检索结果-内蒙古大学图书馆

SSRN 2024年

作者： de Oliveira Evald, Paulo Jefferson Dias Brião, Stephanie Loi Aoki, Vivian Misaki da Silva, César Bastos dos Santos Cardoso, Dayana Pinheiro, Pedro Miranda de Oliveira, Felipe Gomes André Barbosa Cunha, Mauro Jorge Drews, Paulo Lilles Intelligent Systems and Control Group Federal University of Pelotas RS Pelotas Brazil Intelligent Robotics and Automation Group Federal University of Rio Grande RS Rio Grande Brazil Department of Computer Engineering and Industrial Automation State University of Campinas SP Campinas Brazil Federal Institute of Education Science and Technology in Rio Grande do Sul RS Pelotas Brazil Institute of Exact Sciences and Technology Federal University of Amazonas Itacoatiara AM Amazonas Brazil Brazil

Research in mobile robotics is growing into applications for difficult-to-access environments, such as in rescue and transport missions. Furthermore, autonomous vehicles can perform data collection in complex approach areas. Therefore, the study of hybrid unmanned vehicles is relevant for several areas, since these vehicles can act in different domains. The developed vehicle, called Hydrone, is designed in a quadrotor-type structure and equipped with a set of aerial and underwater propellers, which are fixed and independent between them. In this sense, this work presents the mathematical modeling of an unmanned hybrid vehicle, which can navigate underwater and aerial environments. Furthermore, the modeling considers the ground effect due to the influence on the vehicle’s trajectory change and the dynamics of the transition zone between water-air and air-water. These dynamics are important to evaluate the controller’s performance. Numerical simulations consider both transitions (water-air and air-water) and they are performed to discuss the influence of acting forces on the vehicle stability and position-tracking performance using a classical control system. © 2024, The Authors. All rights reserved.

关键词： Hybrid vehicles

来源：评论

学校读者我要写书评

暂无评论

A CNN-LSTM Based Model to Predict Trajectory of Human-Driven Vehicle

A CNN-LSTM Based Model to Predict Trajectory of Human-Driven...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Shehab Alsanwy Houshyar Asadi Mohammad Reza Chalak Qazani Shady Mohamed Saeid Nahavandi Institute of Intelligent Systems Research and Innovation (IISRI) Deakin University Geelong VIC Australia Department of Computer Science and Information Systems (CSIS) Murray State University Murray KY USA Swinburne University of Technology Hawthorn VIC Australia

Vehicle trajectory prediction is essential in ensuring the safe and efficient operation of advanced driver assistance systems (ADAS) and autonomous vehicles (AVs), as it enables highly efficient collision avoidance, path planning, and traffic control. However, existing models for vehicle trajectory prediction predominantly focus on limited driving scenarios, resulting in limited applicability. To address this limitation, we present a novel vehicle trajectory prediction approach that employs a Convolutional Long Short-Term Memory (CNN-LSTM) model, incorporating simulated environments and vehicle dynamic time series data, including longitudinal, vertical, and latitudinal position and acceleration. Our approach is distinguished by its ability to handle diverse urban driving scenarios, such as highways, roundabouts, intersections, and turns, which enhances its applicability and generalizability. We experimented and collected vehicle data from 17 drivers using a stationary driving simulator and the Euro Truck Simulator software. For the model implementation and validation, we utilized Python 3.9 and Google Colab, as well as the Scikit-learn library for Deep learning algorithms. The proposed CNN-LSTM model leverages a convolutional layer to learn local patterns and an LSTM layer to capture long-term temporal dependencies, improving performance in predicting vehicle trajectories. The experimental results demonstrate that the CNN-LSTM model provides more accurate predictions for longitudinal and lateral positions compared to traditional vehicle trajectory prediction methods that employ LSTM and Recurrent Neural Network (RNN). This research contributes to developing robust and reliable vehicle trajectory prediction systems vital for ADAS and AVs' safe and efficient operation. The proposed approach broadens the applicability of trajectory prediction models, enabling better-informed decision-making in various driving conditions and ultimately improving road safety and efficien

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accessibility-Aware Reinforcement Learning for Inclusive Robotic Navigation

