检索结果-内蒙古大学图书馆

Multi-future Transformer: Learning diverse interaction modes for behaviour prediction in autonomous driving

IET INTELLIGENT TRANSPORT SYSTEMS 2022年第9期16卷 1249-1267页

作者： He, Baotian Li, Yibing Tsinghua Univ Sch Vehicle & Mobil Beijing Peoples R China Tsinghua Univ State Key Lab Automobile Safety & Energy Beijing Peoples R China

Predicting the future behaviour of neighbouring agents is crucial for autonomous driving. This task is challenging, largely because of the diverse unobservable intent of each agent which is further complicated by the complex interaction possibilities between them. The authors propose a multi-future Transformer framework that implicitly models the multi-modal joint distribution by capturing the diverse interaction modes of the scene. To this end, a parallel interaction module is constructed, whereby each interaction block learns the joint agent-agent and agent-map interactions for possible future evolution. The model can perform likelihood estimation from the perspective of both the joint distribution of the scene and marginal distribution of each agent. Combined with the proposed scene-level winner-take-all loss strategy complementary to the model architecture, the best performance is achieved for both target agent prediction and scene prediction tasks in a single model. To better utilise the scene context, comprehensive control experiments were conducted highlighting the importance of fine-grained scene representation with content-adaptive aggregation and late fusion of semantic attributes. The method, evaluated on the popular Argoverse forecasting dataset, outperformed previous methods while maintaining low model complexity.

关键词： model complexity target agent prediction multi-agent systems possible future evolution multimodal joint distribution agent-map interactions parallel interaction module learning (artificial intelligence) scene context interaction block fine-grained scene representation behaviour prediction multifuture transformer framework marginal distribution scene-level winner-take-all loss strategy joint agent-agent semantic attributes autonomous driving Argoverse forecasting dataset traffic engineering computing

来源：评论

学校读者我要写书评

暂无评论

Calibration of computationally demanding and structurally uncertain models with an application to a lake water quality model

引用

ENVIRONMENTAL modelLING & SOFTWARE 2012年 38卷 129-146页

作者： Dietzel, Anne Reichert, Peter Eawag Swiss Fed Inst Aquat Sci & Technol CH-8600 Dubendorf Switzerland Swiss Fed Inst Technol Inst Biogeochem & Pollutant Dynam CH-8092 Zurich Switzerland

models of environmental systems are simplified representations of the reality. For this reason, their results are affected by systematic errors. This bias makes it difficult to get reliable uncertainty estimates of model parameters and predictions. A relatively simple way of considering this bias when using deterministic models is to add a statistical representation of the bias to the model output in addition to observation error and to jointly estimate model parameters, bias and observation error. When assuming Normal distributions for bias and observation error, this leads to a relatively simple likelihood function that can easily be evaluated. Nevertheless, the sampling from the posterior distribution still requires long Markov chains to be calculated which can be prohibitive for computationally demanding models. In order to extend the range of applicability of this technique to computationally demanding models, we suggest to replace Markov chain sampling by a Normal approximation to the posterior of the parameters and to estimate prediction uncertainty by linearized error propagation. We tested this procedure for a didactical example and for an application of the biogeochemical-ecological lake model BELAMO to long-term data from Lake Zurich. This is a good test application because the strong coupling of output variables makes it difficult to avoid bias in the results of this model. These tests demonstrate the applicability of the suggested procedure, the approximate reproduction of the results of the full procedure for the didactical example, and meaningful results for the lake model. For the latter, the results demonstrate that the assumption of a realistic likelihood function leads to the conclusion that prediction uncertainty may be high. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Bias Lake water quality model Structurally uncertain model model complexity Multi-objective calibration

来源：评论

学校读者我要写书评

暂无评论

The potential of winter stormflow coefficients for hydrological regionalization purposes in poorly gauged basins of the middle Rhine region

