检索结果-南通市图书馆

Optimal Positioning Strategy for Multi-Camera Zooming Drones

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第8期11卷 1802-1818页

作者： manuel Vargas Carlos Vivas Teodoro Alamo Department of System Engineering and Automation University of SevilleSeville 41092Spain

In the context of multiple-target tracking and surveillance applications,this paper investigates the challenge of determining the optimal positioning of a single autonomous aerial vehicle or agent equipped with multiple independently-steerable zooming cameras to effectively monitor a set of targets of *** camera is dedicated to tracking a specific target or cluster of *** key innovation of this study,in comparison to existing approaches,lies in incorporating the zooming factor for the onboard cameras into the optimization *** enhancement offers greater flexibility during mission execution by allowing the autonomous agent to adjust the focal lengths of the onboard cameras,in exchange for varying real-world distances to the corresponding targets,thereby providing additional degrees of freedom to the optimization *** proposed optimization framework aims to strike a balance among various factors,including distance to the targets,verticality of viewpoints,and the required focal length for each *** primary focus of this paper is to establish the theoretical groundwork for addressing the non-convex nature of the optimization problem arising from these *** this end,we develop an original convex approximation *** paper also includes simulations of diverse scenarios,featuring varying numbers of onboard tracking cameras and target motion profiles,to validate the effectiveness of the proposed approach.

关键词： Convex optimization projective transformation unmanned aerial vehicle visual object tracking visual surveillance.

Why is early detection of colon cancer still not possible in 2023?

在线全文

学校读者我要写书评

暂无评论

World Journal of Gastroenterology 2024年第3期30卷 211-224页

作者： Valeria Tonini manuel Zanni Department of Medical and Surgical Sciences University of BolognaBologna 40138Italy

Colorectal cancer(CRC)screening is a fundamental tool in the prevention and early detection of one of the most prevalent and lethal *** the years,screening,particularly in those settings where it is well organized,has succeeded in reducing the incidence of colon and rectal cancer and improving the prognosis related to *** considerable advancements in screening technologies and strategies,the effectiveness of CRC screening programs remains less than *** paper examined the multifaceted reasons behind the persistent lack of effect-iveness in CRC screening *** a critical analysis of current methodologies,technological limitations,patient-related factors,and systemic challenges,we elucidated the complex interplay that hampers the successful reduction of CRC morbidity and mortality *** acknowledging the ad-vancements that have improved aspects of screening,we emphasized the necessity of addressing the identified barriers *** study aimed to raise awareness of how important CRC screening is in reducing costs for this *** and early diagnosis are not only important in improving the prognosis of patients with CRC but can lead to an important reduction in the cost of treating a disease that is often diagnosed at an advanced *** more sooner can mean saving money later.

关键词： Colorectal cancer Colorectal cancer screening Colorectal screening test Colon and rectal cancer

Tracking the change in Spanish greenhouse gas emissions through an LMDI decomposition model:A global and sectoral approach

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2024年第5期139卷 114-122页

作者： Paula Fernández González María José Presno manuel Landajo Department of Applied Economics University of OviedoAuda del Cristos/n 33011 OviedoSpain

The reduction of GHG emissions to reverse the greenhouse effect is one of the main challenges in this *** this paper we pursue two ***,we analyze the evolution of GHG emissions in Spain in 2008–2018,at both the global and sectoral levels,with the variation in emissions decomposed into a set of determining ***,we propose several actions specifically oriented to more tightly controlling the level of *** results showed a remarkable reduction(18.44%)in GHG emissions,mainly due to the intensity effect,but also to the production-per-capita *** detected somewhat different patterns among the various sectors *** the intensity effect was the most influential one in the agricultural,transport,and others sectors,the production-per-capita effect was predominant in the case of *** carbonization effect was revealed as crucial in the commerce *** above findings highlight the importance of the energy efficiency measures taken in recent years in the Spanish economy,also pointing to the need to deepen those strategies and to propose new measures that entail greater efficiency in *** efforts in areas like innovation,R&D,diffusion of more eco-friendly technologies,and a greater use of greener energies all prove to be essential reduction actions to fight the greenhouse effect.

