽  
Author(s):  
Joseph K. Muguro ◽  
Pringgo Widyo Laksono ◽  
Yuta Sasatake ◽  
Kojiro Matsushita ◽  
Minoru Sasaki
Keyword(s):  
Real World ◽  
Secondary Task ◽  
Autonomous Driving ◽  
Driving Simulation ◽  
Control Loop ◽  
Automated Driving ◽  
Driving System ◽  
The Road ◽  
Current Test ◽  
Autonomous Driving System

As Automated Driving Systems (ADS) technology gets assimilated into the market, the driver’s obligation will be changed to a supervisory role. A key point to consider is the driver’s engagement in the secondary task to maintain the driver/user in the control loop. The paper’s objective is to monitor driver engagement with a game and identify any impacts the task has on hazard recognition. We designed a driving simulation using Unity3D and incorporated three tasks: No-task, AR-Video, and AR-Game tasks. The driver engaged in an AR object interception game while monitoring the road for threatening road scenarios. From the results, there was less than 1 second difference between the means of gaming task (mean = 2.55s, std = 0.1002s) to no-task (mean = 2.55s, std = 0.1002s). Game scoring followed three profiles/phases: learning, saturation, and decline profile. From the profiles, it is possible to quantify/infer drivers’ engagement with the game task. The paper proposes alternative monitoring that has utility, i.e., entertaining the user. Further experiments AR-Game focusing on real-world car environment will be performed to confirm the performance following the recommendations derived from the current test.

scholarly journals EGAT: Extended Graph Attention Network for Pedestrian Trajectory Prediction

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Wei Kong ◽  
Yun Liu ◽  
Hui Li ◽  
Chuanxu Wang
Keyword(s):  
Receptive Field ◽  
Autonomous Driving ◽  
Trajectory Prediction ◽  
Robot Interaction ◽  
Correct Judgment ◽  
Attention Network ◽  
Temporal Domain ◽  
Wide Range ◽  
Public Datasets ◽  
Extended Graph

To improve foresight and make correct judgment in advance, pedestrian trajectory prediction has a wide range of application values in autonomous driving, robot interaction, and safety monitoring. However, most of the existing methods only focus on the interaction of local pedestrians according to distance, ignoring the influence of far pedestrians; the range of network input (receptive field) is small. In this paper, an extended graph attention network (EGAT) is proposed to increase receptive field, which focuses not only on local pedestrians, but also on those who are far away, to further strengthen pedestrian interaction. In the temporal domain, TSG-LSTM (TS-LSTM and TG-LSTM) and P-LSTM are proposed based on LSTM to enhance information transmission by residual connection. Compared with state-of-the-art methods, the model EGAT achieves excellent performance on both ETH and UCY public datasets and generates more reliable trajectories.

scholarly journals Graph Contextualized Self-Attention Network for Session-based Recommendation

2019 ◽  
Author(s):  
Chengfeng Xu ◽  
Pengpeng Zhao ◽  
Yanchi Liu ◽  
Victor S. Sheng ◽  
Jiajie Xu ◽  
...  
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Attention Mechanism ◽  
The Self ◽  
Graph Structure ◽  
Convolutional Network ◽  
Attention Network ◽  
Attention Model ◽  
Sequence Modeling ◽  
Real World Datasets

Session-based recommendation, which aims to predict the user's immediate next action based on anonymous sessions, is a key task in many online services (e.g., e-commerce, media streaming).  Recently, Self-Attention Network (SAN) has achieved significant success in various sequence modeling tasks without using either recurrent or convolutional network. However, SAN lacks local dependencies that exist over adjacent items and limits its capacity for learning contextualized representations of items in sequences.  In this paper, we propose a graph contextualized self-attention model (GC-SAN), which utilizes both graph neural network and self-attention mechanism, for session-based recommendation. In GC-SAN, we dynamically construct a graph structure for session sequences and capture rich local dependencies via graph neural network (GNN).  Then each session learns long-range dependencies by applying the self-attention mechanism. Finally, each session is represented as a linear combination of the global preference and the current interest of that session. Extensive experiments on two real-world datasets show that GC-SAN outperforms state-of-the-art methods consistently.

scholarly journals An Improved Semisupervised Outlier Detection Algorithm Based on Adaptive Feature Weighted Clustering

2016 ◽  
Vol 2016 ◽  
pp. 1-14 ◽  
Author(s):  
Tingquan Deng ◽  
Jinhong Yang
Keyword(s):  
Outlier Detection ◽  
Real World ◽  
Detection Algorithm ◽  
Membership Degree ◽  
Weighted Clustering ◽  
Detection Strategy ◽  
Series Of Experiments ◽  
Effectiveness And Efficiency ◽  
Real World Datasets ◽  
Normal Object

There exist already various approaches to outlier detection, in which semisupervised methods achieve encouraging superiority due to the introduction of prior knowledge. In this paper, an adaptive feature weighted clustering-based semisupervised outlier detection strategy is proposed. This method maximizes the membership degree of a labeled normal object to the cluster it belongs to and minimizes the membership degrees of a labeled outlier to all clusters. In consideration of distinct significance of features or components in a dataset in determining an object being an inlier or outlier, each feature is adaptively assigned different weights according to the deviation degrees between this feature of all objects and that of a certain cluster prototype. A series of experiments on a synthetic dataset and several real-world datasets are implemented to verify the effectiveness and efficiency of the proposal.