引用

HYDROLOGICAL SCIENCES JOURNAL-JOURNAL DES SCIENCES HYDROLOGIQUES 2008年第4期53卷 773-788页

作者： Hellebrand, Hugo van den Bos, Rudi Hoffmann, Lucien Juilleret, Jerome Pfister, Laurent Publ Res Ctr Gabriel Lippmann Dept Environm & Agrobiotechnol EVA L-4422 Belvaux Grand Duchy Luxembourg Delft Univ Technol Sect Hydrol Dept Water Management NL-2628 CN Delft Netherlands

Three different statistical models were used to regionalize the winter stormflow coefficient for mesoscale basins of the Grand Duchy of Luxembourg and the neighbouring Rhineland Palatinate (Germany). The methodology is derived from a previous study, in which winter stormflow coefficient;were regionalized for the Grand Duchy of Luxembourg only. The models are based oil regression analysis and it is shown that model performances do not differ considerably between parsimoniously and heavily parameterized models. Next, a regionalization procedure based on a raster grid was performed, producing a qualitative grid-based analysis of runoff-producing areas for the mesoscale. The winter runoff coefficient turned out to be highly correlated with the permeability of the lithology, yet not with basin area. The grid appeared to be useful in merging basin characteristics, which Were used in a statistical model to describe the winter stormflow coefficients.

关键词： regionalization regression model complexity raster grid runoff coefficient substratum permeability

来源：评论

学校读者我要写书评

暂无评论

Effects of modelling detail on simulated potential crop yields under a wide range of climatic conditions

引用

ECOLOGICAL modelLING 2011年第1期222卷 131-143页

作者： Adam, M. Van Bussel, L. G. J. Leffelaar, P. A. Van Keulen, H. Ewert, F. Wageningen Univ Plant Prod Syst Grp NL-6700 AK Wageningen Netherlands CIRAD INRA SupAgro Ctr Cooperat Int Rech Agron Dev CIRAD UMR Syst F-34060 Montpellier 1 France Univ Wageningen & Res Ctr NL-6700 AP Wageningen Netherlands Netherlands Environm Assessment Agcy PBL NL-3720 AH Bilthoven Netherlands Univ Bonn Inst Crop Sci & Resource Conservat INRES Crop Sci Grp D-53115 Bonn Germany

Crop simulation models are widely applied at large scale for climate change impact assessment or integrated assessment studies. However, often a mismatch exists between data availability and the level of detail in the model used. Good modelling practice dictates to keep models as simple as possible, but enough detail should be incorporated to capture the major processes that determine the system's behaviour. The objective of this study was to investigate the effect of the level of detail incorporated in process-based crop growth models on simulated potential yields under a wide range of climatic conditions. We conducted a multi-site analysis and identified that by using a constant radiation use efficiency (RUE) value under a wide range of climatic conditions, the description of the process of biomass production may be over-simplified, as the effects of high temperatures and high radiation intensities on this parameter are ignored. Further, we found that particular attention should be given to the choice of the light interception approach in a crop model as determined by leaf area index (LA!) dynamics. The two LAI dynamics approaches considered in this study gave different simulated yields irrespective of the characteristics of the location and the light interception approaches better explained the differences in yield sensitivity to climatic variability than the biomass production approaches. Further analysis showed that differences between the two IAI dynamics approaches for simulated yields were mainly due to different representations of leaf senescence in both approaches. We concluded that a better understanding and modelling of leaf senescence, particularly its onset, is needed to reduce model uncertainty in yield simulations. (C) 2010 Elsevier B.V. All rights reserved.

