检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhao, Shengda Liu, Zhekun Yu, Jiaxin Ju, Bocheng Wang, Liang Zhang, Xiaodong Zhang, Xinghua School of Physical Sciences and Engineering Beijing Jiaotong University Haidian District Beijing100044 China Beijing Key Laboratory of Novel Materials Genetic Engineering and Application for Rail Transit Beijing Jiaotong University Haidian District Beijing100044 China School of Computer Science and Technology Beijing Jiaotong University Haidian District Beijing100044 China National School of Elite Engineers Beijing Jiaotong University Haidian District Beijing100044 China Beijing Municipal Institute of City Planning & Design Xicheng District Beijing100045 China

In the context of accelerating urbanization and increasingly severe traffic congestion, optimizing traffic signal systems to enhance road throughput and reduce congestion has become a critical issue that requires attention. This study proposes a short-term traffic situation prediction model based on real-world road topologies and a typical four-way, eight-phase traffic signal control scheme. The model takes into account the traffic flow disparities across different directions and the frequency of signal phase changes, integrating these factors into an optimization objective function aimed at achieving global optimization of urban traffic. The structure of this objective function is analogous to the spin-glass systems in statistical physics. For this model, a Simulated Bifurcation optimization algorithm is introduced, with traditional simulated annealing optimization methods used as a benchmark. The results demonstrate that the Simulated Bifurcation algorithm outperforms simulated annealing in terms of both efficiency and effectiveness. Using real traffic flow and road network data from Beijing, we initialized the model and conducted numerical optimization experiments. The experimental results indicate that the Simulated Bifurcation algorithm significantly outperforms simulated annealing in terms of computational efficiency, effectively addressing combinatorial optimization problems in systems with multiple spin interactions, and reducing the time complexity of the problem to O(N1.35). This successful solution addresses the NP-hard problem of global traffic signal optimization. More importantly, the signal phase patterns generated by the Simulated Bifurcation algorithm are fully compatible with the operational requirements of actual traffic signal systems, showcasing its enormous potential and applicability in optimizing signal control in real-world traffic networks, especially for large, complex urban traffic systems. This work provides strong theoretical support an

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

St-Kan-Former: A novel Spatiotemporal Transformer Neural Network for Air Quality Prediction

SSRN

引用

SSRN 2025年

作者： Zhang, Wenyong Xia, Dawen Chang, Guoyan Zheng, Zhiquan Hu, Yang Huo, Yujia Wang, Ziqiang Feng, Fujian Li, Yantao Li, Huaqing College of Data Science and Information Engineering Guizhou Minzu University Guiyang550025 China School of Computer Science and Engineering South China University of Technology Guangzhou510006 China Engineering Research Center of Micro-nano and Intelligent Manufacturing Ministry of Education Kaili University Kaili556011 China Affiliated Hospital of Guizhou Medical University Guiyang550001 China State Key Laboratory of Public Big Data Guizhou University Guiyang550008 China College of Computer Science Chongqing University Chongqing400044 China College of Electronic and Information Engineering Southwest University Chongqing400715 China

Accurate and timely air quality prediction is important for supporting daily activities and safeguarding respiratory health. However, the complex aerodynamic properties of air pollutants pose significant challenges to accurate air quality prediction. Most existing spatiotemporal prediction models extract spatial features in a coarse-grained manner, which cannot fully utilize the spatial feature data, resulting in poor prediction accuracy. To this end, we propose a novel air quality prediction method based on a Spatiotemporal Transformer with a Kolmogorov-Arnold Network (ST-KAN-Former). Specifically, in the temporal dimension, we use the wavelet transform, KAN, and ProbAttention network to construct the temporal feature extraction model. Based on this, the temporal dimension data are decomposed into high-frequency and low-frequency components, and then feature extraction is performed for fine-grained acquisition of temporal dimension features. Then, in the spatial dimension, we divide the spatial region into four subregions according to the distance parameter between the master site and the slave site and build a spatial feature extraction model for each subregion using KAN and ProbAttention networks. Next, we simulate the attenuation of pollutants during their dispersion to introduce the concept of diffusion coefficients. This approach allows us to apply diffusion processing to data from each subregion, enabling a finer granularity in capturing spatial characteristics. Finally, we employ the KAN and ProbAttention networks to construct a spatiotemporal feature fusion model that integrates temporal and spatial characteristics. Extensive experiments on the Beijing dataset demonstrate that ST-KAN-Former achieves better results compared with the other 11 benchmarks. © 2025, The Authors. All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Semi-supervised Classification Method for Hyperspectral Images by Triple Classifiers with Data Editing and Deep Learning 1

