检索结果-内蒙古大学图书馆

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Yenilmez, Fulya Yildiz, Canan Ugur, Mukden Turkish-German University Department of Computer Engineering Istanbul34820 Turkey Turkish-German University Department of Robotics and Intelligent Systems Istanbul34820 Turkey

ISBN: (纸本)9798350359015

In recent years, deep learning architectures have demonstrated remarkable achievements on diverse computer vision tasks, including the recognition of facial expressions. The development of precise and robust facial expression recognition (FER) models has the potential to improve a wide range of applications in various fields, such as human-computer interaction, emotion analysis, marketing, robotics, psychology, and health *** this domain, several Convolutional Neural Network (CNN) architectures have been employed to yield promising results. In this paper, we undertake a comparative analysis with the latest iterations of five widely adopted CNN models for the FER task: VGG19, InceptionV3, ResNet152V2, MobileNetV2, and EfficientNetV2B1. We also explore the effect of transfer learning, specifically the difference between pretraining on VGGFace versus ImageNet. Our primary goal is to comprehensively assess these architectures under identical conditions and provide clarity on their performance in comparison to each other and to previous works using various training strategies. Our assessments allow the conclusion that increasing the size and depth of these common "backbone"models leads to only minor improvements. Augmenting these models with additional architectural elements such as attention mechanisms seems much more promising in comparison. Our results further show that pretraining on a domain-specific dataset can lead to significant improvements, demonstrating the importance of a large FER related dataset. © 2023 IEEE.

关键词： CNN architectures face expression recognition fine-tuning neural networks transfer learning

来源：评论

学校读者我要写书评

暂无评论

Autonomous 3D Reconstruction with Small Unmanned Aerial Vehicle (UAV) using Structure from Motion: Practical Aspects

Autonomous 3D Reconstruction with Small Unmanned Aerial Vehi...

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Rayon, Nathan Stevens, Raymond Sevil, Hakki Erhan Department of Computer Science University of West Florida FL32514 United States Department of Electrical and Computer Engineering University of West Florida FL32514 United States Department of Intelligent Systems & Robotics University of West Florida FL32514 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

This paper explores the practical considerations and challenges involved in achieving autonomous 3D reconstruction utilizing small Unmanned Aerial Vehicles (UAVs) through the framework of Structure from Motion (SFM). The utilization of small UAVs equipped with lightweight cameras presents a promising resource for cost-effective and rapid 3D mapping in various domains such as disaster response, infrastructure inspection, and search and rescue. In this study, the critical practical aspects of this process, including height level for taking images, UAV selection, number of images, image acquisition strategies, and computational time. The effectiveness and limitations of autonomous 3D reconstruction with small UAVs through practical insights are summarized, with discussions on potential advancements and areas for future research. This paper serves as a guide for researchers interested in utilizing small UAVs for autonomous 3D reconstruction tasks applications. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Training Variational Autoencoders for Population Synthesis in Public Health with Missing Data

Training Variational Autoencoders for Population Synthesis i...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Blackthorn, Nathan Mahyari, Andrew Arash Srinivasan, Ashok University of West Florida Department of Computer Science PensacolaFL United States PensacolaFL United States University of West Florida Department of Intelligent Systems and Robotics PensacolaFL United States

ISBN: (纸本)9798350362480

The importance of social determinants of health in shaping equitable public health policies is gaining increasing recognition. Emerging data sources, such as mobility and social media data, are becoming key to public health models. However, privacy concerns often limit access to these sensitive data, as even anonymized datasets are vulnerable to deductive disclosure. A promising solution to this challenge is the use of synthetic populations, which not only safeguard privacy but also enable the exploration of various "what-if"scenarios. Most existing studies on synthetic populations assume full access to complete datasets for training. However, in many public health applications, such as census data, this assumption is unrealistic due to incomplete responses, especially regarding sensitive questions like wealth or education. This paper introduces a novel approach for training Variational AutoEncoders (VAEs) with incomplete data, without resorting to missing value imputation. Instead, the VAEs are trained solely on the observed data. Using the 2019 PUMS dataset for Florida, we successfully train VAEs to generate diverse and flexible synthetic populations. By comparing marginal distributions and utilizing t-SNE for analysis, the results highlight the effectiveness of this method in addressing missing data challenges. This work demonstrates the potential of VAEs in generating synthetic populations for health research, even when complete datasets are unavailable, thereby offering a robust solution to advance public health studies while preserving data privacy. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Enhance Planning with Physics-informed Safety Controller for End-to-end Autonomous Driving

Enhance Planning with Physics-informed Safety Controller for...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Zhou, Hang Liu, Haichao Lu, Hongliang Ma, Jun Ji, Yiding Robotics and Autonomous Systems Thrust Systems Hub Guangzhou China School of Engineering The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering SAR Hong Kong Hong Kong Intelligent Transportation Thrust Systems Hub Guangzhou China