Accessibility-Aware Reinforcement Learning for Inclusive Rob...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Mengsha Hu Yunhuan Wu Yibei Guo Yi Wu Chao Shi Lei Xu Rui Liu Department of Computer Science Kent State University Kent OH USA Robotics Institute Carnegie Mellon University Pittsburgh PA USA Cognitive Robotics and AI Lab (CRAI) College of Aeronautics and Engineering Kent State University Kent OH USA Informatique et Sciences du Numérique (Computer Research Laboratory) CentraleSupélec Paris-Saclay University Gif-sur-Yvette France Department of Systems Science and Industrial Engineering Binghamton University Binghamton NY USA

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

Robotic navigation aids humans in essential scenarios, including airport customer boarding, commercial meeting receptions, and disaster site navigation. While individuals benefit from robotic services, these services pose accessibility challenges for people with disabilities. Robots may face limitations in mobility, vision, hearing, and cognitive reasoning, hindering disabled individuals' access to these services. As robotic services become increasingly prevalent, ensuring they are inclusive and accessible is crucial, accommodating human disabilities with adaptations such as slower movements, standing support, and hazard detection. To address this issue, this study introduces a novel Accessibility-Aware Reinforcement Learning model (ARL). ARL extracts disability-related information from human behavioral observations using a contextembedding neural network. It then adjusts robot motions to provide inclusive assistance to individuals with disabilities. To assess the effectiveness of this approach, four assisting services in navigation scenarios ('lead', 'wait', 'assist', and 'protect') and three application scenarios involving navigating elderly individuals in a museum, through traffic, and across a building patio were designed. The results validate ARL's efficacy in enabling robots to make accessibility-aware decisions, thereby enhancing their support for individuals with disabilities.

关键词： Robot motion Navigation Neural networks Reinforcement learning Feature extraction People with disabilities Robot learning Data mining Older adults Robots

来源：评论

学校读者我要写书评

暂无评论

Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps 38

Binding in hippocampal-entorhinal circuits enables compositi...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Kymn, Christopher J. Mazelet, Sonia Thomas, Anthony Kleyko, Denis Frady, E. Paxon Sommer, Friedrich T. Olshausen, Bruno A. Redwood Center for Theoretical Neuroscience Helen Wills Neuroscience Institute UC Berkeley Berkeley United States Université Paris-Saclay ENS Paris-Saclay Gif-sur-Yvette France Department of Electrical and Computer Engineering UC Davis Davis United States Centre for Applied Autonomous Sensor Systems Örebro University Örebro Sweden Intelligent Systems Lab Research Institutes of Sweden Kista Sweden Intel Labs Santa Clara United States Herbert Wertheim School of Optometry & Vision Science UC Berkeley Berkeley United States

We propose a normative model for spatial representation in the hippocampal formation that combines optimality principles, such as maximizing coding range and spatial information per neuron, with an algebraic framework for computing in distributed representation. Spatial position is encoded in a residue number system, with individual residues represented by high-dimensional, complex-valued vectors. These are composed into a single vector representing position by a similarity-preserving, conjunctive vector-binding operation. Self-consistency between the representations of the overall position and of the individual residues is enforced by a modular attractor network whose modules correspond to the grid cell modules in entorhinal cortex. The vector binding operation can also associate different contexts to spatial representations, yielding a model for entorhinal cortex and hippocampus. We show that the model achieves normative desiderata including superlinear scaling of patterns with dimension, robust error correction, and hexagonal, carry-free encoding of spatial position. These properties in turn enable robust path integration and association with sensory inputs. More generally, the model formalizes how compositional computations could occur in the hippocampal formation and leads to testable experimental predictions. © 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

DMINet: A lightweight dual-mixed channel-independent network for cataract recognition

DMINet: A lightweight dual-mixed channel-independent network...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiao Wu Yu Chen Qiuyang Yan Yuhang Zhao Jilu Zhao Xiaoqing Zhang Risa Higashita Jiang Liu Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Tomey Corporation Nagoya Japan Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

Cataracts are the leading cause of visual impairment and blindness globally attracting abroad attention from society. Over the years researchers have developed many state-of-the-art convolutional neural networks (CNNs) to recognize cataract severity levels based on different ophthalmic images. However most current works focus on improving cataract recognition performance by designing complex CNNs often ignoring resource-constrained medical device limitations. To this problem this paper proposes a novel dual-mixed channel-independent convolution (DMIConv) method which takes advantage of the multiscale convolution kernels by combining a depthwise convolution with a depthwise dilated convolution sequentially. Moreover we build a lightweight dual-mixed channel-independent network (DMINet) to recognize cataracts. To verify the effectiveness and efficiency of DMINet we conduct extensive experiments on a clinical anterior segment optical coherence tomography (AS-OCT) dataset of nuclear cataract (NC) and a publicly available OCT dataset. The results show that our proposed DMINet keeps a better tradeoff between the model complexity and the classification performance than efficient CNNs e.g DMINet outperforms MixNet by 3.34% of accuracy by using 4.58 % fewer parameters

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of Stroke Risk Within 7-Years Follow Up Using Machine Learning Models

Prediction of Stroke Risk Within 7-Years Follow Up Using Mac...

