检索结果-内蒙古大学图书馆

21st IEEE international conference on intelligent Transportation Systems (ITSC)

作者： Zhan, Hongyuan Gomes, Gabriel Li, Xiaoye S. Madduri, Kamesh Wu, Kesheng Penn State Univ Dept Comp Sci & Engn University Pk PA 16802 USA Univ Calif Berkeley Partners Adv Transportat Technol Berkeley CA 94720 USA Lawrence Berkeley Natl Lab Computat Res Div Berkeley CA USA

ISBN: (纸本)9781728103235

Compute efficiency is an important consideration for traffic flow prediction models. Machine learning algorithms adjust model parameters automatically based on the data, but often require users to set additional parameters, known as hyperparameters. Hyperparameters can significantly impact prediction accuracy. Traffic measurements, typically collected online by sensors, are serially correlated. Moreover, the data distribution may change gradually. A typical adaptation strategy is periodically re-tuning the model hyperparameters, at the cost of computational burden. In this work, we present an efficient and principled online hyperparameter learning algorithm for kernel-based traffic prediction models. In tests with real traffic measurement data, our approach requires as little as one-seventh of the computation time of other tuning methods, while achieving better or similar prediction accuracy.

关键词： Kernel Computational modeling Tuning Prediction algorithms Predictive models Training Adaptation models

来源：评论

学校读者我要写书评

暂无评论

A data mining tool for learning from manufacturing systems

引用

COMPUTERS & INDUstRIAL engineering 1997年第1-2期33卷 27-30页

作者： Koonce, DA Fang, CH Tsai, SC MICROSOFT CORP ISSAQUAHWA

This paper describes a software tool DBMine, developed to assist industrial engineers in data mining. This tool implements three common data mining methodologies: Bacon's algorithm, Decision Trees and DB-Learn. Implemented in Microsoft Visual Basic 3.0(C), DBMine, can utilize data in Microsoft Access 2.0(C) and in Watcom SQL(C) databases. This paper will also present an example session in which job shop sequences produced by a Genetic Algorithm are explored for regularity. (C) 1997 Elsevier Science Ltd.

关键词： Computer aided software engineering

来源：评论

学校读者我要写书评

暂无评论

A One-by-One Method for Community Detection in Attributed Networks 21st

A One-by-One Method for Community Detection in Attributed Ne...

引用

21st international conference on intelligent data engineering and automated learning

作者： Shalileh, Soroosh Mirkin, Boris NRU HSE Moscow Russian Federat Dept Data Sci & Artificial Intelligence 11Pokrovski Blvd Moscow 109028 Russia

ISBN: (纸本)9783030623647;9783030623654

The problem of community detection in a network with features at its nodes takes into account both the graph structure and node features. The goal is to find relatively dense groups of interconnected entities sharing some features in common. We apply the so-called data recovery approach to the problem by combining the least-squares recovery criteria for both, the graph structure and node features. In this way, we obtain a new clustering criterion and a corresponding algorithm for finding clusters/communities one-by-one. We show that our proposed method is effective on real-world data, as well as on synthetic data involving either only quantitative features or only categorical attributes or both. Our algorithm appears competitive against state-of-the-art algorithms.

关键词： Attributed network Cluster analysis Community detection Least squares criterion One by one clustering

来源：评论

学校读者我要写书评

暂无评论

Enhanced Credit Prediction Using Artificial data 21st

Enhanced Credit Prediction Using Artificial Data

引用

21st international conference on intelligent data engineering and automated learning

作者： Mitic, Peter Cooper, James Santander UK 2 Triton SqRegents Pl London NW1 3AN England UCL Dept Comp Sci Gower St London WC1E 6BT England Santander US 75 State St Boston MA 02109 USA

ISBN: (纸本)9783030623647;9783030623654

Analysing credit data using a neural network has hitherto proved to be very resilient to attempts to improve success rates in prediction. We present a technique using simulated data which results in a marginal improvement in success rate. The empirical probability distribution for each feature of the training data is determined, and random samples are drawn from those distributions. The result is termed 'artificial' data. It is then possible to generate equal volumes of data for each of the binary outcomes (default or not), thereby alleviating a class imbalance classification problem. The simulation method uses a copula (to preserve the correlation structure of the original data) and optimal feature weighting to give acceptable results. The results indicate that overall percentage success rates for the more common outcome only are improved, but there is a more significant improvement in the AUC metric. The significance of this result in the context of assessing credit worthiness is discussed.