scholarly journals Attention-Guide Walk Model in Heterogeneous Information Network for Multi-Style Recommendation Explanation

2020 ◽  
Vol 34 (04) ◽  
pp. 6275-6282
Author(s):  
Xin Wang ◽  
Ying Wang ◽  
Yunzhi Ling
Keyword(s):  
Real World ◽  
Attention Mechanism ◽  
Information Network ◽  
Heterogeneous Information Network ◽  
Heterogeneous Information ◽  
Real World Datasets ◽  
Joint Representation ◽  
Interactive Factors ◽  
Explainable Recommendation ◽  
Interaction Relations

Explainable Recommendation aims at not only providing the recommended items to users, but also making users aware why these items are recommended. Too many interactive factors between users and items can be used to interpret the recommendation in a heterogeneous information network. However, these interactive factors are usually massive, implicit and noisy. The existing recommendation explanation approaches only consider the single explanation style, such as aspect-level or review-level. To address these issues, we propose a framework (MSRE) of generating the multi-style recommendation explanation with the attention-guide walk model on affiliation relations and interaction relations in the heterogeneous information network. Inspired by the attention mechanism, we determine the important contexts for recommendation explanation and learn joint representation of multi-style user-item interactions for enhancing recommendation performance. Constructing extensive experiments on three real-world datasets verifies the effectiveness of our framework on both recommendation performance and recommendation explanation.

scholarly journals Dynamic graph convolutional networks with attention mechanism for rumor detection on social media

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0256039
Author(s):  
Jiho Choi ◽  
Taewook Ko ◽  
Younhyuk Choi ◽  
Hyungho Byun ◽  
Chong-kwon Kim
Keyword(s):  
Social Media ◽  
Real World ◽  
Structural Information ◽  
Attention Mechanism ◽  
Temporal Information ◽  
Detection Methods ◽  
Dynamic Graph ◽  
Convolutional Networks ◽  
Real World Datasets ◽  
Rumor Detection

Social media has become an ideal platform for the propagation of rumors, fake news, and misinformation. Rumors on social media not only mislead online users but also affect the real world immensely. Thus, detecting the rumors and preventing their spread became an essential task. Some of the recent deep learning-based rumor detection methods, such as Bi-Directional Graph Convolutional Networks (Bi-GCN), represent rumor using the completed stage of the rumor diffusion and try to learn the structural information from it. However, these methods are limited to represent rumor propagation as a static graph, which isn’t optimal for capturing the dynamic information of the rumors. In this study, we propose novel graph convolutional networks with attention mechanisms, named Dynamic GCN, for rumor detection. We first represent rumor posts with their responsive posts as dynamic graphs. The temporal information is used to generate a sequence of graph snapshots. The representation learning on graph snapshots with attention mechanism captures both structural and temporal information of rumor spreads. The conducted experiments on three real-world datasets demonstrate the superiority of Dynamic GCN over the state-of-the-art methods in the rumor detection task.

scholarly journals Improved Coupled Tensor Factorization with Its Applications in Health Data Analysis

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-16 ◽  
Author(s):  
Qing Wu ◽  
Jie Wang ◽  
Jin Fan ◽  
Gang Xu ◽  
Jia Wu ◽  
...  
Keyword(s):  
Data Fusion ◽  
Real World ◽  
Simulated Data ◽  
Joint Analysis ◽  
Tensor Factorization ◽  
Real World Data ◽  
Series Of Experiments ◽  
Tensor Factorizations ◽  
Real World Datasets ◽  
Improved Accuracy

Coupled matrix and tensor factorizations have been successfully used in many data fusion scenarios where datasets are assumed to be exactly coupled. However, in the real world, not all the datasets share the same factor matrices, which makes joint analysis of multiple heterogeneous sources challenging. For this reason, approximate coupling or partial coupling is widely used in real-world data fusion, with exact coupling as a special case of these techniques. However, to fully address the challenge of tensor factorization, in this paper, we propose two improved coupled tensor factorization methods: one for approximately coupled datasets and the other for partially coupled datasets. A series of experiments using both simulated data and three real-world datasets demonstrate the improved accuracy of these approaches over existing baselines. In particular, when experiments on MRI data is conducted, the performance of our method is improved even by 12.47% in terms of accuracy compared with traditional methods.

Fast Euclidean Cluster Extraction Using GPUs

2020 ◽  
Vol 32 (3) ◽  
pp. 548-560
Author(s):  
Anh Nguyen ◽  
Abraham Monrroy Cano ◽  
Masato Edahiro ◽  
Shinpei Kato ◽  
◽  
...  
Keyword(s):  
Real World ◽  
Graphics Processing Units ◽  
Point Cloud ◽  
Autonomous Driving ◽  
Input Dataset ◽  
Computationally Expensive ◽  
Real World Datasets ◽  
Graphics Processing

Clustering is the task of dividing an input dataset into groups of objects based on their similarity. This process is frequently required in many applications. However, it is computationally expensive when running on traditional CPUs due to the large number of connections and objects the system needs to inspect. In this paper, we investigate the use of NVIDIA graphics processing units and their programming platform CUDA in the acceleration of the Euclidean clustering (EC) process in autonomous driving systems. We propose GPU-accelerated algorithms for the EC problem on point cloud datasets, optimization strategies, and discuss implementation issues of each method. Our experiments show that our solution outperforms the CPU algorithm with speedup rates up to 87X on real-world datasets.

Sign in / Sign up

Export Citation Format

Share Document