引用

9th EAI International Conference on Cloud Computing, CloudComp 2019 and the 4th EAI International Conference on Smart Grid and Innovative Frontiers in Telecommunications, SmartGIFT 2019

作者： Zhang, Guoming Wang, Junshu Shi, Ge Zhang, Jie Dou, Wanchun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Health Statistics and Information Center of Jiangsu Province Nanjing China Key Laboratory for Virtual Geographic Environment Ministry of Education Nanjing Normal University Nanjing China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing China

ISBN: (数字)9783030485139

ISBN: (纸本)9783030485122

A semi-supervised classification method for hyperspectral remote sensing images based on convolutional neural network (CNN) and modified tri-training is proposed. The abstract features are captured by training a CNN model with the pixels’ vectors as inputs. Based on the extracted high-level features, different classifiers will perform different outputs under the same training set, due to the different types of classifiers take on diverse characteristics. Thus, taking multiple classifiers’ results into consideration can integrate different prediction labels synthetically from a high level and can perform more credible results. At the meantime, the number of training samples of hyperspectral images is limited, which will hinder the classification effect. Illuminated by tri-training algorithm, we utilize triple different classifiers to classify the hyperspectral images based on the extracted high-level features in the semi-supervised mode. By utilizing triple classifiers jointly to train and update the training samples set when the number of labeled samples is limited. At the meantime, we pick the confident samples via randomize and majority vote into the training set for data editing during the iterative updating process. Experiments performed on two real hyperspectral images reveal that our method performs very well in terms of classification accuracy and effect. © 2020, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A calcium imaging large dataset reveals novel functional organization in macaque V4

arXiv

引用

arXiv 2023年

作者： Wang, Tianye Yao, Haoxuan Lee, Tai Sing Hong, Jiayi Li, Yang Jiang, Hongfei Andolina, Ian Max Tang, Shiming Peking University School of Life Sciences Beijing China Peking‐Tsinghua Center for Life Sciences Beijing China IDG/McGovern Institute for Brain Research Peking University Beijing China Peking University Beijing China Center for the Neural Basis of Cognition and Computer Science Department Carnegie Mellon University Pittsburgh United States The Center for Excellence in Brain Science and Intelligence Technology State Key Laboratory of Neuroscience Key Laboratory of Primate Neurobiology Institute of Neuroscience Chinese Academy of Sciences Shanghai China

The topological organization and feature preferences of primate visual area V4 have been primarily studied using artificial stimuli. Here, we combined large‐scale calcium imaging with deep learning methods to characterize and understand how V4 processes natural images. By fitting a deep learning model to an unprecedentedly large dataset of columnar scale cortical responses to tens of thousands of natural stimuli and using the model to identify the images preferred by each cortical pixel, we obtained a detailed V4 topographical map of natural stimulus preference. The map contains distinct functional domains preferring a variety of natural image features, ranging from surface‐related features such as color and texture to shape‐related features such as edge, curvature, and facial features. These predicted domains were verified by additional widefield calcium imaging and single‐cell resolution two‐photon imaging. Our study reveals the systematic topological organization of V4 for encoding image features in natural scenes. © 2023, CC BY-NC-SA.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Revisiting Token Dropping Strategy in Efficient BERT Pretraining

arXiv

引用

arXiv 2023年

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Liu, Xuebo Zhang, Min Du, Bo Tao, Dacheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China JD Explore Academy China Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Wuhan University China Institute of Computing and Intelligence Harbin Institute of Technology China University of Sydney Australia

Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers. It can effectively reduce the training time without degrading much performance on downstream tasks. However, we empirically find that token dropping is prone to a semantic loss problem and falls short in handling semantic-intense tasks (§2). Motivated by this, we propose a simple yet effective semantic-consistent learning method (SCTD) to improve the token dropping. SCTD aims to encourage the model to learn how to preserve the semantic information in the representation space. Extensive experiments on 12 tasks show that, with the help of our SCTD, token dropping can achieve consistent and significant performance gains across all task types and model sizes. More encouragingly, SCTD saves up to 57% of pretraining time and brings up to +1.56% average improvement over the vanilla token dropping. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Semantic Prior Distillation with Vision Foundation Model for Enhanced Rapid Bone Scintigraphy Image Restoration

