检索结果-内蒙古大学图书馆

Vehicle Check-In Data-driven POI Recommendation Based on Improved SVD and Graph Convolutional Network

学校读者我要写书评

暂无评论

Vehicle Check-In Data-driven POI Recommendation Based on Imp...

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Yuwen Liu Jie Zhang Ruihan Dou Xiaokang Zhou Xiaolong Xu Shoujin Wang Lianyong Qi College of Computer Science and Technology China University of Petroleum (East China) Qingdao China Department of Computer Science and Technology State Key Laboratory for Novel Software Technology Nanjing University China Shanghai Meteorological Information and Technology Support Center China Faculty of Mathematics University of Waterloo Waterloo Canada Faculty of Data Science Shiga University Japan RIKEN Center for Advanced Intelligence Project RIKEN Japan School of Computer and Software Nanjing University of Information Science and Technology China School of Computing Macquarie University Australia School of Computer Science Qufu Normal University China

The application of automobile tool software is becoming increasingly widespread, and its functions are becoming increasingly diverse. Using vehicle traffic data to give users with recommendations for Points-of-interest (POI) is becoming an intriguing research challenge. However, the current POI recommendation is either a sequence-based method, ignoring the interaction information between users and POIs. Or it needs a lot of model training time to use graph correlation method to mine the interaction between users or vehicles and POIs. In order to address these issues, we propose a method for vehicle check-in data-driven POI recommendation based on improved Singular Value Decomposition (SVD) and Graph Convolutional Network (GCN). First, we apply SVD to replace the neighborhood aggregation update method in traditional GCN, update the node embedding with fewer parameters and faster speed. Second, we propose an information enhancement strategy to make up for the information loss caused by the SVD. Experiments on large vehicle check-in datasets demonstrate that our method is both faster and more effective when making POI recommendations.

关键词：

Learning to Reduce Information Bottleneck for Object Detection in Aerial Images

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shen, Yuchen Zhang, Dong Song, Zhihao Jiang, Xuesong Ye, Qiaolin The College of Information Science and Technology Nanjing Forestry University Jiangsu Nanjing210037 China Key Laboratory Intelligent Information Processing Nanjing Xiaozhuang University Jiangsu Nanjing211171 China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong The College of Mechanical and Electronic Engineering Nanjing Forestry University Jiangsu Nanjing210037 China

Object detection in aerial images is a fundamental research topic in the geoscience and remote sensing domain. However, the advanced approaches on this topic mainly focus on designing the elaborate backbones or head networks but ignore neck networks. In this letter, we first underline the importance of the neck network in object detection from the perspective of information bottleneck. Then, to alleviate the information deficiency problem in the current approaches, we propose a global semantic network (GSNet), which acts as a bridge from the backbone network to the head network in a bidirectional global pattern. Compared to the existing approaches, our model can capture the rich and enhanced image features with less computational costs. Besides, we further propose a feature fusion refinement module (FRM) for different levels of features, which are suffering from the problem of semantic gap in feature fusion. To demonstrate the effectiveness and efficiency of our approach, experiments are carried out on two challenging and representative aerial image datasets (i.e., DOTA and HRSC2016). Experimental results in terms of accuracy and complexity validate the superiority of our method. The code has been open-sourced at GSNet. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

A new Technique in Protein Structure Quantitative Identification 9th

学校读者我要写书评

暂无评论

A new Technique in Protein Structure Quantitative Identifica...

9th International Conference on Information technology and Quantitative Management, ITQM 2022

作者： Guo, Mengjiao Cao, Haobin He, Jing Ji, Tengfei Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne3122 Australia Department of Mechanical Engineering University College London LondonWC1E 6BT United Kingdom Department of Neuroscience University of Oxford OxfordOX39DU United Kingdom State Key Laboratory of Bioactive Substance and Function of Natural Medicines Institute of Materia Medica Peking Union Medical College Chinese Academy of Medical Sciences Beijing100050 China

Graph distance is also named approximate graph isomorphism, error-tolerant graph matching, it is a measure of similarity (or dissimilarity) between two graphs. The graph distance function is an elusive question remaining a pressing problem in a wide range of fields. In general, graphs are usually enriched with node and edge attributes, namely, heterogeneous graphs, our focus is encapsulating node and edge identities in a graph. In addition, an adequate representation of the graph-adjacency matrix can capture the connectivity of the graph structure, while an adjacency matrix bears high-order combinatorial nature. Solving these challenges in the effective analysis of these graphs is of utmost importance. In this paper, structural and semantic features are both preserved by graphs, so the analysis of row sum and eigenspectra for vertex and edge adjacency matrix has captured the affinity interactions within graphs locally and globally. Therefore, we estimate the geometrical and semantic dissimilarities/distances between graphs extensively and systemically. Several illustrative chemical compound cases implement in practical scenarios, thus, the theory could be easily understood. Our method defines a quantitative distance (or dissimilarity) measure for comparing graphs, it has a good measure of expressiveness and a suited polynomial computation complexity, which paves the way for graph analysis. © 2022 The Authors. Published by Elsevier B.V.

