检索结果-内蒙古大学图书馆

A new mobility field and gradient-based traffic signal control approach applicable to large-scale road networks

TRANSPORTATION SAFETY AND ENVIRONMENT 2025年第1期7卷

作者： Yang, Hu Guo, Bao Yan, Changxin Chen, Zhiqiang Wang, Pu Cent South Univ Sch Traff & Transportat Engn Rail Data Res & Applicat Key Lab Hunan Prov Changsha 410000 Peoples R China Changsha Planning & Design Survey Res Inst Changsha 410000 Peoples R China Hunan Engn Res Ctr Urban Transport Data Driven Mod Changsha 410000 Peoples R China

Previous traffic control models were usually developed on small or medium sized road networks. The traffic control models applicable to large-scale road networks have received growing interest. In this study, we develop a new mobility field and gradient-based traffic signal control approach applicable to large road networks. First, we introduce an emerging analytical technique, the mobility field approach, to generate the mobility field of urban travels and measure the gradients of the mobility field. Next, a gradient-based approach is proposed to identify the signalized intersections for implementing traffic control. Finally, a gradient-based traffic control model is developed to alleviate traffic congestion during mass events. A new solution algorithm, termed DBSCAN-FW-GA, is proposed to solve the developed traffic control model. The developed mobility field and gradient-based traffic signal control approach is validated using actual road network data and travel demand data. Results indicate that the proposed new traffic control approach can reduce by 17.97% the travel time compared with the widely used perimeter control approach.

关键词： mobility field gradient human mobility traffic control congestion

来源：评论

学校读者我要写书评

暂无评论

designing RISC-V Instruction Set Extensions for Artificial Neural Networks: An LLVM Compiler-Driven Perspective

引用

IEEE ACCESS 2024年 12卷 55925-55944页

作者： Balasubramanian, Karthikeyan Kalyanasundaram Salvo, Mirco Di Rocchia, Walter Decherchi, Sergio Crepaldi, Marco Ist Italiano Tecnol Elect Design Lab I-16152 Genoa Italy Ist Italiano Tecnol Computat mOdelling NanosCalE & Biophys Syst I-16152 Genoa Italy Ist Italiano Tecnol Data Sci & Computat Facil I-16152 Genoa Italy

The demand for Artificial Intelligence (AI) based solutions is exponentially increasing in all application fields, including low-power devices on the edge. However, due to their limited computational capabilities, these devices, which run Central Processing Units (CPUs) tailored to embedded applications, are typically not optimized to run complex neural networks. Providing ad-hoc extensions to the instruction set architecture of a RISC-V processor can be a viable solution to address this issue. In this work, we propose the use of the PyTorch Graph Lowering (Glow)-LLVM toolchain to understand the impact of compiled code of AI models on a RISC-V machine and extend its instruction set to improve runtime performance. This approach allows code profiling, detection of computational bottlenecks, and provisioning of the necessary CPU enhancements to be implemented in the LLVM backend before hardware implementation. After profiling known Artificial Neural Networks (ANNs) quantized to int8 (particularly, a single perceptron, RESNET18, VGG11, and LENET5), we have identified and devised three additional instructions, we named LWM, LWA and LWS respectively indicating Load Word-and-Multiply, -Add, and -Subtract. As a result, we obtained an edge AI-oriented, significantly improved processor description in terms of inference time and program density, ready to be hardware-designed. For 128 x 128 RGB images, the custom extensions enabled up to 13x speed up compared to RV32I and 5x compared to RV32IM, with a maximum of 11.7% lower code. Together with these findings the paper systematically highlights the main methodological steps to include new instructions in an LLVM backend.

