检索结果-内蒙古大学图书馆

Deep coastal sea elements forecasting using UNet-based models

knowledge-Based Systems 2022年 252卷

作者： Fernández, Jesús García Abdellaoui, Ismail Alaoui Mehrkanoon, Siamak Information and Computing Sciences Utrecht University Utrecht Netherlands Department of Data Science and Knowledge Engineering Maastricht University Netherlands

Due to the recent development of deep learning techniques applied to satellite imagery, weather forecasting that uses remote sensing data has also been the subject of major progress. The present paper investigates multiple hours ahead coastal sea elements forecasting in the Netherlands using UNet based architectures. The hourly satellite image data from the Copernicus observation program spanned over a period of two years has been used to train the models and make the forecasting, including seasonal forecasting. Here, we propose 3D dimension Reducer UNet (3DDR-UNet), a variation of the UNet architecture, and further extend this novel model using residual connections, parallel convolutions and asymmetric convolutions which result in introducing three additional architectures, i.e. Res-3DDR-UNet, InceptionRes-3DDR-UNet and AsymmInceptionRes-3DDR-UNet respectively. In particular, we show that the architecture equipped with parallel and asymmetric convolutions as well as skip connections outperforms the other three discussed models. © 2022 The Author(s)

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

OntoMove: A knowledge Based Framework for Semantic Requirement Profiling and Resource Acquisition

OntoMove: A Knowledge Based Framework for Semantic Requireme...

引用

Australian Conference on Software engineering

作者： Mehul Bhatt Wenny Rahayu Sury Prakash Soni Carlo Wouters Data Engineering and Knowledge Management Group Department of Computer Science La Trobe University Australia

The use of formal knowledge representation structures, or ontologies, has found immense applicability for the interoperability of software systems, e.g., alignment of software and business process models. Toward the management of such knowledge structures, an important foundational problem is that of ontology reuse - it is uncommon for new applications or for different components within one application to use an already available ontology in its entirety. Depending on component specific requirements, typical re-usages are restricted to refined versions of an existing ontology, with the refinement taking the form of a contraction of the knowledge contained therein. Furthermore, when the ontology is used to ascribe meaning to independently existing 'resources' (e.g., documents collections, source code, software manuals, process template repositories) by way of meta-data, there exists a direct mapping between different views/re-uses of an ontology and their respective semantic scopes within an annotated resource repository thereby leading to the concept of view/reuse dependent resource retrieval. We implement a framework that supports ontology reuse by way of a requirement driven sub-ontology extraction methodology. Additionally, based on this concept of a sub-ontology, we implement the idea of a user/component 'requirement profile' consisting of semantic descriptions of the user's interest within a 'resource repository' that has been annotated with semantic types from the ontology under consideration. A generic framework that implements these ideas and its application in the domains of medical information retrieval systems and business process management systems (BPMS) is presented.

关键词： Ontologies Application software Information retrieval Software engineering knowledge management knowledge representation data mining Resource management Software systems Semantic Web

来源：评论

学校读者我要写书评

暂无评论

Autoregressive convolutional recurrent neural network for univariate and multivariate time series prediction

arXiv

引用

arXiv 2019年

作者： Maggiolo, Matteo Spanakis, Gerasimos Department of Data Science and Knowledge Engineering Maastricht University Maastricht6200MD Netherlands

Time Series forecasting (univariate and multivariate) is a problem of high complexity due the different patterns that have to be detected in the input, ranging from high to low frequencies ones. In this paper we propose a new model for timeseries prediction that utilizes convolutional layers for feature extraction, a recurrent encoder and a linear autoregressive component. We motivate the model and we test and compare it against a baseline of widely used existing architectures for univariate and multivariate timeseries. The proposed model appears to outperform the baselines in almost every case of the multivariate timeseries datasets, in some cases even with 50% improvement which shows the strengths of such a hybrid architecture in complex timeseries. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Framework for the Decentralisation and Management of Collaborative Applications in Ubiquitous Computing Environments

A Framework for the Decentralisation and Management of Colla...