关键词： Artificial data Copula Importance weight Neural network Lorenz curve

来源：评论

学校读者我要写书评

暂无评论

Development of Alternative Conception Diagnostic System based on Item Response Theory in MOOCs 25

Development of Alternative Conception Diagnostic System base...

引用

25th international conference on Computers in Education (ICCE) - Technology and Innovation - Computer-Based Educational Systems for the 21st Century

作者： Cheng, Yu-Cheng Tzeng, Jian-Wei Huang, Nen-Fu Lee, Chia-An Kuo, Meng-Lun Natl Tsing Hua Univ Dept Comp Sci Hsinchu Taiwan Natl Tsing Hua Univ Ctr Teaching & Learning Dev Hsinchu Taiwan Netxtream Technol Inc Hsinchu Taiwan Natl Tsing Hua Univ Inst Serv Sci Hsinchu Taiwan

ISBN: (纸本)9789869401265

With the popularities of Massive Open Online Courses, a great number of enrollments in MOOCs generate much educational big data in terms of online activities and logs, which might be valuable for academia and practitioners. More personalized and intelligent online learning environment could be potentially created through educational data mining and learning analytics techniques. Based on Item Response Theory (IRT), the current study builds an item analysis system to identify alternative concepts/misconceptions from leaners' response in exams. By calculating difficulty parameter and discrimination parameter from massive learners, our systems are believed to benefit both teaching faculties and online learners. With the affordances of the system, teaching faculties could assess leaners' learning performance and quality of test items while alternative conception of leaners would be identified for strategic learning. Other practical and technical implications will be discussed in this paper.

关键词： Computer-Assisted Assessment Item Response Theory MOOCs (Massive Open Online Course) learning analytics misconception alternative conception Item Analysis

来源：评论

学校读者我要写书评

暂无评论

Software engineering for automated Vehicles: Addressing the Needs of Cars That Run on Software and data 19

Software Engineering for Automated Vehicles: Addressing the ...

引用

IEEE/ACM 41st international conference on Software engineering - Software engineering in Practice (ICSE-SEIP)

作者： Czarnecki, Krzysztof Univ Waterloo Waterloo Intelligent Syst Engn WISE Lab Waterloo ON Canada

ISBN: (纸本)9781728117645

automated vehicles are AI-based safety-critical robots that fulfill transportation needs while interacting with the general public in traffic. Software engineering for automated vehicles requires a DevOps-style process with special considerations for functions based on machine learning and incremental safety assurance at vehicle and fleet level. This technical briefing reviews current challenges, industry practices, and opportunities for future research in software engineering for automated vehicles.

关键词： control engineering computing learning (artificial intelligence) remotely operated vehicles safety-critical software software engineering

来源：评论

学校读者我要写书评

暂无评论

Security Issues for Distributed Fusion in Coalition Environments 21

Security Issues for Distributed Fusion in Coalition Environm...

引用

21st international conference on Information Fusion (FUSION)

作者： Cirincione, Greg Verma, Dinesh Bertino, Elisa Swami, Ananthram Army Res Lab CISD Adelphi MD 20783 USA IBM TJ Watson Res Ctr Distributed AI Dept Yorktown Hts NY USA Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA

ISBN: (纸本)9780996452762

When sensor fusion operations are conducted in coalition environments, security of the data and infrastructure used for model fusion are very important. AI enabled sensor fusion infrastructure can be attacked on many fronts, including attacks on the data used for sensor information fusion and disrupting the communication between devices and the fusion nodes, in addition to the traditional security attacks. As the infrastructure for sensor fusion becomes more automated with multiple intelligent assistants for data collection, different types of attacks are possible. AI enabled approaches can be used to improve the security and resiliency of federated networks, and the data that is shared across coalition problems. In this paper, we discuss the challenges associated with security of coalition infrastructures, and approaches to improve the security using AI and machine learning techniques

关键词： Distributed learning Security Coalition Operations Generative Policies

来源：评论

学校读者我要写书评

暂无评论

A Deep learning Approach to Forecast the Influent Flow in Wastewater Treatment Plants 21st

A Deep Learning Approach to Forecast the Influent Flow in Wa...

