检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Automation (ICRA)

作者： Aditya Shirwatkar Vamshi Kumar Kurva Devaraju Vinoda Aman Singh Aditya Sagi Himanshu Lodha Bhavya Giri Goswami Shivam Sood Ketan Nehete Shishir Kolathaya Robert Bosch Center for Cyber Physical Systems Indian Institute of Science Bengaluru Department of Computer Science & Automation Indian Institute of Science Bengaluru Indian Institute of Technology Kharagpur Department of Computer Science & Automation Robert Bosch Center for Cyber Physical Systems Indian Institute of Science Bengaluru

This work presents a simple linear policy for direct force control for quadrupedal robot locomotion. The motivation is that force control is essential for highly dynamic and agile motions. We learn a linear policy to generate end-foot trajectory parameters and a centroidal wrench, which is then distributed among the legs based on the foot contact information using a quadratic program (QP) to get the desired ground reaction forces. Unlike the majority of the existing works that use complex nonlinear function approximators to represent the RL policy or model predictive control (MPC) methods with many optimization variables in the order of hundred, our controller uses a simple linear function approximator to represent policy along with only a twelve variable QP for the force distribution. A centroidal dynamics-based MPC method is used to generate reference trajectory data, and then the linear policy is trained using imitation learning to minimize the deviations from the reference trajectory. We demonstrate this compute-efficient controller on our robot Stoch3 in simulation and real-world experiments on indoor and outdoor terrains with push recovery.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs

Cross-Modality Time-Variant Relation Learning for Generating...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jingyi Wang Jinfa Huang Can Zhang Zhidong Deng Department of Computer Science Tsinghua University Beijing China School of Electronic and Computer Engineering Peking University China Department of Computer Science Beijing National Research Center for Information Science and Technology (BNRist) THUAI State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China

Dynamic scene graphs generated from video clips could help enhance the semantic visual understanding in a wide range of challenging tasks such as environmental perception, autonomous navigation, and task planning of self-driving vehicles and mobile robots. In the process of temporal and spatial modeling during dynamic scene graph generation, it is particularly intractable to learn time-variant relations in dynamic scene graphs among frames. In this paper, we propose a Time-variant Relation-aware TRansformer (TR 2 ), which aims to model the temporal change of relations in dynamic scene graphs. Explicitly, we leverage the difference of text embeddings of prompted sentences about relation labels as the supervision signal for relations. In this way, cross-modality feature guidance is realized for the learning of time-variant relations. Implicitly, we design a relation feature fusion module with a transformer and an additional message token that describes the difference between adjacent frames. Extensive experiments on the Action Genome dataset prove that our TR2 can effectively model the time-variant relations. TR2 significantly outperforms previous state-of-the-art methods under two different settings by 2.1 % and 2.6% respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Aided Optimization Approach for Sustainable Energy Systems 1

Machine Learning-Aided Optimization Approach for Sustainable...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Hussian, Ahmed Ali Ettyem, Sajjad Ali Zearah, Sajad Ahmed, Ibrahem Ismail, Laith S. Ibrahem, Marwa Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq National University of Science and Technology Dhi Qar Department of Medical Devices Engineering Technologies Nasiriyah Iraq Al-Ayen University Thi-Qar Scientific Research Center Iraq Al-Farahidi University Medical Instruments Engineering Techniques Baghdad Iraq Al-Turath University College Computer Technologies Engineering Baghdad Iraq Al-Maamoun University College Computer Technology Engineering Baghdad Iraq

ISBN: (纸本)9798350359756

Energy derived from renewable sources is expanding quickly. Renewable energy systems meet off-grid and on-grid load requirements, often connected to conventional sources. Geothermal, solar, wind, and other renewable energy sources can be harnessed economically at the current rate of technological development. Renewable-based electricity production is an alternative form of green power generation that reduces issues with energy consumption. Though this raises numerous uncertainties and difficulties, it may jeopardize potential economic, technological, and environmental gains. Consequently, a Machine Learning aided Optimization Approach (MLOA) for sustainable energy systems has been suggested in this study. The Enhanced Long Short-Term Memory (E-LSTM) model of recurrent neural networks trained by Adam optimizer is employed in MLOA due to its ability to predict solar and wind generation to provide optimal energy consumption control. The numerical outcomes demonstrate that the suggested MLOA method improves prediction and accuracy rates by 98.22% compared to other current approaches. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A review of travel behavioural pattern using GPS dataset: A systematic literature review

