检索结果-内蒙古大学图书馆

基于多分辨率弹性门控注意力和高斯混合模型的地铁站PM_(2.5)浓度区间预测

Journal of Central South University 2023年第8期30卷 2818-2832页

作者：方亚民刘辉 Institute of Artificial Intelligence and Robotics(IAIR) Key Laboratory of Traffic Safety on Track of Ministry of EducationSchool of Traffic&Transportation EngineeringCentral South UniversityChangsha 410075China

地铁是城市中短途通勤的主流交通工具。然而,由于地铁站内空气流动性差,所以监测地铁空气质量并提供高污染预警具有重大意义。为解决地铁站内空气质量预警问题,本文提出了一个概率预测框架。首先,采用基于概率损失的自动编码器对PM_(2.5... 详细信息

地铁是城市中短途通勤的主流交通工具。然而,由于地铁站内空气流动性差,所以监测地铁空气质量并提供高污染预警具有重大意义。为解决地铁站内空气质量预警问题,本文提出了一个概率预测框架。首先,采用基于概率损失的自动编码器对PM_(2.5)数据进行检测并纠正异常值。其次,采用多分辨率弹性门控注意力机制改进序列到序列(Seq2Seq)中编码器的结构,以减弱预测过程中的误差累积和历史信息丢失。此外,将多输出策略和弹性门控注意力机制相结合,来改进Seq2Seq中解码器的结构,以减少预测时的误差累积。最后,在Seq2Seq的输出端嵌入高斯混合模型(Gaussian mixture model,GMM),使其能够适应浓度分布的变化并生成浓度的概率分布。所提出的模型在第1步、3步和5步预测中的平均MAPE分别为0.94%、1.16%和1.26%。模型对地铁站PM_(2.5)数据的测试结果表明,与其他模型相比,所提出的模型的Pinball loss和Winkler score更小。

关键词： PM_(2.5) 地铁站混合高斯分布区间预测注意力机制

来源：评论

学校读者我要写书评

暂无评论

Multi-Robot Path Planning in Narrow Warehouse Environments with Fast Feasibility Heuristics 41

Multi-Robot Path Planning in Narrow Warehouse Environments w...

引用

第41届中国控制会议

作者： Jiaxi Huo Ronghao Zheng Senlin Zhang Meiqin Liu College of Electrical Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Zhejiang University Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,we present a novel method for solving the multi-robot path planning problem in narrow warehouse *** may have to be operated in close proximity to each other in narrow lanes between pod clusters,which challenges robot-robot collision *** motivates us to consider an efficient algorithm to generate collision-free robot paths in narrow warehouse *** algorithm builds a two-stage scheme based on integer programming:(i) multirobot path planning under one-way constraints;and(ii) fast feasibility *** developed algorithm has two advantages:(i) the proposed scheme successfully avoids the situation where the robots collide in narrow lanes;and(ii) by using the fast feasibility heuristics which replaces the integer programming solver's built-in feasibility heuristics,the feasibility heuristics' running time can be effectively reduced while producing better initial feasible solutions for the integer programming model solving *** with the existing optimal,sub-optimal,and polynomial-complexity algorithms,our developed algorithm can leverage the advantage of integer programming to effectively reach a balance between running time and optimality in narrow warehouse *** point is demonstrated in the simulations.

关键词： Path planning Multi-robot or multi-agent systems Collision avoidance Logistics

来源：评论

学校读者我要写书评

暂无评论

Continual Forgetting for Pre-Trained Vision Models

Continual Forgetting for Pre-Trained Vision Models

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hongbo Zhao Bolin Ni Junsong Fan Yuxi Wang Yuntao Chen Gaofeng Meng Zhaoxiang Zhang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

