检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Bai, Zongwen Liu, Xiangzhen Zhou, Meili Wozniak, Marcin Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data School of Physics and Electronic Information Yan’an University Yan’an716000 China School of Physics and Electronic Information Yan’an University Yan’an716000 China Faculty of Applied Mathematics Silesian University of Technology Kaszubska 23 Gliwice44100 Poland

Existing monocular visual SLAM solutions are mostly achieved by adding various sensors to improve the accuracy of monocular cameras, which is not the best performance of monocular cameras and is not friendly to existing hardware devices. This paper proposes a visual SLAM system based on ORB-SLAM3, which aims to maximize monocular resources. On the basis of monocular cameras, depth map prediction network is added to simulate depth cameras. Feature points are extracted using CNN and ORB fusion method, and feature filtering is carried out combining with depth maps. In order to improve the pose prediction accuracy of monocular camera in driving scenes and avoid the interference of dynamic objects to SLAM system, an image instance segmentation network is introduced in this paper. The code is public at https://***/MrLiuXiangzhen/DDM-SLAM . © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research on Path Planning of robot Arm Based on RRT-connect Algorithm

Research on Path Planning of Robot Arm Based on RRT-connect ...

引用

第33届中国控制与决策会议

作者： Chaoli Zhao Xing Ma Chunyang Mu The Key Laboratory of Intelligent Information and Big Data Processing of Ningxia North Minzu University School of Electrical and Information Engineering North Minzu University College of Mechatronic Engineering North Minzu University

To address the shortcomings of the RRT-connect algorithm in terms of low efficiency of path planning in sampling space and high randomness of node sampling,this paper proposes a three-source fast extended random tree algorithm(GT-RRT) combined with gravitational *** algorithm adds a third node as a new extension node between the start point and the target point,so that the algorithm can extend the random tree from the start point,the target point and the third *** the same time,a gravitational field is superimposed on each of the three nodes to guide the generation of nodes,reducing the search range of the null *** GT-RRT and RRT-connect algorithms are compared in 30 simulation experiments,and the results show that the improved algorithm has better path planning efficiency than the original algorithm in complex ***,this paper verifies the effectiveness of the improved algorithm in both the moveit simulation and the real environment by using the robot arm of Baxter robot as an example.

关键词： Path planning RRT-connect Gravitational potential field robotic arm

来源：评论

学校读者我要写书评

暂无评论

A PDDL based Disaster Storyline Generation Approach

A PDDL based Disaster Storyline Generation Approach

引用

第三十九届中国控制会议

作者： Mingrong Tang Jinxin Ni Qifeng Zhou Automation Department of Xiamen University Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision

The rapid development of computer technology has brought challenges to the management of disaster *** an emergency occurs, a huge amounts of relevant information will be produced. In order to form a clear event development context from the overloaded Internet data and improve the corresponding efficiency of emergency events, in this paper, we propose a method for disaster storyline construction based on intelligent planning. Specifically, we first extract the semantic information from the News text to build a Planning Domain Definition Language（PDDL） domain model, which contains complete domain knowledge. Then we use a planner to plan the event storylines that meets the presets in the domain model. To our knowledge, this is the first attempt to combine natural language processing（NLP） technology with intelligent planning technology for disaster storyline generation. Different from the previous method, our proposed model is more focused both on the event evolve information and the government emergency measures, which can provide more reference value for relevant emergency response.

关键词： Planning Domain Definition Language Disaster Storyline Generation Dependency Parsing

来源：评论

学校读者我要写书评

暂无评论

An ontology-supported inquiry learning technique

Journal of Network Intelligence

引用

Journal of Network Intelligence 2021年第1期6卷 16-28页

作者： Xue, Xingsi Zhang, Jie Yang, Chaofan Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology No.33 Xuefu South Road University Town Minhou Fuzhou Fujian350118 China School of Computer Science and Engineering Yulin Normal University No.299 Education Middle Road Yulin City Guanxi Province537000 China School of Computer Science and Mathematics Intelligent Information Processing Research Center Fujian University of Technology No.33 Xueyuan Road University Town Minhou Fuzhou Fujian350118 China Guangxi Key Laboratory of Automatic Detecting Technology and Instruments Guilin University of Electronic Technology No.1 Jinji Road Guilin Guangxi541004 China