引用

Measurement: Sensors 2024年 32卷

作者： Sivalingam, Prahaladhan Asirvatham, David Marjani, Mohsen Syed Masood, Jafar Ali Ibrahim Chakravarthy, N.S. Kalyan Veerisetty, Gopinath Lestari, Martha Tri Faculty of Innovation & Technology Taylor's University Subang Jaya Malaysia Department of Internet of Things School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore632 014 India Center for Data Science School of Computer Science and Engineering QIS College of Engineering and Technology Andhra Pradesh Ongole523272 India Department of Mechanical Engineering QIS College of Engineering and Technology Andhra Pradesh Ongole523272 India Department of Business Communication Telkom University Indonesia

In the last few years, the Global positioning system (GPS) has been used to study travel patterns with the advancement of data collection techniques. A GPS device precisely records the time and the location data of an individual travel. The accuracy of travel studies is usually improved by integrating travel surveys or travel activity diaries with GPS data. GPS surveys are implemented to replace paper-based techniques and reduce human error on trip-misreporting issues. Several reviews have been performed previously on GPS travel studies. Still, a detailed systematic review on the comparison of different modes and methods on the entire procedure of GPS data processing has not been thoroughly studied. This review identified 116 peer-reviewed studies and journal papers from 2013 to 2020, and 53 papers were studied. The review focused on travel behavior pattern (TBP) analysis using GPS studies only and a combination of travel surveys. Our review reveals that 53 only 40 have quality assessment scores of >50 %, meaning the remaining TBP studies are conventional methods. The study also benefits data analysis and researchers to select the most appropriate data collection techniques for studying TBP and improvise them further for meta-analysis travel behavior studies. © 2024 The Authors

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

QoI-Aware Configuration Adaptation and Heterogeneous Resource Allocation for Edge Video Analytics

引用

IEEE Internet of Things Journal 2025年

作者： He, Zixuan Sun, Yanjing Zhang, Beibei Dong, Kaiwen Wang, Bowen Xu, Hongli China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China China University of Mining and Technology IoT Perception Mine Research Center Xuzhou221116 China School of Information and Control Engineering China University of Science and Technology of China School of Computer Science and Technology Anhui Hefei230027 China University of Science and Technology of China Suzhou Institute for Advanced Research Jiangsu Suzhou215123 China

Edge video analytics enables agile responses of machine-centric applications by streaming videos from end devices to edge servers (ESs) for resource-intensive Deep Neural Network (DNN) inference. Quality of Inference (QoI), reflected by end-to-end analytics delay and inference accuracy, is crucial for the high-quality real-time decision-making. Due to the limited ES resources and dynamic network conditions, video configuration adaptation and fine-grained resource allocation are necessary to enhance the QoI of video streams, which involves a delicate balance between delay and accuracy. In this paper, we propose an edge-enabled multi-video analytics framework, in which performing DNN inference relies on heterogeneous resources, including CPU, GPU, and memory. Considering the different impacts of heterogeneous resources on QoI and double-queue backlogs, we formulate the joint video configuration adaptation, CPU-GPU resource allocation, and batch size selection (JCCGB) problem based on semi-Markov Decision Process to maximize the long-term average QoI. Then, Lyapunov optimization is applied to transform the original problem into one that minimizes the Lyapunov drift-plus-penalty upper bound, thereby ensuring the stability of both the transmission and computation queues. To tackle the potential multimodality of the optimal configuration adaptation and resource allocation policy, we propose the diffusion deep reinforcement learning based JCCGB (DD-JCCGB) scheme. This approach effectively enhances the policy performance and accelerates the training process. Experiments driven by real-world network traces demonstrate that the DD-JCCGB algorithm improves the long-term average QoI and outperforms baseline schemes. © 2025 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Classical versus reinforcement learning algorithms for unmanned aerial vehicle network communication and coverage path planning: A systematic literature review

引用

International Journal of Communication Systems 2023年第5期36卷 e5423-e5423页

作者： Mannan, Abdul Obaidat, Mohammad S. Mahmood, Khalid Ahmad, Aftab Ahmad, Rodina Faculty of Computer Science & Information Technology University of Malaya Kuala Lumpur Malaysia Department of Computer Science Bahauddin Zakariya University Multan Pakistan Chair & Computer Science Department and Director of Cybersecurity Center University of Texas-Permian Basin OdessaTX United States King Abdullah II School of Information Technology University of Jordan Amman Jordan Graduate School of Intelligent Data Science National Yunlin University of Science and Technology ROC Yunlin Taiwan Department of Electronics National Yunlin University of Science and Technology ROC Yunlin Taiwan