引用

2023 IEEE EMBS Special Topic Conference on Data science and Engineering in Healthcare, Medicine and Biology, IEEECONF 2023

作者： Tsarapatsani, Konstantina-Helen Sakellarios, Antonis Tsakanikas, Vasilis D. Rudolf, Henrik Trampisch, Hans J. Pezoulas, Vasileios C. Matsopoulos, George K. Fotiadis, Dimitrios I. University of Ioannina Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering IoanninaGR 45110 Greece Biomedical Research Institute Greece Institute for Biostatistics and Informatics in Medicine and Ageing Research University Medical Center Rostock Germany Ruhr University Bochum Department of Medical Informatics Biometry and Epidemiology Bochum Germany National Technical University of Athens School of Electrical and Computer Engineering Athens Greece

ISBN: (纸本)9798350383386

A stroke, also known as brain attack, occurs when blood supply to your brain is interrupted. Primary prevention relies on prompt prediction of a stroke. While currently there are several clinical risk scores, machine learning (ML) models seems to be more suitable tools for accurate prediction of stroke events. Therefore, this work focuses on the prediction of stroke within 7 years follow-up in patients who have not suffered from a stroke or TIA event at baseline. LightGBM (LGBM), Extreme Grading Boosting (XGBoost), Support Vector Machine (SVM) and Decision Tree were employed in the getABI dataset, which includes 5,897 participants. The performance of models was calculated by Accuracy (ACC), Sensitivity (SENS), Specificity (SPE) and area under the receiver operating characteristic curve (AUC) of each model. According to the comparison analysis's results, LGBM has been shown to be the most trustworthy algorithm, with accuracy 68 %. Moreover, sex, age, status of peripheral artery disease (PAD), history of myocardial infarction, angina pectoris, amputation and diabetes and pulse status of different arteries can be used as a simple and cost-effective way to predict *** Relevance: A fatal medical emergency, stroke may be anticipated using artificial intelligence, and the sooner it is predicted, the more cerebrovascular disease occurrences can be avoided. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Learnable Flow Model Conditioned on Graph Representation Memory for Anomaly Detection

Learnable Flow Model Conditioned on Graph Representation Mem...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ziyu Zhu Wenlei Liu Zhidong Deng Department of Computer Science and Technology Tsinghua University Beijing China State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology (BNRist) Institute for Artificial Intelligence at Tsinghua University (THUAI)

Anomaly detection could be applied in a wide range of fields from industrial scene to medical imaging analysis. Although invertible flow models are developed to accomplish unsupervised anomaly detection, they are usually hard to train and have limited capabilities of accurately modeling the distribution of normal samples. To address this problem, we propose a novel enhanced flow model conditioned on graph representation memory (FlowGRM) for visual surface defect detection. In our FlowGRM, a graph neural network is trained to query graph embedding features from memory bank and incorporate them into a learnable flow model as conditional information. Such memorized conditional information, together with the invertible flow model, is jointly optimized to give rise to a probability density score. Experimental results obtained on the industrial visual anomaly detection datasets including MVTec and MTD show that the proposed model has state-of-the-art performance, which could even reach up to 99.6% and 99.2% AUROC scores on the above two bench-marks, respectively. Meanwhile, it requires fewer parameters and saves over 80% training time compared to existing flow models.

