检索结果-内蒙古大学图书馆

Improving Lagos State emergency medical services by analysing road traffic accident data, response time, and efficient allocation of ambulances

引用

The Lancet. Global health 2022年 10卷 S26-S26页

作者： Salam, Sayeed, PhD Mehta, Avirut Kim, Dohyeong, PhD Seyi-Olajide, Justina, PhD Allo, Nicholas, PhD Malolan, Chenchita, MPH Nwariaku, Fiemu, MD Khan, Latifur, PhD Department of Computer Science University of Texas at Dallas Richardson TX United States Department of Public Policy and Political Economy Geospatial Information Sciences University of Texas at Dallas Richardson TX United States Lagos University Teaching HospitalLagos Nigeria Visual Earth London United Kingdom University of Texas Southwestern Medical Center University of Texas Dallas United States Department of Computer Science University of Texas at Dallas Richardson TX United States

BACKGROUND: Emergency medical services (EMS) play a critical role in the response to road traffic accidents (RTAs) by providing critical prehospital care to RTA victims, and thus helping to reduce the severity of injuries and casualties from RTAs. Analysing the efficiency of such systems and optimising the service (often with insufficient resources) would be highly beneficial to inform operating guidelines. In this study, we aimed to assess the ambulance utilisation rate for RTAs and provide insights about the system's efficiency and utilisation metrics in Lagos State, Nigeria. METHODS: We received hospital capacity information (type of hospital [eg, tertiary] and number of beds, nurses, operating rooms, and so on) from hospital survey data in Lagos. Additionally, we received RTA-specific intervention forms from the Lagos State Ambulance Service. With the limited amount of historical data, we highlighted methods to estimate the system parameters (eg, arrival rate, service rate, and so on) of RTA victims at various hospitals in Lagos. We also developed a parametric model and applied approximate dynamic programming approach for ambulance dispatch and location optimisation with a fixed number of base stations. Furthermore, our routing approach was accompanied by directions from OpenRouteService and queue analysis to determine the most appropriate hospital near an RTA for the EMS systems in Lagos. FINDINGS: Using patient-queue based wait-time analysis, we found that in over 80% of cases, one of the nearest three hospitals was the most appropriate recommendation for patient delivery. This exponentially decays with the next closest hospitals. Additionally, we found that optimising the ambulance relocation method, where the ambulance returns to a base selected by our model as opposed to its dedicated base or a random base, can reduce the average response time of the EMS system by 8%, or 3·5 min (from 41 min to 38 min). INTERPRETATION: Appropriate placement of mobile resour

关键词：

来源：评论

学校读者我要写书评

暂无评论

An On-Call Shift for Anaesthetist Rostering Problem (ARP): A Mathematical Model

An On-Call Shift for Anaesthetist Rostering Problem (ARP): A...

引用

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Norizal Abdullah Masri Ayob Nasser R. Sabar Meng Chun Lam Liu Chian Yong Data Mining and Optimisation Lab Faculty of Information Science and Technology Center for Artificial Intelligence Technology (CAIT) UKM Bangi Selangor Malaysia Department of Computer Science and Information Technology La Trobe University Melbourne Australia Faculty of Information Science and 43600 Mixed Reality and Pervasive Computing Lab Center for Artificial Intelligence Technology (CAIT) UKM Bangi Selangor Malaysia Department of Anaesthesiology & Intensive Care UKM Medical Centre Jalan Yaacob Latiff Bandar Tun Razak Kuala Lumpur Malaysia

This work dealt with a real-world Anaesthetist Rostering Problem (ARP) for an on-call shift. An on-call shift for an anaesthetist had already been resolved under the physician's rostering problem. However, in their work, each individual can be assigned to only one place throughout the daily on-call shift. In addition, no consecutive days are rostered for the on-call shift, and each level of preference for the on-call shift is excluded from the study. This scenario is irrelevant to the real-world ARP of an on-call shift at Hospital Canselor Tuanku Muhriz (HCTM) in Malaysia, as an anaesthetist is rostered for multiple places of the on-call shifts daily. Also, they can be rostered on consecutive days for on-call shifts, and each anaesthetist will be rostered depending on their preference level for the on-call shift. Therefore, this work proposes a new mathematical formulation with constraints, parameters, and an evaluation function. We utilise Mixed-integer programming to formulate and solve the model with IBM ILOG CPLEX Optimization Studio. The quality of the solution generated by our model is measured using our proposed evaluation function to minimise the violation of constraints. A case study of real-world data from the HCTM was run and tested to validate the model. The result shows that a new model can produce a better optimal solution, whilst the current solution methodology at HCTM is unable to do.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal deep learning framework for image popularity prediction on social media