引用

IEEE Symposium on Network Operations and Management

作者： K. Quinn A. Kenny K. Feeney D. Lewis D. O'Sullivan V.P. Wade Knowledge & Data Engineering Group Department of Computer Science Trinity College Dublin Dublin Ireland

When deploying collaborative applications such as instant messaging in ubiquitous computing environments significant enhancements can be afforded by offering additional context information, such as location information. However, such environments exert key challenges such as increased diversity of ownership and ad hoc, intermittent network connectivity that suits more decentralized computing architectures. This paper examines how a migration to a more decentralized collaborative architecture can be achieved together with a decentralization of the management of collaborative activities

关键词： Environmental management Collaboration Ubiquitous computing Access control Application software Computer architecture Routing Humans Content management Peer to peer computing

来源：评论

学校读者我要写书评

暂无评论

A multi-agent framework for a P2P data sharing facility

A multi-agent framework for a P2P data sharing facility

引用

International Conference on Advanced Information Networking and Applications (AINA)

作者： S.M. Deen Department of Computer Science Data and Knowledge Engineering (DAKE) Group University of Keele Staffordshire UK

The paper presents a general architecture for a P2P data sharing facility within a multi-agent framework, where peers as autonomous high-level nodal agents cooperate with each other to solve global tasks. A node may have several lower level local agents including local databases and partial global ontologies. In addition there are also minder agents coordinating the activities of the peers that offer the same type of service, thus providing fault-tolerance. The ability of this architecture in data and task sharing has been demonstrated by considering query processing and directory update strategies.

关键词： Peer to peer computing Fault tolerance Query processing Spread spectrum communication Transaction databases knowledge engineering Computer science Computer architecture Ontologies Internet

来源：评论

学校读者我要写书评

暂无评论

Wall Building in the Game of StarCraft with Terrain Considerations

Wall Building in the Game of StarCraft with Terrain Consider...

引用

IEEE Symposium on Computational Intelligence and Games, CIG

作者： Martin L. M. Rooijackers Mark H. M. Winands Games & AI Group Department of Data Science and Knowledge Engineering Maastricht University Maastricht The Netherlands

ISBN: (纸本)9781538643600

StarCraft is a Real-Time Strategy game, which has a large state-space, is played in real-time, and commonly features two opposing players, capable of acting simultaneously. One of the aspects of the game is building walls. In this paper, we present an algorithm that can be used for wall building for an agent playing the game of StarCraft: Brood War.

关键词： Inductors Games Tiles Real-time systems Estimation Programming

来源：评论

学校读者我要写书评

暂无评论

Power conservation for strongly connected topology control in wireless sensor network

Power conservation for strongly connected topology control i...

引用

1st ACM International Workshop on Foundations of Wireless Ad Hoc and Sensor Networking and Computing 2008, FOWANC'08

作者： Li, Deying Du, Hongwei Chen, Wenping School of Information Renmin University of China Key Laboratory of Data Engineering and Knowledge Engineering Beijing 100872 China Department of Computer Science City University of Hong Kong Kowloon Hong Kong School of Information Renmin University of China Beijing 100872 China

ISBN: (纸本)9781605581491

Topology control is one of the most elementary topics in wireless sensor networks. Typically, most of the research only considered the bidirectional communication and symmetric weighted communication model, while the real wireless world contains not only bidirectional but also unidirectional communication links and asymmetric weighted communication model. In this paper, we present two heuristics for the minimum power topology control problem on general model, i.e., given a set of sensors in the Euclidean plane and a transmission power threshold for each directed pair of sensors, to find a power assignment for each sensor to achieve a strong connectivity with minimum total transmission power. Extensive results in simulation evaluate the efficiency of the proposed algorithms. Copyright 2008 ACM.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Efficient approximation of the maximal preference scores by lightweight cubic views

Efficient approximation of the maximal preference scores by ...