关键词： LMDI Decomposition Spain GHG emissions

Scanning transmission electron microscopy and atom probe tomography analysis of non-stoichiometry long-period-stacking-ordered structures in Mg-Ni-Y/Sm alloys

在线全文

学校读者我要写书评

暂无评论

Journal of Magnesium and Alloys 2024年第3期12卷 954-965页

作者： Yimeng Chen manuel Legrée Jean-Louis Bobet Alexander Kvit CAMECA Instruments Inc MadisonWI 53711USA ICMCB Universitéde BordeauxPessacCEDEX 33608France NIAC&Materials Science Department University of WisconsinMadisonWI 53706USA

The long-period-stacking-ordered(LPSO)structure affects the mechanical,corrosion and hydrolysis properties of Mg *** current work employs high angle annular dark field-scanning transmission electron microscopy(HAADF-STEM)and atom probe tomography(APT)to investigate the structural and local chemical information of LPSO phases formed in Mg-Ni-Y/Sm ternary alloys after extended isothermal *** on the alloying elements and their concentrations,Mg-Ni-Y/Sm develops a two-phase LPSO+α-Mg structure in which the LPSO phase contains defects,hybrid LPSO structure,and Mg ***-STEM and APT indicate non-stoichiometric LPSO with incomplete Ni_(6)(Y/Sm)_(8) *** addition,the APT quantitatively determines the local composition of LPSO and confirms the presence of Ni within the Mg bonding *** results provide insight into a better understanding of the structure and hydrolysis properties of LPSO-Mg alloys.

关键词： Magnesium alloys Long-range ordering Atom probe tomography(APT) STEM HAADF Hydrolysis properties.

Improved organs at risk segmentation based on modified U‐Net with self‐attention and consistency regularisation

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第4期9卷 850-865页

作者： Maksym Manko Anton Popov Juan manuel Gorriz Javier Ramirez Electronic Engineering Department Igor Sikorsky Kyiv Polytechnic InstituteKyivUkraine Department of Signal Theory Telematics and CommunicationsUniversity of GranadaGranadaSpain

Cancer is one of the leading causes of death in the world,with radiotherapy as one of the treatment *** planning starts with delineating the affected area from healthy organs,called organs at risk(OAR).A new approach to automatic OAR seg-mentation in the chest cavity in Computed Tomography(CT)images is *** proposed approach is based on the modified U‐Net architecture with the ResNet‐34 encoder,which is the baseline adopted in this *** new two‐branch CS‐SA U‐Net architecture is proposed,which consists of two parallel U‐Net models in which self‐attention blocks with cosine similarity as query‐key similarity function(CS‐SA)blocks are inserted between the encoder and decoder,which enabled the use of con-sistency *** proposed solution demonstrates state‐of‐the‐art performance for the problem of OAR segmentation in CT images on the publicly available SegTHOR benchmark dataset in terms of a Dice coefficient(oesophagus-0.8714,heart-0.9516,trachea-0.9286,aorta-0.9510)and Hausdorff distance(oesophagus-0.2541,heart-0.1514,trachea-0.1722,aorta-0.1114)and significantly outperforms the *** current approach is demonstrated to be viable for improving the quality of OAR segmentation for radiotherapy planning.

关键词： 3‐D computer vision deep learning deep neural networks image segmentation medical image processing object segmentation

Rehabilitation of Semi-Arid Grasslands through the Perennialization of Lots by Implementing Perennial Forage Exotic Grass

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Phyton-International Journal of Experimental Botany 2024年第8期93卷 2115-2125页

作者： Delfina Arancio Sidoti Juan manuel Zeberio Guadalupe Peter Universidad Nacional de Río Negro Sede AtlánticaCEANPaViedma8500Argentina Consejo Nacional de Investigaciones Científicas y Técnicas CONICETCABABuenos Aires1425Argentina Chacra Experimental Patagones Ministerio de Desarrollo Agrario de la Provincia de Buenos AiresCarmen de Patagones8504Argentina

Argentina is the country with the highest proportion of arid and semi-arid ecosystems in Latin *** the rangelands of Southwestern Buenos Aires(Patagones Department),there is a clear advancement of the agricultural frontier to the detriment of the native forest in this *** to rainfall variation and seed acquisition,Thinopyrum ponticum is cultivated as a forage perennial crop in this *** objective was to evaluate the performance of *** as a facilitating crop for the medium-term rehabilitation of natural grasslands in semi-arid *** working hypotheses were that:1)native perennial grass cover increases over the years and 2)diversity and specific richness of the vegetation are enhanced by the duration of Tall Wheatgrass *** were collected from commercial plots where *** was shown:recent implantation(5–8 years,RI);medium implantation(13–15 years,MI);and old implantation(20–22 years,OI).Thirty-four species were identified and classified into seven functional groups:Annual grasses,annual herbs,perennial herbs,exotic perennial herbs,perennial forage grasses,exotic perennial forage grasses,perennial forage exotic grasses,and nonforage perennial *** ponticum’s total cover was between RI and *** cover,species richness,and Shannon-Weaver diversity index showed no differences among *** forage grasses exhibited higher cover values in sites with greater implantation age and annual grasses showed the opposite *** results indicated that *** does not invade the sampled plots and enhances the colonization of the planted plots by perennial forage native ***,even though the herbaceous cover had been recovered,the woody layer which could provide environmental services and specific values for conservation was not.

