检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Gong, Letian Lin, Yan Zhang, Xinyue Lu, Yiwen Han, Xuedi Liu, Yichen Guo, Shengnan Lin, Youfang Wan, Huaiyu School of Computer Science and Technology Beijing Jiaotong University China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing China Department of Computer Science Aalborg University Denmark

Location-based services (LBS) have accumulated extensive human mobility data on diverse behaviors through check-in sequences. These sequences offer valuable insights into users' intentions and preferences. Yet, existing models analyzing check-in sequences fail to consider the semantics contained in these sequences, which closely reflect human visiting intentions and travel preferences, leading to an incomplete comprehension. Drawing inspiration from the exceptional semantic understanding and contextual information processing capabilities of large language models (LLMs) across various domains, we present Mobility-LLM, a novel framework that leverages LLMs to analyze check-in sequences for multiple tasks. Since LLMs cannot directly interpret check-ins, we reprogram these sequences to help LLMs comprehensively understand the semantics of human visiting intentions and travel preferences. Specifically, we introduce a visiting intention memory network (VIMN) to capture the visiting intentions at each record, along with a shared pool of human travel preference prompts (HTPP) to guide the LLM in understanding users' travel preferences. These components enhance the model's ability to extract and leverage semantic information from human mobility data effectively. Extensive experiments on four benchmark datasets and three downstream tasks demonstrate that our approach significantly outperforms existing models, underscoring the effectiveness of Mobility-LLM in advancing our understanding of human mobility data within LBS contexts. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved MPPT algorithm: Artificial neural network trained by an enhanced Gauss-Newton method

AIMS Electronics and Electrical Engineering

引用

AIMS Electronics and Electrical Engineering 2023年第4期7卷 380-405页

作者： Dkhichi, Fayrouz Laboratory of Networks Computer Science Telecommunications & Multimedia Electrical Engineering Department Superior School of Technology Hassan II University of Casablanca Morocco

A novel approach defined by the artificial neural network (ANN) model trained by the improved Gauss-Newton in conjunction with a simulated annealing technique is used to control a step-up converter. To elucidate the superiority of this innovative method and to show its high precision and speed in achieving the right value of the Maximum Power Point (MPP), a set of three comparative Maximum Power Point Tracker (MPPT) methods (Perturbation and observation, ANN and ANN associated with perturbation and observation) are exanimated judiciously. The behavior of these methods is observed and tested for a fixed temperature and irradiance. As a result, the proposed approach quickly tracks the right MPP = 18.59 W in just 0.04382 s. On the other hand, the outstanding ability of the suggested method is demonstrated by varying the irradiance values (200 W/m , 300 W/m , 700 W/m , 1000 W/m , 800 W/m and 400 W/m ) and by varying the temperature values (15°C, 35°C, 45°C and 5°C). Therefore, the ANN trained by Gauss-Newton in conjunction with simulated annealing shows a high robustness and achieves the correct value of MPP for each value of irradiance with an efficiency 99.54% and for each value of temperature with an efficiency 99.98%;the three other methods sometimes struggle to achieve the right MPP for certain irradiance values and often remains stuck in its surroundings. © 2023 The Author(s).

关键词： Maximum power point trackers

来源：评论

学校读者我要写书评

暂无评论

A Tiny Efficient U-Net with Gated Linear Attention for Medical Image Segmentation

A Tiny Efficient U-Net with Gated Linear Attention for Medic...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Ju, Sibo Chen, Zhaozhen Liao, Xiangwen Shen, Yiqing He, Junjun Su, Yanzhou Fuzhou University College of Computer and Data Science Fuzhou China Johns Hopkins University Department of Computer Science Baltimore United States Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (纸本)9798350386226

Medical image segmentation is crucial for diagnosis and treatment planning. While recent advancements in deep learning, particularly UNet variants, have improved segmentation performance, they often result in increased model complexity, which limits their real-time applicability on resource-constrained devices in clinical settings. To address this challenge, we present the Tiny Efficient U-Net (TE-UNet), a novel lightweight model balancing efficiency and accuracy. TE-UNet uses a U-shaped encoder-decoder framework with a gated linear attention mechanism to process low-level and high-level features, preserving details and reducing complexity. It employs depth-wise separable convolutions for higher-level processing, enhancing efficiency without losing performance. Additionally, skip connections improve multi-scale feature extraction and information flow. Experiments on two public datasets across different modalities demonstrate that TE-UNet outperforms ten state-of-the-art methods, maintaining a parameter size under 40KB and low computational cost. TE-UNet makes real-time segmentation more accessible for various clinical applications. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Advancements in Recommender Systems through the Integration of Generative Adversarial Networks 6

Advancements in Recommender Systems through the Integration ...

