检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Guo, Qianyu Ren, Jieji Wang, Haofen Wu, Tianxing Ge, Weifeng Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China College of Design and Innovation Tongji University Shanghai China School of Computer Science and Engineering Southeast University Nanjing China School of Computer Science Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China

ISBN: (纸本)9798400706868

Visual-language models based on CLIP have shown remarkable abilities in general few-shot image classification. However, their performance drops in specialized fields such as healthcare or agriculture, because CLIP's pre-training does not cover all category data. Existing methods excessively depend on the multi-modal information representation and alignment capabilities acquired from CLIP pre-training, which hinders accurate generalization to unfamiliar domains. To address this issue, this paper introduces a novel visual-language collaborative representation network (MCRNet), aiming at acquiring a generalized capability for collaborative fusion and representation of multi-modal information. Specifically, MCRNet learns to generate relational matrices from an information fusion perspective to acquire aligned multi-modal features. This relationship generation strategy is category-agnostic, so it can be generalized to new domains. A class-adaptive fine-tuning inference technique is also introduced to help MCRNet efficiently learn alignment knowledge for new categories using limited data. Additionally, the paper establishes a new broad-domain few-shot image classification benchmark containing seven evaluation datasets from five domains. Comparative experiments demonstrate that MCRNet outperforms current state-of-the-art models, achieving an average improvement of 13.06% and 13.73% in the 1-shot and 5-shot settings, highlighting the superior performance and applicability of MCRNet across various domains. © 2024 ACM.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

AgileVision Academy: Indoor Drone Navigation and Obstacle Avoidance 14

AgileVision Academy: Indoor Drone Navigation and Obstacle Av...

引用

14th International Conference on Information Technology in Medicine and Education, ITME 2024

作者： Jiang, Haolong Gu, Lingdan Wang, Jiayu Lan, Xiao Liu, Qinyao Wang, Fanxin Xi'an Jiaotong Liverpool University University of Liverpool School of Advanced Technology Department of Electrical and Electronic Engineering Suzhou China Xi'an Jiaotong Liverpool University School of Robotics Department of Intelligence Robotics Engineering With Contemporary Entrepreneurialism Suzhou China Xi'an Jiaotong Liverpool University School of Advanced Technology Department of Information and Computer Science Suzhou China Xi'an Jiaotong Liverpool University School of Advanced Technology Department of Electrical and Electronic Engineering Suzhou China Xi'an Jiaotong Liverpool University School of Advanced Technology Department of Mechatronics and Robotics Suzhou China

ISBN: (纸本)9798350356670

Navigating cluttered indoor environments presents a significant challenge for aerial robots, requiring agility, speed, and a high level of reliability to avoid collisions. This project aims to address this challenge by developing advanced algorithms for lightweight drones, enabling them to reach target location and carrying out delivery efficiently and safely. Utilizing camera data to map and avoid obstacles, we create a system that not only maps and perceives the environment but also navigates its path to the destination. Included in the educational content, this project demonstrates the effectiveness of the technology through practical applications and real-world testing, helping the next generation of engineers accumulate technical experience and broaden their understanding of drone navigation algorithms and applications in system integration. It has a milestone impact on education and development of the drone field. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Architecture and Operational Control for Resilient Microgrids

Architecture and Operational Control for Resilient Microgrid...

引用

Annual Meeting Industrial and Commercial Power Systems Technical Conference

作者： Alexandre F. M. Correia Miguel Cavaleiro Miguel Neves A. Paulo Coimbra Tony R. O. Almeida Pedro Moura Aníbal T. de Almeida Department of Electrical and Computer Engineering Institute of System and Robotics University of Coimbra Coimbra Portugal

ISBN: (数字)9798350345308

ISBN: (纸本)9798350345315

The increasing frequency of natural disasters has led to situations in which small urban centers and critical infrastructures become isolated from the main utility grid. The microgrids’ ability to work autonomously from the utility grid presents a viable solution to this problem. Microgrid resiliency is the characteristic related to the capacity of a microgrid to minimize the impact of disruptive events and ensure that the power supply is maintained under a variety of adverse conditions. This is especially important for critical infrastructures such as hospitals, communications, computer networks and military bases. The objective of this paper is to simulate strategies and propose an algorithm for the design and management of electric microgrids with a focus on resiliency towards critical and disaster situations. The proposed solutions were validated, using an experimental microgrid implemented at the University of Coimbra as a pilot. As a result of the work, the study presents an algorithm that efficiently manages loads of a microgrid, including automatic islanding operation, in order to increase its resilience when the microgrid is isolated from the utility grid.

关键词： Surveys Disasters Microgrids computer architecture Quality of service Stability analysis Critical infrastructure

来源：评论

学校读者我要写书评

暂无评论

Static Friction Torque Estimation for Robot Manipulators Using a Data-Driven Approach

Static Friction Torque Estimation for Robot Manipulators Usi...

