检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Sam, Steven Gulia, Ritu Department of Computer Science College of Engineering Design and Physical Science Brunel University London Kingston Lane Uxbridge MiddlesexUB8 3PH United Kingdom Department of Computer Science Level 2 Wilfred Brown Building Brunel University London Kingston Lane Uxbridge MiddlesexUB8 3PH United Kingdom

This paper combines exploratory data analysis and machine learning approaches to develop and compare three ML models namely, Multinomial Logistic Regression, Decision Tree and Random Forest for predicting road accident severity and causality in the UK. It analyses 26 important features for predicting both the models’ performance accuracy and causality for accident severity on motorways and built-up roads in rural and urban areas. The goal is to shed new light on the causality and predictors of the severity of road traffic accident classified into fatal, serious and minor. Using a large available road transport accident dataset from the UK between 1979 and 2016, the analysis shows that the Random Forest Model has high accuracy of 99.3% compared to Decision Tree (93.8%) and Multinomial Logistic Regression (92.7%). Along with well-known factors such as age, gender and weather, the study reveals that variables like region type (urban or rural) and light conditions have significant impact on accident severity. Higher accidents occurred in urban regions, which are expected to have more traffic congestion and transportation. Findings also show that lower speed less than 35 miles per hour limit contributes to accident frequency while high speed has more severe accident injury and fatality effects. The outcomes of this study can help road transport agencies and policymakers predict and understand drivers’ behaviour, road and weather conditions and other variables that cause accidents that result in fatalities or major injuries, allowing them to develop better traffic safety and control policies. © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Single Channel-Based Neonatal Sleep-Wake Classification using Hjorth Parameters and Improved Gradient Boosting

arXiv

引用

arXiv 2024年

作者： Arslan, Muhammad Mubeen, Muhammad Abbasi, Saadullah Farooq Khan, Muhammad Shahbaz Boulila, Wadii Ahmad, Jawad Department of Computer Science Loyola University ChicagoIL60660 United States Department of Computer Science University of People PasadenaCA91101 United States Department of Electronic Electrical and Systems Engineering University of Birmingham BirminghamB15 2TT United Kingdom School of Computing Engineering and the Built Environment Edinburgh Napier University EdinburghEH105DT United Kingdom RIOTU Lab Prince Sultan University Riyadh12435 Saudi Arabia

Sleep plays a crucial role in neonatal development. Monitoring the sleep patterns in neonates in a Neonatal Intensive Care Unit (NICU) is imperative for understanding the maturation process. While polysomnography (PSG) is considered the best practice for sleep classification, its expense and reliance on human annotation pose challenges. Existing research often relies on multichannel EEG signals;however, concerns arise regarding the vulnerability of neonates and the potential impact on their sleep quality. This paper introduces a novel approach to neonatal sleep stage classification using a single-channel gradient boosting algorithm with Hjorth features. The gradient boosting parameters are fine-tuned using random search cross-validation (randomsearchCV), achieving an accuracy of 82.35% for neonatal sleep-wake classification. Validation is conducted through 5-fold cross-validation. The proposed algorithm not only enhances existing neonatal sleep algorithms but also opens avenues for broader applications. © 2024, CC BY.

关键词： Neonatal monitoring

来源：评论

学校读者我要写书评

暂无评论

Cross or Wait? Predicting Pedestrian Interaction Outcomes at Unsignalized Crossings

arXiv

引用

arXiv 2023年

作者： Zhang, Chi Kalantari, Amir Hossein Yang, Yue Ni, Zhongjun Markkula, Gustav Merat, Natasha Berger, Christian Department of Computer Science and Engineering University of Gothenburg Sweden Institute for Transport Studies University of Leeds LeedsLS2 9JT United Kingdom Department of Science and Technology Linköping University Campus Norrköping Sweden

Predicting pedestrian behavior when interacting with vehicles is one of the most critical challenges in the field of automated driving. Pedestrian crossing behavior is influenced by various interaction factors, including time to arrival, pedestrian waiting time, the presence of zebra crossing, and the properties and personality traits of both pedestrians and drivers. However, these factors have not been fully explored for use in predicting interaction outcomes. In this paper, we use machine learning to predict pedestrian crossing behavior including pedestrian crossing decision, crossing initiation time (CIT), and crossing duration (CD) when interacting with vehicles at unsignalized crossings. Distributed simulator data are utilized for predicting and analyzing the interaction factors. Compared with the logistic regression baseline model, our proposed neural network model improves the prediction accuracy and F1 score by 4.46% and 3.23%, respectively. Our model also reduces the root mean squared error (RMSE) for CIT and CD by 21.56% and 30.14% compared with the linear regression model. Additionally, we have analyzed the importance of interaction factors, and present the results of models using fewer factors. This provides information for model selection in different scenarios with limited input *** Codes 68T40 © 2023, CC BY-NC-SA.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Parameter aware utility proportional fairness scheduling technique in a communication network