关键词： Wheatgrass clearing vegetation monte Thinopyrum ponticum

Guest Editorial:Knowledge‐based deep learning system in bio‐medicine

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第4期9卷 787-789页

作者： Yu‐Dong Zhang Juan manuel Górriz University of Leicester LeicesterUK University of Granada GranadaSpain

Numerous healthcare procedures can be viewed as medical sector *** the modern era,computers have become indispensable in the realm of medical decision‐***-ever,the common view of computers in the medical field typically extends only to applications that support doctors in diagnosing *** more tightly intertwine computers with the biomedical sciences,professionals are now more frequently utilising knowledge‐driven deep learning systems(KDLS)and their foundational technologies,especially in the domain of neuroimaging(NI).

关键词： learning computer doctor

Audio Enhancement for Computer Audition—An Iterative Training Paradigm Using Sample Importance

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2024年第4期39卷 895-911页

作者： manuel Milling Shuo Liu Andreas Triantafyllopoulos Ilhan Aslan Björn W.Schuller Chair of Embedded Intelligence for Health Care and Wellbeing University of AugsburgAugsburg 86159Germany Chair of Health Informatics München rechts der IsarTechnical University of MunichMunich 81675Germany Munich Center for Machine Learning Munich 80333Germany Huawei Technologies MunichMunich 80992Germany Munich Data Science Institute Garching 85748Germany Group on Language Audio and MusicImperial College LondonLondon SW72AZU.K.

Neural network models for audio tasks,such as automatic speech recognition(ASR)and acoustic scene classification(ASC),are susceptible to noise contamination for real-life *** improve audio quality,an enhancement module,which can be developed independently,is explicitly used at the front-end of the target audio *** this paper,we present an end-to-end learning solution to jointly optimise the models for audio enhancement(AE)and the subsequent *** guide the optimisation of the AE module towards a target application,and especially to overcome difficult samples,we make use of the sample-wise performance measure as an indication of sample *** experiments,we consider four representative applications to evaluate our training paradigm,i.e.,ASR,speech command recognition(SCR),speech emotion recognition(SER),and *** applications are associated with speech and nonspeech tasks concerning semantic and non-semantic features,transient and global information,and the experimental results indicate that our proposed approach can considerably boost the noise robustness of the models,especially at low signal-to-noise ratios,for a wide range of computer audition tasks in everyday-life noisy environments.

关键词： audio enhancement computer audition joint optimisation multi-task learning voice suppression

GAN‐MD:A myocarditis detection using multi‐channel convolutional neural networks and generative adversarial network‐based data augmentation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第4期9卷 866-878页

作者： Hengame Ahmadi Golilarz Alireza Azadbar Roohallah Alizadehsani Juan manuel Gorriz Department of Medical Radiation Engineering Faculty of EngineeringLahijan BranchIslamic Azad UniversityLahijanIran Department of Medical Radiation Engineering Lahijan BranchIslamic Azad UniversityLahijanIran Institute for Intelligent Systems Research and Innovation(IISRI) Deakin UniversityWaurn PondsVictoriaAustralia Data Science and Computational Intelligence Institute University of GranadaGranadaSpain

Myocarditis is a significant public health concern because of its potential to cause heart failure and sudden *** standard invasive diagnostic method,endomyocardial bi-opsy,is typically reserved for cases with severe complications,limiting its widespread ***,non‐invasive cardiac magnetic resonance(CMR)imaging presents a promising alternative for detecting and monitoring myocarditis,because of its high signal contrast that reveals myocardial *** assist medical professionals via artificial intelligence,the authors introduce generative adversarial networks‐multi discriminator(GAN‐MD),a deep learning model that uses binary classification to diagnose myocarditis from CMR *** approach employs a series of convolutional neural networks(CNNs)that extract and combine feature vectors for accurate *** authors suggest a novel technique for improving the classification precision of *** generative adversarial networks(GANs)to create synthetic images for data augmentation,the authors address challenges such as mode collapse and unstable *** a reconstruction loss into the GAN loss function requires the generator to produce images reflecting the discriminator features,thus enhancing the generated images'quality to more accurately replicate authentic data ***,combining this loss function with other reg-ularisation methods,such as gradient penalty,has proven to further improve the perfor-mance of diverse GAN models.A significant challenge in myocarditis diagnosis is the imbalance of classification,where one class dominates over the *** mitigate this,the authors introduce a focal loss‐based training method that effectively trains the model on the minority class *** GAN‐MD approach,evaluated on the Z‐Alizadeh Sani myocarditis dataset,achieves superior results(F‐measure 86.2%;geometric mean 91.0%)compared with other deep learning models and traditional machine learning methods.

关键词： 2‐D 3‐D