arXiv

引用

arXiv 2021年

作者： Abousaleh, Fatma S. Cheng, Wen-Huang Yu, Neng-Hao Tsao, Yu Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan Department of Computer Science National Chengchi University Taipei11605 Taiwan The Institute of Electronics Department of Electronics Engineering National Chiao Tung University Hsinchu30010 Taiwan The College of Design Department of Design National Taiwan University of Science and Technology Taipei10607 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan

Billions of photos are uploaded to the web daily through various types of social networks. Some of these images receive millions of views and become popular, whereas others remain completely unnoticed. This raises the problem of predicting image popularity on social media. The popularity of an image can be affected by several factors, such as visual content, aesthetic quality, user, post metadata, and time. Thus, considering all these factors is essential for accurately predicting image popularity. In addition, the efficiency of the predictive model also plays a crucial role. In this study, motivated by multimodal learning, which uses information from various modalities, and the current success of convolutional neural networks (CNNs) in various fields, we propose a deep learning model, called visual-social convolutional neural network (VSCNN), which predicts the popularity of a posted image by incorporating various types of visual and social features into a unified network model. VSCNN first learns to extract high-level representations from the input visual and social features by utilizing two individual CNNs. The outputs of these two networks are then fused into a joint network to estimate the popularity score in the output layer. We assess the performance of the proposed method by conducting extensive experiments on a dataset of approximately 432K images posted on Flickr. The simulation results demonstrate that the proposed VSCNN model significantly outperforms state-of-the-art models, with a relative improvement of greater than 2.33%, 7.59%, and 14.16% in terms of Spearman’s Rho, mean absolute error, and mean squared error, respectively. Copyright © 2021, The Authors. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

从四方到立方:高性能太阳能电池的钙钛矿相结构演变

引用

science Bulletin 2023年第2期68卷 141-145,M0003页

作者：魏旗梁昊 Yuki Haruta Makhsud Saidaminov 米启兮 Michael Saliba 崔光磊宁志军 School of Physical Science and Technology ShanghaiTech UniversityShanghai 201210China High Performance Computing Department National Supercomputing Center in ShenzhenShenzhen 200441China Department of Chemistry and Department of Electrical&Computer Engineering and Centre for Advanced Materials and Related Technologies(CAMTEC) University of VictoriaVictoria V8P 5C2Canada Institute for Photovoltaics University of StuttgartStuttgart 70569Germany Qingdao Industrial Energy Storage Research Institute Qingdao Institute of Bioenergy and Bioprocess TechnologyChinese Academy of SciencesQingdao 266101China

Crystal structure, which is generally determined by the composition, ionic radius and valence state of constituent elements, plays a significant role in the material’s fundamental properties such as optical, electronic, and mechanical characters. The manipulation of the crystal structure through compositional engineering, and understanding the relationship between crystal structure and properties are essential for the development of materials.

关键词：太阳能电池结构演变钙钛矿相

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI

arXiv

引用

arXiv 2024年

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina Aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. © 2024, CC BY-NC-ND.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Weak Devices Matter: Model Heterogeneity in Resource-Constrained Federated Learning

Weak Devices Matter: Model Heterogeneity in Resource-Constra...

引用

IEEE International Conference on Communications (ICC)

作者： Tzu–Hsuan Peng Cheng-Wei Huang Ai-Chun Pang Te-Chuan Chiu Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan R.O.C Graduate Institute of Networking and Multimedia National Taiwan University Taipei Taiwan R.O.C High Performance and Scientific Computing Center National Taiwan University Taipei Taiwan R.O.C Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan R.O.C Department of Computer Science National Tsing Hua University Hsinchu Taiwan R.O.C