引用

15th International Conference on Extending database Technology, EDBT 2012

作者： Chen, Yueguo Cui, Bin Du, Xiaoyong Tung, Anthony K. H. Key Laboratory of Data Engineering and Knowledge Engineering Renmin University of China MOE China Department of Computer Science Peking University Beijing China School of Information Renmin University of China Beijing China School of Computing National University of Singapore Singapore Singapore

ISBN: (纸本)9781450307901

Given a multi-features data set, a best preference query (BPQ) computes the maximal preference score (MPS) that the tuples in the data set can achieve with respect to a preference function. BPQs are very useful in applications where users want to efficiently check whether many individual data sets contain tuples that are of interest to them. Although a BPQ can be naïvely answered by issuing a top-1 query and computing the score from the returned tuple, doing so might require to load a larger number of tuples externally. In this paper, we address the problem of efficient processing BPQs by using lightweight cubic (3-dimensional) views. With these in-memory views, the MPSs of BPQs can be efficiently estimated with an error bound guaranteed, by paying only a small number of I/Os. Extensive experimental results over real-life data sets show that our approximate solution can achieve the efficiency of up to three orders of magnitude compared to exact solutions, with certain accuracy guaranteed. © 2012 ACM.

关键词： best preference score materialized views preference query top-k query

来源：评论

学校读者我要写书评

暂无评论

BIOLOGICALLY INSPIRED SEMANTIC LATERAL CONNECTIVITY for CONVOLUTIONAL NEURAL NETWORKS

arXiv

引用

arXiv 2021年

作者： Weidler, Tonio Lehnen, Julian Denman, Quinton Sebok, Dávid Weiss, Gerhard Driessens, Kurt Senden, Mario Department of Cognitive Neuroscience Maastricht University Netherlands Department of Data Science and Knowledge Engineering Maastricht University Netherlands

Lateral connections play an important role for sensory processing in visual cortex by supporting discriminable neuronal responses even to highly similar features. In the present work, we show that establishing a biologically inspired Mexican hat lateral connectivity profile along the filter domain can significantly improve the classification accuracy of a variety of lightweight convolutional neural networks without the addition of trainable network parameters. Moreover, we demonstrate that it is possible to analytically determine the stationary distribution of modulated filter activations and thereby avoid using recurrence for modeling temporal dynamics. We furthermore reveal that the Mexican hat connectivity profile has the effect of ordering filters in a sequence resembling the topographic organization of feature selectivity in early visual cortex. In an ordered filter sequence, this profile then sharpens the filters’ tuning curves. © 2021, CC BY.

关键词： Biomimetics

来源：评论

学校读者我要写书评

暂无评论

Determining performance boundaries on high-level system specifications 16

Determining performance boundaries on high-level system spec...

引用

19th International Workshop on Software and Compilers for Embedded Systems, SCOPES 2016

作者： Van Teijlingen, Wouter Van Leuken, Rene Galuzzi, Carlo Kienhuis, Bart Delft University of Technology Circuits and Systems Mekelweg 4 Delft Netherlands Maastricht University Department of Data Science and Knowledge Engineering Bouillonstraat 8-11 Maastricht Netherlands Leiden University Leiden Institute of Advanced Computer Science Niels Bohrweg 1 Leiden Netherlands

ISBN: (纸本)9781450343206

We can significantly reduce the time required to realize designs if it is possible to find limits to the performance of an embedded system, solely based on high-level system specifications. For that purpose, we present in this paper the cprof profiler, which determines the number of clock cycles needed to execute a C-program in hardware. The cprof tool is based on the Clang compiler front-end to parse C-programs and to produce instrumented source code for the profiling. Using cprof, we determine a lower and upper bound limit for all 29 cases of the PolyBench/C benchmark suite. The lower and upper bound are determined using the absolute performance estimations assuming all statement are mapped onto the same processing resource and unbounded performance estimations assuming unlimited resources. We also compared the clock cycles found by cprof with RTL implementations for all 29 Polybench/C cases and found that cprof determines with 1.2% accuracy the correct number of clock cycles. It does this in a fraction of the time compared to the time needed to do a full RTL simulation. © 2016 ACM.

关键词： Program compilers

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：