For privacy and security concerns, the need to erase un-wanted information from pre-trained vision models is becoming evident nowadays. In real-world scenar-ios, erasure requests originate at any time from both users and model owners. These requests usually form a sequence. Therefore, under such a setting, selective information is expected to be continuously removed from a pre-trained model while maintaining the rest. We define this problem as continual forgetting and identify two key challenges. (i) For unwanted knowledge, efficient and effective deleting is crucial. (ii) For remaining knowledge, the impact brought by the forgetting procedure should be minimal. To address them, we propose Group Sparse LoRA (GS-LoRA). Specifically, towards (i), we use LoRA modules to fine-tune the FFN layers in Transformer blocks for each forgetting task independently, and towards (ii), a simple group sparse regularization is adopted, enabling automatic selection of specific LoRA groups and zeroing out the others. GS-LoRA is effective, parameter-efficient, data-efficient, and easy to implement. We conduct extensive experiments on face recognition, object detection and image classification and demonstrate that GS-LoRA manages to forget specific classes with minimal impact on other classes. Codes will be released on https://***/bjzhb666/GS-LoRA.

关键词： Continuing education Privacy Computer vision Codes Large language models Face recognition Object detection

来源：评论

学校读者我要写书评

暂无评论

Recovering Visual Human's Attention in Human-Robot Interaction for a Promoter Service Robot

Recovering Visual Human's Attention in Human-Robot Interacti...

引用

Intelligent Reality (ICIR), IEEE International Conference on

作者： Jesus Eduardo Hermosilla-Diaz Andrey Solovov Mohammad Zarei Jeeangh Jennessi Reyes-Montiel Vishal Gautam Bruno Perreira Gustavo Assuncao Paulo Menezes Antonio Marin-Hernandez Research Institute of Artificial intelligence Universidad Veracruzana Xalapa Mexico Institute of Systems and Robotics University of Coimbra Coimbra Portugal

ISBN: (数字)9798331534424

ISBN: (纸本)9798331534431

The use of service robots is an alternative for prod-ucts and services promotion. In commercial areas an effective human-robot interaction is essential. However, communicating information effectively and thus maximizing the likelihood of a product or service's acceptance by the potential consumer remains challenging. In this work, we propose an architecture that integrates multiple modules, including visual gaze esti-mation, head tracking, human detection, position estimation, and attention recovery behaviors, to recover human attention during potential scenarios such as promotional tasks. Attention is presented as a decay function on different parameters, such as visual gaze and head position. When the robot detects a shutdown at the attention level, it executes a behavior to recover it. The proposal details our architecture's design and the modules' theoretical implications, highlighting the potential for improved service-robot interaction.

关键词： Measurement Visualization Service robots Natural languages Estimation Human-robot interaction Gesture recognition Behavioral sciences Proposals

来源：评论

学校读者我要写书评

暂无评论

Categorization of IRIS Flower Using Different Machine Learning Strategies

Categorization of IRIS Flower Using Different Machine Learni...

引用

Electrical, Electronics, Communication and Computers (ELEXCOM), International Conference on

作者： Amit Singh Rajawat Ashutosh Kewat Manjhi Anshika Srivastava Department of Information Technology (Artificial Intelligence and Robotics) Madhav Institute of Technology & Science Gwalior India Centre for Artificial Intelligence (Artificial Intelligence and Data Science) Madhav Institute of Technology & Science Gwalior India

Today, machine learning is important in many areas, including agriculture, computer science, healthcare, and medicine, to name a few. It is known that our planet is abundant in species and millions of biomes thrive in the Earth's ecosystem. Some of them share physical characteristics such as size, shape, and color. It is quite difficult for a general human being to determine which items are of which sort. Similarly, it is difficult to determine which flower is of which subspecies in flower species. Classification is the most essential machine learning approach for distinguishing one item from another. Setosa, Versicolor, and Virginica are the three subspecies of the Iris flower. Five approaches are presented in depth, including Decision tree, Naive Bayes, Linear Support Vector Machine (SVM), K-nearest neighbor, and Logistic regression, and the implementation is done using the sci-kit learn the tool. Furthermore, different sizes of training and testing sets are applied to and compared with each method. The IRIS dataset was analyzed using classification and regression algorithms with a 10-fold cross-validation score. The emphasis was on examining patterns utilizing the flower's sepal and petal sizes. In terms of accuracy, the findings showed that the Linear SVM classifier outperformed with 99.17% Model accuracy and 100% of Test accuracy as compared to the Decision tree, Naive Bayes, K-nearest neighbor, and Logistic regression models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GelPixel: A Single-Pixel-Based Tactile Sensor