引用

International Journal of Innovative Computing and Applications 2021年第2-3期12卷 98-107页

作者： Kumar, Neeraj Ahmad, Anwar Awasthi, Shashank Sharma, Kavita Department of Electronics and Communication Engineering Jamia Millia Islamia Jamia Nagar Okhla New DelhiDelhi110025 India Department of Computer Science and Engineering G.L. Bajaj Institute of Technology and Management Plot No. 2 Knowledge Park III Greater Noida Dist. G.B. NagarUP201306 India

Conventionally, real-time (inelastic) users and non-real-time (elastic) users are scheduled separately. Further, some users may be left without getting any radio resources. In real scenario, such as in high network traffic, less network coverage, resource allocation for all types of users are needed. In the proposed technique, a utility function is defined for each elastic traffic and inelastic traffic type users. Then, it maximises the total utilities by network utility maximisation approach with considering scheduling parameters such as queue length, head of the line delay and experienced channel condition. Rate allocation based on queue awareness improves fairness among elastic traffic users, delay awareness improves QoS performance of inelastic traffic users and channel condition awareness improves throughput of all users. Further, the network utility maximisation approach provides minimum throughput to all users. © 2021 Inderscience Enterprises Ltd.

关键词： Queueing theory

来源：评论

学校读者我要写书评

暂无评论

Canadarm, Canadarm2, and Canadarm3: The evolution of Canada's iconic robotic system and its impacts from space down to Earth 58

Canadarm, Canadarm2, and Canadarm3: The evolution of Canada'...

引用

58th IAA History of Astronautics Symposium at the 75th International Astronautical Congress, IAC 2024

作者： Hudon-Castillo, Yianni Lamanque, Jean-Christophe Thénault, Marion Zamudio-Turcotte, Katherine Musunuri, Sri Venkata Vathsala Thilloy, Auriane Leclair, Olivier Roberge, Julien Lavergne Elforaici, Mohamed El Amine Daigneault, Rafael Chazbek, Rachad Beltrame, Giovanni Department of Electrical Engineering Polytechnique Montréal 2500 Chemin de Polytechnique MontréalQCH3T 1J4 Canada Department of Electrical and Computer Engineering McGill University McConnell Engineering Building MontréalQCH3A 0E9 Canada Department of Aerospace Engineering Gina Cody School of Engineering and Computer Science Concordia University 1455 De Maisonneuve Blvd. W. MontréalQCH3G 1M8 Canada Department of Aerospace Engineering Polytechnique Montréal 2500 Chemin de Polytechnique MontréalQCH3T 1J4 Canada Department of Physics Université de Montréal 1375 Ave Thérèse-Lavoie-Roux MontréalQCH2V 0B3 Canada Department of Mechanical Engineering Université Laval QuébecQCG1V 0A6 Canada Department of Biomedical Engineering Polytechnique Montréal 2500 Chemin de Polytechnique MontréalQCH3T 1J4 Canada Department of Engineering Physics Polytechnique Montréal 2500 Chemin de Polytechnique MontréalQCH3T 1J4 Canada Department of Computer and Software Engineering Polytechnique Montréal 2500 Chemin de Polytechnique MontréalQCH3T 1J4 Canada

ISBN: (纸本)9798331312329

Considered to be Canada's groundbreaking technological achievement in the field of robotics and its greatest contribution to space, Canadarm and Canadarm2 have made their mark on both the Canadian and international scene. As the upcoming Canadarm3 reaches the culmination of its design phase for the Lunar Gateway, an opportunity to review the evolution of this robotic technology over its combined 53 years of service arises. Furthermore, the practical impacts of each Canadarm generation will be explored, regarding the safe and sustainable use of space, the commercialization of the space industry, and technological progress in the medical field, in nuclear power plant robotics and in remote explosives disarming robots. This paper will embark on a comprehensive literature review, complemented by interviews conducted with key contributors to the Canadarms' missions as well as Canadian astronauts. This methodological approach aims to provide an accurate outline of the technical, operational, and collaborative complexities that have underpinned the development and deployment of this technology. By comparing the technical specifications of each Canadarm generation in the context of their respective space program, namely Space Shuttle, ISS and Gateway, technological advancements will be highlighted from an engineering and operations standpoint. The conducted interviews with the Canadian Space Agency (CSA) and MacDonald Dettwiler And Associates (MDA) will also help illustrate the obstacles faced throughout the implementation of these programs. Foreseeing the next step in Canada's role in space exploration, this study will also examine Canadarm3's upcoming crucial contribution in missions to the Moon, Mars, and beyond. This outlook includes a mission concept study of the next generation Canadarm : Canadarm4, which will emphasize the ongoing significance of innovation and international collaboration, affirming Canada's leadership in space robotics technology. © 2024 Internation

关键词： Nuclear power plants

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a QoL Improvement System for Visually Impaired Patients

Design and Implementation of a QoL Improvement System for Vi...