Although Inquiry-based Learning (IBL) offers compelling opportunities for the engineering education, one of the challenges to the implementation of it is that the learner always lacks of the background knowledge. To provide him with the necessary knowledge when making the inquiry, this paper proposes an Ontology Supported Inquiry Learning technique (OSIL), which works on the basis of two ontologies, i.e. curriculum ontology and the learner’s ontology. The experimental results show that the constructed curriculum ontology and learner ontology is of high-quality, and the answers recommended by OSIL almost perfectly match with the true answers. From the experimental results, we can see that it is a feasible way of using the software engineering and prototype evolution method to construct the curriculum and learner ontology, and the individual inquiry based on two ontologies is able to provide the learners with high-quality personalized services. © 2021, Taiwan Ubiquitous Information. All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future

arXiv

引用

arXiv 2024年

作者： Sun, Shilin An, Wenbin Tian, Feng Nan, Fang Liu, Qidong Liu, Jun Shah, Nazaraf Chen, Ping School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an710049 China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an710049 China Institute for Future Transport and Cities Coventry University Priory Street CoventryCV1 5FB United Kingdom Department of Engineering University of Massachusetts Boston BostonMA02125 United States

Artificial intelligence (AI) has rapidly developed through advancements in computational power and the growth of massive datasets. However, this progress has also heightened challenges in interpreting the "black-box" nature of AI models. To address these concerns, eXplainable AI (XAI) has emerged with a focus on transparency and interpretability to enhance human understanding and trust in AI decision-making processes. In the context of multimodal data fusion and complex reasoning scenarios, the proposal of Multimodal eXplainable AI (MXAI) integrates multiple modalities for prediction and explanation tasks. Meanwhile, the advent of Large Language Models (LLMs) has led to remarkable breakthroughs in natural language processing, yet their complexity has further exacerbated the issue of MXAI. To gain key insights into the development of MXAI methods and provide crucial guidance for building more transparent, fair, and trustworthy AI systems, we review the MXAI methods from a historical perspective and categorize them across four eras: traditional machine learning, deep learning, discriminative foundation models, and generative LLMs. We also review evaluation metrics and datasets used in MXAI research, concluding with a discussion of future challenges and directions. A project related to this review has been created at https://***/ShilinSun/mxai_review. Copyright © 2024, The Authors. All rights reserved.

关键词： data fusion

来源：评论

学校读者我要写书评

暂无评论

Estimating Power Consumption of Containers and Virtual Machines in data Centers

Estimating Power Consumption of Containers and Virtual Machi...

引用

IEEE International Conference on Cluster Computing

作者： Xusheng Zhang Ziyu Shen Bin Xia Zheng Liu Yun Li Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications

ISBN: (数字)9781728166773

ISBN: (纸本)9781728166780

Virtualization technologies provide solutions of cloud computing. Virtual resource scheduling is a crucial task in data centers, and the power consumption of virtual resources is a critical foundation of virtualization scheduling. Containers are the smallest unit of virtual resource scheduling and migration. Although many effective models for estimating power consumption of virtual machines (VM) have been proposed, few power estimation models of containers have been put forth. In this paper, we offer a fast-training piecewise regression model based on decision tree to build a VM power estimation model and estimate the containers' power by treating the container as a group of processes on the VM. In our model, we characterize the nonlinear relationship between power and features and realize the effective estimation of the containers on the VM. We evaluate the proposed model on 13 workloads in PARSEC and compare it with several models. The experimental results prove the effectiveness of our proposed model on most workloads. Moreover, the estimated power of the containers is in line with expectations.

关键词： Power demand Processor scheduling Estimation Containers Virtual machining data models Virtualization

来源：评论

学校读者我要写书评

暂无评论

Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment

arXiv

引用

arXiv 2024年

作者： Zhou, Fei Gu, Tianhao Huang, Zhicong Qiu, Guoping College of Electronic and Information Engineering Shenzhen University Shenzhen518060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen518060 China SZU-AFS Joint Innovation Center for Artificial Intelligence Technology Shenzhen518000 China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen518060 China School of Computer Science The University of Nottingham Ningbo China Zhejiang315100 China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom

The visual quality of an image is confounded by a number of intertwined factors including its semantic content, distortion characteristics and appearance properties such as brightness, contrast, sharpness, and colourfulness. Distilling high level knowledge about all these quality bearing attributes is crucial for developing objective Image Quality Assessment (IQA). While existing solutions have modeled some of these aspects, a comprehensive solution that involves all these important quality related attributes has not yet been developed. In this paper, we present a new blind IQA (BIQA) model termed Self-supervision and Vision-Language supervision Image QUality Evaluator (SLIQUE) that features a joint vision-language and visual contrastive representation learning framework for acquiring high level knowledge about the images semantic contents, distortion characteristics and appearance properties for IQA. For training SLIQUE, we have developed a systematic approach to constructing a first of its kind large image database annotated with all three categories of quality relevant texts. The Text Annotated Distortion, Appearance and Content (TADAC1) database has over 1.6 million images annotated with textual descriptions of their semantic contents, distortion characteristics and appearance properties. The method for constructing TADAC and the database itself will be particularly useful for exploiting vision-language modeling for advanced IQA applications. Extensive experimental results show that SLIQUE has superior performances over state of the art, demonstrating the soundness of its design principle and the effectiveness of its implementation. The link to the TADAC dataset is https://***/documents/tadactextannotated-distortion-appearance-and-content Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Video-Based 3D Human Pose Estimation Research