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Federated Learning (FL) is a promising framework for enabling edge intelligence while preserving privacy and enhancing communication efficiency. In real-world scenarios, limited and heterogeneous hardware resources among users threaten the overall training efficiency in FL. To address this issue, several model heterogeneity frameworks have emerged in recent years. However, existing studies primarily focus on mitigating idle times on powerful devices, overlooking the fact that strong devices may not always have a positive impact and can potentially become a burden instead. Furthermore, as the resource gap among clients widens or the number of weak devices increases, the model may be hindered by the influence of strong devices. Directly applying existing model heterogeneity frameworks leads to model performance degradation due to the neglect of contributions from weak devices. To make a performance breakthrough, we proposed a novel FL framework called Progressive Width Mixing (PWM), which extracts diverse features and balances the contribution of strong and weak devices and mitigates straggler effects under scenarios with various device distributions. To our best knowledge, we are the first model heterogeneity work that considered straggler effects from the weak devices' point of view. The experiments show that PWM maintains stability over different datasets and outperforms all baselines across various device distributions and non-IID scenarios. PWM makes a leap forward and surpasses all baselines by 7%, and mitigates the negative impact from the strong devices.

关键词： Performance evaluation Training Privacy Philosophical considerations Federated learning Pulse width modulation System recovery

来源：评论

学校读者我要写书评

暂无评论

Transmit Only: An Ultra Low Overhead MAC Protocol for Dense Wireless Systems

Transmit Only: An Ultra Low Overhead MAC Protocol for Dense ...

引用

International Conference on Smart computing (SMARTCOMP)

作者： Yanyong Zhang Bernhard Firner Richard Howard Richard Martin Narayan Mandayam Junichiro Fukuyama Chenren Xu Autonomous Driving Team at Nvidia Holmdel NJ Wireless Information Networks Laboratory (WINLAB) Rutgers University NJ Department of Computer Science Rutgers University Piscataway NJ Applied Research Laboratory University Park PA United States Center for Energy-efficient Computing and Applications Peking University Beijing

ISBN: (纸本)9781509065189

The number of small wireless devices is rapidly increasing, making the radio channel efficiency in limited geographic areas (individual rooms or buildings) an important metric for MAC protocols. Many of these emerging devices have use-cases that are difficult to satisfy with current hardware solutions and channel access methods; for instance device mobility, small energy reserves, and requirements for low cost and small form factors. However, for most of these applications, such as health care monitoring or sensing, feedback to the radio device is unnecessary and unidirectional communication techniques are not only sufficient, but can also be advantageous. We propose an efficient, reliable technique for unidirectional communication, called Transmit Only (TO), that satisfies these requirements while maintaining packet throughput guarantees and reducing energy consumption. In this paper we will demonstrate the feasibility and performance of this kind of highly asymmetric, transmit-only protocol through theoretical, simulated, and experimental results.

关键词： Receivers Multiaccess communication Radio transmitters Throughput Wireless communication Protocols

来源：评论

学校读者我要写书评

暂无评论

Resting-state functional connectivity predicts individual language impairment of patients with left hemispheric gliomas involving language network

Resting-state functional connectivity predicts individual la...

引用

第二十二届全国心理学学术会议

作者： Binke Yuan Nan Zhang Jing Yan Junfeng Lu Jinsong Wu Center for Language and Brain Shenzhen Institute of Neuroscience Department of Neurosurgery The First Affiliated Hospital of USTCDivision of Life Sciences and MedicineUniversity of Science and Technology of China Glioma Surgery Division Department of NeurosurgeryHuashan HospitalFudan University Department of MRI The First Affiliated Hospital of Zhengzhou University Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention

