检索结果-内蒙古大学图书馆

International Conference on computer Vision (ICCV)

作者： Dahuin Jung Dongyoon Han Jihwan Bang Hwanjun Song Department of Electrical and Computer Engineering Seoul National University Seoul Korea NAVER AI Lab NAVER Cloud AWS AI Labs

We introduce Domain-Adaptive Prompt (DAP), a novel method for continual learning using Vision Transformers (ViT). Prompt-based continual learning has recently gained attention due to its rehearsal-free nature. Currently, the prompt pool, which is suggested by prompt-based continual learning, is key to effectively exploiting the frozen pretrained ViT backbone in a sequence of tasks. However, we observe that the use of a prompt pool creates a domain scalability problem between pre-training and continual learning. This problem arises due to the inherent encoding of group-level instructions within the prompt pool. To address this problem, we propose DAP, a pool-free approach that generates a suitable prompt in an instance-level manner at inference time. We optimize an adaptive prompt generator that creates instance-specific fine-grained instructions required for each input, enabling enhanced model plasticity and reduced forgetting. Our experiments on seven datasets with varying degrees of domain similarity to ImageNet demonstrate the superiority of DAP over state-of-the-art prompt-based methods. Code is publicly available at https://***/naver-ai/dap-cl.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Image Mosaicing-Based Method for Bird Identification on Edge Computing Devices 1

引用

Proceedings of the 18th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2023

作者： Teterja, Dmitrij Garcia-Rodriguez, Jose Azorin-Lopez, Jorge Sebastian-Gonzalez, Esther van der Walt, Rita Elise Booysen, M.J. Department of Computer Science and Technology University of Alicante Alicante Spain Department of Ecology University of Alicante Alicante Spain Department of Electrical and Electronic Engineering/MIH Media Lab Stellenbosch University Stellenbosch South Africa Department of Electrical and Electronic Engineering Stellenbosch University Stellenbosch South Africa

ISBN: (数字)9783031425363

ISBN: (纸本)9783031425356

Bird identification is an important task in wildlife monitoring and conservation. However, traditional methods for bird identification often require significant computational resources, making them impractical for use on edge computing devices. In this paper, we propose an image mosaicing-based method for bird identification on edge computing devices. Our method combines image mosaicing and deep learning techniques to accurately identify bird species from a series of individual images. It achieves excellent accuracy of 99.51% for ResNet50 and 97.37% for MobileNetV2, depending on the specific use case. These results demonstrate the effectiveness and potential of our approach for real-time bird recognition and identification on edge computing devices, making it suitable for a wide range of applications including monitoring and conservation of bird populations. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Benefits of High-voltage SiC-based Power Electronics in Medium-voltage Power-distribution Grids

引用

Chinese Journal of electrical engineering 2021年第1期7卷 1-26页

作者： Fred Wang Shiqi Ji Department of Electrical Engineering and Computer Science The University of TennesseeTN 37996USA Oak Ridge National Lab Oak RidgeTN 37830USA Department of Electrical Engineering Tsinghua UniversityBeijing 100084China

Medium-voltage(MV)power electronics equipment has been increasingly applied m distnbution grids,and high-voltage(HV)silicon carbide(SiC)power semiconductors have attracted considerable attention in recent *** paper first overviews the development and status of HV SiC power ***,MV power-converter applications in distribution grids are summarized and the benefits of HV SiC in these applications are ***,including conventional and asynchronous microgrids,that can fully demonstrate the benefits of HV SiC power semiconductors are selected to investigate the benefits of HV SiC in detail,including converter-level benefits and system-level ***,an asynchronous microgrid power-conditioning system(PCS)prototype using a 10 kV SiC MOSFET is presented.