GelPixel: A Single-Pixel-Based Tactile Sensor

引用

2023 IEEE International Conference on Real-Time Computing and robotics, RCAR 2023

作者： Huang, Binhua Li, Xiaoyu Sumari, Putra Ye, Chaoxiang Zhou, Zhenning Yin, Meng Yi, Zhengkun Wu, Xinyu Shenzhen Institute of Artificial Intelligence and Robotics for Society Siat Branch Shenzhen518055 China Universiti Sains Malaysia School of Computer Science 11800 Malaysia Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9798350327182

In this paper, we present the design and development of a novel optical tactile sensor that uses a single-pixel color light-to-frequency converter (TCS3200) and spectral decoding to recognize presses at different positions. This innovative approach overcomes the limitations associated with camera-based sensors, such as increased manufacturing costs and shape restrictions, enabling potential integration as a skin-like layer over a robot's body. Our proposed direct light propagation structure demonstrates enhanced sensitivity and a broader measuring range compared to traditional reflection structures. Using Ecoflex as the elastomer, the sensor's design incorporates a three-layer structure, including an LED layer, an elastomer layer, and a color sensor layer. Experimental results demonstrate that the proposed sensor performs well in localization tasks, achieving over 95% accuracy using multi-target regression for rendering poked positions. This study demonstrates the potential of single-pixel-based tactile sensors in various applications and provides a foundation for further exploration in this area. © 2023 IEEE.

关键词： Tactile sensors

来源：评论

学校读者我要写书评

暂无评论

Fin-MLGAT: Line Graph Attention Network for Dialogue Emotion Recognition in Stock Market and its Evaluations 11

Fin-MLGAT: Line Graph Attention Network for Dialogue Emotion...

引用

11th International Conference on Dependable Systems and Their Applications, DSA 2024

作者： Feng, Xiaobing Feng, Ling Xu, Xiujuan Qiao, Jiaqi Zhang, Wenjian Shanghai University of International Business and Economics School of Finance Institute of Change Management and Artificial Intelligence Shanghai China Shanghai Ocean University School of Robotics Engineering Shanghai China Dalian University of Technology School of Software Technology Dalian China

ISBN: (纸本)9798331532390

With the rapid development of social media and digitalization, the task of emotion pattern recognition and extreme emotion detection in conversation is playing an increasingly important role in understanding emotion interaction among and between parties. Traditional methods employ probabilistic statistical models that leverage prior knowledge to construct models However when dealing with complex patterns, large scale data, and high-dimensional features, their performance becomes limited. Alternatively, deep learning methods are capable of automatically learning highly abstract feature representations from raw datasets. Our Fin-MLGAT mines the emotional information dependent on the target utterance by focusing on local con text and global context at different scales. Experiments show that our model achieves the second-highest performance among all current methods by Wa-F1. Moreover, the model can show high accuracy in a few classes without additional measures. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

A Spatial Feature Extraction Method for Enhancing Upper Limb Motion Intent Prediction in EMG-PR System 46

A Spatial Feature Extraction Method for Enhancing Upper Limb...

