检索结果-内蒙古大学图书馆

Time-aware bike flow prediction framework with dynamic edge fusion and memory integration

Knowledge-Based Systems 2025年 322卷

作者： M.Rajeh, Taha Li, Tianrui Luo, Zhpeng Javed, Muhammad Hafeez Alhaek, Fares School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China Stirling College Chengdu University Chengdu610106 China Computing Science Faculty of Natural Sciences University of Stirling StirlingFK9 4LA United Kingdom

Bike-Sharing Systems (BSSs) have become a popular solution to urban sustainability concerns, providing affordable and environmentally friendly transportation. However, modeling and predicting shared-bike flow patterns are essential for developing intelligent transportation systems and facilitating city management. Despite the existence of several inflow and outflow prediction models, certain unresolved issues remain, including the inability to differentiate and capture heterogeneous dynamic relationships within daily flows, and the suboptimal utilization of historical flow data for forecasting. To address these limitations, we propose MVRC (Multi-View Relational Framework based on Clustering), a novel deep-learning framework for precise inflow and outflow prediction. The MVRC framework models three types of heterogeneous dynamic flow relationships during different periods of the day. Initially, we introduce a novel clustering method to group nearby stations exhibiting similar patterns, followed by creating a dynamic memory module to store and update edge attributes based on the time of day. Furthermore, the dynamic edge fusion mechanism effectively integrates heterogeneous, time-evolving flow features, capturing their varying impacts. To further enhance the model's capabilities, an offline component that leverages historical data is incorporated, improving performance during testing. Extensive experiments conducted on real datasets from New York City and Washington, D.C., demonstrate the superior prediction efficiency and framework effectiveness of the MVRC framework compared to existing state-of-the-art techniques. These results highlight the practicality and efficacy of MVRC in terms of prediction accuracy and stability. © 2025

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Robust optimization for quantum reinforcement learning control using partial observations

引用

Physical Review A 2022年第6期105卷 062443-062443页

作者： Chen Jiang Yu Pan Zheng-Guang Wu Qing Gao Daoyi Dong State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control College of Control Science and Engineering Zhejiang University Hangzhou 310027 China The School of Automation Science and Electrical Engineering and Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing 100191 China The School of Engineering and Information Technology University of New South Wales Canberra Australian Capital Territory 2600 Australia

The current quantum reinforcement learning control models often assume that the quantum states are known a priori for control optimization. However, full observation of the quantum state is experimentally infeasible due to the exponential scaling of the number of required quantum measurements on the number of qubits. In this paper, we investigate a robust reinforcement learning method using partial observations to overcome this difficulty. This control scheme is compatible with near-term quantum devices, where the noise is prevalent and predetermining the dynamics of the quantum state is practically impossible. We show that this simplified control scheme can achieve similar or even better performance when compared to the conventional methods relying on full observation. We demonstrate the effectiveness of this scheme on examples of quantum state control and the quantum approximate optimization algorithm (QAOA). It has been shown that high-fidelity state control can be achieved even if the noise amplitude is at the same level as the control amplitude. Besides, an acceptable level of optimization accuracy can be achieved for a QAOA with a noisy control Hamiltonian. This robust control optimization model can be trained to compensate for the uncertainties in practical quantum computing.

关键词： Machine learning Quantum control Quantum engineering

来源：评论

学校读者我要写书评

暂无评论

An intelligent Resource Scheduling Method with Edge Channel Deployment for BPM

An Intelligent Resource Scheduling Method with Edge Channel ...

引用

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

作者： Bowen Liu Wanchun Dou Xiaokang Zhou Xuyun Zhang Lianyong Qi Fei Dai Chaochao Chen State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Faculty of Data Science Shiga University Hikone Japan Department of Computing Macquarie University Sydney Australia College of Computer and Software China University of Petroleum (East China) Qingdao China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China College of Computer Science and Technology Zhejiang University Hangzhou China

Edge computing is a novel computing paradigm that offers kinds of resources at the network edge. In edge computing, terminal users are connected to edge servers via the wireless network and there are various channels in each wireless link. These wireless channels are limited resource while different channel has different cost and service ability. The dynamic changes of users’ status make it harder to find an appropriate method to satisfy the BPM requirements of channel deployment. With this observation, it is a tricky challenge to make a trade-off between the system cost(rental price) and the service ability(number of users). In view of this challenge, an intelligent resource scheduling method, named EdgeIRS, is proposed in this paper. In the technical sense, the EdgeIRS method can accommodate most users at the edge with a minimum cost of deploying channel resources in an online way. Its performance is analyzed theoretically and the experiments verify the superiority of the method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chronic Disease Detection Via Non-negative Latent Feature Analysis

Chronic Disease Detection Via Non-negative Latent Feature An...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Leming Zhou Qing Li Mingsheng Shang College of Computer Science and Technology Chongqing University of Posts and Telecommunications Academy of Sciences Chongqing China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China