引用

21st international conference on intelligent data engineering and automated learning

作者： Oliveira, Pedro Fernandes, Bruno Aguiar, Francisco Pereira, Maria Alcina Analide, Cesar Novais, Paulo Univ Minho ALGORITMI Ctr Braga Portugal Univ Minho Ctr Biol Engn Braga Portugal Aguas do Norte Guimaraes Portugal

ISBN: (纸本)9783030623616;9783030623623

For the management and operation of a Wastewater Treatment Plant (WWTP), the influent flow is one of the most important variables. Hence, this paper presents an evaluation of multiple Deep learning models to forecast the influent flow in WWTPs for the next three days, taking into account previous influent observations as well as historical climatological data. Long Short-Term Memory networks (LstMs) and one-dimensional Convolutional Neural Networks (CNNs), following a channels' last approach, were conceived to tackle this time series problem. The best candidate LstM model was able to forecast the influent flow with an approximate overall error of 200m3 for the three forecast days. On the other hand, the best candidate CNN model presented a slightly higher error, being outperformed by LstM-based models. Nonetheless, CNNs, which are typically applied in the computer vision domain, also showed interesting performance for time series forecasting.

关键词： Deep learning Wastewater Treatment Plants Influent flow Long Short-Term Memory Networks Convolutional Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Negation Scope Detection using Multitask learning 21

Enhancing Negation Scope Detection using Multitask Learning

引用

21st IEEE international conference on data Mining (IEEE ICDM)

作者： Patel, Harsh Zhang, Xulang Liu, Qian Indian Inst Technol Gandhinagar Palaj India Nanyang Technol Univ Singapore Singapore

ISBN: (纸本)9781665424271

Negation is a linguistic phenomenon that usually occurs in a text for denial or refute of some occasion. Detection of such negative assertions is an essential sub-task in various applications of information extraction and data mining. In this paper, we present a deep multitask learning (MTL) framework to enhance the performance of Negation Scope detection using part-of-speech (POS) tagging as an auxiliary task. We show how the relationship between these two tasks, which do not seem to be easily linked from a linguistic point of view, is mutually beneficial.

关键词： sentiment analysis multitask learning negation scope detection pos-tagging deep learning

来源：评论

学校读者我要写书评

暂无评论

learning to Predict Pedestrian Intention via Variational Tracking Networks 21

Learning to Predict Pedestrian Intention via Variational Tra...

引用

21st IEEE international conference on intelligent Transportation Systems (ITSC)

作者： Hoy, Michael Tu, Zhigang Dang, Kang Dauwels, Justin Nanyang Technol Univ Sch Elect & Elect Engn Singapore Singapore Nanyang Technol Univ ST Engn NTU Corp Lab Singapore Singapore

ISBN: (纸本)9781728103235

We propose a new deep learning based system for short term prediction of pedestrian behavior in front of a vehicle. To achieve this, we first develop a framework for class specific object tracking and short term path prediction based on a variant of a Variational Recurrent Neural Network (VRNN), which incorporates latent variables corresponding to a dynamic state space model. The low level visual features learned from this system were found to be highly informative for the discrete intention prediction task (i.e., predicting whether a pedestrian is stopping or crossing), and achieved high performance on the Daimler benchmark. This is despite a much smaller training dataset than is normally used for training deep learning models. To the best of our knowledge, we are the first to apply deep learning to this problem without using externally trained pedestrian pose estimation systems. Our system performs comparable to the state-of-the-art approach that relies on pose estimation, and runs in real time.

关键词： Object tracking Feature extraction Recurrent neural networks Training Vehicle dynamics Visualization

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：