关键词： RISC-V AI RISC-V custom instructions extensions LLVM instruction set architecture hardware-software co-design

来源：评论

学校读者我要写书评

暂无评论

Cross-Mode Knowledge Adaptation for Bike Sharing Demand Prediction Using Domain-Adversarial Graph Neural Networks

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第5期25卷 3642-3653页

作者： Liang, Yuebing Huang, Guan Zhao, Zhan Univ Hong Kong Dept Urban Planning & Design Hong Kong Peoples R China MIT Senseable City Lab Cambridge MA 02139 USA Univ Hong Kong Musketeers Fdn Inst Data Sci Hong Kong Peoples R China

For bike sharing systems, demand prediction is crucial to ensure the timely re-balancing of available bikes according to predicted demand. Existing methods for bike sharing demand prediction are mostly based on its own historical demand variation, essentially regarding it as a closed system and neglecting the interaction between different transportation modes. This is particularly important for bike sharing because it is often used to complement travel through other modes (e.g., public transit). Despite some recent progress, no existing method is capable of leveraging spatiotemporal information from multiple modes and explicitly considers the distribution discrepancy between them, which can easily lead to negative transfer. To address these challenges, this study proposes a domain-adversarial multi-relational graph neural network (DA-MRGNN) for bike sharing demand prediction with multimodal historical data as input. A spatiotemporal adversarial adaptation network is introduced to extract shareable features from demand patterns of different modes. To capture correlations between spatial units across modes, we adapt a multi-relational graph neural network (MRGNN) considering both geographical proximity and mobility pattern similarity. Extensive experiments are conducted using real-world bike sharing, subway and ride-hailing data from New York City. The results demonstrate the superior performance of our proposed approach compared to existing methods and the effectiveness of different model components.

关键词： Shared transport Adaptation models Public transportation Graph neural networks Spatiotemporal phenomena Predictive models Feature extraction Bike sharing demand prediction inter-modal relationships graph neural networks adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Investigating the role of PmrB mutation on Colistin antibiotics drug resistance in Klebsiella Pneumoniae

引用

INTERNATIONAL JOURNAL OF BIOLOGICAL MACROMOLECULES 2024年第Pt 3期281卷 136414页

作者： Shahab, Muhammad Waqas, Muhammad Fahira, Aamir Zhang, Haoke Zheng, Guojun Huang, Zunnan Guangdong Med Univ Dongguan Affiliated Hosp 1 Sch Pharm Key Lab Comp Aided Drug Design Dongguan City Dongguan 523710 Peoples R China Guangdong Med Univ Sch Pharm Key Lab Big Data Min & Precis Drug Design Key Lab Res & Dev Nat Drugs Guangdong Prov Dongguan 523808 Peoples R China Beijing Univ Chem Technol State Key Labs Chem Resources Engn Beijing 100029 Peoples R China

Klebsiella pneumoniae, a member of the Enterobacteriaceae family, naturally resides in the digestive tracts of both healthy animals and humans. Carbapenem-resistant Klebsiella pneumoniae (CRKP) poses a significant health risk for hospitalized patients worldwide, greatly reducing the effectiveness of commonly used antibiotics. This leaves healthcare providers with limited treatment options, often relying on colistin. PmrB is important for the survival of Klebsiella pneumonia and, a mutation in the PmrB protein is accountable for the development of colistin antibiotic resistance in Klebsiella pneumonia. This is especially important because colistin is a fundamental component in the treatment of pneumonia. Three mutated residues-T157P, G207D, and T246A-are responsible for colistin resistance. The structural alterations and underlying mechanisms in the PmrB protein that cause resistance owing to mutation remain unclear. As a result, this study is focused to the exploration of the putative mechanism of resistance resulting from these mutations, as well as the structure modification of normal and mutant PmrB proteins, using molecular docking and molecular dynamics simulations analysis. Our results demonstrated that the interaction paradigm for the mutants has been altered and thus showing a significant effect upon the hydrogen bonding network. Interestingly, the binding of Colistin with the three mutant demonstrate unstable behavior as compared with WT +Colistin . The proposed drug-resistance mechanism will help to guide the development of PmrB drugs. These finding may give a new framework for developing novel drugs against the mutant version of PmrB.