关键词： Crop growth model Climatic variability Light interception Radiation use efficiency Leaf area index model complexity Leaf senescence

来源：评论

学校读者我要写书评

暂无评论

Using an individual-based model to select among alternative foraging strategies of woodpigeons: Data support a memory-based model with a flocking mechanism

引用

ECOLOGICAL modelLING 2014年 280卷 89-101页

作者： Kulakowska, K. A. Kulakowski, T. M. Inglis, I. R. Smith, G. C. Haynes, P. J. Prosser, P. Thorbek, P. Sibly, R. M. Univ Reading Sch Biol Sci Reading RG6 6A5 Berks England Food & Environm Res Agcy York N Yorkshire England Syngenta Jealotts Hill Int Res Ctr Environm Safety Bracknell Berks England Natl Wildlife Management Ctr AHVLA York N Yorkshire England

Population modelling is increasingly recognised as a useful tool for pesticide risk assessment. For vertebrates that may ingest pesticides with their food, such as woodpigeon (Columba palumbus), population models that simulate foraging behaviour explicitly can help predicting both exposure and population-level impact. Optimal foraging theory is often assumed to explain the individual-level decisions driving distributions of individuals in the field, but it may not adequately predict spatial and temporal characteristics of woodpigeon foraging because of the woodpigeons' excellent memory, ability to fly long distances, and distinctive flocking behaviour. Here we present an individual-based model (IBM) of the woodpigeon. We used the model to predict distributions of foraging woodpigeons that use one of six alternative foraging strategies: optimal foraging, memory-based foraging and random foraging, each with or without flocking mechanisms. We used pattern-oriented modelling to determine which of the foraging strategies is best able to reproduce observed data patterns. Data used for model evaluation were gathered during a long-term woodpigeon study conducted between 1961 and 2004 and a radiotracking study conducted in 2003 and 2004, both in the UK, and are summarised here as three complex patterns: the distributions of foraging birds between vegetation types during the year, the number of fields visited daily by individuals, and the proportion of fields revisited by them on subsequent days. The model with a memory-based foraging strategy and a flocking mechanism was the only one to reproduce these three data patterns, and the optimal foraging model produced poor matches to all of them. The random foraging strategy reproduced two of the three patterns but was not able to guarantee population persistence. We conclude that with the memory-based foraging strategy including a flocking mechanism our model is realistic enough to estimate the potential exposure of woodpigeons t

关键词： Pesticide risk assessment Spatial distribution Optimal foraging theory model complexity Structural sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

2D curtailed harmonic memory polynomial for reduced complexity in concurrent dual-band modelling and digital predistortion with the second band at harmonic frequency

引用

IET COMMUNICATIONS 2018年第12期12卷 1438-1447页

作者： Jaraut, Praveen Rawat, Meenakshi Ghannouchi, Fadhel M. Indian Inst Technol Dept Elect & Commun Engn Roorkee 247667 Uttar Pradesh India Univ Calgary Schulich Sch Engn Dept Elect & Comp Engn Intelligent RF Radio Lab Calgary AB T2N 1N4 Canada

Multi-band transmitter systems are evolving to support the smooth transition from 4G to 5G communication systems. Moreover, recent developments of multi-band and ultra-wideband power amplifiers have led to a possible scenario where the second carrier signal is transmitted at the harmonic frequency of the first carrier signal. This results in harmonic interference from the first carrier signal as well as additional cross-modulation and intermodulation distortion (IMD) components, which cannot be filtered out. The computational and memory requirements for digital predistortion (DPD) in such scenario increase drastically to include all interference terms. This study presents a novel two-dimensional curtailed harmonic memory polynomial (2D-CHMP) model to capture harmonic interferences, cross-modulation and IMDs. The model complexity and memory requirement of 2D-CHMP are very less as compared to the state-of-the-art two-dimensional harmonic memory polynomial (2D-HMP) model. For proof-of-concept, it is shown with two different measurement setups that the proposed 2D-CHMP DPD provides similar linearisation performances as compared to the 2D-HMP DPD with less number of coefficients and computational complexity. As a study, it is shown that the proposed model can be further adapted to a low-precision (low-bit) environment by utilising principal component analysis.