引用

6th International Hybrid Conference on Informatics and Applied Mathematics, IAM 2023

作者： Manaa, Naouel Seridi, Hassina Mendjel, Mohamed Said Mehdi Department of Computer Science Laboratory of Electronic Document Management LabGED Badji Mokhtar Annaba University Algeria

Generative Adversarial Networks (GANs) have emerged as powerful tools in the realm of artificial intelligence, reshaping various domains, from image generation to text synthesis and music composition. In recent years, researchers have ventured into the realm of integrating GANs into recommendation systems, driven by the desire to elevate the quality of recommendations. This article presents an in-depth exploration of the current landscape surrounding the incorporation of GANs in recommendation systems. Researchers have harnessed the potential of GANs to craft highly personalized recommendations by incorporating user and item features. Notably, techniques like conditional GANs have been employed to consider user demographics, browsing history, and item attributes, enabling the tailoring of recommendations to individual preferences. Nevertheless, challenges have surfaced, including issues related to training stability, mode collapse, scalability limitations, and data privacy concerns in the application of GANs to recommendation systems. Diligent and persistent research endeavors are actively addressing these challenges with the overarching goal of not only overcoming the hurdles but also enhancing the stability and performance of GANs within recommendation systems. This article serves as a comprehensive guide to the current state of GANs in recommendation systems, offering insights into their potential and the evolving landscape of research and development in this field. © 2023 Copyright for this paper by its authors.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Critical Path Optimization for Logic Netlists 9

Critical Path Optimization for Logic Netlists

引用

9th International Conference on Integrated Circuits and Microsystems, ICICM 2024

作者： Yu, Xuewen Huang, Pengcheng Chen, Haiyan Chen, Wei School of Computer National University of Defense Technology Key Laboratory of Advanced Microprocessors Chips and Systems Changsha China School of Computer National University of Defense Technology Department of Computer Science Changsha China

ISBN: (纸本)9798331509453

It is of great concern for high performance microprocessors to optimize logic delay and improve performance in the semi-custom design flow based on commercial standard cell library. To solve this issue, the paper proposes an automated method to optimize the delay of critical path in any block. Firstly, we construct the logic cone for critical paths based on the logic netlist obtained from semi-custom design flow. Secondly, the algorithm conducts large-scale graph partitioning on the logic cone with appropriate constraints. Thirdly, using two-level optimization, we perform logic restructuring on sub graphs resulting from partitioning to get a set of new logic cells. Finally, employing a match algorithm, we pick out high-reusable restructured logic cells for full-custom circuit implementation and replace corresponding circuit structures with them in the logic netlist. The proposed algorithm picks out 5 logic cells for restructuring. Experimental results demonstrate that the approach achieves a reduction in the logic levels and logic delay can be reduced by about 10% after replacing the corresponding structures in the logic netlist. The work effectively reduces critical path delay, which has the potential to enhance the performance of microprocessors. © 2024 IEEE.

关键词： computer circuits

来源：评论

学校读者我要写书评

暂无评论

Metaheuristics for Financial Investment Strategies: Applications Survey

Metaheuristics for Financial Investment Strategies: Applicat...

引用

2023 International Conference on Electrical, computer, Communications and Mechatronics Engineering, ICECCME 2023

作者： Bousbaa, Zineb Bencharef, Omar Cady Ayyad University Computer and Systems Engineering Laboratory Faculty of Sciences and Technology Computer Science Department Marrakesh Morocco

ISBN: (纸本)9798350322972

Machine learning has been widely used as part of financial markets investment strategies, whether for forecasting the financial assets exchange rate, managing market volatility, or solving different classification problems that help with decision-making. Building an investment strategy using a scientific approach requires a massive amount of data, good computational power, and some expertise in the finance industry. Machine learning applications to the financial field, such as price exchange rate prediction, market pattern recognition, or other trading strategy tasks, are considered optimization problems. As they require an efficient algorithm dedicated to finding a global optimum, they can be solved using metaheuristics. In this survey, we study how metaheuristic optimization techniques contribute to building a robust learning model dedicated to financial investment strategy applications. © 2023 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

A Unified Semantic Web and IoT Architecture for Enhanced Agricultural ERP Functionality and Management Integration

A Unified Semantic Web and IoT Architecture for Enhanced Agr...