引用

International Conference on Advances in Computational Tools for engineering Applications, ACTEA

作者： Roy Abi Zeid Daou Jad Beaino Johnny Hawat Ramy Ibrahim Ali Hayek Josef Boercsoek Jose Javier Serrano Olmedo Mechatronics department Faculty of Engineering Université La Sagesse Beirut Lebanon MART Learning Education and Research Center Chananir Lebanon Department Lippstadt 2 Hardware Engineering University of Applied Science Hamm-Lippstadt Hamm Department of Computer Architecture and System Programming Faculty of Electrical Engineering/Computer Science University of Kassel Germany Lab of Bioinstrumentation and Nanomedicine Centro de Tecnología Biomédica Universidad Politécnica de Madrid Spain

Visually impaired people encounter several challenges in their mobility and navigation. Their daily activities are obstructed due to their inability to adapt or recognize accurately their surroundings, especially outside their house which they are more familiar with. Thus, it becomes the main reason of accidents, falling off, getting lost in unknown areas, etc. Furthermore, one of the sensory systems that helps the body to process data about the external environment is the visual system. Blind people also lose touch with the outside world, develops poor motor habits, which results in postural problems as a result. This project will assist visually impaired people in their daily life and simplify normal tasks through a system combining two previously designed projects, “Smart Shoes for Blind and Visually Impaired People”, and “Human posture monitoring device”. The multifunctional system is developed with the goal of securing safe movements for visually impaired people as well as maintaining a good back posture by detecting leaning postures (LP). The purpose of the smart shoe is to identify obstacles and protect the user from unintended accidents. A compatible Android application has been developed to alert the user when there is an obstruction or when he is walking on a wet surface. Voice alarms will be used to acoustically alert the user. If the user collapses, a message with their position will be sent right away to a relative. On the other hand, the smart vest will identify the position of the user's back and alert him to maintain a straight posture through the same application as well. As the system is dealing with human health, some safety measurements would be taken into consideration to implement a safe electrical system in order to reduce error and to increase accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

User-Centric Interactive AI for Distributed Diffusion Model-based AI-Generated Content

arXiv

引用

arXiv 2023年

作者： Du, Hongyang Zhang, Ruichen Niyato, Dusit Kang, Jiawen Xiong, Zehui Cui, Shuguang Shen, Xuemin Kim, Dong In The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Chinese University of Hong Kong Shenzhen China The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Distributed Artificial Intelligence-Generated Content (AIGC) has attracted increasing attention. However, it faces two significant challenges: how to maximize the subjective Quality of Experience (QoE) and how to enhance the energy efficiency, which are particularly pronounced in widely adopted Generative Diffusion Model (GDM)-based AIGC services for image generation. In this paper, we propose a novel user-centric Interactive AI (IAI) approach for service management, with a distributed GDM-based AIGC framework, prioritizing efficient and collaborative GDM deployment. Specifically, we restructure the GDM's inference process, i.e., the denoising chain, to enable users' semantically similar prompts to share a portion of diffusion steps. Furthermore, to maximize the users' subjective QoE, we propose a IAI approach, i.e., Reinforcement Learning With Large Language Models Interaction (RLLI), which utilizes Large Language Model (LLM)-empowered generative agents to replicate users interaction, providing real-time and subjective QoE feedback that reflects a spectrum of user personalities. Lastly, we present the GDM-based Deep Deterministic Policy Gradient (G-DDPG) algorithm, adapted to the proposed RLLI framework, for effective communication and computing resource allocation while considering user subjective personalities and dynamic wireless environments in decision-making. Simulation results show that G-DDPG can increase the sum QoE by 15%, compared with the conventional DDPG algorithm. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Life Cycle Assessment of Different Hydrogen Production Routes 35

Life Cycle Assessment of Different Hydrogen Production Route...