关键词： computational complexity radio transmitters 5G mobile communication 4G mobile communication power amplifiers radiofrequency interference intermodulation distortion polynomials linearisation techniques signal processing 2D curtailed harmonic memory polynomial reduced complexity concurrent dual-band modelling digital predistortion harmonic frequency multiband transmitter systems 5G communication systems 4G communication systems ultra-wideband power amplifiers multiband power amplifiers second carrier signal harmonic interference intermodulation distortion components IMD components cross-modulation interference terms two-dimensional curtailed harmonic memory polynomial model harmonic interferences model complexity 2D-CHMP DPD model computational complexity linearisation performances principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Computing AIC for black-box models using generalized degrees of freedom: A comparison with cross-validation

引用

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION 2018年第5期47卷 1382-1396页

作者： Hauenstein, Severin Wood, Simon N. Dormann, Carsten F. Univ Freiburg Dept Biometry & Environm Syst Anal Tennenbacherstr 4 D-79106 Freiburg Germany Univ Bristol Sch Math Bristol Avon England

Generalized degrees of freedom (GDF), as defined by Ye (1998 JASA 93:120-131), represent the sensitivity of model fits to perturbations of the data. Such GDF can be computed for any statistical model, making it possible, in principle, to derive the effective number of parameters in machine-learning approaches and thus compute information-theoretical measures of fit. We compare GDF with cross-validation and find that the latter provides a less computer-intensive and more robust alternative. For Bernoulli-distributed data, GDF estimates were unstable and inconsistently sensitive to the number of data points perturbed simultaneously. Cross-validation, in contrast, performs well also for binary data, and for very different machine-learning approaches.

关键词： Boosted regression trees Data perturbation model complexity Random forest

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Activity Recognition: A System Level Perspective

引用

IEEE ACCESS 2023年 11卷 64442-64457页

作者： Kalabakov, Stefan Jovanovski, Borche Denkovski, Daniel Rakovic, Valentin Pfitzner, Bjarne Konak, Orhan Arnrich, Bert Gjoreski, Hristijan Ss Cyril & Methodius Univ Skopje Fac Elect Engn & Informat Technol Skopje North Macedonia Univ Potsdam Hasso Plattner Inst Digital Hlth Connected Healthcare Grp Potsdam Germany Jozef Stefan Int Postgrad Sch Ljubljana 1000 Slovenia

The past decade has seen substantial growth in the prevalence and capabilities of wearable devices. For instance, recent human activity recognition (HAR) research has explored using wearable devices in applications such as remote monitoring of patients, detection of gait abnormalities, and cognitive disease identification. However, data collection poses a major challenge in developing HAR systems, especially because of the need to store data at a central location. This raises privacy concerns and makes continuous data collection difficult and expensive due to the high cost of transferring data from a user's wearable device to a central repository. Considering this, we explore the adoption of federated learning (FL) as a potential solution to address the privacy and cost issues associated with data collection in HAR. More specifically, we investigate the performance and behavioral differences between FL and deep learning (DL) HAR models, under various conditions relevant to real-world deployments. Namely, we explore the differences between the two types of models when (i) using data from different sensor placements, (ii) having access to users with data from heterogeneous sensor placements, (iii) considering bandwidth efficiency, and (iv) dealing with data with incorrect labels. Our results show that FL models suffer from a consistent performance deficit in comparison to their DL counterparts, but achieve these results with much better bandwidth efficiency. Furthermore, we observe that FL models exhibit very similar responses to those of DL models when exposed to data from heterogeneous sensor placements. Finally, we show that the FL models are more robust to data with incorrect labels than their centralized DL counterparts.