Aim: Language deficits following brain tumors should consider the dynamic interactions between different tumor growth kinetics and functional network reorganization. However, no study has attempted to investigate the language network basis at the whole brain level to determine the language network reorganization differences between low-grade glioma(LGG) and high-grade glioma(HGG) patients. Methods: Inclusion Criteria:(1) Pathologically confirmed glioma in left cerebral hemisphere and overlapped or was within the language network areas proposed by Fedorenko et al.(2010);(2) patients' age was 18–75 years old;(3) Right-handedness;(4) No symptoms of motor impairment;(5) No history of brain surgery;(6) No midline shift in structural images;(7) No history of other major neurological or psychiatric disorders. In total, 126 patients,including 77 patients with LGG and 49 patients with HGG met all inclusion criteria and completed the entire preoperative clinical, language, and imaging data acquisition. All processes strictly followed the requirements of the Declaration of Helsinki. This study was approved and supervised by the Ethics Committee of Huashan Hospital and the Ethics Committee of the First Affiliated Hospital of Zhengzhou University, respectively. Written informed consents were obtained from the human subjects and their legal guardians. Language function: ABC(Aphasia Battery for Chinese speakers) was used and Aphasia Quotient(AQ) score(range, 0–100) was calculated for each patient. Rs-f MRI data: TR = 2,000 ms;TE = 35 ms;FA =90°;240 volumes;eyes closed. T1 and T2 images were also acquired for tumor mapping and registration. Rs-f MRI data preprocessing: slice timing, motion correction, normalization by DARTEL(MNI), smoothness(6 mm), detrend, nuisance regression, filter(0.01-0.1 Hz) and scrubbing(FD > 0.05). No patients exhibited a head motion > 3 mm maximum translation or 3° rotation. Nuisance signals included 36 head motion parameters, global signals, cerebrospinal

关键词： low-grade glioma high-grade glioma resting-state fMRI language machine learning

来源：评论

学校读者我要写书评

暂无评论

A Summarization Generation Method for E-Courseware on the Internet Platform

A Summarization Generation Method for E-Courseware on the In...

引用

IEEE International Conference on Big Data and Cloud computing (BdCloud)

作者： Gang Cui Yan Wang Hao Yu Hong Liu Shibin Shibin Liang Xiaodong Guo College of Computer Science Inner Mongolia University Hohhot China Inner Mongolia Engineering Lab of Cloud Computing and Service Software Hohhot China Vocational Qualification Center of Inner Mongolia Autonomous Region Department of Transport Hohhot China Bureau of Transportation of Inner Mongolia Autonomous Region Hohhot China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

With the increase of various online learning platforms, lots of electronic coursewares (e-courseware) are uploaded to the Internet platform for users' learning and sharing. Constructing the summarization for e-courseware through extracting the content of e-courseware is of great importance for users to select and utilize e-courseware for the self-learning process. But the information extraction algorithm for e-courseware has not been fully studied on the Internet Platform. This paper proposes a new method for extracting courseware information based on automatic summarization, and then applies it to generate automatically the summarization covering the knowledge content of e-courseware on the Internet platform. Based on the analysis of e-courseware structure, the method uses the extractive and abstractive automatic digest algorithm to deal with the text of a single slide, and then calculates the similarity of two sentences outputted by the two algorithms to determine the final key information, finally organizes the summarization of e-courseware based on the extracted key information. The experimental results show that the algorithm has a good performance in the summarization and generalization of text information for e-coursewares, which is conducive to the generation of learning notes for users so as to quickly understand the content of e-courseware.

关键词： Courseware Data mining Internet Information retrieval Semantics Prediction algorithms Decoding

来源：评论

学校读者我要写书评

暂无评论

Robust online matrix factorization for dynamic background subtraction

arXiv

引用

arXiv 2017年

作者： Yong, Hongwei Meng, Deyu Zuo, Wangmeng Zhang, Lei School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi'an Jiaotong University Shaanxi China School of Computer Science and Technology Harbin Institute of Technology Harbin China Biometrics Research Center Department of Computing Hong Kong Polytechnic University Kowloon Hong Kong

We propose an effective online background subtraction method, which can be robustly applied to practical videos that have variations in both foreground and background. Different from previous methods which often model the foreground as Gaussian or Laplacian distributions, we model the foreground for each frame with a specific mixture of Gaussians (MoG) distribution, which is updated online frame by frame. Particularly, our MoG model in each frame is regularized by the learned foreground/background knowledge in previous frames. This makes our online MoG model highly robust, stable and adaptive to practical foreground and background variations. The proposed model can be formulated as a concise probabilistic MAP model, which can be readily solved by EM algorithm. We further embed an affine transformation operator into the proposed model, which can be automatically adjusted to fit a wide range of video background transformations and make the method more robust to camera movements. With using the sub-sampling technique, the proposed method can be accelerated to execute more than 250 frames per second on average, meeting the requirement of real-time background subtraction for practical video processing tasks. The superiority of the proposed method is substantiated by extensive experiments implemented on synthetic and real videos, as compared with state-of-the-art online and offline background subtraction methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Video signal processing

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：