检索结果-内蒙古大学图书馆

3D Image Acquisition and Display: Technology, Perception and Applications, 3D 2024 - Part of Optica Imaging Congress

作者： Javidi, Bahram Krishnan, Gokul Pla, Filiberto Department of Electrical and Computer Engineering University of Connecticut StorrsCT06269 United States Institute of New Imaging Technologies Universitat Jaume I Campus Riu Sec s/n Castelló de la Plana12071 Spain

In this work, we present an overview of human gesture recognition in degraded environments with multi-dimensional integral imaging. It is shown that for human gesture recognition in degraded environments such as low light, and occlusion, we can gain substantial improvements in performance over conventional imaging. © 2024 The Author(s).

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

An Interdisciplinary Framework for Systematic Innovation: A Case Study on Nature-Inspired Imaging Solutions

An Interdisciplinary Framework for Systematic Innovation: A ...

引用

2024 IEEE International Conference on Imaging Systems and Techniques, IST 2024

作者： Douard, Nicolas Samet, Ahmed Cavallucci, Denis Giakos, George National Institute of Applied Sciences University of Strasbourg 24 Bd de la Victoire Strasbourg67000 France Manhattan University Department of Electrical and Computer Engineering 3825 Corlear Ave New YorkNY10463 United States

ISBN: (纸本)9798350378214

This research presents a novel interdisciplinary framework designed to uncover connections across diverse knowledge domains through advanced semantic modeling techniques. A case study focused on nature-inspired imaging solutions illustrates the potential of the framework. Innovation often emerges at the intersection of various scientific fields. However, manually identifying these intersections within the vast scientific literature is impractical. By exploring how biological principles can inspire the development of advanced imaging technologies, such as image sensors for rapid motion tracking, we underscore the critical role of interdisciplinary research in the promotion of technological innovation. Our framework systematically identifies and analyzes cross-domain connections, showcasing the potential of automated bioinspired approaches to drive innovation from the early stages. This research highlights how semantic modeling can bridge gaps between disparate fields, facilitating the discovery of novel insights, and fostering a more integrated approach to academic research. By automating the process of identifying relevant intersections within extensive literature, our framework not only enhances research efficiency, but also broadens the scope for innovative solutions. Ultimately, this work underscores the value of interdisciplinary collaboration and the transformative potential of bioinspired methodologies in the advancement of technology. The findings presented offer an actionable roadmap for leveraging semantic modeling to accelerate the pace of innovation in various domains. © 2024 IEEE.

关键词： bioinspired innovation imaging technologies interdisciplinary research semantic modeling technological innovation

来源：评论

学校读者我要写书评

暂无评论

Non-impulsive Contact-Implicit Motion Planning for Morpho-functional Loco-manipulation

Non-impulsive Contact-Implicit Motion Planning for Morpho-fu...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Adarsh Salagame Kruthika Gangaraju Harin Kumar Nallaguntla Bibek Gupta Eric Sihite Gunar Schirner Alireza Ramezani Department of Electrical and Computer Engineering Northeastern University Boston MA California Institute of Technology Pasadena CA

ISBN: (数字)9798350355369

ISBN: (纸本)9798350355376

Object manipulation has been extensively studied in the context of fixed base and mobile manipulators. However, the overactuated locomotion modality employed by snake robots allows for a unique blend of object manipulation through locomotion, referred to as loco-manipulation. The following work presents an optimization approach to solving the loco-manipulation problem based on non-impulsive implicit contact path planning for our snake robot COBRA. We present the mathematical framework and show high fidelity simulation results for fixed-shape lateral rolling trajectories that demonstrate the object manipulation.

关键词： Mechatronics Simulation Snake robots Manipulators Trajectory Planning Optimization

来源：评论

学校读者我要写书评

暂无评论

A 23-nA Quiescent Current Output-Capacitorless LDO Regulator for IoT Devices 15

A 23-nA Quiescent Current Output-Capacitorless LDO Regulator...

引用

15th IEEE International Conference on ASIC, ASICON 2023

作者： Zhou, Shengnan Mao, Xiangyu Huang, Cheng Martins, Rui P. Lu, Yan University of Macau State Key Laboratory of Analog and Mixed-Signal VLSI Institute of Microelectronics and FST-DECE China Iowa State University Department of Electrical and Computer Engineering Ames United States

ISBN: (纸本)9798350312980

This paper presents an ultra-low quiescent current output-capacitorless low dropout regulator (OCL-LDO) with fast transient response. We design a rail-to-rail error amplifier with improved adaptive biasing, which provides a limited bias current at heavy load for better load regulation. The buffer with adaptive biasing and almost zero input-output voltage shift and embedded body-bias, combines the error amplifier and the gate of MP. The proposed LDO is designed in a 65-nm CMOS process. Simulation result shows that the proposed LDO consumes a quiescent current of only 23 nA at a supply voltage of 0.8 V. The voltage undershoot is 98 mV during a 20-mA maximum load transient. And we obtain a FOMT of 0.00023 ps. © 2023 IEEE.