ISBN: (纸本)9781665481090

Recent years have seen a growing research interest in applications of Deep Neural Networks (DNN) on autonomous vehicle technology. The trend started with perception and prediction a few years ago and it is gradually being applied to motion planning tasks. Despite the performance of networks improve over time, DNN planners inherit the natural drawbacks of Deep Learning. Learning-based planners have limitations in achieving perfect accuracy on the training dataset and network performance can be affected by out-of-distribution problem. In this paper, we propose FusionAssurance, a novel trajectory-based end-to-end driving fusion framework which combines physics-informed control for safety assurance. By incorporating Potential Field into Model Predictive Control, FusionAssurance is capable of navigating through scenarios that are not included in the training dataset and scenarios where neural network fail to generalize. The effectiveness of the approach is demonstrated by extensive experiments under various scenarios on the CARLA benchmark. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Robust Counting in Overcrowded Scenes Using Batch-Free Normalized Deep ConvNet

引用

computer systems Science & Engineering 2023年第9期46卷 2741-2754页

作者： Sana Zahir Rafi Ullah Khan Mohib Ullah Muhammad Ishaq Naqqash Dilshad Amin Ullah Mi Young Lee Institute of Computer Sciences and Information Technology(ICS/IT) The University of AgriculturePeshawar25130Khyber PakhtunkhwaPakistan Department of Convergence Engineering for Intelligent Drone Sejong UniversitySeoul05006Korea Collaborative Robotics and Intelligent Systems(CoRIS)Institute Oregon State UniversityORUSA Department of Software Sejong UniversitySeoul05006Korea

The analysis of overcrowded areas is essential for flow monitoring,assembly control,and *** counting’s primary goal is to calculate the population in a given region,which requires real-time analysis of congested scenes for prompt reactionary *** crowd is always unexpected,and the benchmarked available datasets have a lot of variation,which limits the trained models’performance on unseen test *** this paper,we proposed an end-to-end deep neural network that takes an input image and generates a density map of a crowd *** proposed model consists of encoder and decoder networks comprising batch-free normalization layers known as evolving normalization(EvoNorm).This allows our network to be generalized for unseen data because EvoNorm is not using statistics from the training *** decoder network uses dilated 2D convolutional layers to provide large receptive fields and fewer parameters,which enables real-time processing and solves the density drift problem due to its large receptive *** benchmark datasets are used in this study to assess the proposed model,resulting in the conclusion that it outperforms conventional models.

关键词： Artificial intelligence deep learning crowd counting scene understanding

来源：评论

学校读者我要写书评

暂无评论

Smart Manufacturing Integration of Heterogeneous Information systems via OPC UA. A Case Study

Smart Manufacturing Integration of Heterogeneous Information...

引用

2024 International Conference Automatics and Informatics, ICAI 2024

作者： Vasilev, Plamen Boneva, Ani Ivanova, Veronika Tsvetanov, Tsetso University of Chemical Technology and Metallurgy Department of Industrial Automation Sofia Bulgaria Institute of Information and Communication Technologies Bulgarian Academy of Sciences Department of Communication and Computer Systems Sofia Bulgaria Institute of Robotics Bulgaria Academy of Sciences Department of Robotized and Mechatronics Intelligent Systems Sofia Bulgaria

ISBN: (纸本)9798350353907

Modern automation, digitalization, virtualization, and intelligent production impose new criteria and approaches to process management. The operation and performance of any system and device depend on how it is managed. The article describes Smart Manufacturing Integration of Heterogeneous Information systems via OPC UA. The main goal is the development of heterogeneous information systems with real applications, with which reliable and up-to-date information can be exchanged between systems of different hierarchical levels. The goal was achieved with the following steps i) building the research infrastructure ii) analyzing the information compatibility and challenges in integrating systems from different hierarchical levels, and iii) implementing the integration by means of the OPC-UA standard communication protocol. The setup has been tested under laboratory conditions. The obtained results are shown. © 2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Centralizing Data Warehouse Platform for Mining Management Using AWS Computing Instance

Centralizing Data Warehouse Platform for Mining Management U...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Sathaporn, Posathip Chaowalittawin, Vasutorn Krungseanmuang, Woranidtha Benjangkaprasert, Chawalit Purahong, Boonchana School of Engineering King Mongkut's Institute of Technology Ladkrabang Department of Robotics and Computational Intelligent Systems Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Computer Engineering Department Bangkok Thailand

ISBN: (纸本)9798350350821

Mining industry is one of significant industry in the world. In order to increase efficiency, safety, sustainability and environmental impacts in mining process. This article presents a centralized data platform for mining process by design based on microservices architecture which can be supported various of input data source such as manual form, excel file and internet of things (IoT) device and notification when the value is abnormal. Our platform implementation on Amazon Web Service (AWS) cloud. For development of productivity in process and controlling quality the mine environment. The results of the platform operations with various source of data acquisition with response time is less than 1.5 seconds per each request. © 2024 IEEE.

