检索结果-内蒙古大学图书馆

6th International Conference on Advances in robotics, AIR 2023

作者： Sarmah, Nilavjyoti Bordoloi, Prapti Hazarika, Shyamanta Nirma University Gujrat Ahmedabad India Biomimetic Robotics and Artificial Intelligence Laboratory Indian Institute of Technology Guwahati India

ISBN: (纸本)9781450399807

This paper presents a comprehensive study of real-time finger movement classification using surface electromyogram (EMG) signals. The objective is to accurately classify four different grasp types by analyzing the signals obtained from the forearm muscles. Various commonly used EMG signal classification methods are evaluated and compared: K-Nearest Neighbors (KNN), Binary Neural Network (BNN), Ternary Neural Network (TNN), Linear Support Vector Machine (SVM), Fine Gaussian SVM, Quadratic SVM, Cubic SVM, and Medium Gaussian SVM are the classification methods considered in this study. These methods are chosen based on their prevalence and effectiveness in EMG signal analysis. Medium Gaussian SVM demonstrates a high accuracy in correctly recognizing the different hand grasp types with an accuracy of 86.5 percent. © 2023 ACM.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Intention-Oriented Fast Joint Prediction and Planning for Safe Driving 27

Intention-Oriented Fast Joint Prediction and Planning for Sa...

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Zhang, Mingyi Xue, Jianru Lv, Chen Fang, Jianwu Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence China School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798331505929

The primary challenges for Autonomous Vehicle (AV) navigation in complex scenarios are to effectively handle the interactions between the Ego-Vehicle (EV) and surrounding participants and generate safe yet non-conservative plans. Current approaches employ Planning-Informed Prediction (PIP) and Joint Prediction and Planning (JPP) to model these interactions. At the same time, information loss exists in PIP and JPP always ignores the intention interactions for a free space generation. To this end, this paper incorporates intention interactions into JPP, where a shared intention interaction module is adopted to both the planning and the prediction tasks via a cross-query mechanism, enabling the model to reduce the model size and accelerate inference speed. In contrast to previous methods that typically plan a single trajectory and result in conservative behaviors, we introduce a contingent-masked planner to balance the safety and efficiency, so as to fulfill the scene-level prediction and greatly improve computational efficiency. We evaluate our approach through closed-loop experiments on the CARLA longest6 and Town05 benchmarks, and faster inference speed and more robust performance against state-of-the-art methods. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Design and Optimization of Intelligent Recommendation System Using Machine Learning 5

Design and Optimization of Intelligent Recommendation System...

引用

5th International Symposium on Computer Engineering and Intelligent Communications, ISCEIC 2024

作者： Liu, Ting Zhu, Yafeng Guangzhou Institute of Science and Technology Department of Robotics and Artificial Intelligence Guangzhou China The School of Intelligent Manufacturing and Electrical Engineering Guangzhou Institute of Science and Technology Guangzhou China

ISBN: (纸本)9798331518677

Intelligent recommendation system is a service that is widely studied in the field of data science, implemented through machine learning technology. This article proposes a design scheme for an intelligent recommendation system based on collaborative filtering, providing users with personalized and accurate recommendations. Label classification is crucial in intelligent recommendation, but there are still issues such as diversity, ambiguity, and spam labels. This article first introduces the traditional intelligent recommendation system and improves it a machine learning based intelligent recommendation system design scheme was proposed, and the effectiveness of the improved intelligent recommendation system was verified through experiments. The experimental results show that the intelligent recommendation system design proposed in this article can effectively solve some of the problems existing in traditional intelligent recommendation systems. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Grounded Answers for Multi-agent Decision-making Problem through Generative World Model 38