引用

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

作者： Peng, Boxing Zhang, Haoshi Li, Xiangxin Zheng, Yue Li, Guanglin Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China University of Chinese Academy of Sciences Shenzhen College of Advanced Technology Shenzhen518055 China Southern University of Science and Technology Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Shenzhen518055 China Siat Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

ISBN: (纸本)9798350371499

High-Density Surface Electromyography (HD-sEMG) enriches motion intention pattern recognition systems by providing more spatial information. Multichannel linear descriptors (MLD) could provide a comprehensive description of the overall state characteristics within the muscle regions. In this study, an MLD-based spatial feature extraction method was proposed to capture differences and correlations in various muscle regions during movement, ultimately enhancing the system's classification accuracy. The performance of the feature extraction method was compared with traditional time domain feature extraction method under various classifiers and different movement types. The results show that employing the proposed method with the spatial features improves the classification error rates of combined movements from 11.14% to 7.28%, and better adaptability for all classifiers utilized in this study, which shows the effect of utilization of spatial information in different muscle regions. © 2024 IEEE.

关键词： Electromyography

来源：评论

学校读者我要写书评

暂无评论

Visual Detection for Non-Ferrous Metal Ingots With Wavelet Denoising and Contour Corner Extraction 7

Visual Detection for Non-Ferrous Metal Ingots With Wavelet D...

引用

7th Asia-Pacific Conference on Intelligent Robot Systems, ACIRS 2022

作者： Qiu, Zehao Sun, Ning Zhang, Chenglin Sang, Wenchuang Fang, Yongchun Institute of Robotics and Automatic Information Systems College of Artificial Intelligence Nankai University Tianjin300350 China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen518083 China

ISBN: (数字)9781665485197

ISBN: (纸本)9781665485197

To realize the intelligent grinding of non-ferrous metal ingots, visual detection algorithms are required to provide the information of metal ingots for robotic manipulators. However, metal ingots in moving molds on ingot casting lines are accompanied by complicated backgrounds and continuous changes, which demands higher accuracy and stronger robustness of visual detection. Based on two kinds of metal ingots and the analysis of metal ingot images, a wavelet-based method with an improved threshold and threshold function is utilized to reduce noises. Afterward, the edge information of metal ingots is obtained by edge line segment detection, and the detected edges are selected according to their positions and lengths. Moreover, in order to extract the contour corners of metal ingots, basic contours are detected and further fitted into metal ingot contours. Finally, experimental results verify that the proposed metal ingot detection algorithm achieves satisfactory accuracy, robustness, and real-time performance for different images and metal ingots. © 2022 IEEE.

关键词： Metals

来源：评论

学校读者我要写书评

暂无评论

Large-scale Deployment of Vision-based Tactile Sensors on Multi-fingered Grippers

Large-scale Deployment of Vision-based Tactile Sensors on Mu...

引用

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

作者： Meng Wang Wanlin Li Hao Liang Boren Li Kaspar Althoefer Yao Su Hangxin Liu State Key Laboratory of General Artificial Intelligence Beijing Institute for General Artificial Intelligence (BIGAI) Centre for Advanced Robotics @ Queen Mary (ARQ) Queen Mary University of London

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Vision-based Tactile Sensors (VBTSs) show significant promise in that they can leverage image measurements to provide high-spatial-resolution human-like performance. However, current VBTS designs, typically confined to the fingertips of robotic grippers, prove somewhat inadequate, as many grasping and manipulation tasks require multiple contact points with the object. With an end goal of enabling large-scale, multi-surface tactile sensing via VBTSs, our research (i) develops a synchronized image acquisition system with minimal latency, (ii) proposes a modularized VBTS design for easy integration into finger phalanges, and (iii) devises a zero-shot calibration approach to improve data efficiency in the simultaneous calibration of multiple VBTSs. In validating the system within a miniature 3-fingered robotic gripper equipped with 7 VBTSs we demonstrate improved tactile perception performance by covering the contact surfaces of both gripper fingers and palm. Additionally, we show that our VBTS design can be seamlessly integrated into various end-effector morphologies significantly reducing the data requirements for calibration.

关键词： Fingers Tactile sensors Surface morphology Morphology Grasping Calibration Sensors Synchronization Grippers Intelligent robots

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：