arXiv

引用

arXiv 2025年

作者： Liang, Pengchen Shi, Leijun Yao, Huiping Pu, Bin Chen, Jianguo Zhao, Lei Huang, Haishan Chen, Zhuangzhuang Xu, Zhaozhao Xu, Lite Chang, Qing Li, Yiwei Department of Nuclear Medicine Shanghai Children’s Hospital School of Medicine Shanghai Jiao Tong University Shanghai200062 China School of Microelectronics Shanghai University Shanghai201800 China Department of Ophthalmology Ruijin Hospital Shanghai Jiao Tong University School of Medicine Shanghai201800 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology 999077 Hong Kong School of Software Engineering Sun Yat-sen University Guangdong Province Zhuhai519000 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China School of Computer Science and Technology Henan Polytechnic University Henan Jiaozuo454000 China Department Shanghai Key Laboratory of Gastric Neoplasms Department of Surgery Shanghai Institute of Digestive Surgery Ruijin Hospital Shanghai Jiao Tong University School of Medicine Shanghai201800 China

Rapid bone scintigraphy is an essential tool for diagnosing skeletal diseases and tumor metastasis in pediatric patients, as it reduces scan time and minimizes patient discomfort. However, rapid scans often result in poor image quality, potentially affecting diagnosis due to reduced resolution and detail, which make it challenging to identify and evaluate finer anatomical structures. To address this issue, we propose the first application of SAM-based semantic priors for medical image restoration, leveraging the Segment Anything Model (SAM) to enhance rapid bone scintigraphy images in pediatric populations. Our method comprises two cascaded networks, fIR1 and fIR2, augmented by three key modules: a Semantic Prior Integration (SPI) module, a Semantic Knowledge Distillation (SKD) module, and a Semantic Consistency Module (SCM). The SPI and SKD modules incorporate domain-specific semantic information from a fine-tuned SAM, while the SCM maintains consistent semantic feature representation throughout the cascaded networks. In addition, we will release a novel Rapid Bone Scintigraphy dataset called RBS, the first dataset dedicated to rapid bone scintigraphy image restoration in pediatric patients. RBS consists of 137 pediatric patients aged between 0.5 and 16 years who underwent both standard and rapid bone scans. The dataset includes scans performed at 20 cm/min (standard) and 40 cm/min (rapid), representing a 2× acceleration. We conducted extensive experiments on both the publicly available endoscopic dataset and RBS. The results demonstrate that our method outperforms all existing methods across various metrics, including PSNR, SSIM, FID, and LPIPS. Copyright © 2025, The Authors. All rights reserved.

关键词： Pediatrics

来源：评论

学校读者我要写书评

暂无评论

MW-GAN: Multi-Warping GAN for Caricature Generation with Multi-Style Geometric Exaggeration

arXiv

引用

arXiv 2020年

作者： Hou, Haodi Huo, Jing Wu, Jing Lai, Yu-Kun Gao, Yang The State Key Laboratory for Novel Software Technology Nanjing University No. 163 Xianlin Avenue Jiangsu Nanjing210023 China The School of Computer Science & Informatics Cardiff University United Kingdom

Given an input face photo, the goal of caricature generation is to produce stylized, exaggerated caricatures that share the same identity as the photo. It requires simultaneous style transfer and shape exaggeration with rich diversity, and meanwhile preserving the identity of the input. To address this challenging problem, we propose a novel framework called Multi-Warping GAN (MW-GAN), including a style network and a geometric network that are designed to conduct style transfer and geometric exaggeration respectively. We bridge the gap between the style/landmark space and their corresponding latent code spaces by a dual way design, so as to generate caricatures with arbitrary styles and geometric exaggeration, which can be specified either through random sampling of latent code or from a given caricature sample. Besides, we apply identity preserving loss to both image space and landmark space, leading to a great improvement in quality of generated caricatures. Experiments show that caricatures generated by MW-GAN have better quality than existing methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Partial Multi-label Learning

Semi-Supervised Partial Multi-label Learning

引用

IEEE International Conference on Data Mining (ICDM)

作者： Ming-Kun Xie Sheng-Jun Huang College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIlT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China