关键词： Graphic methods

Room-temperature magnetoelectric effect in Al-doped Sr3Co2(Fe1-xAlx)24O41 hexaferrites

学校读者我要写书评

暂无评论

JOURNAL OF ALLOYS AND COMPOUNDS 2020年第0期820卷 153130-000页

作者： Wu, Chongsheng Liu, Yingli Liu, Qian Wang, Yu Yin, Qisheng Chen, Jianfeng Harris, Vincent G. Zhang, Huaiwu [a]State Key Laboratory of Electronic Thin Films and Integrated Devices University of Electronic Science and Technology of China Chengdu Sichuan 610054 China [b]Center for Microwave Magnetic Materials and Integrated Circuits Department of Electrical and Computer Engineering Northeastern University Boston MA 02115 USA

Here we present the results of a systematic investigation of the effect of Al doping on the roomtemperature magnetoelectric properties of Z-type hexaferrites of the composition Sr3Co2(Fe1-xAlx)(24)O-41 where x = 0, 0.02, 0.04, and 0.08. Aluminum doping is shown to stabilize the transverse conical spin structure and increase the range of magnetic fields in which the ferroelectric phase occurs for x <= 0.04. These characteristics are attributed to the favoring of the easy-axis magnetic anisotropy over the easy-plane brought about by Al doping. Furthermore, when x approaches 0.08, switching of the magnetic field leads to switching of the ferroelectric polarization, which is attributed to the transformation of the transverse conical spin structure into a new structure. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Magnetoelectric properties Ferroelectric phase Magnetic anisotropy Switching of the ferroelectric polarization

Structure-consistent Restoration Network for Cataract Fundus Image Enhancement

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Heng Liu, Haofeng Fu, Huazhu Shu, Hai Zhao, Yitian Luo, Xiaoling Hu, Yan Liu, Jiang Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China IHPC A*STAR Singapore Department of Biostatistics School of Global Public Health New York University New York United States Cixi Institute of Biomedical Engineering Chinese Academy of Sciences China Shenzhen People's Hospital Shenzhen China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China

Fundus photography is a routine examination in clinics to diagnose and monitor ocular diseases. However, for cataract patients, the fundus image always suffers quality degradation caused by the clouding lens. The degradation prevents reliable diagnosis by ophthalmologists or computer-aided systems. To improve the certainty in clinical diagnosis, restoration algorithms have been proposed to enhance the quality of fundus images. Unfortunately, challenges remain in the deployment of these algorithms, such as collecting sufficient training data and preserving retinal structures. In this paper, to circumvent the strict deployment requirement, a structure-consistent restoration network (SCR-Net) for cataract fundus images is developed from synthesized data that shares an identical structure. A cataract simulation model is firstly designed to collect synthesized cataract sets (SCS) formed by cataract fundus images sharing identical structures. Then high-frequency components (HFCs) are extracted from the SCS to constrain structure consistency such that the structure preservation in SCR-Net is enforced. The experiments demonstrate the effectiveness of SCR-Net in the comparison with state-of-the-art methods and the follow-up clinical applications. The code is available at https://***/liamheng/ArcNet-Medical-Image-Enhancement. Copyright © 2022, The Authors. All rights reserved.

关键词： Image enhancement

Differential-Critic GAN: Generating What You Want by a Cue of Preferences

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yao, Yinghua Pan, Yuangang Tsang, Ivor W. Yao, Xin Guangdong Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Australian Artificial Intelligence Institute University of Technology Sydney Australia A*STAR Center for Frontier AI Research Singapore. Australian Artificial Intelligence Institute University of Technology Sydney Australia Guangdong Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China School of Computer Science University of Birmingham United Kingdom

This paper proposes Differential-Critic Generative Adversarial Network (DiCGAN) to learn the distribution of user-desired data when only partial instead of the entire dataset possesses the desired property. DiCGAN generates desired data that meets the user’s expectations and can assist in designing biological products with desired properties. Existing approaches select the desired samples first and train regular GANs on the selected samples to derive the user-desired data distribution. However, the selection of the desired data relies on global knowledge and supervision over the entire dataset. DiCGAN introduces a differential critic that learns from pairwise preferences, which are local knowledge and can be defined on a part of training data. The critic is built by defining an additional ranking loss over the Wasserstein GAN’s critic. It endows the difference of critic values between each pair of samples with the user preference and guides the generation of the desired data instead of the whole data. For a more efficient solution to ensure data quality, we further reformulate DiCGAN as a constrained optimization problem, based on which we theoretically prove the convergence of our DiCGAN. Extensive experiments on a diverse set of datasets with various applications demonstrate that our DiCGAN achieves state-of-the-art performance in learning the user-desired data distributions, especially in the cases of insufficient desired data and limited supervision. The code is available in https://***/EvaFlower/Differential-Critic-GAN. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

Robust Multi-Modal Pedestrian Detection Using Deep Convolutional Neural Network with Ensemble Learning Model

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Jain, Deepak Kumar Zhao, Xudong Garcia, Salvador Neelakandan, Subramani Chongqing University China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China School of Artificial Intelligence Dalian116024 China DaSCI Andalusian Research Institute University of Granada Granada Spain Department of Computer Science and Engineering R.M.K Engineering College 601206 India