The unmanned aerial vehicle network communication includes all points of interest during the coverage path planning. Coverage path planning in such networks is crucial for many applications, such as surveying, monitoring, and disaster management. Since the coverage path planning belongs to NP-hard issues, researchers in this domain are constantly looking for optimal solutions for this task. The speed, direction, altitude, environmental variations, and obstacles make coverage path planning more difficult. Researchers have proposed numerous algorithms regarding coverage path planning. In this study, we examined and discussed existing state-of-the-art coverage path planning algorithms. We divided the existing techniques into two core categories: Classical and reinforcement learning. The classical algorithms are further divided into subcategories due to the availability of considerable variations in this category. For each algorithm in both types, we examined the issues of mobility, altitude, and characteristics of known and unknown environments. We also discuss the optimality of different algorithms. At the end of each section, we discuss the existing research gaps and provide future insights to overcome those gaps. © 2022 John Wiley & Sons Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Screen Space Rendering Method for Particle-Based Multiphase Fluid Simulation

SSRN

引用

SSRN 2024年

作者： Zhang, Yalan Xu, Xuhang Xu, Yanrui Hou, Yue Wang, Xiaokun Yu, Guo Obaidat, Mohammad S. Ban, Xiaojuan Xu, Yuhang School of Intelligence Science and Technology University of Science and Technology Beijing China Shunde Innovation School University of Science and Technology Guangdong Beijing China Computer Science Department Director of Cybersecurity Center University of Texas-Permian Basin 4901 E. University Blvd. OdessaTX79762 United States University of Science and Technology Beijing China

Existing fluid simulation techniques mainly process single-phase fluids, and they have difficulties in accurately simulating and visualizing multiphase fluid dynamics. This paper proposes a new method for the real-time rendering of multiphase fluid simulations, which uses smoothed particle hydrodynamics in screen space. Meanwhile, the method employs phase fraction textures to differentiate various materials in multiphase fluid simulations, thereby portraying mixing and separation effects more realistically. Besides, efficient texture computation allows it to be integrated seamlessly into real-time simulation rendering workflows. Extensive testing confirms the effectiveness of the proposed method in rendering multiphase fluid behaviors with high visual fidelity and demonstrates its capability to process frames within 0.01 seconds, even in cases with up to 300,000 particles. This study enhances the fluid dynamics simulation field and provides a more accurate and efficient method for visualizing complex multiphase fluids in simulations. © 2024, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the Solar Heat Pipe with Aluminium Tube Collector in different Environmental Conditions 3

Evaluation of the Solar Heat Pipe with Aluminium Tube Collec...

引用

3rd IEEE Asian Conference on Innovation in technology, ASIANCON 2023

作者： Pithode, Kamya Singh, Devendra Chaturvedi, Rishabh Goyal, Bhawna Dogra, Ayush Hasoon, Ahmed Lepcha, Dawa Chyophel Ies College of Technology Department of Computer Science Engineering Madhya Pradesh Bhopal India Uttaranchal Institute of Technology Uttaranchal University Department of Computer Science Engineering Dehradun248007 India Gla University Mathura Department of Mechanical Engineering Mathura India University Center for Research and Development Chandigarh University Punjab Mohali India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Medical Technical College Al-Farahidi University Iraq Chandigarh University Department Electronics and Communication Engineering Punjab Mohali India

ISBN: (纸本)9798350302288

Based on the energy transfer mechanism, a model for a solar heating system is established in the current study. In addition, heat pipe-oriented solar collectors offer the most viable technology for many uses. The thermal performance of contemporary solar collectors using heat pipes is superior to that of traditional solar collectors. Heat pipes technology is gaining popularity as a passive energy transmission method due to their good thermal performance. In this research, a solar photovoltaic thermal heat pipe's thermal and electrical efficiency are analyzed using modeling and simulation. This study was conducted under an innovative wide range of climatic circumstances. This research explores a solar heat pump heating system that makes use of a tubular collector made of aluminum. More research is needed to fully understand the financial implications of using heat pipes in solar collectors. The results show that both the amount of solar radiation and the wind speed have a major impact on the heat transfer performance of the aluminum tubular collector. © 2023 IEEE.