引用

2024 IEEE International Multi-Conference on Smart Systems and Green Process, IMC-SSGP 2024

作者： Lynda, Djakhdjakha Brahim, Farou LabSTIC Laboratory Computer Science Department Guelma University 8 Mai 1945 Guelma24000 Algeria

ISBN: (纸本)9798350378382

In modern agriculture, the need for efficient data management and seamless system integration has become increasingly critical. Existing Enterprise Resource Planning (ERP) systems, while effective in various industries, often face limitations when applied to agriculture due to the complexity and diversity of agricultural operations and data sources. This paper proposes a unified architecture that leverages ERP principles alongside Semantic Web technologies and the Internet of Things (IoT) to address these challenges. By combining these technologies, the proposed architecture can significantly improve data interoperability and process integration across heterogeneous systems. The architecture also incorporates smart contracts for secure and automated management of agricultural processes. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

K-CAE: Image Classification Using Convolutional AutoEncoder Pre-Training and K-means Clustering

引用

Informatica (Slovenia) 2023年第7期47卷 31-40页

作者： Chefrour, Aida Drissi, Samia Computer Science Department Mohamed Cherif Messaadia University Souk Ahras Algeria LISCO Laboratory Computer Science Department Badji Mokhtar University B.P-12 Annaba23000 Algeria LiM Laboratory Faculty of Science and Technology University of Souk Ahras P.O. Box 1553 Souk-Ahras41000 Algeria

The work presented in this paper is in the general framework of classification using deep learning and, more precisely, that of convolutional Autoencoder. In particular, this last proposes an alternative for the processing of high-dimensional data, to facilitate their classification. In this paper, we propose the incorporation of convolutional autoencoders as a general unsupervised learning data dimension reduction method for creating robust and compressed feature representations for better storage and transmission to the classification process to improve K-means performance on image classification tasks. The experimental results on three image databases, MNIST, Fashion-MNIST, and CIFAR-10, show that the proposed method significantly outperforms deep clustering models in terms of clustering quality. © 2023 Slovene Society Informatika. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Impact of time delay and cooperation strategy on the stability of a predator-prey model with Holling type III functional response

引用

International Journal of Biomathematics 2023年第3期16卷 165-193页

作者： I.Benamara A.El Abdllaouit J.Mikramt Laboratory of Mathematics Computer Science&Applications-Security of Information Department of Mathematics Faculty of Sciences Mohammed V University in RabatMorocco

In this paper,we propose and analyze a delayed predator-prey model with Holling type III functional response taking into account cooperation behavior in *** time delay is introduced in the attack rate to represent the time necessary to trigger the *** analytical result is followed by an ecological *** investigate the effect of hunting cooperation on both the number and the level of positive steady *** observe that the level of the positive equilibrium decreases when increasing the hunting cooperation ***,we study the impact of the delay as well as the cooperation in hunting on the dynamics of the *** prove that the presence of delay in the attack rate induces stability switches around the coexisting equilibrium when predators *** addition,we consider the discrete delay as a bifurcation parameter and prove that the model undergoes a Hopf-bifurcation at the coexisting equilibrium when the delay crosses some critical *** simulations are presented to confirm our analytical findings.

关键词： Predator-prey system Holling type III discrete delay cooperative hunting Hopf-bifurcation switch of stability

来源：评论

学校读者我要写书评

暂无评论

Optimization of Lane-changing Advisory in Mixed Traffic of Connected Vehicles and Human-driven Vehicles at Expressway Bottlenecks

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2023年 1-10页

作者： Lin, Jingmin Yu, Chunhui Wang, Ling Liu, Guanjun Wang, Jiacun Ma, Wanjing Key Laboratory of Road and Traffic Engineering of the Ministry of Education Tongji University Shanghai P.R. China Department of Computer Science and Technology Tongji University Shanghai P.R. China Computer Science and Software Engineering Department Monmouth University USA

Lane closure due to events such as accidents creates bottlenecks on expressways. The mandatory lane changes of merging vehicles lead to congestion. As the cyber-physical system (CPS) develops, mixed traffic consisting of connected vehicles (CVs) and human-driven vehicles (HVs) has emerged. CVs can receive lane-changing (LC) advisories and complete merging to alleviate congestion. Most existing studies assume CVs can timely and exactly follow LC advisories, which is not realistic with human drivers. This study develops an LC advisory model for CVs, whose response time and compliance degrees are considered, at an expressway bottleneck with lane closure under mixed traffic of CVs and HVs. The LC strategies are optimized for CVs to minimize the total delay of CVs and HVs approaching the bottleneck. The constraints include the domains of decision variables, vehicle passing states at the bottleneck, vehicle kinematics, implementation of LC advisories, LC safety, the maximum number of LC manoeuvres, the minimum time interval between LC advisories, the potential LC CVs, and the evolution of vehicle states. The simulation-based method is applied to predict vehicle delay, which is formulated as an implicit function of the LC strategies for CVs. Genetic Algorithm (GA) is designed for solutions. The numerical studies validate the advantages of the proposed model. The sensitivity analysis shows that: 1) the critical CV penetration rate is 60%, below which the marginal benefits are significant with increasing CV penetration rates;and 2) the consideration of the response time and the compliance degree of CVs makes a great difference. IEEE

关键词： Vehicles

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：