In the realm of video surveillance systems, pedestrian detection (PD) is a crucial task that enables the identification and tracking of individuals, crowd monitoring, and people counting. However, accurate PD is a challenging task due to variations in the appearance and pose of pedestrians. With the advent of deep learning (DL) techniques, particularly convolutional neural networks (CNNs), computer vision (CV) methods for object classification and detection have been revolutionized. Successful PD depends on supervised learning, which necessitates large labeled datasets. This paper proposes a Robust Multi-modal Pedestrian Detection using a Deep Convolutional Neural Network with an Ensemble Learning (RMPD-DCNNEL) model to address the challenges of PD. This model leverages computer vision and ensemble learning to achieve accurate pedestrian detection. The SimAM-EfficientNet model with a stochastic gradient descent (SGD) optimizer is utilized for feature extraction, while ensemble classification is performed using three DL models: nested long short-term memory (NLSTM), deep belief networks (DBNs), and extreme learning machine (ELM).To evaluate the effectiveness of the proposed approach, we use the INRIA dataset, and the experimental results demonstrate the superior performance of RMPD-DCNNEL over other DL approaches. The proposed technique enables robust pedestrian detection despite variations in appearance and pose, making it an effective solution for video surveillance systems in smart transportation environments. © 2023, The Authors. All rights reserved.

关键词： Learning systems

GRATIS: Deep Learning Graph Representation with Task-specific Topology and Multi-dimensional Edge Features

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Song, Siyang Song, Yuxin Luo, Cheng Song, Zhiyuan Kuzucu, Selim Jia, Xi Guo, Zhijiang Xie, Weicheng Shen, Linlin Gunes, Hatice The Department of Computer Science and Technology University of Cambridge CambridgeCB3 0FT United Kingdom Baidu Inc Beijing100193 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China Department of Computer Engineering Middle East Technical University Ankara Turkey School of Computer Science University of Birmingham Birmingham United Kingdom

Graph is powerful for representing various types of real-world data. The topology (edges’ presence) and edges’ features of a graph decides the message passing mechanism among vertices within the graph. While most existing approaches only manually define a single-value edge to describe the connectivity or strength of association between a pair of vertices, task-specific and crucial relationship cues may be disregarded by such manually defined topology and single-value edge features. In this paper, we propose the first general graph representation learning framework (called GRATIS) which can generate a strong graph representation with a task-specific topology and task-specific multi-dimensional edge features from any arbitrary input (i.e., graph or non-graph data). To learn each edge’s presence and multi-dimensional feature, our framework takes both of the corresponding vertices pair and their global contextual information into consideration, enabling the generated graph representation to have a globally optimal message passing mechanism for different down-stream tasks. The principled investigation results achieved for various graph analysis tasks (e.g., graph classification, vertex classification, and link prediction) on 11 graph and non-graph datasets show that our GRATIS can not only largely enhance pre-defined graphs but also learns a strong graph representation for non-graph data, with clear performance improvements on all tasks. In particular, the learned topology and multi-dimensional edge features provide complementary task-related cues for graph analysis tasks. Our framework is effective, robust and flexible, and is a plug-and-play module that can be combined with different backbones and Graph Neural Networks (GNNs) to generate a task-specific graph representation from various graph and non-graph data. Our code is made publicly available at https://***/SSYSteve/Learning-Graph-Representation-with-Task-specific-Topology-and-Multi-dimensional-Edge-Feature

关键词： Graph neural networks

An Improved YOLOv5 Detection Method for Strip Surface Defect

学校读者我要写书评

暂无评论

An Improved YOLOv5 Detection Method for Strip Surface Defect

International Conference on Automation and Computing (ICAC)

作者： Yefeng Liu Longfei Yu Qichun Zhang dept. Liaoning Key Laboratory of Information Physical Fusion and Intelligent CNC Machine Tool Manufacturing Shenyang Institute of Technology dept. School of Automation and Electrical Fushun China dept. School of Automation and Electrica Engineering Shenyang Ligong University dept. Department of Computer Science University of Bradford Bradford U. K.

Traditional steel surface defect detection methods have issues such as low detection accuracy and efficiency. It is suggested a technique based on enhanced YOLOv5 steel surface fault identification. In order to improve the network's capacity to handle feature information, this study suggests adding SE attention mechanisms to the YOLOv5s network's Backbone, Neck, and SPPF and replacing the C3 structure at the end of the Backbone with C3TR. To achieve network model lightweight, it is proposed to replace the Neck part in the YOLOv5s model and the convolution in SPPF with Ghost convolution. Then, to improve network feature fusion, extend the improved SPPF to the Neck part. Introduce the SPD convolution in the Backbone section to reduce the information loss caused by the neural network's convolution. The tested mAP is 75.3%, which is 5.3% higher than the original model, 24.6% higher than the SSD method, and 4.6% higher than the YOLOv6 algorithm after the upgraded model has been trained on the NEU-DET dataset. The observed FPS is 81.3, which is 6.3 more than the relative literature algorithm and 18.0 more than the SSD algorithm.

关键词：