引用

2023 IEEE International Symposium on Sensorless Control for Electrical Drives, SLED 2023

作者： Shim, Jaehoon Lee, Sangwon Jeon, Daesung Ha, Jung-Ik Seoul National University Department of Electrical and Computer Engineering Seoul Korea Republic of HD Hyundai Robotics Co. Ltd. Youngin-si Korea Republic of

ISBN: (纸本)9798350335422

In analyzing dynamic multi-joint robots, the accuracy of model-based robot dynamics is significantly affected by various forces that are not adequately modeled in the joints. Among these factors, joint friction torque plays a crucial role. Numerous studies have focused on modeling joint friction, and this paper proposes joint friction models for multi-joint robots based on a data-driven approach. The key ideas are summarized into two aspects. First, comprehensive data acquisition is essential to utilize the data-driven model. This study covers a method to obtain data that includes comprehensive information which is insufficiently addressed in previous research. Second, previous studies using neural networks have only considered partial joint information. This paper proposes a model that utilizes joint velocity, torque, and temperature information together to develop a comprehensive friction model. The proposed friction torque models are verified using a real-world 6-axis collaborative robot. © 2023 IEEE.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

A Spectral Mask - Based on Method for Applying into Generalized Sidelobe Canceller Beamformer 12th

A Spectral Mask - Based on Method for Applying into Gener...

引用

Proceedings of the12th International Conference on Information Technology and its Applications, CITA 2023

作者： Huy, Nguyen Ba Anh, Pham Tuan The, Quan Trong Faculty of Control Systems and Robotics University ITMO St.Petersburg Russia Faculty of Software Engineering and Computer Systems University ITMO St.Petersburg Russia

ISBN: (纸本)9783031368851

The problem of signal processing is extracting the desired target speaker while suppressing the annoying background noise in complex recording situation, where exists third-party talker, transport vehicle or interference, noise. Speech quality or speech intelligibility are the major characteristics, which confirm the effectiveness of processed method. In speech applications, such as hearing-aids, hands-free telephony, teleconferencing, acoustic instruments, microphone array (MA) is applied for increasing the speech quality. MA uses the spatial response, the priori information about direction - of - arrival (DOA) of interest signal, the properties of recording environment to obtain speech components and remove noise. Generalized Sidelobe Canceller (GSC) is one of the most widely exploited in microphone array beamforming, due to its convenience and effective noise reduction. However, in several situations, the performance of GSC beamformer is often degraded, because of the imprecise DOA. In this paper, the authors suggested an additive spectral mask for improving the evaluation of GSC beamformer. The resulting experiment proves the received advantage of the author’s proposed algorithm to increase in the term of the signal-to-noise ratio (SNR). © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Protein-Folding Inspired Programmable Control System for Robot Swarms

Protein-Folding Inspired Programmable Control System for Rob...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Zhang, Feng Gu, Yuping Wang, Zebin Yuan, Shuai Yang, Yongliang School of Electrical and Control Engineering Shenyang Jianzhu University Liaoning Shenyang110168 China Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Liaoning Shenyang110106 China School of Computer Science and Engineering Shenyang Jianzhu University Liaoning Shenyang110168 China

ISBN: (纸本)9781665481090

In swarm robotics, most of the control algorithms are inspired by the behaviors of animal swarms. The capability gap between robots and animals, however, hinders the reliability of these algorithms. Toward developing reliable algorithms of robot swarms, a promising solution is learning from the collective behaviors of low-intelligent natural swarms, such as cell collectives and molecular assemblies. Here, we proposed a programmable control system inspired by protein folding. Using our homemade RoboFold platform, we demonstrated a protein-folding inspired programmable control method for robot swarms. By programming and designing the sequence of a thread of protein-like robots, the developed system can mimic the formation of hierarchical structures in robot swarms as the three-level of protein structures. We quantitatively characterized the specific features of self-organized morphologies. The experimental results together demonstrated the feasibility of this method. To summarize, this work successfully translated the principles of protein-folding into programming methods to control the morphology of robot swarms. Considering that the protein folding problem is essentially a physicochemical problem, this system is not only beneficial for the control of swarm robots but also has the potential to develop into a tool for studying the protein folding problem. © 2024 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Dysplasia Grading in Colorectal Polyps Using an Explainable Weakly Supervised Deep Learning Model

SSRN

引用

SSRN 2025年

作者： Hernández, Nerea Ortuño, Francisco Rojas, Ignacio Department of Computer Engineering Automation and Robotics ETSIIT CITIC-UGR University of Granada 18071 Spain

Colorectal cancer remains one of the leading causes of mortality worldwide, often developing from precancerous polyps. The risk of malignant transformation is closely linked to the degree of dysplasia, characterized by abnormalities in cell morphology and tissue organization. Accurate dysplasia grading is vital for early diagnosis and improved patient outcomes. Whole slide imaging (WSI) facilitates high-resolution digital analysis of tissue samples, but the complexity of histological patterns and subjective human interpretation highlight the need for more automated analysis *** this study, we propose a deep learning model for dysplasia classification in colorectal histology using a weakly supervised learning approach. Unlike traditional methods, our model does not require pixel-level annotations and can automatically identify the most relevant regions for classification. We achieve state-of-the-art accuracy, reaching 96.7\% on the CRS10K dataset and 95.5\% in external validation using TCGA images. To enhance model transparency, we integrate interpretability mechanisms through heatmap visualizations, allowing a better understanding of the model’s decision-making process. Additionally, we emphasize the importance of uncertainty-aware classification in medical Artificial Intelligence (AI), ensuring that highly confident predictions can be automated while directing expert attention to ambiguous cases. Our goal is to develop reliable and explainable AI tools that support pathologists in making accurate and timely diagnoses, ultimately improving colorectal cancer detection and patient care. © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Intersection Coordination with Priority-Based Search for Autonomous Vehicles 37