关键词： Cloud Computing Data Warehouse Internet of Things Microservices Architecture Mining Industry

来源：评论

学校读者我要写书评

暂无评论

Deep Generative Models for Constructing Synthetic Populations in Public Health Applications

Deep Generative Models for Constructing Synthetic Population...

引用

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Farmer, Nathan Mahyari, Arash Sirinivasan, Ashok University of West Florida Department of Computer Science PensacolaFL United States PensacolaFL United States University of West Florida Department of Intelligent Systems and Robotics PensacolaFL United States

ISBN: (纸本)9798350359527

There is a growing acknowledgment of the significance of social determinants of health in shaping fair public health policies. These determinants, reflected in emerging data streams like mobility and social media data, are increasingly integral to public health models. However, privacy concerns impede broad access to sensitive data, because even non-identifiable data are susceptible to deductive disclosure. To address this, synthetic populations trained on such data emerge as a privacy-conscious solution, offering the added benefit of exploring various "what-if"scenarios. This paper delves into the application of Generative Adversarial Networks (GANs) to craft synthetic populations that tackle privacy issues linked to social determinants of health data. Utilizing the 2019 PUMS dataset for Florida, the study trains the GAN to produce diverse and adaptable synthetic populations. An autoencoder manages the mix of continuous and categorical variables, ensuring the generated data aligns with categorical ranges. The results, assessed by comparing marginal distributions and employing tSNE, underscore the GAN's efficacy in balancing privacy and data utility. The significance of this work lies in identifying the promise of GANs in generating synthetic populations to advance health research. © 2023 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Deep Image Clustering by Spiking Neural Networks

Deep Image Clustering by Spiking Neural Networks

引用

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Mahyari, Arash Aliakbarpour, Hadi PensacolaFL United States University of West Florida Department of Intelligent Systems and Robotics PensacolaFL United States Saint Louis University Department of Computer Science St. LouisMO United States

ISBN: (纸本)9798350359527

Neuromorphic cameras, or event cameras, are biologically-inspired sensors that detect changes in illumination at a pixel level, different from traditional cameras where each pixel independently and asynchronously outputs when it senses illumination changes. The neuromorphic cameras exhibit high-Temporal resolution and dynamic range, useful in various applications. Spiking Neural Networks (SNNs), mimicking biological neurons, are efficient in processing neuromorphic images due to their event-driven, low-power nature. However, training SNNs is challenging because of the non-differentiability of neuron models which require different optimization techniques. Inspired by recent works on unsupervised deep clustering in conventional deep learning, we introduce a novel deep clustering algorithm that employs SNNs to extract and group visual features from neuromorphic images into clusters. It utilizes an SNN feature extractor for neuromorphic images, grouping the extracted features using K-means clustering. This algorithm, which doesn't require pre-Trained SNN weights, alternates between cluster updates and SNN weight adjustments. The extracted feature vectors in SNN are clustered and used as pseudo-labels for supervised training of the SNN extractor. The performance of the proposed algorithm is evaluated on two datasets of MNIST and NMNIST, and its effectiveness is assessed using the Normalized Mutual Information (NMI) metric. The performance of our SNN system with neuromorphic images, while marginally below its counterparts of ANNs with traditional images, demonstrates considerable potential. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Onboard Perception-Assisted High Fidelity Simulation Framework for Autonomous Planetary Soft-Landing

Onboard Perception-Assisted High Fidelity Simulation Framewo...

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Alibekov, Ulugbek Banerjee, Avijit Satpute, Sumeet Gajanan Nikolakopoulos, George ERASMUS MUNDUS JOINT MASTER in Intelligent Field Robotic Systems Faculty of Informatics Eötvös Loránd University Budapest Hungary Robotics and AI research group Department of Computer Science Electrical and Space Engineering Luleå University of Technology Luleå Sweden

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

This article presents an onboard perception-assisted high-fidelity simulation framework for autonomous planetary soft-landing, enabling visual information processing tightly integrated with advanced onboard guidance system in a realistic simulation environments. Utilizing the open source Unity game engine, a physics-based simulation toolbox integrated with the Robotic Operating System (ROS2), we effectively emulate the motion of spacecraft approaching planetary terrain. The simulation environment features a realistic 3D terrain model and a lander spacecraft equipped with onboard camera to effectively capture detailed local terrain images. The simulation engine accurately captures the spacecraft’s 6-degrees of freedom motion, seamlessly integrating space craft orientation with the associated camera feed while incorporating various illumination conditions using a light source representing the Sun. To demonstrate the efficacy of the framework, we implement a recently developed attitude-constrained minimum jerk guidance algorithm to emulate spacecraft motion. Concurrently, the visual feed from the onboard RGB camera is processed through a gradient extraction-based perception system, providing the visual odometer. This system identifies provably safe landing sites, effectively avoiding potential risks of landing on uneven terrain. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Planetary landers

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：