Video-Based 3D Human Pose Estimation Research

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Siting Tao Zhi Zhang College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan China China

ISBN: (纸本)9781665409858

At present, most of the video-based 3D human pose estimation methods process the video frame by frame, ignoring the timing information of the upper and lower frames of the video. When there is a single-frame estimation error caused by self-occlusion, the occlusion part will be Some strange movements appear due to information loss, and the estimated results make it difficult to produce accurate motion sequences. Therefore, considering the continuity of the upper and lower frames of the video, this paper adopts the HMR algorithm and introduces a bidirectional long-term memory network (BI-LSTM) in the encoding part to process the video sequence, and then outputs the parameters of the human body model through the SMPL parameters and inputs them into the discriminator for confrontation, train. In order for the discriminator to also take into account the semantic information of the temporal context, the discriminator in this paper also introduces a BI-LSTM network to improve the authenticity of the generated poses. Experimental results show that the accuracy of the model is improved when self-occlusion occurs.

关键词： Training Industrial electronics Solid modeling Estimation error Three-dimensional displays Biological system modeling Pose estimation

来源：评论

学校读者我要写书评

暂无评论

Low-Light Enhancement Effect on Classification and Detection: An Empirical Study

arXiv

引用

arXiv 2024年

作者： Wu, Xu Lai, Zhihui Jie, Zhou Gao, Can Hou, Xianxu Zhang, Ya-Nan Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China

Low-light images are commonly encountered in real-world scenarios, and numerous low-light image enhancement (LLIE) methods have been proposed to improve the visibility of these images. The primary goal of LLIE is to generate clearer images that are more visually pleasing to humans. However, the impact of LLIE methods in high-level vision tasks, such as image classification and object detection, which rely on high-quality image datasets, is not well explored. To explore the impact, we comprehensively evaluate LLIE methods on these high-level vision tasks by utilizing an empirical investigation comprising image classification and object detection experiments. The evaluation reveals a dichotomy: While Low-Light Image Enhancement (LLIE) methods enhance human visual interpretation, their effect on computer vision tasks is inconsistent and can sometimes be harmful. Our findings suggest a disconnect between image enhancement for human visual perception and for machine analysis, indicating a need for LLIE methods tailored to support high-level vision tasks effectively. This insight is crucial for the development of LLIE techniques that align with the needs of both human and machine vision. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

EEG-GNet: GCN-Based EEG Signal Fatigue Detection Network for Edge Devices

EEG-GNet: GCN-Based EEG Signal Fatigue Detection Network for...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Fuquan Zhang Yu Wu Xinxin Xu Chuansheng Wang Minjia Ma Antoni Grau Jiayan Huang School of Computer and Big Data Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of New Engineering Industry Putian University Putian China Department of Automatic Control Polytechnic University of Catalonia Barcelona Spain School of Robotics Xi’an Jiaotong-Liverpool University Suzhou China College of New Engineering Industry Putian University Fujian Ruituo Information Technology Limited Company Putian China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Fatigue driving is a common potential traffic safety hazard. To detect and analysis the driver Fatigue degree in real-time, more attention have been increasing paid to application research of EEG fatigue detection device. However, existing methods suffer from complex model structure or large-scale model parameters. In the other words, they requires high computational consumption and large memory footprint, which creates a contradiction between model and portable EEG machine with limited hardware resources. In this work, we take both time and frequency domains of EEG signal into account and design an lightweight and efficient driver fatigue detection network based on GCN (EEG-GNet), which is available edge-end device application. Experiments on 4th Raspberry Pi on a public baseline dataset show that our EEG-GNet outperforms the state-of-the-art methods and takes good tradeoff between detection accuracy and resource consumption. Our EEG-GNet provides a new potential opportunity for future applications in practical portable/wearable (P/W) devices.

关键词： Accuracy Computational modeling Image edge detection Frequency-domain analysis Fatigue Brain modeling Feature extraction Electroencephalography Real-time systems Time-domain 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：