引用

35th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems, ECOS 2022

作者： Wei, Xinyi Sharma, Shivom Kantor, Ivan Margni, Manuele Maréchal, François Van Herle, Jan IPESE EPFL Valais Wallis Sion1950 Switzerland GEM EPFL Valais Wallis Sion1950 Switzerland CIRAIG Mathematical and Industrial Engineering Department Polytechnique Montreal MontrealQCH3V 1A2 Canada Sion Switzerland Department of Chemical and Materials Engineering Gina Cody School of Engineering and Computer Science Concordia University MontréalQC Canada

ISBN: (纸本)9788774756989

Replacing fossil fuel with a renewable energy carrier is one possible solution for mitigating global CO2 emissions. Hydrogen, due to its thermochemical properties such as its high energy content and clean combustion, is considered as one such promising carrier, provided that its production has limited life-cycle CO2 emissions and that it is efficiently stored. In this study, methodology of analyzing different hydrogen production routes has been defined. Life cycle environmental impact of different routes with/without carbon capture storage (CCS) by using chemical absorption process, for grey/blue/green hydrogen production, have been investigated: Route 1: Steam methane reforming;Route 2: Biomass gasification;Route 3: Solid oxide fuel cell (SOFC) system for cogenerating power and hydrogen (25 kW and 20 kg-H2/day);Route 4: SOFC reversible system (i.e., solid oxide electrolysis cell, 50 kg-H2/day) using electricity (from grid mix or renewable). Moreover, for Route 3, fuel sources, electricity generation locations, and mutilfunctional system functional unit methodologies have been studied. As expected, use of renewable electricity and CCS technology can reduce the CO2 emissions of the hydrogen production process. Exergy allocation is less sensible than system expansion in electricity generation locations and emissions. Hydrogen production via biomass gasification has higher CO2 emissions, grid mix electricity is used for operation in this scenario. Further, the potential hydrogen production routes have been chosen under different scenarios, such as electricity availability, and a dynamic CO2 emission profile has been presented. © Proceedings of ECOS 2022 - 35th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Adaptation Via Proxy: Building Instance-Aware Proxy for Unsupervised Domain Adaptive 3d Object Detection

SSRN

引用

SSRN 2023年

作者： Li, Ziyu Yao, Yuncong Quan, Zhibin Qi, Lei Feng, Zhenhua Yang, Wankou School of Automation Southeast University Nanjing210096 China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China School of Computer Science and Engineering Southeast University Nanjing210096 China Department of Computer Science University of Surrey GuildfordGU2 7XH United Kingdom

LiDAR-based 3D detectors perform well on particular autonomous driving benchmarks, but may poorly generalize to other domains. Existing 3D domain adaptive detection methods usually require annotation-related statistics or continuous refinement of pseudo-labels. The former is not always feasible for practical applications, while the latter lacks sufficient accurate supervision. In this work, we propose a novel unsupervised domain adaptive framework, namely Adaptation Via Proxy (AVP), that explicitly leverages cross-domain relationships to generate adequate high-quality samples without any target statistics, thus mitigating domain shifts for existing LiDAR-based 3D detectors. Specifically, we first train the detector on the source domain with curriculum example mining to enhance its generalization capability. Then, we fine-tune the pre-trained detector on the instance-aware proxy that is a data collection with stronger supervision. The instance-aware proxy utilizes the profitable instances from the source domain to provide more robust supervision for optimizing the detector to overcome domain gaps. Note that AVP is architecture-agnostic thus it can be easily injected with any LiDAR-based 3D detectors. Extensive experiments on Waymo, nuScenes, KITTI and Lyft demonstrate the superiority of the proposed method over the state-of-the-art approaches for different adaptation scenarios. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Enhanced Quantum Emission from a Topological Floquet Resonance

引用

PRX Quantum 2024年第4期5卷 040331-040331页

作者： Shirin Afzal Tyler J. Zimmerling Mahdi Rizvandi Majid Taghavi Leili Esmaeilifar Taras Hrushevskyi Manpreet Kaur Vien Van Shabir Barzanjeh Institute for Quantum Science and Technology and Department of Physics and Astronomy University of Calgary 2500 University Drive NW Calgary Alberta T2N 1N4 Canada Department of Electrical and Computer Engineering University of Alberta 9211 116 Street NW Edmonton Alberta T6G 1H9 Canada

Entanglement is a valuable resource in quantum information technologies. The practical implementation of entangled photon sources faces obstacles from imperfections and defects inherent in physical systems, resulting in a loss or degradation of entanglement. The topological photonic insulators, however, have emerged as promising candidates, demonstrating an exceptional capability to resist defect-induced scattering, thus enabling the development of robust entangled sources. Despite their inherent advantages, building programmable topologically protected entangled sources remains challenging due to complex device designs and weak material nonlinearity. Here, we present a development in entangled photon-pair generation achieved through a nonmagnetic and tunable anomalous Floquet insulator, utilizing an optical spontaneous four-wave-mixing process. We verify the nonclassicality and time-energy entanglement of the photons generated by our topological system. Our experiment demonstrates a substantial enhancement in nonclassical photon-pair generation compared to devices reliant only on topological edge states. Our results could lead to the development of resilient quantum sources with potential applications in quantum technology.

关键词： Quantum circuits Quantum engineering

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：