ISBN: (数字)9781728183169

ISBN: (纸本)9781728183176

Partial multi-label learning (PML) deals with problems where each instance is associated with a candidate label set, which contains multiple relevant labels and some noisy labels. In many real-world scenarios, it is impractical to annotate all examples for a huge-size dataset. Instead, a more common case is that only a small set of the data are annotated with partial labels, while most data are unlabeled. In this paper, we formalize such problems as a new learning framework called Semi-Supervised Partial Multi-label Learning (SSPML). To solve the SSPML problem, a latent label variable is introduced for each example as the low-dimensional embedding of the feature space. On one hand, label variables are recovered by encouraging consistent similarity measurement between the feature space and the label space; on the other hand, the similarities are adaptively updated based on the feedback from the label space. Meanwhile, the multi-label classifier is jointly trained under the supervision of label variables. Extensive experiments on multiple datasets from various real-world tasks validate the effectiveness of the proposed approach.

关键词： Weight measurement Measurement uncertainty Prediction algorithms Extraterrestrial measurements Noise measurement Data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Private Estimation of Symptom Distribution for Infectious Disease Analysis in Edge Computing

Private Estimation of Symptom Distribution for Infectious Di...

引用

IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC

作者： Xiaotong Wu Xiaolong Xu Shaohua Wan Lianyong Qi State Key Lab. for Novel Software Technology Nanjing University P.R. China School of Computer and Electronic Information Nanjing Normal University P.R. China School of Computer and Software Nanjing University of Information Science & Technology P.R. China School of Information and Safety Engineering Zhongnan University of Economics and Law P.R. China School of Information Science and Engineering Qufu Normal University PR. China

ISBN: (纸本)9781665400374

Distribution estimation of physical symptom is a powerful statistical technique to monitor and predict the situation of infectious diseases. With the widespread popularization of smart devices, edge computing is an efficient computing paradigm, which takes advantage of these devices to implement the safe and fast collection and distribution analysis of physical symptoms. However, the sharing of individuals' data, especially of sensitive information (e.g., age, symptom), inevitably raises the great privacy concerns of people due to the possible leakage and the illegal utilization. It is necessary and important to not only implement the highly intelligent epidemic analysis, but also guarantee the privacy of data. In this paper, we focus on locally private distribution estimation of physical symptom with attribute constraints in edge computing. At first, we present an edge-computing-based framework for distribution estimation of physical symptoms, in which each component undertakes the respective task. Then, we propose a naive privacy algorithm, i.e., NAIVEPRIVDISTEST, to directly perturb the values of quasi-identifying attributes and physical symptoms. Finally, extensive experiments demonstrate that NAIVEPRIVDISTEST has the accurate distribution estimation under the privacy constraints.

关键词： Privacy Data privacy Infectious diseases Estimation Ubiquitous computing Smart devices Computational complexity

来源：评论

学校读者我要写书评

暂无评论

IO dependent SSD cache allocation for elastic Hadoop applications

引用

science China(Information sciences) 2018年第5期61卷 55-71页

作者： Zhen TANG Wei WANG Lei SUN Yu HUANG Heng WU Jun WEI Tao HUANG State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Tianjin Massive Data Processing Technology Laboratory Tianjin Shenzhou General Data Technology Co. Ltd. State Key Laboratory for Novel Software Technology Nanjing University

Elastic Hadoop applications consisting of multiple virtual machines(VMs) are widely used to support big data analysis and processing. In this scenario, flash-based solid state drive(SSD) is usually deployed on hypervisors and used as the cache to improve the IO performance. However, existing SSD caching schemes are mostly VM-centric, which focus on the low-level IO performance metrics of individual VMs. They may not lead to the optimized performance of elastic Hadoop applications, i.e., the job completion time(JCT), as the importance of VMs inside the application are different even though they have the similar low-level IO patterns. Considering the IO dependency among VMs and figuring out the importance, which we regard as the application-centric metrics, may potentially better improve the performance. We present IO dependency based requirement model, to characterize the requirement of SSD cache for each VM inside the elastic Hadoop application, and then use it in a genetic algorithm(GA) based approach to calculate the nearly optimal weights of VMs for allocating the per-VM SSD cache space and the capacity of the I/O operations per second(IOPS). Furthermore, we present a tool AC-SSD based on the approach and introduce the closed-loop adaptation to react to continuously changing workloads. The evaluation shows that by using AC-SSD, the JCT is reduced by up to 39% for IO sensitive workloads, up to 29% for continuously changing workloads, and over 12.5% for different scale of data comparing to the shared cache.

关键词： Hadoop SSD cache resource management virtualization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：