ISBN: (纸本)9781665440493

Chronic diseases such as coronary heart disease (CHD) are of significant harm to human health. However, chronic disease detection commonly relies on many examinations to implement reliable diagnosis, resulting in a fatal delay in therapy. On the other hand, obtained examination data are often incomplete with numerous missing data, which further increases the difficulty in detection. To address this issue, this paper develops an inherently non-negative latent feature analysis-incorporating into a chronic disease detection (INC) model. The main idea are as follows: 1) adopting an inherently non-negative latent feature analysis model with a non-linear function to extract the non-negative latent features from incomplete examination data for accurate prediction of the unknown missing ones; 2) detecting the chronic disease based on the high-dimensional and different types of inspection features via classifiers. Experiments on actual CHD datasets demonstrate that the proposed INC model outperforms state-of-the-art models in detection accuracy, which well fits the desire of preliminary screening on coronary heart disease (CHD).

关键词： Learning systems Heart Representation learning Analytical models Predictive models Feature extraction data models

来源：评论

学校读者我要写书评

暂无评论

Deep learning radiomics model related with genomics phenotypes for pathological complete response prediction in locally advanced rectal cancer under neoadjuvant chemoradiotherapy

Deep learning radiomics model related with genomics phenotyp...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Ye Wang Zhen Pan Lanyan Lin Huajun Cai Feng Ding Chaojun Tan Dingyuan Zheng Yajun Xie Guoxian Guan Department of Colorectal Surgery The First Affiliated Hospital of Fujian Medical University Fuzhou China Department of Geriatric Medicine Fujian Key Laboratory of Geriatrics Diseases Fujian Provincial Center for Geriatrics Fuzhou University Affiliated Provincial Hospital Shengli Clinical Medical College of Fujian Medical University Fuzhou China Fujian Huaye Information Technology Co. Ltd China School of Big Data \& Key Laboratory of Data Science and Intelligent Computing Fuzhou University of International Studies and Trade Fuzhou China Department of Colorectal Surgery The First Affiliated Hospital of Fujian Medical University National Regional Medical Center Binhai Campus of the First Affiliated Hospital Fuzhou China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

Background: Developing a treatment strategy after neoadjuvant chemoradiotherapy (nCRT) based on accurate pathological complete response (pCR) predictions is crucial for locally advanced rectal cancer (LARC).Objective: To determine the effectiveness of a radiomics model using diffusion-weighted imaging (DWI) and T2-weighted in predicting post-nCRT pCR efficacy after ***: This study enrolled 237 LARC patients who had radical surgery under nCRT between February 2020 and August 2023. Tumor tissues from 54 patients were RNA sequenced. Radiomics features from preoperative MRI data were used to develop a model for deep learning via the LASSO algorithm. ROC curves were used to assess the model performance. Following Spearman's correlation, analyses of transcriptomic data were conducted to identify the genes correlated with the DPL ***: The DPL model, incorporating 7 features and 5 machine-learning algorithms, was used to create risk assessment models. The RF model excelled in predicting pCR, achieving an AUC of 0.91, accuracy of 0.88, and F1 score of 0.89. Furthermore, catabolic processes and pathways related to immunity were associated with selected DPL ***: The modified MRI-based radiomics model shows good predictive efficacy in predicting pCR after nCRT in LARC patients. Additionally, we investigated the genomic phenotypes associated with DPL.

关键词： Deep learning Support vector machines Pathology Analytical models Transcriptomics Predictive models data models Random forests Radiomics Cancer

来源：评论

学校读者我要写书评

暂无评论

MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection

arXiv

引用

arXiv 2025年

作者： Cheng, Jiayi Gao, Can Zhou, Jie Wen, Jiajun Dai, Tao Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

3D Anomaly Detection (AD) is a promising means of controlling the quality of manufactured products. However, existing methods typically require carefully training a task-specific model for each category independently, leading to high cost, low efficiency, and weak generalization. Therefore, this paper presents a novel unified model for Multi-Category 3D Anomaly Detection (MC3D-AD) that aims to utilize both local and global geometry-aware information to reconstruct normal representations of all categories. First, to learn robust and generalized features of different categories, we propose an adaptive geometry-aware masked attention module that extracts geometry variation information to guide mask attention. Then, we introduce a local geometry-aware encoder reinforced by the improved mask attention to encode group-level feature tokens. Finally, we design a global query decoder that utilizes point cloud position embeddings to improve the decoding process and reconstruction ability. This leads to local and global geometry-aware reconstructed feature tokens for the AD task. MC3D-AD is evaluated on two publicly available Real3D-AD and Anomaly-ShapeNet datasets, and exhibits significant superiority over current state-of-the-art single-category methods, achieving 3.1% and 9.3% improvement in object-level AUROC over Real3D-AD and Anomaly-ShapeNet, respectively. The source code will be released upon acceptance. Copyright © 2025, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Exploration of Novel Nsm Methods to Achieve Stronger Frps with Minimal Epoxy