关键词： Silicon carbide power semiconductor distribution grid asynchronous microgrid power-conditioning system

来源：评论

学校读者我要写书评

暂无评论

HeRAFC: Heuristic Resource Allocation and Optimization in MultiFog-cloud Environment

arXiv

引用

arXiv 2023年

作者： Dehury, Chinmaya Kumar Veeravalli, Bharadwaj Srirama, Satish Narayana Mobile & Cloud Lab Institute of Computer Science University of Tartu Tartu50090 Estonia Department of Electrical and Computer Engineering National University of Singapore Singapore School of Computer and Information Sciences University of Hyderabad Telangana Gachibowli India

By bringing computing capacity from a remote cloud environment closer to the user, fog computing is introduced. As a result, users can access the services from more nearby computing environments, resulting in better quality of service and lower latency on the network. From the service providers’ point of view, this addresses the network latency and congestion issues. This is achieved by deploying the services in cloud and fog computing environments. The responsibility of service providers is to manage the heterogeneous resources available in both computing environments. In recent years, resource management strategies have made it possible to efficiently allocate resources from nearby fog and clouds to users’ applications. Unfortunately, these existing resource management strategies fail to give the desired result when the service providers have the opportunity to allocate the resources to the users’ application from fog nodes that are at a multi-hop distance from the nearby fog node. The complexity of this resource management problem drastically increases in a MultiFog-cloud environment. This problem motivates us to revisit and present a novel Heuristic Resource Allocation and Optimization algorithm in a MultiFog-cloud (HeRAFC) environment. Taking users’ application priority, execution time, and communication latency into account, HeRAFC optimizes resource utilization and minimizes cloud load. The proposed algorithm is evaluated and compared with related algorithms. The simulation results show the efficiency of the proposed HeRAFC over other algorithms. © 2023, CC BY.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Emotion Classification Through Speech Data Analysis

Emotion Classification Through Speech Data Analysis

引用

2023 Winter Simulation Conference, WSC 2023

作者： Marcos, Luzalen Mai, Kristiina Valter Abhari, Abdolreza Toronto Metropolitan University Department of Electrical Computer and Biomedical Engineering Resilience Engineering Lab 350 Victoria Street TorontoONM5B 2K3 Canada Lab Department of Computer Science 245 Church Street TorontoONM5B 1Z4 Canada

ISBN: (纸本)9798350369663

Good quality healthcare services require effective communication between the patient and the healthcare provider. This work will help improve the areas of healthcare systems automation and optimization by applying Speech Emotion Recognition (SER) in health consultations to prevent miscommunication between patients and healthcare providers. Crowd-Sourced Emotional Multimodal Actors Dataset (CREMA-D) was used to compare the performances of different machine learning models in classifying emotions. Before feeding the raw dataset to the models, exploratory data analysis was done to determine features that should be considered for future analysis. Our results showed that depending on the emotion, there are some syllables in the text that were emphasized or took time to be pronounced by the speaker. After data analysis, the dataset was fed into different models and determined that the Support Vector Machine (SVM) is a machine-learning model for SER. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Composite Dataset of Lumbar Spine Images with Mid-Sagittal View Annotations and Clinically Significant Spinal Measurements 2

A Composite Dataset of Lumbar Spine Images with Mid-Sagittal...

引用

2nd International Conference on Digital Futures and Transformative Technologies, ICoDT2 2022

作者： Masood, Rao Farhat Hassan, Taimur Raja, Hina Hassan, Bilal Dias, Jorge Werghi, Naoufel Nust CUST Islamabad & College of Eme Department of Electrical Engineering Rawalpindi Pakistan Khalifa University C2PS and Kucars Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates College of EME Nust Biomisa Lab Department of Computer and Software Engineering Rawalpindi Pakistan Khalifa University Kucars Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates

ISBN: (纸本)9781665498197

The modern computer-aided screening systems re-quire a large amount of well-annotated training data to produce robust and consistent diagnostic performance. Furthermore, the public datasets designed to evaluate automated spinal disorders screening frameworks lack quantitative labels, which are marked by expert radiologists and clinically validated by spinal surgeons. This paper presents a dataset containing high-resolution (and well-labeled) mid-sagittal views of lumbar spine magnetic resonance imaging (MRI) scans. These scans also contain vertebral body masks along with clinically significant spinal measurements, including lumbar height, intervertebral body distances, vertebral body sidewall dimensions, vertebral body superior and inferior end-plates dimensions, lumbar lordotic angles, and lumbosacral angles. The mid-sagittal view MRI scans within the proposed dataset were first procured, and then they were manually marked by the expert radiologists and validated by the expert spinal surgeons. Afterward, different spinal measurements were recorded, which serves as a benchmark to evaluate the autonomous frameworks for predicting spinal misalignments. In addition to this, the proposed dataset is, to the best of our knowledge, the first composite database that contains lumbar spine mid-sagittal images along with spinal attributes and detailed markings of radiologists duly verified by the spinal surgeons. The proposed dataset, unlike its competitors, also introduces a quantitative vote to the clinicians and researchers in the assessment process of lumbar spine disorders. Apart from this, the dataset is publicly available at https://***/datasets/k3b363f3vz/2. © 2022 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Exploiting DLMS/COSEM Data Compression to Learn Power Consumption Patterns

Exploiting DLMS/COSEM Data Compression to Learn Power Consum...

引用

2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2021

作者： Feher, Marcell Lucani, Daniel E. Hansen, Morten Tranberg Vester, Flemming Enevold Aarhus University Agile Cloud Lab Department of Electrical and Computer Engineering DIGIT Aarhus Denmark Kamstrup A/S Skanderborg Denmark

ISBN: (纸本)9781665415026

Smart electricity meters are widely deployed report power consumption automatically and frequently. However, the current compression methods have been suspected to leak information about the times when consumers are active, by mirroring spikes of power consumption in the compressed message size. In this paper we show that, compressed message sizes are indeed highly correlated with the underlying power use. We present a clustering-based method that allows a passive adversary monitoring encrypted network traffic to build and exploit power consumption profiles of homes. We evaluate the vulnerability of legacy compressors of the DLMS/COSEM standard as well as a recently proposed algorithm. Our results show that the novel algorithm not only provides higher compression potential, but results in the least information leakage. We evaluate our results on an real, anonymized dataset spanning 9 months and 95 households. © 2021 IEEE.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Long-Term Invariant Local Features via Implicit Cross-Domain Correspondences

arXiv

引用

arXiv 2023年

作者： Pataki, Zador Altillawi, Mohammad Kanakis, Menelaos Pautrat, Rémi Shen, Fengyi Liu, Ziyuan Van Gool, Luc Pollefeys, Marc The Computer Vision and Geometry Lab Department of Computer Science ETH Zurich Switzerland The Computer Vision Center CVC-Barcelona The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Computer Vision Lab Department Electrical Engineering ETH Zurich Switzerland The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Center for Processing Speech and Images KU Leuven The Computer Vision Lab ETH Zurich Switzerland

Modern learning-based visual feature extraction networks perform well in intra-domain localization, however, their performance significantly declines when image pairs are captured across long-term visual domain variations, such as different seasonal and daytime variations. In this paper, our first contribution is a benchmark to investigate the performance impact of long-term variations on visual localization. We conduct a thorough analysis of the performance of current state-of-the-art feature extraction networks under various domain changes and find a significant performance gap between intra- and cross-domain localization. We investigate different methods to close this gap by improving the supervision of modern feature extractor networks. We propose a novel data-centric method, Implicit Cross-Domain Correspondences (iCDC). iCDC represents the same environment with multiple Neural Radiance Fields, each fitting the scene under individual visual domains. It utilizes the underlying 3D representations to generate accurate correspondences across different long-term visual conditions. Our proposed method enhances cross-domain localization performance, significantly reducing the performance gap. When evaluated on popular long-term localization benchmarks, our trained networks consistently outperform existing methods. This work serves as a substantial stride toward more robust visual localization pipelines for long-term deployments, and opens up research avenues in the development of long-term invariant descriptors. Copyright © 2023, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Learning Hand Gestures using Synergies in a Humanoid Robot