关键词： Colistin antibiotics Docking Mutation Resistance PmrB Binding mechanism

来源：评论

学校读者我要写书评

暂无评论

Constrained Evolutionary Bayesian Optimization for Expensive Constrained Optimization Problems With Inequality Constraints

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2025年第3期55卷 2009-2021页

作者： Liu, Jiao Wang, Yong Sun, Guangyong Pang, Tong Cent South Univ Sch Automat Changsha 410083 Peoples R China Nanyang Technol Univ Coll Comp & Data Sci Singapore 639798 Singapore Hunan Univ State Key Lab Adv Design & Mfg Technol Vehicle Changsha 410082 Peoples R China

This article proposes a constrained evolutionary Bayesian optimization (CEBO) algorithm to cope with expensive constrained optimization problems with inequality constraints. The uniqueness of CEBO lies in its capability of balancing feasibility and objective improvement under a limited function evaluation budget, which is achieved by designing two strategies to obtain promising solutions. The first strategy prefers feasibility. It tends to obtain a feasible solution by utilizing the predicted value and uncertainty provided by Gaussian process (GP). The second strategy prefers objective improvement. It maintains and evolves the population of evolutionary algorithms, and selects a solution with a good objective function value and violating the constraints not too much based on the predicted value and uncertainty provided by GP at each iteration. The sequential implementation of these two strategies allows CEBO to balance feasibility and objective improvement. The effectiveness of CEBO is verified by 26 test instances and a practical application. The results demonstrate that CEBO is able to find high-quality solutions with 100 FEs.

关键词： Optimization Linear programming Iron Entropy Bayes methods Uncertainty Sun Gaussian processes Cybernetics Automobiles Bayesian optimization (BO) evolutionary algorithms (EAs) expensive constrained optimization problems (ECOPs) infill criterion infill solution

来源：评论

学校读者我要写书评

暂无评论

Information acquisition optimizer: a new efficient algorithm for solving numerical and constrained engineering optimization problems

引用

JOURNAL OF SUPERCOMPUTING 2024年第18期80卷 25736-25791页

作者： Wu, Xiao Li, Shaobo Jiang, Xinghe Zhou, Yanqiu Guizhou Univ Sch Mech Engn Guiyang 550025 Peoples R China Guizhou Univ State Key Lab Publ Big Data Guiyang 550025 Peoples R China Jiangnan Inst Mech & Elect Design Guiyang 550025 Peoples R China

This paper addresses the increasing complexity of challenges in the field of continuous nonlinear optimization by proposing an innovative algorithm called information acquisition optimizer (IAO), which is inspired by human information acquisition behaviors and consists of three crucial strategies: information collection, information filtering and evaluation, and information analysis and organization to accommodate diverse optimization requirements. Firstly, comparative assessments of performance are conducted between the IAO and 15 widely recognized algorithms using the standard test function suites from CEC2014, CEC2017, CEC2020, and CEC2022. The results demonstrate that IAO is robustly competitive regarding convergence rate, solution accuracy, and stability. Additionally, the outcomes of the Wilcoxon signed rank test and Friedman mean ranking strongly validate the effectiveness and reliability of IAO. Moreover, the time comparison analysis experiments indicate its high efficiency. Finally, comparative tests on five real-world optimization difficulties affirm the remarkable applicability of IAO in handling complex issues with unknown search spaces. The code for the IAO algorithm is available at https://***/matlabcentral/fileexchange/169331-information-acquisition-optimizer.