Grounded Answers for Multi-agent Decision-making Problem thr...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Liu, Zeyang Yang, Xinrui Sun, Shiguang Qian, Long Wan, Lipeng Chen, Xingyu Lan, Xuguang National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Application Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent decision-making problems because they miss the trial-and-error experience and reasoning as humans. To address this limitation, we explore a paradigm that integrates a language-guided simulator into the multi-agent reinforcement learning pipeline to enhance the generated answer. The simulator is a world model that separately learns dynamics and reward, where the dynamics model comprises an image tokenizer as well as a causal transformer to generate interaction transitions autoregressively, and the reward model is a bidirectional transformer learned by maximizing the likelihood of trajectories in the expert demonstrations under language guidance. Given an image of the current state and the task description, we use the world model to train the joint policy and produce the image sequence as the answer by running the converged policy on the dynamics model. The empirical results demonstrate that this framework can improve the answers for multi-agent decision-making problems by showing superior performance on the training and unseen tasks of the StarCraft Multi-Agent Challenge benchmark. In particular, it can generate consistent interaction sequences and explainable reward functions at interaction states, opening the path for training generative models of the future. © 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

An Efficient Wide-Range Pseudo-3D Vehicle Detection Using A Single Camera

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-11页

作者： Ye, Zhupeng Li, Yinqi Yuan, Zejian Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

Wide field-of-view and distant (wide-range) vehicle detection enables active safety in intelligent driving systems. However, existing vehicle detection methods based on rectangular bounding boxes (BBox) often struggle with perceiving wide-range objects, especially small objects at long distances. And BBox expression cannot provide detailed vehicle geometric shape and pose information. This paper proposes a novel wide-range Pseudo-3D Vehicle Detection method based on images from a single camera and incorporates efficient learning methods. This model takes a spliced image as input, obtained by combining two sub-window images from a high-resolution image. This image format maximizes the utilization of limited image resolution to retain essential information about wide-range vehicle objects and effectively improves the detection performance of small targets. To detect pseudo-3D objects, our model adopts specifically designed detection heads. These heads simultaneously output expanded BBox and Side Projection Line (SPL) representations, which capture vehicle shapes and poses, enabling high-precision detection. Furthermore, a joint constraint loss combining the object box and SPL is designed to enhance the detection performance. Experimental results on self-built and KITTI datasets both demonstrate that our model achieves favorable performance in wide-range pseudo-3D vehicle detection across multiple evaluation metrics. Our demo video is available at https://***/watch?v=1gk1PmsQ5Q8. IEEE

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Air2Land:A deep learning dataset for unmanned aerial vehicle autolanding from air to land

引用

IET Cyber-Systems and robotics 2022年第2期4卷 77-85页

作者： Xunchen Zheng Tianjiang Hu Machine Intelligence and Collective Robotics(MICRO)Lab Sun Yat-sen UniversityGuangzhouChina Institute for Artificial Intelligence Sun Yat-sen UniversityGuangzhouChina

In this paper,a novel deep learning dataset,called Air2Land,is presented for advancing the state‐of‐the‐art object detection and pose estimation in the context of one fixed‐wing unmanned aerial vehicle autolanding *** bridges vision and control for ground‐based vision guidance systems having the multi‐modal data obtained by diverse sensors and pushes forward the development of computer vision and autopilot algorithms tar-geted at visually assisted landing of one fixed‐wing *** dataset is composed of sequential stereo images and synchronised sensor data,in terms of the flying vehicle pose and Pan‐Tilt Unit angles,simulated in various climate conditions and landing *** real‐world automated landing data is very limited,the proposed dataset provides the necessary foundation for vision‐based tasks such as flying vehicle detection,key point localisation,pose estimation ***,in addition to providing plentiful and scene‐rich data,the developed dataset covers high‐risk scenarios that are hardly accessible in *** dataset is also open and available at https://***/micros‐uav/micros_air2land as well.