Learning Hand Gestures using Synergies in a Humanoid Robot

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Olikkal, Parthan Pei, Dingyi Karri, Bharat Kashyap Satyanarayana, Ashwin Kakoty, Nayan M. Vinjamuri, Ramana University of Maryland Baltimore County Vinjamuri Lab The Department of Computer Science and Electrical Engineering BaltimoreMD21220 United States City Tech Cuny United States Tezpur University Assam India

ISBN: (纸本)9798350325706

Hand gestures are a natural way of communication and integrating them into robots could allow for more efficient human-robot collaboration. In recent years, researchers and roboticists have attempted to replicate human hand motor control using the concept of synergies. In this paper, we present a new approach to obtaining kinematic synergies from hand gestures using a single RGB camera. We capture real-time hand gestures using the MediaPipe framework and convert them to joint angular velocities. We then use dimensionality reduction to obtain kinematic synergies from the joint angular velocities. These synergies can be used to reconstruct new hand gestures. We translate these reconstructed hand movement patterns into a humanoid robot, Mitra. Our results show that it is possible to control most of the joints of the robot for performing hand gestures using only a few synergies. This is more efficient than other contemporary methods. Furthermore, robots and prosthetics that use synergy models could enable near-natural human-robot collaboration. © 2023 IEEE.

关键词： bioinspired robots biomimetic robots hand kinematics human robot interaction kinematic synergies MediaPipe

来源：评论

学校读者我要写书评

暂无评论

Efficient Optimization in RIS-Assisted UAV System Using Deep Reinforcement Learning for mmWave-NOMA 6G Communications

引用

IEEE Internet of Things Journal 2025年

作者： Sobhi-Givi, Sima Nouri, Mahdi Shayesteh, Mahrokh G. Behroozi, Hamid Kwon, Hyun Han Piran, Md. Jalil Urmia University Electrical and Computer Engineering Department Urmia Iran University of Mohaghegh Ardabili Electrical and Computer Engineering Department Ardabil Iran Sharif University of Technology Electrical Engineering Department Tehran Iran Sharif University of Technology Wireless Research Lab ACRI Electrical Engineering Department Tehran Iran Sejong University Department of Civil and Environmental Engineering Seoul05006 Korea Republic of Sejong University Department of Computer Science and Engineering Seoul05006 Korea Republic of

In the evolving landscape of wireless communications for 5G, 6G, and beyond, the deployment of unmanned aerial vehicles (UAVs) has emerged as a groundbreaking strategy to expand coverage areas due to their flexibility and ease of deployment. Simultaneously, reflecting intelligent surfaces (RIS) have introduced a transformative paradigm aimed at improving key performance metrics, such as average sum-rate and energy efficiency (EE). The seamless integration of advanced technologies, including UAVs, RIS, and non-orthogonal multiple access (NOMA), presents a promising avenue for significantly boosting the performance and efficiency of next-generation communication systems. This study investigates EE maximization for two scenarios in a NOMA-enabled mmWave network: multi-UAV-mounted base stations (BS) and multi-UAV-mounted distributed RIS. In both cases, each UAV serves a NOMA cluster with imperfect successive interference cancellation (SIC), capturing the impact of hardware impairments in real-world NOMA systems. For each scenario, an optimization problem is formulated to maximize EE by jointly optimizing the beamforming matrix, phase shift matrix, NOMA power allocation, and UAV 3D placement. The non-convex problems are tackled using both model-based and model-free deep reinforcement learning (DRL) algorithms under constraints such as minimum quality of service (QoS), beamforming and phase shift limits, and UAV trajectory constraints. The simulation results demonstrate that the proposed DRL algorithms significantly enhance spectral efficiency (SE) and EE, showcasing their suitability for 6G communication systems. Furthermore, a comparative analysis with orthogonal multiple access (OMA) and spatial division multiple access (SDMA) confirms that NOMA outperforms both techniques, achieving substantial gains in efficiency and performance. © 2014 IEEE.

关键词： Deep reinforcement learning

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：