关键词： Continuous nonlinear optimization Information acquisition optimizer Information collection Information filtering and evaluation Information analysis and organization

来源：评论

学校读者我要写书评

暂无评论

Explaining Anomalous Events in Flight data of UAV With Deep Attention-Based Multi-Instance Learning

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第1期73卷 107-119页

作者： Yang, Jie Tang, Diyin Yu, Jinsong Zhang, Jian Liu, Haigang Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China Lab Big Data Decis Making Green Dev Beijing 100192 Peoples R China Shenyang Aircraft Design & Res Inst Shenyang 110035 Peoples R China

Ensuring the safety and reliability of unmanned aerial vehicles (UAVs) has become a critical issue as they continue to advance. Analyzing anomalous events using event-based explanations is an effective approach to identifying key anomalous behaviors and mitigating potential risks. However, this task is challenging because anomalous events in flight data lack time-step labels in real-world UAV flight scenarios. To address this challenge, we propose a dual attention-based multi-instance learning (DA-DI-MIL) for pinpointing anomaly instances and automatically explaining anomalous events. Our MIL-based framework, from a weakly supervised learning perspective, treats a segment of flight data as a 'bag' with an available label, and its time steps as 'instances' without labels. The dual attention mechanism in DA-DI-MIL combines a temporal pseudo-label, predicted by temporal attention, and sensor variable importance obtained from delta feature attention to better pinpoint anomalies from instance-level labels. We use these labels in our proposed MIL-based framework to establish the relationships between anomalous events and anomalous behaviors. We conducted extensive experiments on real UAV flight data with engine failures to demonstrate the effectiveness and robustness of our proposed method compared to existing state-of-the-art methods. DA-DI-MIL achieves near 90% in evaluation metrics with less than 5 time steps' delay of anomalous event detection and around 85% in temporal anomaly detection. Additionally, we present an illustration of both global and local interpretations in the time domain and feature space, providing comprehensive insights into anomalous events. Our proposed method has efficiently and automatically explained anomalous events in UAV flight data, contributing to high-level aviation safety and reliability.

关键词： Sensors Anomaly detection Behavioral sciences Autonomous aerial vehicles Time series analysis data models Training anomalous events attention mechanism aviation safety deep learning multiple instance learning unmanned aerial vehicle

来源：评论

学校读者我要写书评

暂无评论

Building Type Classification Using CNN-Transformer Cross-Encoder Adaptive Learning From Very High Resolution Satellite Images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 976-994页

作者： Zhang, Shaofeng Li, Mengmeng Zhao, Wufan Wang, Xiaoqin Wu, Qunyong Fuzhou Univ Acad Digital China Minist Educ Key Lab Spatial Data Min & Informat Sharing Fuzhou 350108 Peoples R China Hong Kong Univ Sci & Technol Guangzhou Urban Governance & Design Thrust Soc Hub Guangzhou 511453 Peoples R China

Building type information indicates the functional properties of buildings and plays a crucial role in smart city development and urban socioeconomic activities. Existing methods for classifying building types often face challenges in accurately distinguishing buildings between types while maintaining well-delineated boundaries, especially in complex urban environments. This study introduces a novel framework, i.e., CNN-Transformer cross-attention feature fusion network (CTCFNet), for building type classification from very high resolution remote sensing images. CTCFNet integrates convolutional neural networks (CNNs) and Transformers using an interactive cross-encoder fusion module that enhances semantic feature learning and improves classification accuracy in complex scenarios. We develop an adaptive collaboration optimization module that applies human visual attention mechanisms to enhance the feature representation of building types and boundaries simultaneously. To address the scarcity of datasets in building type classification, we create two new datasets, i.e., the urban building type (UBT) dataset and the town building type (TBT) dataset, for model evaluation. Extensive experiments on these datasets demonstrate that CTCFNet outperforms popular CNNs, Transformers, and dual-encoder methods in identifying building types across various regions, achieving the highest mean intersection over union of 78.20% and 77.11%, F1 scores of 86.83% and 88.22%, and overall accuracy of 95.07% and 95.73% on the UBT and TBT datasets, respectively. We conclude that CTCFNet effectively addresses the challenges of high interclass similarity and intraclass inconsistency in complex scenes, yielding results with well-delineated building boundaries and accurate building types.