关键词： Heat pipes

来源：评论

学校读者我要写书评

暂无评论

Temporal Gated Face Alignment Network for Camera-Based Physiological Sensing

SSRN

引用

SSRN 2024年

作者： Li, Qi Guo, Dan Qian, Wei Zhou, Yuanen Zhao, Haifeng Sun, Xiao Wang, Meng School of Computer Science and Technology Anhui University Hefei230601 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230026 China

The remote photoplethysmography (rPPG) technique enables the estimation of vital signs such as heart rate by analyzing pulse-induced subtle skin color variation from facial videos. Robustly deriving cardiac pulse information with head motion (\eg, rotation and swings) interference, remains a critical challenge, as it inevitably introduces complex noise disturbances such as facial geometric deformation and head motions. Most existing approaches primarily focus on how to extract the weak pulse signals, overlooking the detrimental effects induced by such noises. In response to this, we propose a Temporal Gated Face Alignment Network (TGFAN) to adaptively counteract motion noise in long-term video sequences. As key modules in TGFAN, the bidirectional temporal face alignment block first captures inter-frame motion discrepancies and achieves temporal alignment, and then extracts motion-robust pulse features by spatiotemporal convolution. Furthermore, we also propose a temporal gating mechanism, which can dynamically guide motion-disturbed segments for face alignment to alleviate local temporal interference. Experimental evaluations on four public datasets demonstrate the superior performance of our proposed model under both intra-dataset and cross-dataset tests. Our codes will be available at \url{https://***/Eadith/TGFAN}. © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Reviewing metal supported solid oxide fuel cells for efficient electricity generation with biofuels for mobility

引用

Journal of Energy Chemistry 2025年第4期103卷 106-153页

作者： Fábio C.Antunes João P.J.de Oliveira Ricardo S.de Abreu Thiago Dias Bruno B.N.S.Brandão Josué M.Gonçalves Josimar Ribeiro Julian Hunt Hudson Zanin Gustavo Doubek School of Electrical and Computer Engineering University of CampinasCampinas 13083-852Brazil School of Food Engineering University of CampinasCampinas 13083-852Brazil School of Chemical Engineering University of CampinasCampinas 13083-852Brazil Mackenzie Institute for Research in Graphene and Nanotechnologies(MackGraphe) Mackenzie Presbyterian InstituteSão Paulo 01302-907Brazil Electrochemistry Research and Development Laboratory(LPDE) Department of ChemistryCenter of Exact SciencesFederal University of Espírito SantoCampus GoiabeirasVitória 29075-910Brazil Biological and Environmental Science and Engineering Division King Abdullah University of Science and TechnologyThuwal 23955-6900Saudi Arabia

Metal-Supported Solid Oxide Fuel Cells(MS-SOFCs)hold significant potential for driving the energy *** electrochemical devices represent the most advanced generation of Solid Oxide Fuel Cell(SOFCs)and can pave the way for mass production and wider adoption than Proton Exchange Membrane Fuel Cells(PEMFCs)due to their fuel flexibility,higher power density and the absence of noble metals in the fabrication *** review examines the state-of-the-art of SOFCs and MS-SOFCs,presenting perspectives and research directions for these key technological devices,highlighting novel materials,techniques,architectures,devices,and degradation mechanisms to address current challenges and future *** such as infiltration/impregnation,ex-solution catalyst synthesis,and the use of a pre-catalytic reformer layer are discussed as their impact on efficiency and prolonged *** concepts are also described and connected with well-dispersed nano particles,hindrance of coarsening,and an increased number of Triple Phase Boundaries(TPBs).This review also describes the synergistic use of reformers with MS-SOFCs to compose solutions in energy generation from readily available ***,the End-of-Life(EoL),recycling,and life-cycle assessments(LCAs)of the Fuel Cell Hybrid Electric Vehicles(FCHEVs)were *** comparing Fuel Cell Electric Vehicles(FCEVs)equipped with(PEMFCs)and FCHEVs equipped with MS-SOFCs,both powered with hydrogen(H_(2))generated by different routes were *** review aims to provide valuable insights into these key technological devices,emphasizing the importance of robust research and development to enhance performance and lifespan while reducing costs and environmental impact.

关键词： Reform Metal-supported solid oxide fuel cell Powertrain systems Fuel cell Hybrid electric vehicle Biofuel

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：