关键词： autonomous landing(autolanding) deep learning,ground stereo vision open dataset unmanned aerial vehicle(UAV)

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on security issues in vehicle-to-grid networks

引用

Journal of Control and Decision 2023年第2期10卷 150-159页

作者： Arun Sekar Rajasekaran Maria Azees Fadi Al-Turjman Department of Electronics and Communication Engineering GMR Institute of TechnologyRajamIndia Artificial Intelligence Engineering Department. Research Center for AI and IoTAI and Robotics InstituteNear East UniversityMersin 10Turkey

Vehicle to grid(V2G)is the most hopeful approach to transfer energy as well as information in the bidirectional way.V2G network is formed by electric vehicles which connect with smart metres for information and energy transfer in a wireless *** though many security preserving schemes developed in V2G networks,they were prone to enormous number of security breaches.A countless deal of works has been done towards it,but security mechanisms in V2G networks are not *** survey work provides a summary about the V2G network characteristics,significance,security services and the security ***,this work offers a summary of some foremost security attacks on various security services such as accessibility,confidentiality,authentication,integrity and non-repudiation and the related countermeasures to make the V2G communications more protected.

关键词： Authentication confidentiality integrity privacy security

来源：评论

学校读者我要写书评

暂无评论

MEG Channel Selection Using Copula Entropy-Based Transfer Entropy for Motor Imagery BCI 46

MEG Channel Selection Using Copula Entropy-Based Transfer En...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Tang, Chao Jiang, Dongyao Chen, Badong Xi'an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an China

ISBN: (纸本)9798350371499

Multi-channel magnetoencephalography (MEG) data provides high spatiotemporal resolution for motor imagery (MI)-based brain-machine interfaces (BCIs). However, not all channels contribute to the performance of BCIs. Taking into account the importance of specific channels in measuring their causal relationships with other channels during MI tasks, a novel channel selection method using copula entropy-based transfer entropy (CTE) is proposed to select task-relevant channels. Experiments on a publicly available dataset validate the effectiveness of the proposed methods. Compared to using all channels, channel selection based on CTE can significantly (p © 2024 IEEE.

关键词： Magnetoencephalography

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Curriculum Learning for Ultra-Wide-Angle fundus Optic Disc Segmentation

Semi-Supervised Curriculum Learning for Ultra-Wide-Angle fun...

引用

2024 China Automation Congress, CAC 2024

作者： Wang, Yingkai Chen, Yiyi Wu, Jiayi Xin, Jingmin National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9798350368604

Segmentation of the optic disc in ultra-wide-angle fundus images could aid in detection and diagnosis of diabetic kidney disease and diabetic retinopathy. Due to the wide field of view, large image size, and small targets of ultra-wide-angle fundus images, it’s hard to annotate them. In this case, semi-supervised methods could solve this problem. However, standalone semi-supervised training does not take into account the differences between samples. We developed a new semi-supervised training method incorporating curriculum learning, where the model initially trains on easier samples and gradually progresses to more hard ones. This strategy could avoid the possible negative impact of the unlabeled samples in early stages in training and strengthen model’s robustness and serves as a plug- and-play approach and is adaptable to existing semi-supervised semantic segmentation methods. More concretely, we design a difficulty measurer to estimate the training difficulty of samples from the perspective of the entire dataset and a pace controller to control training time and duration of different samples according to their training difficulty. The experiment result shows the method we proposed could improves the performance. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a VTOL UAV and its Digital Twin

Design and Implementation of a VTOL UAV and its Digital Twin

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Zhong, Yebin Huang, Xizheng Lin, Zexin Chen, Jiayu Sun, Zhenglong Ji, Xiaoqiang The Chinese University of Hong Kong The Shenzhen Institute of Artificial Intelligence and Robotics for Society The School of Science and Engineering Shenzhen China

ISBN: (纸本)9798350325706

In this paper, we adopted a VTOL UAV model design and developed a digital twin for the corresponding model. The digital twin consists of the following parts: Unity simulation system, physical VTOL UAV, and communication interface. As we know, the main function of the digital twin is verification. However, there is a gap between the virtual simulation and physical test results. Therefore, based on the Unity engine and the VTOL UAV, this paper will demonstrate a simulation case of performing short takeoff and vertical landing operations using the VTOL UAV. These simulation results show that the system can simulate the aerodynamics, physics, and controls of the UAV with high fidelity and reliability. The digital twin system can also provide a platform for VTOL UAV application development, theoretical investigation, and intelligent training. © 2023 IEEE.

关键词： Digital Twin UAV Design Unity VTOL

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：