关键词： adaptive biasing internet of things Output-capacitorless LDO rail-to-rail buffer ultra-low quiescent current

来源：评论

学校读者我要写书评

暂无评论

On Contrastive Learning for Domain Generalization

On Contrastive Learning for Domain Generalization

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Thuan Nguyen D. Richard Brown Department of Engineering Engineering Technology and Surveying East Tennessee State University TN Department of Electrical and-Computer Engineering Worcester Polytechnic Institute Worcester MA

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

Given the training data and labels from several seen domains, Domain Generalization (DG) aims to learn models that generalize well on unlabeled data from unseen domains. Due to the distribution of data and/or labels may vary between domains, current DG methods are mainly based on the theme of domain-invariant representation learning which decomposes the learning process into two steps: (1) finding a representation function from the input space to the representation/feature space to learn the so-called domain-invariant features, i.e., the features that are statistically stable between domains, and (2) designing a classifier on top of these domain-invariant features which is mutually optimal for all domains. Recent works on DG show that Contrastive Learning (CL) which was originally proposed to learn a representation function such that similar samples are pulled closer while dissimilar samples are pushed far away in the representation/feature space, appears as a promising solution for domain-invariant features learning. In this paper, we first establish the fundamental theory to justify why CL might be a potential approach for DG by showing that CL, under particular settings, allows a mechanism to minimize a loss function that enforces an optimal classifier for all training domains. Based on these foundations, we revisit the recent works that apply CL for DG to indicate their limitations and suggest a modification by combining the CL method with current DG methods for better out-of-domain generalization. Our numerical results point out that our proposed algorithm can achieve state-of-the-art performance on multiple DG benchmark datasets.

关键词： Training Representation learning Machine learning algorithms Training data Contrastive learning Benchmark testing Data models Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Effects of volume-confinement on lithium-ion battery with silicon-based anode

引用

Materials Today Communications 2024年 39卷

作者： Jhan, Cheng-Ying Wang, Pin-Sen Sung, Shi-Hong Tzeng, Yonhua Institute of Microelectronics Department of Electrical Engineering College of Electrical and Computer Engineering National Cheng Kung University Tainan Taiwan

The heightened resistivity and volumetric expansion stemming from alloy formation between silicon and lithium pose significant obstacles to the widespread adoption of silicon-based anodes. We demonstrate that internal pressure induced by volume confinement of a lithium ion battery with silicon-based anode helps retain anode density and form uniform and dense solid electrolyte interphase (SEI). Anode polarization and uneven lithium deposition are minimized, and thereby the consumption of electrolyte and lithium sources is reduced. Experimental data reveals that the interfacial resistance is reduced while specific capacity, coulombic efficiency and cycle stability of a battery improve due to the restriction against the expansion of the volume of half-cells and full-cells of lithium ion battery. The approach holds promise for advanced packaging technology to apply effective means of restricting the volume of lithium ion batteries from increase further during long-term cycling. © 2024 Elsevier Ltd

关键词： Anode Lithium-ion battery Silicon Volume confinement Volume expansion

来源：评论

学校读者我要写书评

暂无评论

Joint Communication and Computation Resource Allocation for Emerging mmWave Multi-User 3D Video Streaming Systems

Joint Communication and Computation Resource Allocation for ...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Babak Badnava Jacob Chakareski Morteza Hashemi Department of Electrical Engineering and Computer Science University of Kansas College of Computing New Jersey Institute of Technology

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

We consider a multi-user joint rate adaptation and computation distribution problem in a millimeter wave (mmWave) virtual reality (VR) system. The VR system that we consider comprises an edge computing unit (ECU) that serves 360° videos to VR users. We formulate a multi-user quality of experience (QoE) maximization problem, in which VR users are assisted with the ECU to decode/render 360° videos. The ECU provides additional computational resources that can be used for processing video frames, at the expense of increased data volume and required bandwidth. To balance this trade-off, we leverage deep reinforcement learning (DRL) for joint rate adaptation and computational resource allocation optimization. Our proposed method, dubbed Deep VR, does not rely on any predefined assumption about the environment and relies on video playback statistics (i.e., past throughput, decoding time, transmission time, etc.), video information, and the resulting performance to adjust the video bitrate and computation distribution. We train Deep VR with real-world mmWave network traces and 360° video datasets to obtain evaluation results in terms of the average QoE, peak signal-to-noise ratio (PSNR), rebuffering time, and quality variation. Our results indicate that the Deep VR improves the users’ QoE compared to state-of-the-art rate adaptation algorithm. Specifically, we show a 3.08 dB to 4.49 dB improvement in video quality in terms of PSNR, a 12.5x to 14x reduction in rebuffering time, and a 3.07 dB to 3.96 dB improvement in quality variation.