关键词： Training Visualization Time series analysis Signal processing Graph neural networks Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Accommodating Self-attentional Heterophily Topology into High- and Low-pass Graph Convolutional Network for Skeleton-based Action Recognition

Accommodating Self-attentional Heterophily Topology into Hig...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Chao Wei Zhidong Deng Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology (BNRist) State Key Laboratory of Intelligent Technology and Systems Institute for Artificial Intelligence at Tsinghua University (THUAI) Tsinghua University Beijing China

In the scene of human skeleton-based action recognition, graph convolutional network (GCN) is widely applied to model human action dynamics and achieves extraordinary results, where graph topology is in charge of feature extraction and plays a crucial role in learning representation in GCNs. This paper presents a novel high- and low-pass graph convolutional network (HLP-GCN), aiming to effectively aggregate joint features based on learned homophily and heterophily topologies using self-attention modules for skeleton-based action recognition tasks. Specifically, such an HLP-GCN framework first learns homophily and heterophily topologies dynamically so as to capture different correlations between input samples and then combine similar information arising from homophily topologies with dissimilar ones from heterophily topologies to get the final embeddings. Furthermore, a temporal modeling module is added to this HLPGCN framework, and a new pooling strategy called global node (GNode) is cascaded subsequently, in order to have the extraction of more robust spatiotemporal features for skeleton action recognition. Finally, the experimental results demonstrate that our method outperforms previous state-of-the-art methods by 0.2%, 0.4%, and 0.3% on three large-scale action recognition datasets including NTU RGB+D X-Set, NTU RGB+D 120 X-Sub, and NW-UCLA, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAMOYE: ZERO-SHOT SINGING VOICE CONVERSION MODEL BASED ON FEATURE DISENTANGLEMENT AND ENHANCEMENT

arXiv

引用

arXiv 2024年

作者： Wang, Zihao Ma, Le Feng, Yongsheng Pan, Xin Jin, Yuhang Zhang, Kejun Department of Computer Science Zhejiang University Hangzhou China Department of AI Music and Music Information Technology Central Conservatory of Music Beijing China Institute of Remote Sensing and Applications Beijing University of Civil Engineering and Architecture Beijing China Department of Computer Science Zhejiang University Hangzhou310027 China Department of Computer Science Zhejiang Key Laboratory of Intelligent Systems and Equipment for Digital Creativity Innovation Center of Yangtze River Delta Zhejiang University Hangzhou China

Singing voice conversion (SVC) aims to convert a singer’s voice to another singer’s from a reference audio while keeping the original semantics. However, existing SVC methods can hardly perform zero-shot due to incomplete feature disentanglement or dependence on the speaker look-up table. We propose the first open-source high-quality zero-shot SVC model SaMoye that can convert singing to human and non-human timbre. SaMoye disentangles the singing voice’s features into content, timbre, and pitch features, where we combine multiple ASR models and compress the content features to reduce timbre leakages. Besides, we enhance the timbre features by unfreezing the speaker encoder and mixing the speaker embedding with top-3 similar speakers. We also establish an unparalleled large-scale dataset to guarantee zero-shot performance, which comprises more than 1,815 hours of pure singing voice and 6,367 speakers. We conduct objective and subjective experiments to find that SaMoye outperforms other models in zero-shot SVC tasks even under extreme conditions like converting singing to animals’ timbre. The weights, code, dataset, and documents of SaMoye are publicly available on https://***/CarlWangChina/*** Codes 68Txx(Primary)14F05, 91Fxx(Secondary) Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

On-policy Actor-Critic Reinforcement Learning for Multi-UAV Exploration

arXiv

引用

arXiv 2024年

作者： Farid, Ali Moltajaei Roshanian, Jafar Mouhoub, Malek Intelligent Control Systems Institute K. N. Toosi University of Technology Daneshgah Street Tehran*** Iran Department of Computer Science University of Regina Wascana Pkwy ReginaS4S0A2 Canada

Unmanned aerial vehicles (UAVs) have become increasingly popular in various fields, including precision agriculture, search and rescue, and remote sensing. However, exploring unknown environments remains a significant challenge. This study aims to address this challenge by utilizing on-policy Reinforcement Learning (RL) with Proximal Policy Optimization (PPO) to explore the two dimensional area of interest with multiple UAVs. The UAVs will avoid collision with obstacles and each other and do the exploration in a distributed manner. The proposed solution includes actor-critic networks using deep convolutional neural networks (CNN) and long short-term memory (LSTM) for identifying the UAVs and areas that have already been covered. Compared to other RL techniques, such as policy gradient (PG) and asynchronous advantage actor-critic (A3C), the simulation results demonstrate the superiority of the proposed PPO approach. Also, the results show that combining LSTM with CNN in critic can improve exploration. Since the proposed exploration has to work in unknown environments, the results showed that the proposed setup can complete the coverage when we have new maps that differ from the trained maps. Finally, we showed how tuning hyper-parameters may affect the overall performance. © 2024, CC BY-NC-SA.

关键词： Convolutional neural networks

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：