关键词： Buildings Feature extraction Transformers Accuracy Remote sensing Semantics Visualization Architecture Optimization Earth Building type classification CNN-transformer networks cross-encoder feature interaction very high resolution remote sensing

来源：评论

学校读者我要写书评

暂无评论

A SIXTH-ORDER ACCURACY CONSERVATIVE LINEAR FINITE DIFFERENCE SCHEME FOR RLW EQUATION

引用

THERMAL SCIENCE 2025年第2A期29卷 1063-1069页

作者： Zheng, Mao-Bo Hu, Jin-Song Yan, Wen-Yong Chen, Zhong Chengdu Technol Univ Coll Big Data & Artificial Intelligence Chengdu Peoples R China Univ South China Key Lab Adv Nucl Energy Design & Safety Minist Educ Hengyang Hunan Peoples R China

By the Taylor expansion and extrapolation combinations in the spatial direction, the second order and fourth order components of spatial truncation errors can be removed, resulting in a theoretical accuracy of sixth order. In the temporal direction, the average implicit method is employed to achieve second-order theoretical accuracy. Subsequently, a linear average implicit difference scheme for the initial boundary value problem of regularized long wave equation is constructed, which can reasonably simulate the two conservative quantities of the problem. Moreover, the convergence and stability of the scheme are also proved. Numerical examples also demonstrate the effectiveness of the proposed method.

关键词： RLW equation high accuracy conservation finite difference scheme convergence stability

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based screening and molecular simulations for discovering novel PARP-1 inhibitors targeting DNA repair mechanisms for breast cancer therapy

引用

MOLECULAR DIVERSITY 2025年 1-21页

作者： Shahab, Muhammad Waqas, Muhammad Fahira, Aamir Sharma, Bharat Prasad Zhang, Haoke Zheng, Guojun Huang, Zunnan Guangdong Med Univ Dongguan Affiliated Hosp 1 Dongguan Key Lab Comp Aided Drug Design Dongguan 523710 Peoples R China Guangdong Med Univ Key Lab Big Data Min & Precis Drug Design Sch Pharm Guangdong Prov Key Lab Res & Dev Nat Drugs Dongguan 523808 Peoples R China Beijing Univ Chem Technol State Key Labs Chem Resources Engn Beijing 100029 Peoples R China

Cancer remains one of the leading causes of death worldwide, with the rising incidence of breast cancer being a significant public health concern. Poly (ADP-ribose) polymerase-1 (PARP-1) has emerged as a promising therapeutic target for breast cancer treatment due to its crucial role in DNA repair. This study aimed to discover novel, targeted, and non-toxic PARP-1 inhibitors using an integrated approach that combines machine learning-based screening, molecular docking simulations, and quantum mechanical calculations. We trained a widely used machine learning models, Random Forest, using bioactivity data from known PARP-1 inhibitors. After evaluating the performance, it was used to screen an FDA-approved drug library, successfully identifying Atazanavir, Brexpiprazole, Raltegravir, and Nisoldipine as potential PARP-1 inhibitors. These compounds were further validated through molecular docking and all-atom molecular dynamics simulations, highlighting their potential for breast cancer therapy. The binding free energies indicated that Atazanavir at - 41.86 kJ/mol and Brexpiprazole at - 45.44 kJ/mol exhibited superior binding affinity compared to the control drug at - 30.42 kJ/mol, highlighting their promise as candidates for breast cancer therapy. Subsequent optimized geometries and electron density mappings of the two molecular structures revealed a Gibbs free energy of - 2334.610 Ha for the first molecule and - 1682.278316 Ha for the second, confirming enhanced stability compared to the standard drug. This study not only highlights the efficacy of machine learning in drug discovery but also underscores the importance of quantum mechanics in validating molecular stability, setting a robust foundation for future pharmacological explorations. Additionally, this approach could revolutionize the drug repurposing process by significantly reducing the time and cost associated with traditional drug development methods. Our results establish a promising basis for subsequent re

关键词： Breast cancer PARP-1 ML-based screening Molecular docking simulation DFT analysis

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：