关键词： PSNR Bit rate Bandwidth Virtual reality Streaming media Quality of experience Resource management Millimeter wave communication Videos Edge computing

来源：评论

学校读者我要写书评

暂无评论

Novel Deep Learning Network Architectures for Time Series Forecasting

Novel Deep Learning Network Architectures for Time Series Fo...

引用

2023 IEEE International Conference on Paradigm Shift in Information Technologies with Innovative Applications in Global Scenario, ICPSITIAGS 2023

作者： Katariya, Jitendra Kumar Yadav, Dhananjay Gayathri, C. Kolekar, Vikas K. Daivagna, Umesh M. Pushparajesh, V. Vivekananda Global University Department of Computer Science & Application Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology UP India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai India Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Atlas SkillTech University Department of UGDX Maharastra Mumbai India Faculty of Engineering and Technology Department of Electrical and Electronics Engineering Karnataka Bangalore India

ISBN: (纸本)9798350329773

This paper presents novel deep-learning network architectures for time series forecasting. First, a singular deep gaining knowledge of network architecture is proposed and tested for the usage of the Google tendencies dataset as a benchmark. The proposed structure combines 1-dimensional convolution neural networks, recurrent neural networks, and long-term cells to seize and study lengthy-term styles in the time series information. The structure is compared to current deep getting-to-know architectures and is shown to outperform them in phrases of accuracy. Moreover, the proposed structure is applied to a secondary time collection dataset, the COVID-19 confirmed infection dataset, to attain compelling effects. Eventually, an open-source implementation of the proposed architecture is made available for use in addition to research. © 2023 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

FRAME: Fast and Robust Autonomous 3D Point Cloud Map-Merging for Egocentric Multi-Robot Exploration

FRAME: Fast and Robust Autonomous 3D Point Cloud Map-Merging...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Nikolaos Stathoulopoulos Anton Koval Ali-akbar Agha-mohammadi George Nikolakopoulos Department of Computer Electrical and Space Engineering Robotics and AI Group Luleå University of Technology Luleå Sweden Jet Propulsion Laboratory California Institute of Technology Pasadena CA

This article presents a 3D point cloud map-merging framework for egocentric heterogeneous multi-robot exploration, based on overlap detection and alignment, that is independent of a manual initial guess or prior knowledge of the robots' poses. The novel proposed solution utilizes state-of-the-art place recognition learned descriptors, that through the framework's main pipeline, offer a fast and robust region overlap estimation, hence eliminating the need for the time-consuming global feature extraction and feature matching process that is typically used in 3D map integration. The region overlap estimation provides a homogeneous rigid transform that is applied as an initial condition in the point cloud registration algorithm Fast-GICP, which provides the final and refined alignment. The efficacy of the proposed framework is experimentally evaluated based on multiple field multi-robot exploration missions in underground environments, where both ground and aerial robots are deployed, with different sensor configurations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RECONFIGURABLE INTELLIGENT SURFACES TO ENABLE ENERGY-EFFICIENT IOT NETWORKS

RECONFIGURABLE INTELLIGENT SURFACES TO ENABLE ENERGY-EFFICIE...

引用

2024 International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI, ICSCAI 2024

作者： William, P. Salagrama, Shailaja Maindola, Meenakshi Shrivastava, Anurag Almusawi, Muntather Yadav, Kanchan Department of Information Technology Sanjivani College of Engineering SPPU Kopargaon Pune India Department of Information Technology University of Cumberlands 6178 College Station Drive WilliamsburgKY40769 United States Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Electrical Engineering GLA University Mathura India

ISBN: (纸本)9798350355338

In this research, we investigate the uplink (UL) channel of a cellular network that is composed of Internet of Things (IoT) devices by using a reconfigurable intelligent surface (RIS) that has a limited number of different configurations for reflecting angles. The effect of the RIS on the angles at which the signal is reflected is the primary focus of our attention here. Before we can begin to work towards the signal-to-noise ratio (SNR) that we have set for ourselves, we need to first acquire an accurate estimate of the amount of transmit power that is necessary for machine-type devices (MTDs). This equation has to take into account the discretization of the RIS into In order to achieve the highest possible level of accuracy, the components that are being reflected need to be subwavelength. In order to accomplish this goal, it is necessary for you to construct a model of the channel. According to the calculations, the transmit power need to be selected in accordance with the goal signal-to-noise ratio (SNR), the placement of the MTD within the service area, and the design of the RIS, which ought to take into consideration the number and variety of possible reflecting components. This is because the MTDs are the ones in charge of determining the transmit power and the EBL for their respective channels. The numerical simulations on the energy efficiency (EE) examined by the EBL demonstrate the benefits of installing RISs to enable energy-efficient IoT networks. The primary focus of these simulations, which are designed to demonstrate the benefits of deploying RISs in order to allow energy-efficient IoT networks, is on highlighting the primary advantages of doing so. This is done so that the aforementioned simulations can demonstrate these benefits. © 2024 IEEE.

关键词： energy efficiency (EE) Internet of Things (IoT) Reconfigurable intelligent surface (RIS)

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：