关键词： INDEX TERMS Human activity recognition federated learning deep learning system-level aspects different and heterogeneous sensor placements FL optimizers fraction fit bandwidth efficiency data errors feature selection model complexity

来源：评论

学校读者我要写书评

暂无评论

Data assimilation of physical and chlorophyll a observations in the California Current System using two biogeochemical models

引用

OCEAN modelLING 2017年 109卷 55-71页

作者： Mattern, Jann Paul Song, Hajoon Edwards, Christopher A. Moore, Andrew M. Fiechter, Jerome Univ Calif Santa Cruz Dept Ocean Sci Santa Cruz CA 95064 USA MIT Dept Earth Atmospher & Planetary Sci Cambridge MA 02139 USA

Biogeochemical numerical models coupled to physical ocean circulation models are commonly combined with data assimilation in order to improve the models' state or parameter estimates. Yet much still needs to be learned about important aspects of biogeochemical data assimilation, such as the effect of model complexity and the importance of more realistic model formulations on assimilation results. In this study, 4D-Var-based state estimation is applied to two biogeochemical ocean models: a simple NPZD model with 4 biogeochemical variables (including 1 phytoplankton, 1 zooplankton) and the more complex NEMURO model, containing 11 biogeochemical variables (including 2 phytoplankton, 3 zooplankton). Both models are coupled to a 3-dimensional physical ocean circulation model of the U.S. west coast based on the Regional Ocean modelling System (ROMS). Chlorophyll satellite observations and physical observations are assimilated into the model, yielding substantial improvements in state estimates for the observed physical and biogeochemical variables in both model formulations. In comparison to the simpler NPZD model, NEMURO shows a better overall fit to the observations. The assimilation also results in small improvements for simulated nitrate concentrations in both models and no apparent degradation of the output for other unobserved variables. The forecasting skill of the biogeochemical models is strongly linked to model performance without data assimilation: for both models, the improved fit obtained through assimilation degrades at similar relative rates, but drops to different absolute levels. Despite the better performance of NEMURO in our experiments, the choice of model and desired level of complexity should depend on the model application and the data available for assimilation. (C) 2016 Published by Elsevier Ltd.

关键词： Data assimilation model complexity Biogeochemical ocean model State estimation 4D-Var NEMURO

来源：评论

学校读者我要写书评

暂无评论

A general framework for Dynamic Emulation modelling in environmental problems

引用

ENVIRONMENTAL modelLING & SOFTWARE 2012年 34卷 5-18页

作者： Castelletti, A. Galelli, S. Ratto, M. Soncini-Sessa, R. Young, P. C. Politecn Milan Dept Elect & Informat I-20133 Milan Italy Commiss European Communities Joint Res Ctr I-21020 Ispra Italy Univ Lancaster Dept Environm Sci Lancaster England Australian Natl Univ Fenner Sch Environm & Soc Canberra ACT Australia Univ New S Wales Sch Elect Engn & Telecommun Sydney NSW 2052 Australia

Emulation modelling is an effective way of overcoming the large computational burden associated with the process-based models traditionally adopted by the environmental modelling community. An emulator is a low-order, computationally efficient model identified from the original large model and then used to replace it for computationally intensive applications. As the number and forms of the problem that benefit from the identification and subsequent use of an emulator is very large, emulation modelling has emerged in different sectors of science, engineering and social science. For this reason, a variety of different strategies and techniques have been proposed in the last few years. The main aim of the paper is to provide an introduction to emulation modelling, together with a unified strategy for its application, so that modellers from different disciplines can better appreciate how it may be applied in their area of expertise. Particular emphasis is devoted to Dynamic Emulation modelling (DEMo), a methodological approach that preserves the dynamic nature of the original process-based model, with consequent advantages in a wide variety of problem areas. The different techniques and approaches to DEMo are considered in two macro categories: structure-based methods, where the mathematical structure of the original model is manipulated to a simpler, more computationally efficient form;and data-based approaches, where the emulator is identified and estimated from a data-set generated from planned experiments conducted on the large simulation model. The main contribution of the paper is a unified, six-step procedure that can be applied to most kinds of dynamic emulation problem. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Dynamic emulation modelling model reduction model complexity Process-based models Response surfaces Metamodelling

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：