SSRN

引用

SSRN 2024年

作者： Yan, Handong Yin, Jianli Zhu, Xinan Lou, Tiejiong Li, Haifeng Sun, Wei College of Civil Engineering Huaqiao University Xiamen361021 China Higher-educational Engineering Research Centre for Intelligence and Automation in Construction of Fujian Province College of Civil Engineering Huaqiao University Xiamen361021 China Key Laboratory for Intelligent Infrastructure and Monitoring of Fujian Province College of Civil Engineering Huaqiao University Xiamen361021 China KZJ New Materials Group Co. Ltd. Xiamen361101 China Shandong Province Big Data Center Shandong Jinan250000 China University of Coimbra Department of Civil Engineering Cemmpre Arise 3030-788 Portugal

Conventional NSM methods require a significant amount of epoxy to achieve the desired bond strength, leading to substantial material costs and carbon emissions. Anchorages offer an opportunity to fully develop the tensile strength of NSM FRPs and reduce epoxy consumption. However, there is a lack of comprehensive studies to guide the application of this promising technology. Unlike conventional pull-off tests, a series of bending experiments were carried out to investigate the direct impacts of groove arrangement, bond condition, anchorage, and FRP cross-sectional area on the failure modes and load capacities of flexural elements. The findings were then utilized to calibrate numerical models, which could be directly integrated into equilibrium equations to predict the load-deflection responses for the concrete elements strengthened with NSM methods. FRP models were developed to capture the softening behavior caused by slip. Cracking models that incorporated the tensile contributions of filler material and cracked concrete was proposed to describe the post-cracking behavior. Failure modes such as FRP debonding and rupture related to specific FRP arrangements were employed to determine the ultimate load capacities. The outcomes indicate that anchored NSM methods improve FRP utilization and flexural strength in comparison to traditional NSM techniques, while also reducing epoxy consumption. © 2024, The Authors. All rights reserved.

关键词： Numerical models

来源：评论

学校读者我要写书评

暂无评论

GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Yu, Zitong Wang, Tianyi Huang, Xiaobin Shen, Linlin Gao, Zan Ren, Jianfeng Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China Jinan250014 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China School of Computer Science University of Nottingham Ningbo China

The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative Cross Appearance-Edge Learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an Appearance-Edge Cross-Attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at https://***/Jenine-321/GenFace. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Graph Regularized Nonnegative Latent Factor Analysis Model for Temporal Link Prediction in Cryptocurrency Transaction Networks

arXiv

引用

arXiv 2022年

作者： Zhou, Yue Liu, Zhigang Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The Chongqing School University of Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

With the development of blockchain technology, the cryptocurrency based on blockchain technology is becoming more and more popular. This gave birth to a huge cryptocurrency transaction network has received widespread attention. Link prediction learning structure of network is helpful to understand the mechanism of network, so it is also widely studied in cryptocurrency network. However, the dynamics of cryptocurrency transaction networks have been neglected in the past researches. We use graph regularized method to link past transaction records with future transactions. Based on this, we propose a single latent factor-dependent, non-negative, multiplicative and graph regularized-incorporated update (SLF-NMGRU) algorithm and further propose graph regularized nonnegative latent factor analysis (GrNLFA) model. Finally, experiments on a real cryptocurrency transaction network show that the proposed method improves both the accuracy and the computational efficiency. © 2022, CC BY-NC-ND.

关键词： Multivariant analysis

来源：评论

学校读者我要写书评

暂无评论

Domain generalization for document authentication against practical recapturing attacks

arXiv

引用

arXiv 2021年

作者： Chen, Changsheng Zhang, Shuzheng Lan, Fengbo Huang, Jiwu The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology College of Electronics and Information Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Recapturing attack can be employed as a simple but effective anti-forensic tool for digital document images. Inspired by the document inspection process that compares a questioned document against a reference sample, we proposed a document recapture detection scheme by employing Siamese network to compare and extract distinct features in a recapture document image. The proposed algorithm takes advantages of both metric learning and image forensic techniques. Instead of adopting Euclidean distance-based loss function, we integrate the forensic similarity function with a triplet loss and a normalized softmax loss. After training with the proposed triplet selection strategy, the resulting feature embedding clusters the genuine samples near the reference while pushes the recaptured samples apart. In the experiment, we consider practical domain generalization problems, such as the variations in printing/imaging devices, substrates, recapturing channels, and document types. To evaluate the robustness of different approaches, we benchmark some popular off-the-shelf machine learning-based approaches, a state-of-the-art document image detection scheme, and the proposed schemes with different network backbones under various experimental protocols. Experimental results show that the proposed schemes with different network backbones have consistently outperformed the state-of-the-art approaches under different experimental settings. Specifically, under the most challenging scenario in our experiment, i.e., evaluation across different types of documents that produced by different devices, we have achieved less than 5.00% APCER (Attack Presentation Classification Error Rate) and 5.56% BPCER (Bona Fide Presentation Classification Error Rate) by the proposed network with ResNeXt101 backbone at 5% BPCER decision *** Codes 94A08 Copyright © 2021, The Authors. All rights reserved.

关键词： Feature extraction

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：