Intersection Coordination with Priority-Based Search for Aut...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Li, Jiaoyang Hoang, The Anh Lin, Eugene Vu, Hai L. Koenig, Sven Robotics Institute Carnegie Mellon University United States Department of Civil Engineering Monash University Australia Computer Science Department University of Southern California United States

ISBN: (纸本)9781577358800

The development of connected and autonomous vehicles opens an opportunity to manage intersections without signals. One promising approach is to use a central autonomous intersection manager to optimize the movement of the vehicles in the intersection. Existing work uses Mixed Integer Linear Programming (MILP) to find optimal solutions for this problem but is time-consuming and cannot be applied in real-time. On the other hand, the coordination of the vehicles is essentially a Multi-Agent Path Finding (MAPF) problem, for which dozens of efficient algorithms have been proposed in recent years. Inspired by these MAPF algorithms, we propose a three-level algorithm called PSL to solve the intersection coordination problem. Theoretically, PSL is complete and polynomial-time in the number of vehicles. Empirically, PSL runs significantly faster with only a slight compromise in the solution quality than the optimal MILP method. It also generates significantly better solutions with a slightly larger runtime than the traditional First-Come-First-Served strategy. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Optimal view point and kinematic control for grape stem detection and cutting with an in-hand camera robot

Optimal view point and kinematic control for grape stem dete...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Sotiris Stavridis Zoe Doulgeri Automation & Robotics Lab School of Electrical & Computer Engineering Aristotle University of Thessaloniki Greece

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In this work, a methodology to find the best view of a grape stem and approach angle in order to crop it is proposed. The control scheme is based only on a classified point cloud obtained by the in-hand camera attached to the robot’s end effector without continuous stem tracking. It is shown that the proposed controller finds and reaches the optimal view point and subsequently the stem fast and efficiently, accelerating the overall harvesting procedure. The proposed control scheme is evaluated through experiments in the lab with a UR5e robot with an in-hand RealSense camera on a mock-up vine.

关键词： Point cloud compression Robot vision systems Pipelines Crops Kinematics Cameras End effectors Reliability Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Intelligent Deep Learning Enabled Human Activity Recognition for Improved Medical Services

引用

computer Systems Science & engineering 2023年第2期44卷 961-977页

作者： E.Dhiravidachelvi M.Suresh Kumar L.D.Vijay Anand D.Pritima Seifedine Kadry Byeong-Gwon Kang Yunyoung Nam Department of Electronics and Communication Engineering Mohamed Sathak A.J.College of EngineeringChennai603103India Department of Information Technology Sri Sairam Engineering CollegeChennai602109India Department of Robotics Engineering Karunya Institute of Technology and SciencesCoimbatore641114India Department of Mechatronics Engineering Sri Krishna College of Engineering and TechnologyCoimbatore641008India Deparmtent of Applied Data Science Noroff University CollegeKristiansandNorway Department of Information and Communication Engineering Soonchunhyang UniversityAsanKorea Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea

Human Activity Recognition(HAR)has been made simple in recent years,thanks to recent advancements made in Artiﬁcial Intelligence(AI)*** techniques are applied in several areas like security,surveillance,healthcare,human-robot interaction,and *** wearable sensor-based HAR system includes in-built sensors,human activities can be categorized based on sensor ***,it can also be employed in other applications such as gait diagnosis,observation of children/adult’s cognitive nature,stroke-patient hospital direction,Epilepsy and Parkinson’s disease examination,***-developed Artiﬁcial Intelligence(AI)techniques,especially Deep Learning(DL)models can be deployed to accomplish effective outcomes on HAR *** this motivation,the current research paper focuses on designing Intelligent Hyperparameter Tuned Deep Learning-based HAR(IHPTDL-HAR)technique in healthcare *** proposed IHPTDL-HAR technique aims at recogniz-ing the human actions in healthcare environment and helps the patients in mana-ging their healthcare *** addition,the presented model makes use of Hierarchical Clustering(HC)-based outlier detection technique to remove the ***-HAR technique incorporates DL-based Deep Belief Network(DBN)model to recognize the activities of ***,Harris Hawks Opti-mization(HHO)algorithm is used for hyperparameter tuning of DBN ***,a comprehensive experimental analysis was conducted upon benchmark dataset and the results were examined under different *** experimental results demonstrate that the proposed IHPTDL-HAR technique is a superior per-former compared to other recent techniques under different measures.

关键词： Artiﬁcial intelligence human activity recognition deep learning deep belief network hyperparameter tuning healthcare

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：